CBF Papers Tracker

Control Barrier Function papers | Updated: 2026-03-26 23:35 UTC

GitHub Repository Update Workflow Project README Issues More Repositories

No papers match current filters.

Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Robotics151 citations2023-06-01Paper ->

BarrierNet: Differentiable Control Barrier Functions for Learning of Safe Robot Control

Wei Xiao, Tsun-Hsuan Wang, Ramin M. Hasani, Makram Chahine, Alexander Amini et al.

Many safety-critical applications of neural networks, such as robotic control, require safety guarantees. This article introduces a method for ensuring the safety of learned models for control using differentiable control barrier functions (dCBFs). dCBFs are end-to-end trainable and guarantee safety. They improve over classical control barrier functions (CBFs), which are usually overly conservative. Our dCBF solution relaxes the CBF definitions by: 1) using environmental dependencies; 2) embedding them into differentiable quadratic programs. These novel safety layers are called a BarrierNet. They can be used in conjunction with any neural network-based controller. They are trained by gradient descent. With BarrierNet, the safety constraints of a neural controller become adaptable to changing environments. We evaluate BarrierNet on the following several problems: 1) robot traffic merging; 2) robot navigation in 2-D and 3-D spaces; 3) end-to-end vision-based autonomous driving in a sim-to-real environment and in physical experiments; 4) demonstrate their effectiveness compared to state-of-the-art approaches.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics104 citations2021-09-14Paper ->

Safety-Critical Containment Maneuvering of Underactuated Autonomous Surface Vehicles Based on Neurodynamic Optimization With Control Barrier Functions

Nan Gu, Dan Wang, Zhouhua Peng, Jun Wang

This article addresses the safety-critical containment maneuvering of multiple underactuated autonomous surface vehicles (ASVs) in the presence of multiple stationary/moving obstacles. In a complex marine environment, every ASV suffers from model uncertainties, external disturbances, and input constraints. A safety-critical control method is proposed for achieving a collision-free containment formation. Specifically, a fixed-time extended state observer is employed for estimating the model uncertainties and external disturbances. By estimating lumped disturbances in fixed time, nominal containment maneuvering control laws are designed in an Earth-fixed reference frame. Input-to-state safe control barrier functions (ISSf-CBFs) are constructed for mapping safety constraints on states to constraints on control inputs. A distributed quadratic optimization problem with the norm of control inputs as the objective function and ISSf-CBFs as constraints is formulated. A recurrent neural network-based neurodynamic optimization approach is adopted to solve the quadratic optimization problem for computing the forces and moments within the safety and input constraints in real time. It is proven that the error signals in the closed-loop control system are uniformly ultimately bounded and the multi-ASVs system is guaranteed for input-to-state safety. Simulation results are elaborated to substantiate the effectiveness of the proposed safety-critical control method for ASVs based on neurodynamic optimization with control barrier functions.

Robotics436 citations2021-08-18Paper ->

High-Order Control Barrier Functions

Wei Xiao, C. Belta

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

Learning214 citations2021-07-01Paper ->

Robust Adaptive Control Barrier Functions: An Adaptive and Data-Driven Approach to Safety

B. Lopez, J. Slotine, J. How

A new framework is developed for control of constrained nonlinear systems with structured parametric uncertainty. Forward invariance of a safe set is achieved through online parameter adaptation and data-driven model estimation. The new adaptive data-driven safety paradigm is merged with a recent adaptive controller for systems nominally contracting in closed-loop. This unification is more general than other safety controllers as contraction does not require the system be invertible or in a particular form. The method is tested on the pitch dynamics of an aircraft with uncertain nonlinear aerodynamics.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

MPC/Planning172 citations2021-04-21Paper ->

Adaptive Control Barrier Functions

Wei Xiao, C. Belta, C. Cassandras

It has been shown that optimizing quadratic costs while stabilizing affine control systems to desired (sets of) states subject to state and control constraints can be reduced to a sequence of quadratic programs (QPs) by using control barrier functions (CBFs) and control Lyapunov functions (CLFs). In this article, we introduce adaptive CBFs (aCBFs) that can accommodate time-varying control bounds and noise in the system dynamics while also guaranteeing the feasibility of the QPs if the original quadratic cost optimization problem itself is feasible, which is a challenging problem in current approaches. We propose two different types of aCBFs: parameter-adaptive CBF (PACBF) and relaxation-adaptive CBF (RACBF). Central to aCBFs is the introduction of appropriate time-varying functions to modify the definition of a common CBF. These time-varying functions are treated as high-order CBFs with their own auxiliary dynamics, which are stabilized by CLFs. We demonstrate the advantages of using aCBFs over the existing CBF techniques by applying both the PACBF-based method and the RACBF-based method to a cruise control problem with time-varying road conditions and noise in the system dynamics, and compare their relative performance.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Robotics0 citations2020-10-30arXiv ->

Multi-Layered Safety for Legged Robots via Control Barrier Functions and Model Predictive Control

R. Grandia, Andrew J. Taylor, A. Ames, Marco Hutter

The problem of dynamic locomotion over rough terrain requires both accurate foot placement together with an emphasis on dynamic stability. Existing approaches to this problem prioritize immediate safe foot placement over longer term dynamic stability considerations, or relegate the coordination of foot placement and dynamic stability to heuristic methods. We propose a multi-layered locomotion framework that unifies Control Barrier Functions (CBFs) with Model Predictive Control (MPC) to simultaneously achieve safe foot placement and dynamic stability. Our approach incorporates CBF based safety constraints both in a low frequency kinodynamic MPC formulation and a high frequency inverse dynamics tracking controller. This ensures that safety-critical execution is considered when optimizing locomotion over a longer horizon. We validate the proposed method in a 3D stepping-stone scenario in simulation and experimentally on the ANYmal quadruped platform.

Robotics0 citations2020-10-19arXiv ->

Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance

Andrew W. Singletary, Karl Klingebiel, Joseph R. Bourne, Andrew W. Browning, P. Tokumaru et al.

Artificial potential fields (APFs) and their variants have been a staple for collision avoidance of mobile robots and manipulators for almost 40 years. Its model-independent nature, ease of implementation, and real-time performance have played a large role in its continued success over the years. Control barrier functions (CBFs), on the other hand, are a more recent development, commonly used to guarantee safety for nonlinear systems in real-time in the form of a filter on a nominal controller. In this paper, we address the connections between APFs and CBFs. At a theoretic level, we show that given a broad class of APFs, one can construct a CBF that guarantees safety. Additionally, we prove that CBFs obtained from these APFs have additional beneficial properties and can be applied to nonlinear systems. Practically, we compare the performance of APFs and CBFs in the context of obstacle avoidance on simple illustrative examples and for a quadrotor with unknown dynamics, both in simulation and on hardware using onboard sensing.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Robotics0 citations2020-03-10arXiv ->

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach

M. Srinivasan, A. Dabholkar, S. Coogan, P. Vela

Control barrier functions are mathematical constructs used to guarantee safety for robotic systems. When integrated as constraints in a quadratic programming optimization problem, instantaneous control synthesis with real-time performance demands can be achieved for robotics applications. Prevailing use has assumed full knowledge of the safety barrier functions, however there are cases where the safe regions must be estimated online from sensor measurements. In these cases, the corresponding barrier function must be synthesized online. This paper describes a learning framework for estimating control barrier functions from sensor data. Doing so affords system operation in unknown state space regions without compromising safety. Here, a support vector machine classifier provides the barrier function specification as determined by sets of safe and unsafe states obtained from sensor measurements. Theoretical safety guarantees are provided. Experimental ROS-based simulation results for an omnidirectional robot equipped with LiDAR demonstrate safe operation.

Learning0 citations2020-03-07arXiv ->

Control barrier functions for stochastic systems

Andrew Clark

Control Barrier Functions (CBFs) aim to ensure safety by constraining the control input at each time step so that the system state remains within a desired safe region. This paper presents a framework for CBFs in stochastic systems in the presence of Gaussian process and measurement noise. We first consider the case where the system state is known at each time step, and present reciprocal and zero CBF constructions that guarantee safety with probability 1. We extend our results to high relative degree systems with linear dynamics and affine safety constraints. We then develop CBFs for incomplete state information environments, in which the state must be estimated using sensors that are corrupted by Gaussian noise. We prove that our proposed CBF ensures safety with probability 1 when the state estimate is within a given bound of the true state, which can be achieved using an Extended Kalman Filter when the system is linear or the process and measurement noise are sufficiently small. We propose control policies that combine these CBFs with Control Lyapunov Functions in order to jointly ensure safety and stochastic stability. Our results are validated via numerical study on an adaptive cruise control example.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Learning0 citations2019-10-01arXiv ->

Adaptive Safety with Control Barrier Functions

Andrew J. Taylor, A. Ames

Adaptive Control Lyapunov Functions (aCLFs) were introduced 20 years ago, and provided a Lyapunov-based methodology for stabilizing systems with parameter uncertainty. The goal of this paper is to revisit this classic formulation in the context of safety-critical control. This will motivate a variant of aCLFs in the context of safety: adaptive Control Barrier Functions (aCBFs). Our proposed approach adaptively achieves safety by keeping the system’s state within a safe set even in the presence of parametric model uncertainty. We unify aCLFs and aCBFs into a single control methodology for systems with uncertain parameters in the context of a Quadratic Program (QP) based framework. We validate the ability of this unified framework to achieve stability and safety in an Adaptive Cruise Control (ACC) simulation.

Robotics2120 citations2019-03-27arXiv ->

Control Barrier Functions: Theory and Applications

A. Ames, S. Coogan, M. Egerstedt, Gennaro Notomista, K. Sreenath et al.

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Learning0 citations2019-03-12arXiv ->

Control Barrier Functions for Systems with High Relative Degree

Wei Xiao, C. Belta

This paper extends control barrier functions (CBFs) to high order control barrier functions (HOCBFs) that can be used for high relative degree constraints. The proposed HOCBFs are more general than recently proposed (exponential) HOCBFs. We introduce high order barrier functions (HOBFs), and show that their satisfaction of Lyapunov-like conditions implies the forward invariance of the intersection of a series of sets. We then introduce HOCBF, and show that any control input that satisfies the HOCBF constraint renders the intersection of a series of sets forward invariant. We formulate optimal control problems with constraints given by HOCBF and control Lyapunov functions (CLF), and provide a promising method to address the conflict between HOCBF constraints and control limitations by penalizing the class $\mathcal{K}$ functions. We illustrate the proposed method on an adaptive cruise control problem.

Robotics347 citations2019-01-01Paper ->

Control Barrier Functions for Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

The need for computationally-efficient control methods of dynamical systems under temporal logic tasks has recently become more apparent. Existing methods are computationally demanding and hence often not applicable in practice. Especially with respect to multi-robot systems, these methods do not scale computationally. In this letter, we propose a framework that is based on control barrier functions and signal temporal logic. In particular, time-varying control barrier functions are considered where the temporal properties are used to satisfy signal temporal logic tasks. The resulting controller is given by a switching strategy between a computationally-efficient convex quadratic program and a local feedback control law.

Robotics393 citations2018-10-01Paper ->

Robust control barrier functions for constrained stabilization of nonlinear systems

M. Janković

Abstract Quadratic Programming (QP) has been used to combine Control Lyapunov and Control Barrier Functions (CLF and CBF) to design controllers for nonlinear systems with constraints. It has been successfully applied to robotic and automotive systems. The approach could be considered an extension of the CLF-based point-wise minimum norm controller. In this paper we modify the original QP problem in a way that guarantees that V 0 , if the barrier constraint is inactive, as well as local asymptotic stability under the standard (minimal) assumptions on the CLF and CBF. We also remove the assumption that the CBF has uniform relative degree one. The two design parameters of the new QP setup allow us to control how aggressive the resulting control law is when trying to satisfy the two control objectives. The paper presents the controller in a closed form making it unnecessary to solve the QP problem on line and facilitating the analysis. Next, we introduce the concept of Robust-CBF that, when combined with existing ISS-CLFs, produces controllers for constrained nonlinear systems with disturbances. In an example, a nonlinear system is used to illustrate the ease with which the proposed design method handles non-convex constraints and disturbances and to illuminate some tradeoffs.

Theory296 citations2018-03-08arXiv ->

Input-to-State Safety With Control Barrier Functions

Shishir N Y Kolathaya, A. Ames

This letter presents a new notion of input-to-state safe control barrier functions (ISSf-CBFs), which ensure safety of nonlinear dynamical systems under input disturbances. Similar to how safety conditions are specified in terms of forward invariance of a set, input-to-state safety conditions are specified in terms of forward invariance of a slightly larger set. In this context, invariance of the larger set implies that the states stay either inside or very close to the smaller safe set; and this closeness is bounded by the magnitude of the disturbances. The main contribution of the letter is the methodology used for obtaining a valid ISSf-CBF, given a control barrier function. The associated universal control law will also be provided. Towards the end, we will study unified quadratic programs that combine control Lyapunov functions and ISSf-CBFs in order to obtain a single control law that ensures both safety and stability in systems with input disturbances.

Robotics342 citations2017-07-12Paper ->

Discrete Control Barrier Functions for Safety-Critical Control of Discrete Systems with Application to Bipedal Robot Navigation

Ayush Agrawal, K. Sreenath

MPC/Planning649 citations2016-12-05arXiv ->

Robustness of Control Barrier Functions for Safety Critical Control

Xiangru Xu, P. Tabuada, J. Grizzle, A. Ames

Abstract Barrier functions (also called certificates) have been an important tool for the verification of hybrid systems, and have also played important roles in optimization and multi-objective control. The extension of a barrier function to a controlled system results in a control barrier function. This can be thought of as being analogous to how Sontag extended Lyapunov functions to control Lypaunov functions in order to enable controller synthesis for stabilization tasks. A control barrier function enables controller synthesis for safety requirements specified by forward invariance of a set using a Lyapunov-like condition. This paper develops several important extensions to the notion of a control barrier function. The first involves robustness under perturbations to the vector field defining the system. Input-to-State stability conditions are given that provide for forward invariance, when disturbances are present, of a “relaxation” of set rendered invariant without disturbances. A control barrier function can be combined with a control Lyapunov function in a quadratic program to achieve a control objective subject to safety guarantees. The second result of the paper gives conditions for the control law obtained by solving the quadratic program to be Lipschitz continuous and therefore to gives rise to well-defined solutions of the resulting closed-loop system.

Other568 citations2016-07-06Paper ->

Exponential Control Barrier Functions for enforcing high relative-degree safety-critical constraints

Quan Nguyen, K. Sreenath

Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Robotics0 citations2026-03-25arXiv ->

MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics

Junheng Li, Lizhi Yang, Aaron D. Ames

Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.

Robotics0 citations2026-03-24arXiv ->

Task-Space Singularity Avoidance for Control Affine Systems Using Control Barrier Functions

Kimia Forghani, Suraj Raval, Lamar Mair, Axel Krieger, Yancy Diaz-Mercado

Singularities in robotic and dynamical systems arise when the mapping from control inputs to task-space motion loses rank, leading to an inability to determine inputs. This limits the system's ability to generate forces and torques in desired directions and prevents accurate trajectory tracking. This paper presents a control barrier function (CBF) framework for avoiding such singularities in control-affine systems. Singular configurations are identified through the eigenvalues of a state-dependent input-output mapping matrix, and barrier functions are constructed to maintain a safety margin from rank-deficient regions. Conditions for theoretical guarantees on safety are provided as a function of actuator dynamics. Simulations on a planar 2-link manipulator and a magnetically actuated needle demonstrate smooth trajectory tracking while avoiding singular configurations and reducing control input spikes by up to 100x compared to the nominal controller.

MPC/Planning0 citations2026-03-24arXiv ->

Universal Formula Families for Safe Stabilization of Single-Input Nonlinear Systems

Bo Wang, Miroslav Krstic

We develop an optimization-free framework for safe stabilization of single-input control-affine nonlinear systems with a given control Lyapunov function (CLF) and a given control barrier function (CBF), where the desired equilibrium lies in the interior of the safe set. An explicit compatibility condition is derived that is necessary and sufficient for the pointwise simultaneous satisfaction of the CLF and CBF inequalities. When this condition holds, two closed-form continuous state-feedback laws are constructed from the Lie-derivative data of the CLF and CBF via standard universal stabilizer formulas, yielding asymptotic stabilization of the origin and forward invariance of the interior of the safe set, without online quadratic programming. The two laws belong to broader families parametrized by a free nondecreasing function, providing additional design flexibility. When the compatibility condition fails, a safety-prioritizing modification preserves forward invariance and drives the state toward the safe-set boundary until a compatible region is reached, whereupon continuity at the origin and asymptotic stabilization are recovered. The framework produces families of explicit constructive alternatives to CLF-CBF quadratic programming for scalar-input nonlinear systems.

MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-23arXiv ->

Interaction-Aware Predictive Environmental Control Barrier Function for Emergency Lane Change

Ying Shuai Quan, Paolo Falcone, Jonas Sjöberg

Safety-critical motion planning in mixed traffic remains challenging for autonomous vehicles, especially when it involves interactions between the ego vehicle (EV) and surrounding vehicles (SVs). In dense traffic, the feasibility of a lane change depends strongly on how SVs respond to the EV motion. This paper presents an interaction-aware safety framework that incorporates such interactions into a control barrier function (CBF)-based safety assessment. The proposed method predicts near-future vehicle positions over a finite horizon, thereby capturing reactive SV behavior and embedding it into the CBF-based safety constraint. To address uncertainty in the SV response model, a robust extension is developed by treating the model mismatch as a bounded disturbance and incorporating an online uncertainty estimate into the barrier condition. Compared with classical environmental CBF methods that neglect SV reactions, the proposed approach provides a less conservative and more informative safety representation for interactive traffic scenarios, while improving robustness to uncertainty in the modeled SV behavior.

Robotics0 citations2026-03-22arXiv ->

Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation

Jeffrey Chen, Rohan Chandra

Robots operating in dynamic, unstructured environments must balance safety and efficiency under potentially limited sensing. While control barrier functions (CBFs) provide principled collision avoidance via safety filtering, their behavior is often governed by fixed parameters that can be overly conservative in benign scenes or overly permissive near hazards. We present AlphaAdj, a vision-to-control navigation framework that uses egocentric RGB input to adapt the conservativeness of a CBF safety filter in real time. A vision-language model(VLM) produces a bounded scalar risk estimate from the current camera view, which we map to dynamically update a CBF parameter that modulates how strongly safety constraints are enforced. To address asynchronous inference and non-trivial VLM latency in practice, we combine a geometric, speed-aware dynamic cap and a staleness-gated fusion policy with lightweight implementation choices that reduce end-to-end inference overhead. We evaluate AlphaAdj across multiple static and dynamic obstacle scenarios in a variety of environments, comparing against fixed-parameter and uncapped ablations. Results show that AlphaAdj maintains collision-free navigation while improving efficiency (in terms of path length and time to goal) by up to 18.5% relative to fixed settings and improving robustness and success rate relative to an uncapped baseline.

Robotics0 citations2026-03-22arXiv ->

Koopman Meets Discrete-Time Control Barrier Functions: A Linear Model Predictive Control Framework

Shuo Liu, Liang Wu, Dawei Zhang, Jan Drgona, Calin. A. Belta

This paper proposes a Koopman-based linear model predictive control (LMPC) framework for safety-critical control of nonlinear discrete-time systems. Existing MPC formulations based on discrete-time control barrier functions (DCBFs) enforce safety through barrier constraints but typically result in computationally demanding nonlinear programming. To address this challenge, we construct a DCBF-augmented dynamical system and employ Koopman operator theory to lift the nonlinear dynamics into a higher-dimensional space where both the system dynamics and the barrier function admit a linear predictor representation. This enables the transformation of the nonlinear safety-constrained MPC problem into a quadratic program (QP). To improve feasibility while preserving safety, a relaxation mechanism with slack variables is introduced for the barrier constraints. The resulting approach combines the modeling capability of Koopman operators with the computational efficiency of QP. Numerical simulations on a navigation task for a robot with nonlinear dynamics demonstrate that the proposed framework achieves safe trajectory generation and efficient real-time control.

Robotics0 citations2026-03-21arXiv ->

Current state of the multi-agent multi-view experimental and digital twin rendezvous (MMEDR-Autonomous) framework

Logan Banker, Michael Wozniak, Mohanad Alameer, Smriti Nandan Paul, David Meisinger et al.

As near-Earth resident space objects proliferate, there is an increasing demand for reliable technologies in applications of on-orbit servicing, debris removal, and orbit modification. Rendezvous and docking are critical mission phases for such applications and can benefit from greater autonomy to reduce operational complexity and human workload. Machine learning-based methods can be integrated within the guidance, navigation, and control (GNC) architecture to design a robust rendezvous and docking framework. In this work, the Multi-Agent Multi-View Experimental and Digital Twin Rendezvous (MMEDR-Autonomous) is introduced as a unified framework comprising a learning-based optical navigation network, a reinforcement learning-based guidance approach under ongoing development, and a hardware-in-the-loop testbed. Navigation employs a lightweight monocular pose estimation network with multi-scale feature fusion, trained on realistic image augmentations to mitigate domain shift. The guidance component is examined with emphasis on learning stability, reward design, and systematic hyperparameter tuning under mission-relevant constraints. Prior Control Barrier Function results for Clohessy-Wiltshire dynamics are reviewed as a basis for enforcing safety and operational constraints and for guiding future nonlinear controller design within the MMEDR-Autonomous framework. The MMEDR-Autonomous framework is currently progressing toward integrated experimental validation in multi-agent rendezvous scenarios.

MPC/Planning0 citations2026-03-20arXiv ->

Multi-Agent Motion Planning on Industrial Magnetic Levitation Platforms: A Hybrid ADMM-HOCBF approach

Bavo Tistaert, Stan Servaes, Alejandro Gonzalez-Garcia, Ibrahim Ibrahim, Louis Callens et al.

This paper presents a novel hybrid motion planning method for holonomic multi-agent systems. The proposed decentralised model predictive control (MPC) framework tackles the intractability of classical centralised MPC for a growing number of agents while providing safety guarantees. This is achieved by combining a decentralised version of the alternating direction method of multipliers (ADMM) with a centralised high-order control barrier function (HOCBF) architecture. Simulation results show significant improvement in scalability over classical centralised MPC. We validate the efficacy and real-time capability of the proposed method by developing a highly efficient C++ implementation and deploying the resulting trajectories on a real industrial magnetic levitation platform.

Other0 citations2026-03-20arXiv ->

A Spectral Perspective on Stochastic Control Barrier Functions

Inkyu Jang, Chams E. Mballo, Claire J. Tomlin, H. Jin Kim

Stochastic control barrier functions (SCBFs) provide a safety-critical control framework for systems subject to stochastic disturbances by bounding the probability of remaining within a safe set. However, synthesizing a valid SCBF that explicitly reflects the true safety probability of the system, which is the most natural measure of safety, remains a challenge. This paper addresses this issue by adopting a spectral perspective, utilizing the linear operator that governs the evolution of the closed-loop system's safety probability. We find that the dominant eigenpair of this Koopman-like operator encodes fundamental safety information of the stochastic system. The dominant eigenfunction is a natural and valid SCBF, with values that explicitly quantify the relative long-term safety of the state, while the dominant eigenvalue indicates the global rate at which the safety probability decays. A practical synthesis algorithm is proposed, termed power-policy iteration, which jointly computes the dominant eigenpair and an optimized backup policy. The method is validated using simulation experiments on safety-critical dynamics models.

Robotics0 citations2026-03-19arXiv ->

A Closed-Form CLF-CBF Controller for Whole-Body Continuum Soft Robot Collision Avoidance

Kiwan Wong, Maximillian Stölzle, Wei Xiao, Daniela Rus

Safe operation is essential for deploying robots in human-centered 3D environments. Soft continuum manipulators provide passive safety through mechanical compliance, but still require active control to achieve reliable collision avoidance. Existing approaches, such as sampling-based planning, are often computationally expensive and lack formal safety guarantees, which limits their use for real-time whole-body avoidance. This paper presents a closed-form Control Lyapunov Function--Control Barrier Function (CLF--CBF) controller for real-time 3D obstacle avoidance in soft continuum manipulators without online optimization. By analytically embedding safety constraints into the control input, the proposed method ensures stability and safety under the stated modeling assumptions, while avoiding feasibility issues commonly encountered in online optimization-based methods. The resulting controller is up to $10\times$ faster than standard CLF--CBF quadratic-programming approaches and up to $100\times$ faster than traditional sampling-based planners. Simulation and hardware experiments on a tendon-driven soft manipulator demonstrate accurate 3D trajectory tracking and robust obstacle avoidance in cluttered environments. These results show that the proposed framework provides a scalable and provably safe control strategy for soft robots operating in dynamic, safety-critical settings.

Robotics0 citations2026-03-19arXiv ->

ADMM-Based Distributed MPC with Control Barrier Functions for Safe Multi-Robot Quadrupedal Locomotion

Yicheng Zeng, Ruturaj S. Sambhus, Basit Muhammad Imran, Jeeseop Kim, Vittorio Pastore et al.

This paper proposes a fully decentralized model predictive control (MPC) framework with control barrier function (CBF) constraints for safety-critical trajectory planning in multi-robot legged systems. The incorporation of CBF constraints introduces explicit inter-agent coupling, which prevents direct decomposition of the resulting optimal control problems. To address this challenge, we reformulate the centralized safety-critical MPC problem using a structured distributed optimization framework based on the alternating direction method of multipliers (ADMM). By introducing a novel node-edge splitting formulation with consensus constraints, the proposed approach decomposes the global problem into independent node-local and edge-local quadratic programs that can be solved in parallel using only neighbor-to-neighbor communication. This enables fully decentralized trajectory optimization with symmetric computational load across agents while preserving safety and dynamic feasibility. The proposed framework is integrated into a hierarchical locomotion control architecture for quadrupedal robots, combining high-level distributed trajectory planning, mid-level nonlinear MPC enforcing single rigid body dynamics, and low-level whole-body control enforcing full-order robot dynamics. The effectiveness of the proposed approach is demonstrated through hardware experiments on two Unitree Go2 quadrupedal robots and numerical simulations involving up to four robots navigating uncertain environments with rough terrain and external disturbances. The results show that the proposed distributed formulation achieves performance comparable to centralized MPC while reducing the average per-cycle planning time by up to 51% in the four-agent case, enabling efficient real-time decentralized implementation.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

MPC/Planning0 citations2026-03-19arXiv ->

Safety-Guaranteed Imitation Learning from Nonlinear Model Predictive Control for Spacecraft Close Proximity Operations

Alexander Meinert, Niklas Baldauf, Peter Stadler, Alen Turnwald

This paper presents a safety-guaranteed, runtime-efficient imitation learning framework for spacecraft close proximity control. We leverage Control Barrier Functions (CBFs) for safety certificates and Control Lyapunov Functions (CLFs) for stability as unified design principles across data generation, training, and deployment. First, a nonlinear Model Predictive Control (NMPC) expert enforces CBF constraints to provide safe reference trajectories. Second, we train a neural policy with a novel CBF-CLF-informed loss and DAgger-like rollouts with curriculum weighting, promoting data-efficiency and reducing future safety filter interventions. Third, at deployment a lightweight one-step CBF-CLF quadratic program minimally adjusts the learned control input to satisfy hard safety constraints while encouraging stability. We validate the approach for ESA-compliant close proximity operations, including fly-around with a spherical keep-out zone and final approach inside a conical approach corridor, using the Basilisk high-fidelity simulator with nonlinear dynamics and perturbations. Numerical experiments indicate stable convergence to decision points and strict adherence to safety under the filter, with task performance comparable to the NMPC expert while significantly reducing online computation. A runtime analysis demonstrates real-time feasibility on a commercial off-the-shelf processor, supporting onboard deployment for safety-critical on-orbit servicing.

Theory0 citations2026-03-19arXiv ->

Mean-field control barrier functions for stochastic multi-agent systems

Cinzia Tomaselli, Gian Carlo Maffettone, Samy Wu Fung, Levon Nurbekyan, Mario di Bernardo

Many applications involving multi-agent systems require fulfilling safety constraints. Control barrier functions offer a systematic framework to enforce forward invariance of safety sets. Recent work extended this paradigm to mean-field scenarios, where the number of agents is large enough to make density-space descriptions a reasonable workaround for the curse of dimensionality. However, an open gap in the recent literature concerns the development of mean-field control barrier functions for Fokker-Planck (advection-diffusion) equations. In this work, we address this gap, enabling safe mean-field control of agents with stochastic microscopic dynamics. We provide bounded stability guarantees under safety corrections and corroborate our results through numerical simulations in two representative scenarios, coverage and shepherding control of multi-agent systems.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Das, Tamas G. Molnar, Aaron D. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key challenge in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, the standard bCBF method utilizes the same backup controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative dynamic behavior. In this study, we generalize the bCBF framework by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Moreover, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2026-03-19arXiv ->

Topological Obstructions to the Existence of Control Barrier Functions

Massimiliano de Sa, Aaron D. Ames

In 1983, Brockett developed a topological necessary condition for the existence of continuous, asymptotically stabilizing control laws. Building upon recent work on necessary conditions for set stabilization, we develop Brockett-like necessary conditions for the existence of control barrier functions (CBFs). By leveraging the unique geometry of CBF safe sets, we provide simple and self-contained derivations of necessary conditions for the existence of CBFs and their safe, continuous controllers. We demonstrate the application of these conditions to instructive examples and kinematic nonholonomic systems, and discuss their relationship to Brockett's necessary condition.

Theory0 citations2026-03-18arXiv ->

Adversarial Robustness for Matrix Control Barrier Functions in Sampled-Data Systems

James Usevitch

This paper presents novel theoretical results to guarantee multi-agent set invariance using Matrix Control Barrier Functions in sampled-data systems. More specifically, the paper presents conditions under which heterogeneous control-affine agents applying zero-order-hold control inputs can compute control inputs to render safe sets defined by matrix inequalities forward invariant. It then introduces methods to guarantee set invariance while accounting for the presence of adversarial agents seeking to drive the system state to unsafe sets. Finally, the paper presents theoretical extensions of these set invariance results to systems having high relative degree with respect to the matrix-valued safe set function.

MPC/Planning0 citations2026-03-18arXiv ->

Robust Dynamic Pricing and Admission Control with Fairness Guarantees

Yingqing Chen, Anni Li, Christos G. Cassandras, Homayoun Hamedmoghadam, Fabian Wirth et al.

Dynamic pricing is commonly used to regulate congestion in shared service systems. This paper is motivated by the fact that in the presence of users with varying price sensitivity (responsiveness), conventional monotonic pricing can lead to unfair outcomes by disproportionately excluding price-elastic users, particularly under high or uncertain demand. We therefore develop a fairness-oriented mechanism under demand uncertainty. The paper's contributions are twofold. First, we show that when fairness is imposed as a hard state constraint, the optimal (revenue maximizing) pricing policy is generally non-monotonic in demand. This structural result departs fundamentally from standard surge pricing rules and reveals that price reduction under heavy load may be necessary to maintain equitable access. Second, we address the problem that price elasticity among heterogeneous users is unobservable. To solve it, we develop a robust dynamic pricing and admission control framework that enforces capacity and fairness constraints for all user type distributions consistent with aggregate measurements. By integrating integral High Order Control Barrier Functions (iHOCBFs) with a robust optimization framework under uncertain user-type distribution, we obtain a controller that guarantees forward invariance of safety and fairness constraints while optimizing revenue. Numerical experiments demonstrate improved fairness and revenue performance relative to monotonic surge pricing policies.

Theory0 citations2026-03-18arXiv ->

Dynamical Properties of Safety Filters for Linear Systems and Affine Control Barrier Functions

Pol Mestres, Shima Sadat Mousavi, Aaron D. Ames

This letter studies the dynamical properties of safety filters designed based on Control Barrier Functions (CBF). This mechanism, which is popular in safety-critical applications, takes a nominal controller and minimally modifies it to render it safe. Although CBF-based safety filters make the closed-loop system safe, characterizing their additional dynamical properties, such as stability, boundedness, or existence of spurious equilibria, remains a challenging problem. Here, we address this problem for the case of linear systems and an affine CBF constraint. We provide conditions under which the closed-loop system presents undesired equilibria, unbounded trajectories, or the origin is globally exponentially stable.

Robotics0 citations2026-03-17arXiv ->

Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints

Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray

Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.

Other0 citations2026-03-17arXiv ->

Enforcing Mixed State-Input Constraints with Multiple Backup Control Barrier Functions: A Projection-based Approach

Laszlo Gacsi, Adam K. Kiss, Ersin Das, Tamas G. Molnar

Ensuring the safety of control systems often requires the satisfaction of constraints on states (such as position or velocity), control inputs (such as force), and a mixture of states and inputs (such as power that depends on both velocity and force). This paper presents a safety-critical control framework for enforcing mixed state-input constraints through a generalization of backup control barrier functions (backup CBFs). First, we extend the backup CBF approach to maintain multiple decoupled state and input constraints using a single backup set-backup controller pair. Second, we address mixed state-input constraints by converting them into state constraints using a projection from the state-input space to the state space along the backup controller. In the special case of decoupled state and input constraints, the proposed method simplifies the synthesis of backup CBFs by eliminating the need for saturating backup control laws. Finally, we demonstrate the efficacy of the proposed method on an inverted pendulum example, where constraints on the angle (state), torque (input), and power (mixture of state and input) are satisfied simultaneously.

Other0 citations2026-03-17arXiv ->

Constricting Tubes for Prescribed-Time Safe Control

Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti

We propose a constricting Control Barrier Function (CBF) framework for prescribed-time control of control-affine systems with input constraints. Given a system starting outside a target safe set, we construct a time-varying safety tube that shrinks from a relaxed set containing the initial condition to the target set at a user-specified deadline. Any controller rendering this tube forward invariant guarantees prescribed-time recovery by construction. The constriction schedule is bounded and tunable by design, in contrast to prescribed-time methods where control effort diverges near the deadline. Feasibility under input constraints reduces to a single verifiable condition on the constriction rate, yielding a closed-form minimum recovery time as a function of control authority and initial violation. The framework imposes a single affine constraint per timestep regardless of state dimension, scaling to settings where grid-based reachability methods are intractable. We validate on a 16-dimensional multi-agent system and a unicycle reach-avoid problem, demonstrating prescribed-time recovery with bounded control effort.

Theory0 citations2026-03-17arXiv ->

Near-Optimal Constrained Feedback Control of Nonlinear Systems via Approximate HJB and Control Barrier Functions

Milad Alipour Shahraki, Laurent Lessard

This paper presents a two-stage framework for constrained near-optimal feedback control of input-affine nonlinear systems. An approximate value function for the unconstrained control problem is computed offline by solving the Hamilton--Jacobi--Bellman equation. Online, a quadratic program is solved that minimizes the associated approximate Hamiltonian subject to safety constraints imposed via control barrier functions. Our proposed architecture decouples performance from constraint enforcement, allowing constraints to be modified online without recomputing the value function. Validation on a linear 2-state 1D hovercraft and a nonlinear 9-state spacecraft attitude control problem demonstrates near-optimal performance relative to open-loop optimal control benchmarks and superior performance compared to control Lyapunov function-based controllers.

MPC/Planning0 citations2026-03-17arXiv ->

Eliminating Persistent Boundary Residence via Matrosov-Type Auxiliary Functions

Tianyu Han, Guangwei Wang, Bo Wang

Control barrier functions enforce safety by guaranteeing forward invariance of an admissible set. Under standard (non-strict) barrier conditions, however, forward invariance alone does not prevent trajectories from remaining on the boundary of the safe set for arbitrarily long time intervals, potentially leading to boundary sticking or deadlock phenomena. This paper studies the elimination of persistent boundary residence under forward-invariant barrier conditions. Inspired by Matrosov-type arguments, we introduce an auxiliary function framework that preserves forward invariance while excluding infinite-time residence within boundary layers. Sufficient conditions are established under which any trajectory can only remain in a prescribed neighborhood of the boundary for finite time, thereby restoring boundary-level liveness without altering forward invariance. The proposed construction does not rely on singular barrier formulations or controller-specific modifications, and can be incorporated into standard safety-critical control architectures. Numerical examples illustrate the removal of boundary sticking behaviors while maintaining safety across representative systems.

Learning0 citations2026-03-16arXiv ->

Multi-Scale Control of Large Agent Populations: From Density Dynamics to Individual Actuation

Mario di Bernardo

We review a body of recent work by the author and collaborators on controlling the spatial organisation of large agent populations across multiple scales. A central theme is the systematic bridging of microscopic agent-level dynamics and macroscopic density descriptions, enabling control design at the most natural level of abstraction and subsequent translation across scales. We show how this multi-scale perspective provides a unified approach to both \emph{direct control}, where every agent is actuated, and \emph{indirect control}, where few leaders or herders steer a larger uncontrolled population. The review covers continuification-based control with robustness under limited sensing and decentralised implementation via distributed density estimation; leader--follower density regulation with dual-feedback stability guarantees and bio-inspired plasticity; optimal-transport methods for coverage control and macro-to-micro discretisation; nonreciprocal field theory for collective decision-making; mean-field control barrier functions for population-level safety; and hierarchical reinforcement learning for settings where closed-form solutions are intractable. Together, these results demonstrate the breadth and versatility of a multi-scale control framework that integrates analytical methods, learning, and physics-inspired approaches for large agent populations.

Learning0 citations2026-03-15arXiv ->

Robust Safety Filters for Lipschitz-Bounded Adaptive Closed-Loop Systems with Structured Uncertainties

Johannes Autenrieb, Peter A. Fisher, Anuradha Annaswamy

Adaptive control provides closed-loop stability and reference tracking for uncertain dynamical systems through online parameter adaptation. These properties alone, however, do not ensure safety in the sense of forward invariance of state constraints, particularly during transient phases of adaptation. Control barrier function (CBF)-based safety filters have been proposed to address this limitation, but existing approaches often rely on conservative constraint tightening or static safety margins within quadratic program formulations. This paper proposes a reference-based adaptive safety framework for systems with structured parametric uncertainty that explicitly accounts for transient plant-reference mismatch. Safety is enforced at the reference level using a barrier-function-based filter, while adaptive control drives the plant to track the safety-certified reference. By exploiting Lipschitz bounds on the closed-loop error dynamics, a robust CBF condition is derived and reformulated as a convex second-order cone program (SOCP). The resulting approach reduces conservatism while preserving formal guarantees of forward invariance, stability, and tracking.

Robotics0 citations2026-03-13arXiv ->

Verification and Forward Invariance of Control Barrier Functions for Differential-Algebraic Systems

Hongchao Zhang, Mohamad H. Kazma, Meiyi Ma, Taylor T. Johnson, Ahmad F. Taha

Differential-algebraic equations (DAEs) arise in power networks, chemical processes, and multibody systems, where algebraic constraints encode physical conservation laws. The safety of such systems is critical, yet safe control is challenging because algebraic constraints restrict allowable state trajectories. Control barrier functions (CBFs) provide computationally efficient safety filters for ordinary differential equation (ODE) systems. However, existing CBF methods are not directly applicable to DAEs due to potential conflicts between the CBF condition and the constraint manifold. This paper introduces DAE-aware CBFs that incorporate the differential-algebraic structure through projected vector fields. We derive conditions that ensure forward invariance of safe sets while preserving algebraic constraints and extend the framework to higher-index DAEs. A systematic verification framework is developed, establishing necessary and sufficient conditions for geometric correctness and feasibility of DAE-aware CBFs. For polynomial systems, sum-of-squares certificates are provided, while for nonpolynomial and neural network candidates, satisfiability modulo theories are used for falsification. The approach is validated on wind turbine and flexible-link manipulator systems.

Theory0 citations2026-03-13arXiv ->

A Feasibility-Enhanced Control Barrier Function Method for Multi-UAV Collision Avoidance

Qishen Zhong, Junlong Wu, Jian Yang, Guanwei Xiao, Junqi Wu et al.

This paper presents a feasibility-enhanced control barrier function (FECBF) framework for multi-UAV collision avoidance. In dense multi-UAV scenarios, the feasibility of the CBF quadratic program (CBF-QP) can be compromised due to internal incompatibility among multiple CBF constraints. To address this issue, we analyze the internal compatibility of CBF constraints and derive a sufficient condition for internal compatibility. Based on this condition, a sign-consistency constraint is introduced to mitigate internal incompatibility. The proposed constraint is incorporated into a decentralized CBF-QP formulation using worst-case estimates and slack variables. Simulation results demonstrate that the proposed method significantly reduces infeasibility and improves collision avoidance performance compared with existing baselines in dense scenarios. Additional simulations under varying time delays demonstrate the robustness of the proposed method. Real-world experiments validate the practical applicability of the proposed method.

Learning0 citations2026-03-11arXiv ->

Distributed Safety Critical Control among Uncontrollable Agents using Reconstructed Control Barrier Functions

Yuzhang Peng, Wei Wang, Jiaqi Yan, Mengze Yu

This paper investigates the distributed safety critical control for multi-agent systems (MASs) in the presence of uncontrollable agents with uncertain behaviors. To ensure system safety, the control barrier function (CBF) is employed in this paper. However, a key challenge is that the CBF constraints are coupled when MASs perform collaborative tasks, which depend on information from multiple agents and impede the design of a fully distributed safe control scheme. To overcome this, a novel reconstructed CBF approach is proposed. In this method, the coupled CBF is reconstructed by leveraging state estimates of other agents obtained from a distributed adaptive observer. Furthermore, a prescribed performance adaptive parameter is designed to modify this reconstruction, ensuring that satisfying the reconstructed CBF constraint is sufficient to meet the original coupled one. Based on the reconstructed CBF, we design a safety-critical quadratic programming (QP) controller and prove that the proposed distributed control scheme rigorously guarantees the safety of the MAS, even in the uncertain dynamic environments involving uncontrollable agents. The effectiveness of the proposed method is illustrated through a simulation.

Robotics0 citations2026-03-11arXiv ->

Safety-critical Control Under Partial Observability: Reach-Avoid POMDP meets Belief Space Control

Matti Vahs, Joris Verhagen, Jana Tumova

Partially Observable Markov Decision Processes (POMDPs) provide a principled framework for robot decision-making under uncertainty. Solving reach-avoid POMDPs, however, requires coordinating three distinct behaviors: goal reaching, safety, and active information gathering to reduce uncertainty. Existing online POMDP solvers attempt to address all three within a single belief tree search, but this unified approach struggles with the conflicting time scales inherent to these objectives. We propose a layered, certificate-based control architecture that operates directly in belief space, decoupling goal reaching, information gathering, and safety into modular components. We introduce Belief Control Lyapunov Functions (BCLFs) that formalize information gathering as a Lyapunov convergence problem in belief space, and show how they can be learned via reinforcement learning. For safety, we develop Belief Control Barrier Functions (BCBFs) that leverage conformal prediction to provide probabilistic safety guarantees over finite horizons. The resulting control synthesis reduces to lightweight quadratic programs solvable in real time, even for non-Gaussian belief representations with dimension $>10^4$. Experiments in simulation and on a space-robotics platform demonstrate real-time performance and improved safety and task success compared to state-of-the-art constrained POMDP solvers.

Robotics0 citations2026-03-11arXiv ->

Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control

Jake Gonzales, Kazuki Mizuta, Karen Leung, Lillian J. Ratliff

In this paper, we present a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control to provide formal safety guarantees while considering complex human behavior. The approach uses conformal risk control to quantify and control the prediction errors in CBF safety values and establishes formal guarantees on the probability of constraint satisfaction during interaction. We introduce an algorithm that dynamically adjusts the safety margins produced by conformal risk control based on the current interaction context. Through experiments on human-robot navigation scenarios, we demonstrate that our approach significantly reduces collision rates and safety violations as compared to baseline methods while maintaining high success rates in goal-reaching tasks and efficient control. The code, simulations, and other supplementary material can be found on the project website: https://jakeagonzales.github.io/crc-cbf-website/.

Robotics0 citations2026-03-10arXiv ->

Towards Terrain-Aware Safe Locomotion for Quadrupedal Robots Using Proprioceptive Sensing

Peiyu Yang, Jiatao Ding, Wei Pan, Claudio Semini, Cosimo Della Santina

Achieving safe quadrupedal locomotion in real-world environments has attracted much attention in recent years. When walking over uneven terrain, achieving reliable estimation and realising safety-critical control based on the obtained information is still an open question. To address this challenge, especially for low-cost robots equipped solely with proprioceptive sensors (e.g., IMUs, joint encoders, and contact force sensors), this work first presents an estimation framework that generates a 2.5-D terrain map and extracts support plane parameters, which are then integrated into contact and state estimation. Then, we integrate this estimation framework into a safety-critical control pipeline by formulating control barrier functions that provide rigorous safety guarantees. Experiments demonstrate that the proposed terrain estimation method provides smooth terrain representations. Moreover, the coupled estimation framework of terrain, state, and contact reduces the mean absolute error of base position estimation by 64.8%, decreases the estimation variance by 47.2%, and improves the robustness of contact estimation compared to a decoupled framework. The terrain-informed CBFs integrate historical terrain information and current proprioceptive measurements to ensure global safety by keeping the robot out of hazardous areas and local safety by preventing body-terrain collision, relying solely on proprioceptive sensing.

Robotics1 citations2026-03-10arXiv ->

SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments

Shiyi Chen, Mingye Yang, Haiyan Mao, Jiaqi Zhang, Haiyi Liu et al.

Efficiently training quadruped robot navigation in densely cluttered environments remains a significant challenge. Existing methods are either limited by a lack of safety and agility in simple obstacle distributions or suffer from slow locomotion in complex environments, often requiring excessively long training phases. To this end, we propose SEA-Nav (Safe, Efficient, and Agile Navigation), a reinforcement learning framework for quadruped navigation. Within diverse and dense obstacle environments, a differentiable control barrier function (CBF)-based shield constraints the navigation policy to output safe velocity commands. An adaptive collision replay mechanism and hazardous exploration rewards are introduced to increase the probability of learning from critical experiences, guiding efficient exploration and exploitation. Finally, kinematic action constraints are incorporated to ensure safe velocity commands, facilitating successful physical deployment. To the best of our knowledge, this is the first approach that achieves highly challenging quadruped navigation in the real world with minute-level training time.

MPC/Planning0 citations2026-03-09arXiv ->

SEP-NMPC: Safety Enhanced Passivity-Based Nonlinear Model Predictive Control for a UAV Slung Payload System

Seyedreza Rezaei, Junjie Kang, Amaldev Haridevan, Jinjun Shan

Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a Safety Enhanced Passivity-Based Nonlinear MPC (SEP-NMPC) that provides formal guarantees of stability and safety for a quadrotor transporting a slung payload through cluttered environments. Stability is enforced by embedding a strict passivity inequality, which is derived from a shaped energy storage function with adaptive damping, directly into the NMPC. This formulation dissipates excess energy and ensures asymptotic convergence despite payload swings. Safety is guaranteed through high-order control barrier functions (HOCBFs) that render user-defined clearance sets forward-invariant, obliging both the quadrotor and the swinging payload to maintain separation while interacting with static and dynamic obstacles. The optimization remains quadratic-program compatible and is solved online at each sampling time without gain scheduling or heuristic switching. Extensive simulations and real-world experiments confirm stable payload transport, collision-free trajectories, and real-time feasibility across all tested scenarios. The SEP-NMPC framework therefore unifies passivity-based closed-loop stability with HOCBF-based safety guarantees for UAV slung-payload transportation.

Robotics0 citations2026-03-07arXiv ->

SSP: Safety-guaranteed Surgical Policy via Joint Optimization of Behavioral and Spatial Constraints

Jianshu Hu, ZhiYuan Guan, Lei Song, Kantaphat Leelakunwet, Hesheng Wang et al.

The paradigm of robot-assisted surgery is shifting toward data-driven autonomy, where policies learned via Reinforcement Learning (RL) or Imitation Learning (IL) enable the execution of complex tasks. However, these ``black-box" policies often lack formal safety guarantees, a critical requirement for clinical deployment. In this paper, we propose the Safety-guaranteed Surgical Policy (SSP) framework to bridge the gap between data-driven generality and formal safety. We utilize Neural Ordinary Differential Equations (Neural ODEs) to learn an uncertainty-aware dynamics model from demonstration data. This learned model underpins a robust Control Barrier Function (CBF) safety controller, which minimally alters the actions of a surgical policy to ensure strict safety under uncertainty. Our controller enforces two constraint categories: behavioral constraints (restricting the task space of the agent) and spatial constraints (defining surgical no-go zones). We instantiate the SSP framework with surgical policies derived from RL, IL and Control Lyapunov Functions (CLF). Validation on in both the SurRoL simulation and da Vinci Research Kit (dVRK) demonstrates that our method achieves a near-zero constraint violation rate while maintaining high task success rates compared to unconstrained baselines.

Robotics0 citations2026-03-07arXiv ->

Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions

Taekyung Kim

This tutorial provides a critical review of the practical application of Control Barrier Functions (CBFs) in robotic safety. While the theoretical foundations of CBFs are well-established, I identify a recurring gap between the mathematical assumption of a safe controller's existence and its constructive realization in systems with input constraints. I highlight the distinction between candidate and valid CBFs by analyzing the interplay of system dynamics, actuation limits, and class-K functions. I further show that some purported demonstrations of safe robot policies or controllers are limited to passively safe systems, such as single integrators or kinematic manipulators, where safety is already inherited from the underlying physics and even naive geometric hard constraints suffice to prevent collisions. By revisiting simple low-dimensional examples, I show when CBF formulations provide valid safety guarantees and when they fail due to common misuses. I then provide practical guidelines for constructing realizable safety arguments for systems without such passive safety. The goal of this tutorial is to bridge the gap between theoretical guarantees and actual implementation, supported by an open-source interactive web demonstration that visualizes these concepts intuitively.

Robotics0 citations2026-03-06arXiv ->

CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments

Bojan Derajić, Sebastian Bernhard, Wolfgang Hönig

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are easy to deploy but difficult to design. Motivated by the shortcomings of existing learning- and model-based methods, we propose a simple yet effective neural CBF design method for safe robot navigation in dynamic environments. We employ the idea of a composite CBF, where multiple neural CBFs are combined into a single CBF. The individual CBFs are trained via the Hamilton-Jacobi reachability framework to approximate the optimal safe set for single moving obstacles. Additionally, we use the residual neural architecture, which guarantees that the estimated safe set does not intersect with the corresponding failure set. The method is extensively evaluated in simulation experiments for a ground robot and a quadrotor, comparing it against several baseline methods. The results show improved success rates of up to 18\% compared to the best baseline, without increasing the conservativeness of the motion. Also, the method is demonstrated in hardware experiments for both types of robots.

Robotics0 citations2026-03-06arXiv ->

Control Barrier Corridors: From Safety Functions to Safe Sets

Ömür Arslan, Nikolay Atanasov

Safe autonomy is a critical requirement and a key enabler for robots to operate safely in unstructured complex environments. Control barrier functions and safe motion corridors are two widely used but technically distinct safety methods, functional and geometric, respectively, for safe motion planning and control. Control barrier functions are applied to the safety filtering of control inputs to limit the decay rate of system safety, whereas safe motion corridors are geometrically constructed to define a local safe zone around the system state for use in motion optimization and reference-governor design. This paper introduces a new notion of control barrier corridors, which unifies these two approaches by converting control barrier functions into local safe goal regions for reference goal selection in feedback control systems. We show, with examples on fully actuated systems, kinematic unicycles, and linear output regulation systems, that individual state safety can be extended locally over control barrier corridors for convex barrier functions, provided the control convergence rate matches the barrier decay rate, highlighting a trade-off between safety and reactiveness. Such safe control barrier corridors enable safely reachable persistent goal selection over continuously changing barrier corridors during system motion, which we demonstrate for verifiably safe and persistent path following in autonomous exploration of unknown environments.

Robotics0 citations2026-03-06arXiv ->

Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions

Simiao Zhuang, Bingkun Huang, Zewen Yang

Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneously enforcing strict safety constraints in varying environments with limited communication and real-time computation budgets. This paper presents a distributed control framework that achieves consensus coordination with safety guarantees via hierarchical event-triggered control barrier functions (CBFs). We first develop a consensus-based protocol that relies solely on local neighbor information to enforce both translational and rotational consistency in task space. Building on this coordination layer, we propose a three-level hierarchical event-triggered safety architecture with CBFs, which is integrated with a risk-aware leader selection and smooth switching strategy to reduce online computation. The proposed approach is validated through real-world hardware experiments using two Franka manipulators operating with static obstacles, as well as comprehensive simulations demonstrating scalable multi-arm cooperation with dynamic obstacles. Results demonstrate higher precision cooperation under strict safety constraints, achieving substantially reduced computational cost and communication frequency compared to baseline methods.

Robotics0 citations2026-03-06arXiv ->

Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes

Shuo Liu, Zhe Huang, Calin A. Belta

Obstacle avoidance of polytopic obstacles by polytopic robots is a challenging problem in optimization-based control and trajectory planning. Many existing methods rely on smooth geometric approximations, such as hyperspheres or ellipsoids, which allow differentiable distance expressions but distort the true geometry and restrict the feasible set. Other approaches integrate exact polytope distances into nonlinear model predictive control (MPC), resulting in nonconvex programs that limit real-time performance. In this paper, we construct linear discrete-time control barrier function (DCBF) constraints by deriving supporting hyperplanes from exact closest-point computations between convex polytopes. We then propose a novel iterative convex MPC-DCBF framework, where local linearization of system dynamics and robot geometry ensures convexity of the finite-horizon optimization at each iteration. The resulting formulation reduces computational complexity and enables fast online implementation for safety-critical control and trajectory planning of general nonlinear dynamics. The framework extends to multi-robot and three-dimensional environments. Numerical experiments demonstrate collision-free navigation in cluttered maze scenarios with millisecond-level solve times.

Robotics0 citations2026-03-06arXiv ->

Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints

Bo Leng, Weiqi Zhang, Zhuoren Li, Lu Xiong, Guizhe Jin et al.

Reinforcement learning has demonstrated significant potential in the field of autonomous driving. However, it suffers from defects such as training instability and unsafe action outputs when faced with autonomous racing environments characterized by high dynamics and strong nonlinearities. To this end, this paper proposes a trajectory guidance and dynamics constraints Reinforcement Learning (TraD-RL) method for autonomous racing. The key features of this method are as follows: 1) leveraging the prior expert racing line to construct an augmented state representation and facilitate reward shaping, thereby integrating domain knowledge to stabilize early-stage policy learning; 2) embedding explicit vehicle dynamic priors into a safe operating envelope formulated via control barrier functions to enable safety-constrained learning; and 3) adopting a multi-stage curriculum learning strategy that shifts from expert-guided learning to autonomous exploration, allowing the learned policy to surpass expert-level performance. The proposed method is evaluated in a high-fidelity simulation environment modeled after the Tempelhof Airport Street Circuit. Experimental results demonstrate that TraD-RL effectively improves both lap speed and driving stability of the autonomous racing vehicle, achieving a synergistic optimization of racing performance and safety.

Other0 citations2026-03-05arXiv ->

Combinatorial Safety-Critical Coordination of Multi-Agent Systems via Mixed-Integer Responsibility Allocation and Control Barrier Functions

Johannes Autenrieb, Mark Spiller, Hyo-Sang Shin, Namhoon Cho

This paper presents a hybrid safety-critical coordination architecture for multi-agent systems operating in dense environments. While control barrier functions (CBFs) provide formal safety guarantees, decentralized implementations typically rely on ego-centric safety filtering and may lead to redundant constraint enforcement and conservative collective behavior. To address this limitation, we introduce a combinatorial coordination layer formulated as a mixed-integer linear program (MILP) that assigns collision-avoidance responsibilities among agents. By explicitly distributing enforcement tasks, redundant reactions are eliminated and computational complexity is reduced. Each agent subsequently solves a reduced local quadratic program enforcing only its assigned constraints.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Robotics0 citations2026-03-05arXiv ->

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes et al.

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

Theory0 citations2026-03-04arXiv ->

Local Safety Filters for Networked Systems via Two-Time-Scale Design

Emiliano Dall'Anese

Safety filters based on Control Barrier Functions (CBFs) provide formal guarantees of forward invariance, but are often difficult to implement in networked dynamical systems. This is due to global coupling and communication requirements. This paper develops locally implementable approximations of networked CBF safety filters that require no coordination across subsystems. The proposed approach is based on a two-time-scale dynamic implementation inspired by singular perturbation theory, where a small parameter $ε$ separates fast filter dynamics from the plant dynamics; then, a local implementation is enabled via derivative estimation. Explicit bounds are derived to quantify the mismatch between trajectories of the systems with dynamic filter and with the ideal centralized safety filter. These results characterize how safety degradation depends on the time-scale parameter $ε$, estimation errors, and filter activation time, thereby quantifying trade-offs between safety guarantees and local implementability.

Theory0 citations2026-03-03arXiv ->

Designing Barrier Functions for Graceful Safety Control

Yejin Moon, Gabor Orosz, Hosam K. Fathy

This paper examines the problem of achieving "grace" when controlling dynamical systems for safety, which is defined in terms of providing multi-layered safety assurances. Namely, two safety layers are created: a primary layer that represents a desirable degree of safety, and a secondary failsafe layer. Graceful control then involves ensuring that even if the primary layer is breached, the failsafe layer remains forward invariant. The paper pursues this goal by constructing a safety constraint that combines the concepts of zeroing and reciprocal control barrier functions with regard to the primary and secondary safe sets, respectively. This constraint is analogous to a stiffening spring, making it possible to construct energy-based analytical proofs of the resulting graceful safety guarantees. The proposed approach is developed for systems with a relative degree of either 1 or 2, the latter case being particularly useful for mechanical systems. We demonstrate the applicability of the method using a wall collision avoidance example. This demonstration highlights the benefits of the proposed approach compared to traditional benchmarks from the literature.

Learning0 citations2026-03-03arXiv ->

Grid-Forming Control with Assignable Voltage Regulation Guarantees and Safety-Critical Current Limiting

Bhathiya Rathnayake, Sijia Geng

This paper develops a nonlinear grid-forming (GFM) controller with provable voltage-formation guarantees, with over-current limiting enforced via a control-barrier-function (CBF)-based safety filter. The nominal controller follows a droop-based inner-outer architecture, in which voltage references and frequency are generated by droop laws, an outer-loop voltage controller produces current references using backstepping (BS), and an inner-loop current controller synthesizes the terminal voltage. The grid voltage is treated as an unknown bounded disturbance, without requiring knowledge of its bound, and the controller design does not rely on any network parameters beyond the point of common coupling (PCC). To robustify voltage formation against the grid voltage, a deadzone-adapted disturbance suppression (DADS) framework is incorporated, yielding practical voltage regulation characterized by asymptotic convergence of the PCC voltage errors to an assignably small and known residual set. Furthermore, the closed-loop system is proven to be globally well posed, with all physical and adaptive states bounded and voltage error transients (due to initial conditions) decaying exponentially at an assignable rate. On top of the nominal controller, hard over-current protection is achieved through a minimally invasive CBF-based safety filter that enforces strict current limits via a single-constraint quadratic program. The safety filter is compatible with any locally Lipschitz nominal controller. Rigorous analysis establishes forward invariance of the safe-current set and boundedness of all states under current limiting. Numerical results demonstrate improved transient performance and faster recovery during current-limiting events when the proposed DADS-BS controller is used as the nominal control law, compared with conventional PI-based GFM control.

Learning0 citations2026-03-03arXiv ->

Event-Driven Safe and Resilient Control of Automated and Human-Driven Vehicles under EU-FDI Attacks

Yi Zhang, Yichao Wang, Wei Xiao, Mohamadamin Rajabinezhad, Shan Zuo

This paper studies the safe and resilient control of Connected and Automated Vehicles (CAVs) operating in mixed traffic environments where they must interact with Human-Driven Vehicles (HDVs) under uncertain dynamics and exponentially unbounded false data injection (EU-FDI) attacks. These attacks pose serious threats to safety-critical applications. While resilient control strategies can mitigate adversarial effects, they often overlook collision avoidance requirements. Conversely, safety-critical approaches tend to assume nominal operating conditions and lack resilience to adversarial inputs. To address these challenges, we propose an event-driven safe and resilient (EDSR) control framework that integrates event-driven Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) with adaptive attack-resilient control. The framework further incorporates data-driven estimation of HDV behaviors to ensure safety and resilience against EU-FDI attacks. Specifically, we focus on the lane-changing maneuver of CAVs in the presence of unpredictable HDVs and EU-FDI attacks on acceleration inputs. The event-driven approach reduces computational load while maintaining real-time safety guarantees. Simulation results, including comparisons with conventional safety-critical control methods that lack resilience, validate the effectiveness and robustness of the proposed EDSR framework in achieving collision-free maneuvers, stable velocity regulation, and resilient operation under adversarial conditions.

  • A. Ames15
  • Wei Xiao14
  • K. Sreenath7
  • Aaron D. Ames22
  • Andrew J. Taylor6
  • Ersin Das3
  • Tamas G. Molnar3
  • Anni Li5
  • Yingqing Chen3
  • Christos G. Cassandras3
  • C. Belta3
  • Adam K. Kiss2
  • Lizhi Yang6
  • Bo Wang2
  • Shuo Liu2
  • Daniela Rus2
  • Mario di Bernardo2
  • Johannes Autenrieb2
  • Bingkun Huang4
  • Zewen Yang3
  • Jason J. Choi11
  • C. Tomlin2
  • Anil Alan10
  • C. He2
  • G. Orosz2
  • Jun Zeng2
  • Andrew W. Singletary2
  • Lars Lindemann17
  • Dimos V. Dimarogonas21
  • S. Coogan13
CBF Related Papers
Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Robotics169 citations2021-01-01Paper ->

Guaranteed Obstacle Avoidance for Multi-Robot Operations With Limited Actuation: A Control Barrier Function Approach

Yuxiao Chen, Andrew W. Singletary, A. Ames

This letter considers the problem of obstacle avoidance for multiple robotic agents moving in an environment with obstacles. A decentralized supervisory controller is synthesized based on control barrier functions (CBF) that guarantees obstacle avoidance with limited actuation capability. The proposed method is applicable to general nonlinear robot dynamics and is scalable to an arbitrary number of agents. Agent-to-agent communication is not required, yet a simple broadcasting scheme improves the performance of the algorithm. The key idea is based on a control barrier function constructed with a backup controller, and we show that by assuming other agents respecting the same CBF condition, the supervisory control algorithm can be implemented decentrally and guarantees obstacle avoidance for all agents.

Robotics0 citations2020-10-30arXiv ->

Multi-Layered Safety for Legged Robots via Control Barrier Functions and Model Predictive Control

R. Grandia, Andrew J. Taylor, A. Ames, Marco Hutter

The problem of dynamic locomotion over rough terrain requires both accurate foot placement together with an emphasis on dynamic stability. Existing approaches to this problem prioritize immediate safe foot placement over longer term dynamic stability considerations, or relegate the coordination of foot placement and dynamic stability to heuristic methods. We propose a multi-layered locomotion framework that unifies Control Barrier Functions (CBFs) with Model Predictive Control (MPC) to simultaneously achieve safe foot placement and dynamic stability. Our approach incorporates CBF based safety constraints both in a low frequency kinodynamic MPC formulation and a high frequency inverse dynamics tracking controller. This ensures that safety-critical execution is considered when optimizing locomotion over a longer horizon. We validate the proposed method in a 3D stepping-stone scenario in simulation and experimentally on the ANYmal quadruped platform.

Robotics0 citations2020-10-19arXiv ->

Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance

Andrew W. Singletary, Karl Klingebiel, Joseph R. Bourne, Andrew W. Browning, P. Tokumaru et al.

Artificial potential fields (APFs) and their variants have been a staple for collision avoidance of mobile robots and manipulators for almost 40 years. Its model-independent nature, ease of implementation, and real-time performance have played a large role in its continued success over the years. Control barrier functions (CBFs), on the other hand, are a more recent development, commonly used to guarantee safety for nonlinear systems in real-time in the form of a filter on a nominal controller. In this paper, we address the connections between APFs and CBFs. At a theoretic level, we show that given a broad class of APFs, one can construct a CBF that guarantees safety. Additionally, we prove that CBFs obtained from these APFs have additional beneficial properties and can be applied to nonlinear systems. Practically, we compare the performance of APFs and CBFs in the context of obstacle avoidance on simple illustrative examples and for a quadrotor with unknown dynamics, both in simulation and on hardware using onboard sensing.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Learning0 citations2019-10-01arXiv ->

Adaptive Safety with Control Barrier Functions

Andrew J. Taylor, A. Ames

Adaptive Control Lyapunov Functions (aCLFs) were introduced 20 years ago, and provided a Lyapunov-based methodology for stabilizing systems with parameter uncertainty. The goal of this paper is to revisit this classic formulation in the context of safety-critical control. This will motivate a variant of aCLFs in the context of safety: adaptive Control Barrier Functions (aCBFs). Our proposed approach adaptively achieves safety by keeping the system’s state within a safe set even in the presence of parametric model uncertainty. We unify aCLFs and aCBFs into a single control methodology for systems with uncertain parameters in the context of a Quadratic Program (QP) based framework. We validate the ability of this unified framework to achieve stability and safety in an Adaptive Cruise Control (ACC) simulation.

Robotics2120 citations2019-03-27arXiv ->

Control Barrier Functions: Theory and Applications

A. Ames, S. Coogan, M. Egerstedt, Gennaro Notomista, K. Sreenath et al.

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Theory296 citations2018-03-08arXiv ->

Input-to-State Safety With Control Barrier Functions

Shishir N Y Kolathaya, A. Ames

This letter presents a new notion of input-to-state safe control barrier functions (ISSf-CBFs), which ensure safety of nonlinear dynamical systems under input disturbances. Similar to how safety conditions are specified in terms of forward invariance of a set, input-to-state safety conditions are specified in terms of forward invariance of a slightly larger set. In this context, invariance of the larger set implies that the states stay either inside or very close to the smaller safe set; and this closeness is bounded by the magnitude of the disturbances. The main contribution of the letter is the methodology used for obtaining a valid ISSf-CBF, given a control barrier function. The associated universal control law will also be provided. Towards the end, we will study unified quadratic programs that combine control Lyapunov functions and ISSf-CBFs in order to obtain a single control law that ensures both safety and stability in systems with input disturbances.

MPC/Planning649 citations2016-12-05arXiv ->

Robustness of Control Barrier Functions for Safety Critical Control

Xiangru Xu, P. Tabuada, J. Grizzle, A. Ames

Abstract Barrier functions (also called certificates) have been an important tool for the verification of hybrid systems, and have also played important roles in optimization and multi-objective control. The extension of a barrier function to a controlled system results in a control barrier function. This can be thought of as being analogous to how Sontag extended Lyapunov functions to control Lypaunov functions in order to enable controller synthesis for stabilization tasks. A control barrier function enables controller synthesis for safety requirements specified by forward invariance of a set using a Lyapunov-like condition. This paper develops several important extensions to the notion of a control barrier function. The first involves robustness under perturbations to the vector field defining the system. Input-to-State stability conditions are given that provide for forward invariance, when disturbances are present, of a “relaxation” of set rendered invariant without disturbances. A control barrier function can be combined with a control Lyapunov function in a quadratic program to achieve a control objective subject to safety guarantees. The second result of the paper gives conditions for the control law obtained by solving the quadratic program to be Lipschitz continuous and therefore to gives rise to well-defined solutions of the resulting closed-loop system.

MPC/Planning0 citations2016-09-22arXiv ->

Correctness Guarantees for the Composition of Lane Keeping and Adaptive Cruise Control

Xiangru Xu, J. Grizzle, P. Tabuada, A. Ames

This paper develops a control approach with correctness guarantees for the simultaneous operation of lane keeping and adaptive cruise control. The safety specifications for these driver assistance modules are expressed in terms of set invariance. Control barrier functions (CBFs) are used to design a family of control solutions that guarantee the forward invariance of a set, which implies satisfaction of the safety specifications. The CBFs are synthesized through a combination of sum-of-squares program and physics-based modeling and optimization. A real-time quadratic program is posed to combine the CBFs with the performance-based controllers, which can be either expressed as control Lyapunov function conditions or as black-box legacy controllers. In both cases, the resulting feedback control guarantees the safety of the composed driver assistance modules in a formally correct manner. Importantly, the quadratic program admits a closed-form solution that can be easily implemented. The effectiveness of the control approach is demonstrated by simulations in the industry-standard vehicle simulator Carsim. Note to Practitioners—Safety is of paramount importance for the control of automated vehicles. This paper is motivated by the problem of designing controllers that are provably correct for the simultaneous operation of two driver assistance modules, lane keeping and adaptive cruise control. This is a challenging problem partially, because the lateral and longitudinal dynamics of the vehicles are coupled, with few results known to exist that provide formal guarantees. In this paper, we employ an assume-guarantee formalism between these two subsystems, such that they can be considered individually; based on that, we use optimization to design safe sets that serves as “supervisors” for vehicle behavior, such that the trajectories of the closed-loop system are confined within the safe sets using predetermined bounds on wheel force and steering angle. The feedback controller is constructed by solving convex quadratic programs online, which can also be given in closed form, making the implementation much easier. One particular advantage of this control approach is that the safety set and the performance controller can be designed separately, which enables the integration of a legacy controller into a correct-by-construction solution.

MPC/Planning0 citations2016-09-21arXiv ->

Control Barrier Function Based Quadratic Programs for Safety Critical Systems

A. Ames, Xiangru Xu, J. Grizzle, P. Tabuada

Safety critical systems involve the tight coupling between potentially conflicting control objectives and safety constraints. As a means of creating a formal framework for controlling systems of this form, and with a view toward automotive applications, this paper develops a methodology that allows safety conditions—expressed as control barrier functions—to be unified with performance objectives—expressed as control Lyapunov functions—in the context of real-time optimization-based controllers. Safety conditions are specified in terms of forward invariance of a set, and are verified via two novel generalizations of barrier functions; in each case, the existence of a barrier function satisfying Lyapunov-like conditions implies forward invariance of the set, and the relationship between these two classes of barrier functions is characterized. In addition, each of these formulations yields a notion of control barrier function (CBF), providing inequality constraints in the control input that, when satisfied, again imply forward invariance of the set. Through these constructions, CBFs can naturally be unified with control Lyapunov functions (CLFs) in the context of a quadratic program (QP); this allows for the achievement of control objectives (represented by CLFs) subject to conditions on the admissible states of the system (represented by CBFs). The mediation of safety and performance through a QP is demonstrated on adaptive cruise control and lane keeping, two automotive control problems that present both safety and performance considerations coupled with actuator bounds.

Robotics226 citations2015-07-01Paper ->

Control barrier function based quadratic programs with application to bipedal robotic walking

Shao-Chen Hsu, Xiangru Xu, A. Ames

Learning1011 citations2014-12-01Paper ->

Control barrier function based quadratic programs with application to adaptive cruise control

A. Ames, J. Grizzle, P. Tabuada

Non-CBF Papers
Robotics99 citations2021-01-23arXiv ->

3-D Underactuated Bipedal Walking via H-LIP Based Gait Synthesis and Stepping Stabilization

Xiaobin Xiong, A. Ames

In this article, we holistically present a hybrid-linear inverted pendulum (H-LIP) based approach for synthesizing and stabilizing 3-D foot-underactuated bipedal walking, with an emphasis on thorough hardware realization. The H-LIP is proposed to capture the essential components of the underactuated and actuated part of the robotic walking. The robot walking gait is then directly synthesized based on the H-LIP. We comprehensively characterize the periodic orbits of the H-LIP and provably derive the stepping stabilization via its step-to-step (S2S) dynamics, which is then utilized to approximate the S2S dynamics of the horizontal state of the center of mass of the robotic walking. The approximation facilities a H-LIP based stepping controller to provide desired step sizes to stabilize the robotic walking. By realizing the desired step sizes, the robot achieves dynamic and stable walking. The approach is fully evaluated in both simulation and experiment on the 3-D underactuated bipedal robot Cassie, which demonstrates dynamic walking behaviors with both high versatility and robustness.

Robotics524 citations2020-04-22Paper ->

Biofuel-powered soft electronic skin with multiplexed and wireless sensing for human-machine interfaces

You Yu, J. Nassar, Changhao Xu, Jihong Min, Yiran Yang et al.

A flexible and fully biofuel-powered electronic skin enables continuous, multiplexed, and multimodal wireless sensing. Existing electronic skin (e-skin) sensing platforms are equipped to monitor physical parameters using power from batteries or near-field communication. For e-skins to be applied in the next generation of robotics and medical devices, they must operate wirelessly and be self-powered. However, despite recent efforts to harvest energy from the human body, self-powered e-skin with the ability to perform biosensing with Bluetooth communication are limited because of the lack of a continuous energy source and limited power efficiency. Here, we report a flexible and fully perspiration-powered integrated electronic skin (PPES) for multiplexed metabolic sensing in situ. The battery-free e-skin contains multimodal sensors and highly efficient lactate biofuel cells that use a unique integration of zero- to three-dimensional nanomaterials to achieve high power intensity and long-term stability. The PPES delivered a record-breaking power density of 3.5 milliwatt·centimeter−2 for biofuel cells in untreated human body fluids (human sweat) and displayed a very stable performance during a 60-hour continuous operation. It selectively monitored key metabolic analytes (e.g., urea, NH4+, glucose, and pH) and the skin temperature during prolonged physical activities and wirelessly transmitted the data to the user interface using Bluetooth. The PPES was also able to monitor muscle contraction and work as a human-machine interface for human-prosthesis walking.

Robotics138 citations2017-09-01Paper ->

FROST∗: Fast robot optimization and simulation toolkit

Ayonga Hereid, A. Ames

This paper presents FROST, an open-source MATLAB toolkit for modeling, trajectory optimization and simulation of hybrid dynamical systems with a particular focus in dynamic locomotion. The design objective of FROST is to provide a unified software environment for developing model-based control and motion planning algorithms for robotic systems whose dynamics is hybrid in nature. In particular, FROST uses directed graphs to describe the underlying discrete structure of hybrid system models, which renders it capable of representing a wide variety of robotic systems. Equipped with a custom symbolic math toolbox in MATLAB using Wolfram Mathematica, one can rapidly prototype the mathematical model of robot kinematics and dynamics and generate optimized code of symbolic expressions to boost the speed of optimization and simulation in FROST. In favor of agile and dynamic behaviors, we utilize virtual constraint based motion planning and feedback controllers for robotic systems to exploit the full-order dynamics of the model. Moreover, FROST provides a fast and tractable framework for planning optimal trajectories of hybrid dynamical systems using advanced direct collocation algorithms. FROST has been successfully used to synthesize dynamic walking in multiple bipedal robots. Case studies of such applications are considered in this paper, wherein different types of walking gaits are generated for two specific humanoid robots and validated in simulation.

Robotics768 citations2017-02-15Paper ->

Safety Barrier Certificates for Collisions-Free Multirobot Systems

Li Wang, A. Ames, M. Egerstedt

Robotics353 citations2016-09-15arXiv ->

The Robotarium: A remotely accessible swarm robotics research testbed

Daniel Pickem, Paul Glotfelter, Li Wang, Mark L. Mote, A. Ames et al.

This paper describes the Robotarium — a remotely accessible, multi-robot research facility. The impetus behind the Robotarium is that multi-robot testbeds constitute an integral and essential part of the multi-robot research cycle, yet they are expensive, complex, and time-consuming to develop, operate, and maintain. These resource constraints, in turn, limit access for large groups of researchers and students, which is what the Robotarium is remedying by providing users with remote access to a state-of-the-art multi-robot test facility. This paper details the design and operation of the Robotarium and discusses the considerations one must take when making complex hardware remotely accessible. In particular, safety must be built into the system already at the design phase without overly constraining what coordinated control programs users can upload and execute, which calls for minimally invasive safety routines with provable performance guarantees.

Robotics0 citations2016-08-24arXiv ->

Multi-objective compositions for collision-free connectivity maintenance in teams of mobile robots

Li Wang, A. Ames, M. Egerstedt

Compositional barrier functions are proposed in this paper to systematically compose multiple objectives for teams of mobile robots. The objectives are first encoded as barrier functions, and then composed using AND and OR logical operators. The advantage of this approach is that compositional barrier functions can provably guarantee the simultaneous satisfaction of all composed objectives. The compositional barrier functions are applied to the example of ensuring collision avoidance and static/dynamical graph connectivity of teams of mobile robots. The resulting composite safety and connectivity barrier certificates are verified experimentally on a team of four mobile robots.

Robotics199 citations2016-05-16Paper ->

3D dynamic walking with underactuated humanoid robots: A direct collocation framework for optimizing hybrid zero dynamics

Ayonga Hereid, Eric A. Cousineau, Christian M. Hubicki, A. Ames

Robotics301 citations2015-01-23Paper ->

Valkyrie: NASA's First Bipedal Humanoid Robot

N. Radford, Philip Strawser, K. Hambuchen, J. Mehling, W. Verdeyen et al.

In December 2013, 16 teams from around the world gathered at Homestead Speedway near Miami, FL to participate in the DARPA Robotics Challenge (DRC) Trials, an aggressive robotics competition partly inspired by the aftermath of the Fukushima Daiichi reactor incident. While the focus of the DRC Trials is to advance robotics for use in austere and inhospitable environments, the objectives of the DRC are to progress the areas of supervised autonomy and mobile manipulation for everyday robotics. NASA's Johnson Space Center led a team comprised of numerous partners to develop Valkyrie, NASA's first bipedal humanoid robot. Valkyrie is a 44 degree‐of‐freedom, series elastic actuator‐based robot that draws upon over 18 years of humanoid robotics design heritage. Valkyrie's application intent is aimed at not only responding to events like Fukushima, but also advancing human spaceflight endeavors in extraterrestrial planetary settings. This paper presents a brief system overview, detailing Valkyrie's mechatronic subsystems, followed by a summarization of the inverse kinematics‐based walking algorithm employed at the Trials. Next, the software and control architectures are highlighted along with a description of the operator interface tools. Finally, some closing remarks are given about the competition, and a vision of future work is provided.

Robotics274 citations2015Paper ->

Control Barrier Certificates for Safe Swarm Behavior

Urs Borrmann, Li Wang, A. Ames, M. Egerstedt

Abstract Multi-agent robotics involves the coordination of large numbers of robots, which leads to significant challenges in terms of collision avoidance. This paper generates provably collision free swarm behaviours by constructing swarm safety control barrier certificates. The safety barrier, implemented via an optimization-based controller, serves as a low level safety controller formally ensuring the forward invariance of the safe operating set. In addition, the proposed method naturally combines the goals of collision avoidance and interference with the coordination laws in a unified and computationally efficient manner. The centralized version of safety barrier certificate is designed on double integrator dynamic model, and then a decentralized formulation is proposed as a less computationally intensive and more scalable solution. The safety barrier certificate is validated in simulation and implemented experimentally on multiple mobile robots; the proposed optimization-based controller successfully generates collision free control commands with minimal overall impact on the coordination control laws.

Robotics341 citations2014-08-01Paper ->

Models, feedback control, and open problems of 3D bipedal robotic walking

J. Grizzle, C. Chevallereau, Ryan W. Sinnet, A. Ames

Robotics441 citations2014-01-10Paper ->

Rapidly Exponentially Stabilizing Control Lyapunov Functions and Hybrid Zero Dynamics

A. Ames, Kevin S. Galloway, K. Sreenath, J. Grizzle

This paper addresses the problem of exponentially stabilizing periodic orbits in a special class of hybrid models-systems with impulse effects-through control Lyapunov functions. The periodic orbit is assumed to lie in a C1 submanifold Z that is contained in the zero set of an output function and is invariant under both the continuous and discrete dynamics; the associated restriction dynamics are termed the hybrid zero dynamics. The orbit is furthermore assumed to be exponentially stable within the hybrid zero dynamics. Prior results on the stabilization of such periodic orbits with respect to the full-order dynamics of the system with impulse effects have relied on input-output linearization of the dynamics transverse to the zero dynamics manifold. The principal result of this paper demonstrates that a variant of control Lyapunov functions that enforce rapid exponential convergence to the zero dynamics surface, Z, can be used to achieve exponential stability of the periodic orbit in the full-order dynamics, thereby significantly extending the class of stabilizing controllers. The main result is illustrated on a hybrid model of a bipedal walking robot through simulations and is utilized to experimentally achieve bipedal locomotion via control Lyapunov functions.

Robotics220 citations2014-01-10Paper ->

Human-Inspired Control of Bipedal Walking Robots

A. Ames

Robotics84 citations2012Paper ->

First Steps toward Automatically Generating Bipedal Robotic Walking from Human Data

A. Ames

Robotics145 citations2010-09-01Paper ->

3D Bipedal Robotic Walking: Models, Feedback Control, and Open Problems

J. Grizzle, C. Chevallereau, A. Ames, Ryan W. Sinnet

Other669 citations2000-11-01Paper ->

CNS energy metabolism as related to function.

A. Ames

Other173 citations1992Paper ->

Energy requirements of CNS cells as related to their function and to their vulnerability to ischemia: a commentary based on studies on retina.

A. Ames

Other260 citations1976-11-01Paper ->

Responses to acetylcholine of ganglion cells in an isolated mammalian retina.

R. Masland, A. Ames

Other206 citations1972-09-01Paper ->

Studies on Mechanisms of Impairment of Cerebral Circulation Following Ischemia: Effect of Hemodilution and Perfusion Pressure

E. Fischer, A. Ames

Other136 citations1966-06-01Paper ->

A SIMPLE FREEZE-FRACTURE REPLICATION METHOD FOR ELECTRON MICROSCOPY

S. Bullivant, A. Ames

A simple method to achieve results similar to the freeze-etching technique of Moor et al. (1961) is described. The frozen tissue is cut under liquid nitrogen with a razor blade outside the evaporator rather than inside with a cooled microtome. The conditions of the experiment do not favor sublimation, and it is proposed that the structure of the replica be explained by local faults in the cleavage plane which leaves structures, such as membranes, standing above the ice. Micrographs of replicas of glycerol-protected frozen small intestine of mouse prepared by the method are presented and the structural details they show are discussed. The problem of vapor-deposited contamination is discussed. It is concluded that this is a practical method for obtaining electron micrographs that are relatively free of artifact, and that further improvements may be expected from the use of rapidly frozen fresh tissue and a clean vacuum system, possibly of the ion-pumped type.

Other128 citations1965-12-01Paper ->

Effects of Pco2 acetazolamide and ouabain on volume and composition of choroid‐plexus fluid.

A. Ames, K. Higashi, F. Nesbett

CBF Related Papers
MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-19arXiv ->

A Closed-Form CLF-CBF Controller for Whole-Body Continuum Soft Robot Collision Avoidance

Kiwan Wong, Maximillian Stölzle, Wei Xiao, Daniela Rus

Safe operation is essential for deploying robots in human-centered 3D environments. Soft continuum manipulators provide passive safety through mechanical compliance, but still require active control to achieve reliable collision avoidance. Existing approaches, such as sampling-based planning, are often computationally expensive and lack formal safety guarantees, which limits their use for real-time whole-body avoidance. This paper presents a closed-form Control Lyapunov Function--Control Barrier Function (CLF--CBF) controller for real-time 3D obstacle avoidance in soft continuum manipulators without online optimization. By analytically embedding safety constraints into the control input, the proposed method ensures stability and safety under the stated modeling assumptions, while avoiding feasibility issues commonly encountered in online optimization-based methods. The resulting controller is up to $10\times$ faster than standard CLF--CBF quadratic-programming approaches and up to $100\times$ faster than traditional sampling-based planners. Simulation and hardware experiments on a tendon-driven soft manipulator demonstrate accurate 3D trajectory tracking and robust obstacle avoidance in cluttered environments. These results show that the proposed framework provides a scalable and provably safe control strategy for soft robots operating in dynamic, safety-critical settings.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

Robotics0 citations2026-03-07arXiv ->

SSP: Safety-guaranteed Surgical Policy via Joint Optimization of Behavioral and Spatial Constraints

Jianshu Hu, ZhiYuan Guan, Lei Song, Kantaphat Leelakunwet, Hesheng Wang et al.

The paradigm of robot-assisted surgery is shifting toward data-driven autonomy, where policies learned via Reinforcement Learning (RL) or Imitation Learning (IL) enable the execution of complex tasks. However, these ``black-box" policies often lack formal safety guarantees, a critical requirement for clinical deployment. In this paper, we propose the Safety-guaranteed Surgical Policy (SSP) framework to bridge the gap between data-driven generality and formal safety. We utilize Neural Ordinary Differential Equations (Neural ODEs) to learn an uncertainty-aware dynamics model from demonstration data. This learned model underpins a robust Control Barrier Function (CBF) safety controller, which minimally alters the actions of a surgical policy to ensure strict safety under uncertainty. Our controller enforces two constraint categories: behavioral constraints (restricting the task space of the agent) and spatial constraints (defining surgical no-go zones). We instantiate the SSP framework with surgical policies derived from RL, IL and Control Lyapunov Functions (CLF). Validation on in both the SurRoL simulation and da Vinci Research Kit (dVRK) demonstrates that our method achieves a near-zero constraint violation rate while maintaining high task success rates compared to unconstrained baselines.

Learning0 citations2026-03-03arXiv ->

Event-Driven Safe and Resilient Control of Automated and Human-Driven Vehicles under EU-FDI Attacks

Yi Zhang, Yichao Wang, Wei Xiao, Mohamadamin Rajabinezhad, Shan Zuo

This paper studies the safe and resilient control of Connected and Automated Vehicles (CAVs) operating in mixed traffic environments where they must interact with Human-Driven Vehicles (HDVs) under uncertain dynamics and exponentially unbounded false data injection (EU-FDI) attacks. These attacks pose serious threats to safety-critical applications. While resilient control strategies can mitigate adversarial effects, they often overlook collision avoidance requirements. Conversely, safety-critical approaches tend to assume nominal operating conditions and lack resilience to adversarial inputs. To address these challenges, we propose an event-driven safe and resilient (EDSR) control framework that integrates event-driven Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) with adaptive attack-resilient control. The framework further incorporates data-driven estimation of HDV behaviors to ensure safety and resilience against EU-FDI attacks. Specifically, we focus on the lane-changing maneuver of CAVs in the presence of unpredictable HDVs and EU-FDI attacks on acceleration inputs. The event-driven approach reduces computational load while maintaining real-time safety guarantees. Simulation results, including comparisons with conventional safety-critical control methods that lack resilience, validate the effectiveness and robustness of the proposed EDSR framework in achieving collision-free maneuvers, stable velocity regulation, and resilient operation under adversarial conditions.

Robotics151 citations2023-06-01Paper ->

BarrierNet: Differentiable Control Barrier Functions for Learning of Safe Robot Control

Wei Xiao, Tsun-Hsuan Wang, Ramin M. Hasani, Makram Chahine, Alexander Amini et al.

Many safety-critical applications of neural networks, such as robotic control, require safety guarantees. This article introduces a method for ensuring the safety of learned models for control using differentiable control barrier functions (dCBFs). dCBFs are end-to-end trainable and guarantee safety. They improve over classical control barrier functions (CBFs), which are usually overly conservative. Our dCBF solution relaxes the CBF definitions by: 1) using environmental dependencies; 2) embedding them into differentiable quadratic programs. These novel safety layers are called a BarrierNet. They can be used in conjunction with any neural network-based controller. They are trained by gradient descent. With BarrierNet, the safety constraints of a neural controller become adaptable to changing environments. We evaluate BarrierNet on the following several problems: 1) robot traffic merging; 2) robot navigation in 2-D and 3-D spaces; 3) end-to-end vision-based autonomous driving in a sim-to-real environment and in physical experiments; 4) demonstrate their effectiveness compared to state-of-the-art approaches.

Robotics0 citations2023-05-31arXiv ->

SafeDiffuser: Safe Planning with Diffusion Probabilistic Models

Wei Xiao, Tsun-Hsuan Wang, Chuang Gan, Daniela Rus

Diffusion model-based approaches have shown promise in data-driven planning, but there are no safety guarantees, thus making it hard to be applied for safety-critical applications. To address these challenges, we propose a new method, called SafeDiffuser, to ensure diffusion probabilistic models satisfy specifications by using a class of control barrier functions. The key idea of our approach is to embed the proposed finite-time diffusion invariance into the denoising diffusion procedure, which enables trustworthy diffusion data generation. Moreover, we demonstrate that our finite-time diffusion invariance method through generative models not only maintains generalization performance but also creates robustness in safe data generation. We test our method on a series of safe planning tasks, including maze path generation, legged robot locomotion, and 3D space manipulation, with results showing the advantages of robustness and guarantees over vanilla diffusion models.

Robotics0 citations2022-03-04arXiv ->

Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving

Wei Xiao, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, Ramin M. Hasani et al.

Guaranteeing safety of perception-based learning systems is challenging due to the absence of ground-truth state information unlike in state-aware control scenarios. In this paper, we introduce a safety guaranteed learning framework for vision-based end-to-end autonomous driving. To this end, we design a learning system equipped with differentiable control barrier functions (dCBFs) that is trained end-to-end by gradient descent. Our models are composed of conventional neural network architectures and dCBFs. They are interpretable at scale, achieve great test performance under limited training data, and are safety guaranteed in a series of autonomous driving scenarios such as lane keeping and obstacle avoidance. We evaluated our framework in a sim-to-real environment, and tested on a real autonomous car, achieving safe lane following and obstacle avoidance via Augmented Reality (AR) and real parked vehicles.

Robotics436 citations2021-08-18Paper ->

High-Order Control Barrier Functions

Wei Xiao, C. Belta

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

MPC/Planning172 citations2021-04-21Paper ->

Adaptive Control Barrier Functions

Wei Xiao, C. Belta, C. Cassandras

It has been shown that optimizing quadratic costs while stabilizing affine control systems to desired (sets of) states subject to state and control constraints can be reduced to a sequence of quadratic programs (QPs) by using control barrier functions (CBFs) and control Lyapunov functions (CLFs). In this article, we introduce adaptive CBFs (aCBFs) that can accommodate time-varying control bounds and noise in the system dynamics while also guaranteeing the feasibility of the QPs if the original quadratic cost optimization problem itself is feasible, which is a challenging problem in current approaches. We propose two different types of aCBFs: parameter-adaptive CBF (PACBF) and relaxation-adaptive CBF (RACBF). Central to aCBFs is the introduction of appropriate time-varying functions to modify the definition of a common CBF. These time-varying functions are treated as high-order CBFs with their own auxiliary dynamics, which are stabilized by CLFs. We demonstrate the advantages of using aCBFs over the existing CBF techniques by applying both the PACBF-based method and the RACBF-based method to a cruise control problem with time-varying road conditions and noise in the system dynamics, and compare their relative performance.

Robotics94 citations2021-01-14arXiv ->

Rule-based optimal control for autonomous driving

Wei Xiao, N. Mehdipour, Anne Collin, A. Bin-Nun, Emilio Frazzoli et al.

We develop optimal control strategies for Autonomous Vehicles (AVs) that are required to meet complex specifications imposed by traffic laws and cultural expectations of reasonable driving behavior. We formulate these specifications as rules, and specify their priorities by constructing a priority structure, called Total ORder over eQuivalence classes (TORQ). We propose a recursive framework, in which the satisfaction of the rules in the priority structure are iteratively relaxed based on their priorities. Central to this framework is an optimal control problem, where convergence to desired states is achieved using Control Lyapunov Functions (CLFs), and safety is enforced through Control Barrier Functions (CBFs). We also show how the proposed framework can be used for after-the-fact, pass/fail evaluation of trajectories - a given trajectory is rejected if we can find a controller producing a trajectory that leads to less violation of the rule priority structure. We present case studies with multiple driving scenarios to demonstrate the effectiveness of the proposed framework.

Learning77 citations2020-11-16arXiv ->

Sufficient Conditions for Feasibility of Optimal Control Problems Using Control Barrier Functions

Wei Xiao, C. Belta, C. Cassandras

It has been shown that satisfying state and control constraints while optimizing quadratic costs subject to desired (sets of) state convergence for affine control systems can be reduced to a sequence of quadratic programs (QPs) by using Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs). One of the main challenges in this approach is ensuring the feasibility of these QPs, especially under tight control bounds and safety constraints of high relative degree. In this paper, we provide sufficient conditions for guranteed feasibility. The sufficient conditions are captured by a single constraint that is enforced by a CBF, which is added to the QPs such that their feasibility is always guaranteed. The additional constraint is designed to be always compatible with the existing constraints, therefore, it cannot make a feasible set of constraints infeasible - it can only increase the overall feasibility. We illustrate the effectiveness of the proposed approach on an adaptive cruise control problem.

Robotics89 citations2020-08-17arXiv ->

Bridging the Gap between Optimal Trajectory Planning and Safety-Critical Control with Applications to Autonomous Vehicles

Wei Xiao, C. Cassandras, C. Belta

We address the problem of optimizing the performance of a dynamic system while satisfying hard safety constraints at all times. Implementing an optimal control solution is limited by the computational cost required to derive it in real time, especially when constraints become active, as well as the need to rely on simple linear dynamics, simple objective functions, and ignoring noise. The recently proposed Control Barrier Function (CBF) method may be used for safety-critical control at the expense of sub-optimal performance. In this paper, we develop a real-time control framework that combines optimal trajectories generated through optimal control with the computationally efficient CBF method providing safety guarantees. We use Hamiltonian analysis to obtain a tractable optimal solution for a linear or linearized system, then employ High Order CBFs (HOCBFs) and Control Lyapunov Functions (CLFs) to account for constraints with arbitrary relative degrees and to track the optimal state, respectively. We further show how to deal with noise in arbitrary relative degree systems. The proposed framework is then applied to the optimal traffic merging problem for Connected and Automated Vehicles (CAVs) where the objective is to jointly minimize the travel time and energy consumption of each CAV subject to speed, acceleration, and speed-dependent safety constraints. In addition, when considering more complex objective functions, nonlinear dynamics and passenger comfort requirements for which analytical optimal control solutions are unavailable, we adapt the HOCBF method to such problems. Simulation examples are included to compare the performance of the proposed framework to optimal solutions (when available) and to a baseline provided by human-driven vehicles with results showing significant improvements in all metrics.

Learning0 citations2019-03-12arXiv ->

Control Barrier Functions for Systems with High Relative Degree

Wei Xiao, C. Belta

This paper extends control barrier functions (CBFs) to high order control barrier functions (HOCBFs) that can be used for high relative degree constraints. The proposed HOCBFs are more general than recently proposed (exponential) HOCBFs. We introduce high order barrier functions (HOBFs), and show that their satisfaction of Lyapunov-like conditions implies the forward invariance of the intersection of a series of sets. We then introduce HOCBF, and show that any control input that satisfies the HOCBF constraint renders the intersection of a series of sets forward invariant. We formulate optimal control problems with constraints given by HOCBF and control Lyapunov functions (CLF), and provide a promising method to address the conflict between HOCBF constraints and control limitations by penalizing the class $\mathcal{K}$ functions. We illustrate the proposed method on an adaptive cruise control problem.

Non-CBF Papers
Other32 citations2024-06-14Paper ->

Transcriptome and metabolome atlas reveals contributions of sphingosine and chlorogenic acid to cold tolerance in Citrus.

Peng Xiao, Jing Qu, Yue Wang, Tian Fang, Wei Xiao et al.

Citrus is one of the most important fruit crop genera in the world, but many Citrus species are vulnerable to cold stress. Ichang papeda (Citrus ichangensis), a cold-hardy citrus species, holds great potential for identifying valuable metabolites that are critical for cold tolerance in Citrus. However, the metabolic changes and underlying mechanisms that regulate Ichang papeda cold tolerance remain largely unknown. In this study, we compared the metabolomes and transcriptomes of Ichang papeda and HB pummelo (Citrus grandis 'Hirado Buntan', a cold-sensitive species) to explore the critical metabolites and genes responsible for cold tolerance. Metabolomic analyses led to the identification of common and genotype-specific metabolites, consistent with transcriptomic alterations. Compared to HB pummelo under cold stress, Ichang papeda accumulated more sugars, flavonoids, and unsaturated fatty acids, which are well-characterized metabolites involved in stress responses. Interestingly, sphingosine and chlorogenic acid substantially accumulated only in Ichang papeda. Knockdown of CiSPT (C. ichangensis serine palmitoyltransferase) and CiHCT2 (C. ichangensis hydroxycinnamoyl-CoA: shikimate hydroxycinnamoyltransferase2), two genes involved in sphingosine and chlorogenic acid biosynthesis, dramatically decreased endogenous sphingosine and chlorogenic acid levels, respectively. This reduction in sphingosine and chlorogenic acid notably compromised the cold tolerance of Ichang papeda, whereas exogenous application of these metabolites increased plant cold tolerance. Taken together, our findings indicate that greater accumulation of a spectrum of metabolites, particularly sphingosine and chlorogenic acid, promotes cold tolerance in cold-tolerant citrus species. These findings broaden our understanding of plant metabolic alterations in response to cold stress and provide valuable targets that can be manipulated to improve Citrus cold tolerance.

Theory36 citations2023-05-30Paper ->

Data security crisis in universities: identification of key factors affecting data breach incidents

Jin Li, Wei Xiao, Chong Zhang

The extremely complex and dynamic digital environments of universities make them highly vulnerable to the risk of data breaches. This study empirically investigated the factors influencing data breach risks in the context of higher education, according to crime opportunity theory and routine activity theory . The data consisted of university samples from China and were collected mainly from the Chinese Education Industry Vulnerability Reporting Platform. After applying Poisson regression for the estimation, increased public disclosure of vulnerabilities was found to escalate the frequency of data breaches, whereas cross-border data flow decreased the number of data breaches. Furthermore, the mechanism by which academic strength affects data breaches was examined through the two mediators of cross-border data flow and vulnerability disclosure. In addition, cloud adoption reduced data breaches, and public clouds were determined to be relatively more secure than private clouds. Cloud adoption also acted as a moderator between the negative impact of vulnerabilities and the positive impact of cross-border data flow on data breaches. The estimation and robustness findings revealed the underlying mechanisms that impacted university data security, clarifying the understanding of data breaches and suggesting practical implications for universities and other institutes to improve information security. The findings of this study provide insights and directions for future research.

Biomedical102 citations2023-04-01Paper ->

Liberation of daidzein by gut microbial β-galactosidase suppresses acetaminophen-induced hepatotoxicity in mice.

Yunong Zeng, Rong Wu, Fangzhao Wang, Shan Li, Lei Li et al.

Acetaminophen (APAP) overdose is a leading cause of drug-induced liver injury (DILI). The impact of the gut microbiota and associated metabolites on APAP and liver function remains unclear. We show that APAP disturbance is associated with a distinct gut microbial community, with notable decreases in Lactobacillus vaginalis. Mice receiving L. vaginalis showed resistance to APAP hepatotoxicity due to the liberation of the isoflavone daidzein from the diet by bacterial β-galactosidase. The hepatoprotective effects of L. vaginalis in APAP-exposed germ-free mice were abolished with a β-galactosidase inhibitor. Similarly, β-galactosidase-deficient L. vaginalis produced poorer outcomes in APAP-treated mice than the wild-type strain, but these differences were overcome with daidzein administration. Mechanistically, daidzein prevented ferroptotic death, which was linked to decreased expression of farnesyl diphosphate synthase (Fdps) that activated a key ferroptosis pathway involving AKT-GSK3β-Nrf2. Thus, liberation of daidzein by L. vaginalis β-galactosidase inhibits Fdps-mediated hepatocyte ferroptosis, providing promising therapeutic approaches for DILI.

Other82 citations2023-03-01Paper ->

A movable unshielded magnetocardiography system

Wei Xiao, Chenxi Sun, Liang Shen, Yulong Feng, Menglong Liu et al.

Magnetocardiography (MCG), which uses high-sensitivity magnetometers to record magnetic field signals generated by electrical activity in the heart, is a noninvasive method for evaluating heart diseases such as arrhythmia and ischemia. The MCG measurements usually require the participant keeping still in a magnetically shielded room due to the immovable sensor and noisy external environments. These requirements limit MCG applications, such as exercise MCG tests and long-term MCG observations, which are useful for early detections of heart diseases. Here, we introduce a movable MCG system that can clearly record MCG signals of freely behaving participants in an unshielded environment. On the basis of optically pumped magnetometers with a sensitivity of 140 fT/Hz1/2, we successfully demonstrated the resting MCG and the exercise MCG tests. Our method is promising to realize a practical movable multichannel unshielded MCG system that nearly sets no limits to participants and brings another kind of insight into the medical diagnosis of heart disease.

Learning120 citations2022-08-15Paper ->

CREAT: Blockchain-Assisted Compression Algorithm of Federated Learning for Content Caching in Edge Computing

Laizhong Cui, Xiaoxin Su, Zhongxing Ming, Ziteng Chen, Shu Yang et al.

Edge computing architectures can help us quickly process the data collected by Internet of Things (IoT) and caching files to edge nodes can speed up the response speed of IoT devices requesting files. Blockchain architectures can help us ensure the security of data transmitted by IoT. Therefore, we have proposed a system that combines IoT devices, edge nodes, remote cloud, and blockchain. In the system, we designed a new algorithm in which blockchain-assisted compressed algorithm of federated learning is applied for content caching, called CREAT to predict cached files. In the CREAT algorithm, each edge node uses local data to train a model and then uses the model to learn the features of users and files, so as to predict popular files to improve the cache hit rate. In order to ensure the security of edge nodes’ data, we use federated learning (FL) to enable multiple edge nodes to cooperate in training without sharing data. In addition, for the purpose of reducing communication load in FL, we will compress gradients uploaded by edge nodes to reduce the time required for communication. What is more, in order to ensure the security of the data transmitted in the CREAT algorithm, we have incorporated blockchain technology in the algorithm. We design four smart contracts for decentralized entities to record and verify the transactions to ensure the security of data. We used MovieLens data sets for experiments and we can see that CREAT greatly improves the cache hit rate and reduces the time required to upload data.

Other117 citations2022-04-25Paper ->

VO2 metasurface smart thermal emitter with high visual transparency for passive radiative cooling regulation in space and terrestrial applications

K. Sun, Wei Xiao, Callum Wheeler, M. Simeoni, A. Urbani et al.

Abstract Smart radiative cooling devices based on thermochromic materials such as vanadium dioxide (VO2) are of practical interest for temperature regulation and artificial homeostasis, i.e., maintaining stable equilibrium conditions for survival, both in terrestrial and space applications. In traditional solar reflector configurations, solar absorption in the VO2 layer is a performance limiting factor due to the multiple reflections of sunlight in the stack. Here, we demonstrate a visually transparent, smart radiator panel with reduced solar absorption. An Al-doped ZnO transparent conducting oxide layer acts as a frequency selective infrared back-reflector with high transmission of solar radiation. In this study we make use of high-quality VO2 thin films deposited using atomic layer deposition and optimized annealing process. Patterning of the VO2 layer into a metasurface results in a further reduction of the solar absorption parameter α to around 0.3, while exhibiting a thermal emissivity contrast Δε of 0.26 by exploiting plasmonic enhancement effects. The VO2 metasurface provides a visual spectrum transmission of up to 62%, which is of interest for a range of applications requiring visual transparency. The transparent smart metasurface thermal emitter offers a new approach for thermal management in both space and terrestrial radiative cooling scenarios.

Other166 citations2022-03-15Paper ->

LncRNA-mediated DNA methylation: an emerging mechanism in cancer and beyond

Wanxu Huang, Hua Li, Qingsong Yu, Wei Xiao, D. Wang

DNA methylation is one of the most important epigenetic mechanisms to regulate gene expression, which is highly dynamic during development and specifically maintained in somatic cells. Aberrant DNA methylation patterns are strongly associated with human diseases including cancer. How are the cell-specific DNA methylation patterns established or disturbed is a pivotal question in developmental biology and cancer epigenetics. Currently, compelling evidence has emerged that long non-coding RNA (lncRNA) mediates DNA methylation in both physiological and pathological conditions. In this review, we provide an overview of the current understanding of lncRNA-mediated DNA methylation, with emphasis on the roles of this mechanism in cancer, which to the best of our knowledge, has not been systematically summarized. In addition, we also discuss the potential clinical applications of this mechanism in RNA-targeting drug development.

Other56 citations2022-01-01Paper ->

High-fidelity multi-physics coupling study on advanced heat pipe reactor

Wei Xiao, Xiangyue Li, Peijie Li, Tengfei Zhang, Xiaojing Liu

Abstract The advanced heat pipe cooled reactor is a potential candidate to generate nuclear power for space exploration, and exhibits strong neutron leakage and complicated multi-physics coupled effects. Traditional numerical methods based on single-field simulations do not adequately describe these interactive physical phenomena. It is thus necessary to apply high-fidelity multi-physics coupling simulations for the analysis and design of heat pipe reactors. In this work, a three-dimensional high-fidelity neutronics-thermo-elasticity multi-physics coupling code is developed for the heat pipe reactor, Kilowatt Reactor Using Stirling TechnologY (KRUSTY), based on the Monte Carlo method and the finite element method. The code combines existing open-source codes (OpenMC, Nektar++, SfePy) and implements the functional expansion tally method to perform data mapping between the Monte Carlo and the finite element method solver. An on-the-fly convergence criterion dedicated to the functional expansion tally method is developed based on statistical uncertainties and the L 2 norm. This new criterion is shown to be unconditionally stable with various statistical uncertainties. Using the coupling code, high-fidelity coupling simulations are performed under different steady-state conditions, which provide insights to the physical phenomena of the reactor. The coupling results present same trends as the previous KRUSTY simulation, and illustrate that the feedback from thermal expansion is critical for capturing the negative reactivity feedback. The heat pipe analysis shows that a sufficient heat-removing margin for heat pipe failure accidents is guaranteed. The depletion coupling result shows that the burn-up effects are negligible for the reactor.

Theory104 citations2021-10-22Paper ->

Versatile Preparation of Mesoporous Single‐Layered Transition‐Metal Sulfide/Carbon Composites for Enhanced Sodium Storage

Xing Zhang, Wei Weng, Hao Gu, Zibo Hong, Wei Xiao et al.

Transition‐metal sulfides are promising electrochemical energy storage materials due to their abundant active sites, large interlayer space, and high theoretical capacities, especially for sodium storage. However, the low conductivity and poor cycling stability at high current densities hamper their applications. Herein, a versatile dual‐template method is reported to elaborate ordered mesoporous single‐layered MoS2/carbon composite with high specific area, uniform pore size, and large pore volume. The single‐layered MoS2 is confined in the carbon matrix. The mesopores between the composite nanorods provide fast electrolyte diffusion. The obtained nanocomposite shows a high sodium‐storage capability, excellent rate capacity, and very good cycling performance. A capacity of 310 mAh g−1 can remain at 5.0 A g−1 after 2500 cycles. Furthermore, a sodium‐ion battery (SIB) full cell composed of the MoS2/carbon composite anode and a Na3V2(PO4)3 (NVP) cathode maintains a specific capacity of 330 mAh g−1 at 1.0 A g−1 during 100 cycles. The mechanism is investigated by in situ and ex situ characterizations as well as density functional theory (DFT) calculations.

Learning0 citations2021-10-16arXiv ->

Lifelong Pretraining: Continually Adapting Language Models to Emerging Corpora

Xisen Jin, Dejiao Zhang, Henghui Zhu, Wei Xiao, Shang-Wen Li et al.

Pretrained language models (PTLMs) are typically learned over a large, static corpus and further fine-tuned for various downstream tasks. However, when deployed in the real world, a PTLM-based model must deal with data distributions that deviates from what the PTLM was initially trained on. In this paper, we study a lifelong language model pretraining challenge where a PTLM is continually updated so as to adapt to emerging data. Over a domain-incremental research paper stream and a chronologically-ordered tweet stream, we incrementally pretrain a PTLM with different continual learning algorithms, and keep track of the downstream task performance (after fine-tuning). We evaluate PTLM’s ability to adapt to new corpora while retaining learned knowledge in earlier corpora. Our experiments show distillation-based approaches to be most effective in retaining downstream performance in earlier domains. The algorithms also improve knowledge transfer, allowing models to achieve better downstream performance over latest data, and improve temporal generalization when distribution gaps exist between training and evaluation because of time. We believe our problem formulation, methods, and analysis will inspire future studies towards continual pretraining of language models.

Other134 citations2021-09-01Paper ->

A scalable, cost-effective and salt-rejecting MoS2/SA@melamine foam for continuous solar steam generation

Juanxiu Xiao, Yang Guo, W. Luo, Dong Wang, Shengkui Zhong et al.

Other152 citations2021-09-01Paper ->

Railway dangerous goods transportation system risk identification: Comparisons among SVM, PSO-SVM, GA-SVM and GS-SVM

Wencheng Huang, Hongyi Liu, Yue Zhang, Rongwei Mi, Chuangui Tong et al.

Other281 citations2021-07-01Paper ->

Catalytic decomposition of methane to produce hydrogen: A review

Zeyu Fan, Wei Weng, Jing Zhou, D. Gu, Wei Xiao

Abstract The increasing demands of hydrogen and the recent discovery of large reserves of methane have prompted the conversion of methane to hydrogen. The challenges raised by intensive CO2 emission from the traditional conversion of methane have provoked emission-free hydrogen production from methane. The catalytic decomposition of methane (CDM) to produce hydrogen and advanced carbon hence comes into consideration due to the short process and environmental benignity. Although many researchers have made considerable progress in CDM research on the laboratory scale, CDM is still in its infancy in industrialization. The history of its development, fundamental mechanisms, and recent research progress in catalysts and catalytic systems are herein highlighted. The problems of catalytic interface degradation are reviewed, focusing on deactivation from coke deposition in the CDM process. The introduction of a liquid phase interface which can in-situ remove carbon products provides a new strategy for this process. Furthermore, the challenges and prospects for future research into novel CDM catalysts or catalyst systems are included.

Biomedical129 citations2021-05-18Paper ->

The protein corona hampers the transcytosis of transferrin-modified nanoparticles through blood-brain barrier and attenuates their targeting ability to brain tumor.

Wei Xiao, Yazhen Wang, Huilin Zhang, Yuwei Liu, Rou Xie et al.

The modification of targeting ligands on nanoparticles (NPs) is anticipated to enhance the delivery of therapeutics to diseased tissues. However, once exposed to the blood stream, NPs can immediately adsorb proteins to form the "protein corona," which may greatly hinder the targeting ligand from binding to its receptor. For brain-targeting delivery, nanotherapeutics must traverse the blood-brain barrier (BBB) to enter the brain parenchyma and then target the diseased cells. However, it remains elusive whether, apart from receptor recognition, the protein corona can affect other processes involved in BBB transcytosis, such as endocytosis, intracellular trafficking, and exocytosis. Furthermore, the targeting ability of NPs toward diseased cells after transcytosis remains unclear. Herein, transferrin (Tf), a brain-targeting ligand, was coupled to NPs to evaluate BBB transcytosis and brain tumor targeting ability. Different impacts of the in vitro and in vivo protein corona on receptor targeting, lysosomal escape, and BBB transcytosis were found. The in vitro protein corona abolished the Tf-mediated effects of the abovementioned processes, whereas the in vivo protein corona attenuated these effects. After crossing the BBB, Tf retained its targeting specificity towards brain tumor cells. Together, these results revealed that several bound apolipoproteins, especially apolipoprotein A-I, may help NPs traverse the BBB, thereby providing novel insights into the development of brain-targeted delivery.

Theory65 citations2021-05-01Paper ->

Constructing high-rate and long-life phosphorus/carbon anodes for potassium-ion batteries through rational nanoconfinement

Wei Xiao, Xifei Li, Bin Cao, Gang Huang, C. Xie et al.

Abstract The development of stable and durable phosphorus anodes for potassium-ion batteries (PIBs) has been retarded by a sluggish reaction kinetics and a notorious volume change with an ambiguous reaction mechanism upon cycling. Herein, the phosphorus nanoparticles have been rationally encapsulated into a commercial porous carbon through an evaporation-condensation strategy. Benefitted from the improved structural integrity/stability of electronically/ionically insulating phosphorus in a conductive/robust carbon matrix with abundant K+/electron migration channels, the phosphorus/carbon anode material with an appropriate phosphorus content (59.4 wt%) would achieve a large initial charging capacity of 744 mA h g−1 at 100 mA g−1 and a highly reversible capacity of 212 mA h g−1 at 3200 mA g−1 over 10,000 cycles with a superior rate capability of 287 mA h g−1 at 11,200 mA g−1. Simultaneously, the electrochemical importance of phosphorus loading on potassium storage capability of derived phosphorus/carbon composites was also uncovered. Critically, the noticeable capacitive intercalation/extraction of K+ in carbon nanostructure would significantly boost the charge storage process and promote the electrochemical performance of phosphorus/carbon anode. In terms of reaction mechanism for phosphorus/carbon anode, the active phosphorus would prefer to proceed a potassiation below 0.5 V upon discharging and a depotassiation below 1.0 V upon charging, accompanied by a reversible emergence/decomposition of K4P3. This novel study shedding lights on nanostructure design and mechanism clarification of phosphorus anode would contribute to the development of high-energy and long-life PIBs in practical applications.

Theory282 citations2021-02-17Paper ->

Direct Observation on p- to n-Type Transformation of Perovskite Surface Region during Defect Passivation Driving High Photovoltaic Efficiency

Shaobing Xiong, Zhangyu Hou, Shijie Zou, Xiaoshuang Lu, Jianming Yang et al.

Summary Perovskite solar cells (PSCs) suffer from significant nonradiative recombination, limiting their power conversion efficiencies. Here, for the first time, we directly observe a complete transformation of perovskite MAPbI3 surface region energetics from p- to n-type during defect passivation caused by natural additive capsaicin, attributed to the spontaneous formation of a p-n homojunction in perovskite active layer. We demonstrate that the p-n homojunction locates at ∼100 nm below perovskite surface. The energetics transformation and defect passivation promote charge transport in bulk perovskite layer and at perovskite/PCBM interface, suppressing both defect-assisted recombination and interface carrier recombination. As a result, an efficiency of 21.88% and a fill factor of 83.81% with excellent device stability are achieved, both values are the highest records for polycrystalline MAPbI3 based p-i-n PSCs reported to date. The proposed new concept of synergetic defect passivation and energetic modification via additive provides a huge potential for further improvement of PSC performance.

Other57 citations2021-01-01Paper ->

Decentralized optimal merging control for Connected and Automated Vehicles with safety constraint guarantees

Wei Xiao, Christos G. Cassandras

Abstract This paper addresses the optimal control of Connected and Automated Vehicles (CAVs) arriving from two roads at a Merging Point (MP) where the objective is to jointly minimize the travel time and energy consumption of each CAV. The optimal solution can be used as a reference for tracking control and it guarantees that a speed-dependent safety constraint is satisfied both at the MP and everywhere within a Control Zone (CZ) which precedes it. We analyze the case of no active constraints and prove that under certain conditions the safety and speed constraints remain inactive, thus significantly simplifying the determination of an explicit decentralized solution. When these conditions do not apply, a complete solution is still obtained which includes all possible constraints becoming active. Our analysis allows us to study the tradeoff between the two objective function components (travel time and energy within the CZ). Simulation examples are provided to compare the performance of the optimal controller to a baseline consisting of human-driven vehicles with results showing improvements in both metrics.

Biomedical149 citations2020-12-07Paper ->

Autophagy alleviates hypoxia-induced blood-brain barrier injury via regulation of CLDN5 (claudin 5)

Zhenguo Yang, Panpan Lin, Bing Chen, Xiaoqin Zhang, Wei Xiao et al.

ABSTRACT Blood-brain barrier (BBB) disruption is a key event in triggering secondary damage to the central nervous system (CNS) under stroke, and is frequently associated with abnormal macroautophagy/autophagy in brain microvascular endothelial cells (BMECs). However, the underlying mechanism of autophagy in maintaining BBB integrity remains unclear. Here we report that in BMECs of patients suffering stroke, CLDN5 (claudin 5) abnormally aggregates in the cytosol accompanied by autophagy activation. In vivo zebrafish and in vitro cell studies reveal that BBB breakdown is partially caused by CAV1 (caveolin 1)-mediated redistribution of membranous CLDN5 into the cytosol under hypoxia. Meanwhile, autophagy is activated and contributes mainly to the degradation of CAV1 and aggregated CLDN5 in the cytosol of BMECs, therefore alleviating BBB breakdown. Blockage of autophagy by genetic methods or chemicals aggravates cytosolic aggregation of CLDN5, resulting in severer BBB impairment. These data demonstrate that autophagy functions in the protection of BBB integrity by regulating CLDN5 redistribution and provide a potential therapeutic strategy for BBB disorder-related cerebrovascular disease. Abbreviations: BBB: blood-brain barrier; BECN1: beclin 1; BMEC: brain microvascular endothelial cell; CAV1: caveolin 1; CCA: common carotid artery; CLDN5: claudin 5; CNS: central nervous system; CQ: chloroquine; HIF1A: hypoxia inducible factor 1 subunit alpha; MCAO: middle cerebral artery occlusion-reperfusion; OCLN: occludin; ROS: reactive oxygen species; STED: stimulated emission depletion; TEER: trans-endothelial electrical resistance; TEM: transmission electron microscopy; TJ: tight junction; TJP1: tight junction protein 1; UPS: ubiquitin-proteasome system

Theory352 citations2020-12-05Paper ->

0D/2D Co3O4/TiO2 Z-Scheme heterojunction for boosted photocatalytic degradation and mechanism investigation

Yuting Wang, Chengzhang Zhu, Gancheng Zuo, Yang Guo, Wei Xiao et al.

Abstract The development of stable, efficient photocatalyst for environmental antibiotics degradation is great significant and remains a major challenge. Herein, zero dimensional Co3O4 nanodots are grown in situ onto two dimensional TiO2 nanosheets, successfully producing a Z-scheme heterojunction Co3O4/TiO2 photocatalyst for the photocatalytic degradation of enrofloxacin. The synthesized nanohybrid exhibits superior photodegradation performance (0.0269 min−1 for enrofloxacin) and excellent stability (four cycles). The matched energy bands allow the formation of the Z-scheme heterojunction, and the built-in electric field provides the reaction driving force. The formed Z-scheme heterojunction can simultaneously inhibit photoinduced electron-hole recombination, boost photoinduced charge carrier transfer, and produce more active electrons and holes, therefore generating more active species for eventual photocatalytic degradation. In addition, a the possible enrofloxacin degradation pathway was proposed based on simulated calculations and GC MS analysis. This work can inspire further design and construction of Z-scheme heterojunction photocatalysts.

Other344 citations2020-10-22Paper ->

Adsorption of organic dyes from wastewater by metal-doped porous carbon materials

Wei Xiao, Xingpeng Jiang, Xi Liu, Weiming Zhou, Z. N. Garba et al.

Abstract In this review paper, the recent development on the adsorption of organic dyes by metal-doped porous carbon materials were reviewed. The primary objective of this paper is to sort out the dispersion information of metal-doped porous carbon materials widely used in organic dye adsorption. Various metal-doped porous carbon materials adsorbing organic dyes are summarized and discussed here for the first time. Key factors affecting the adsorption process such as the amount of doped metal, solution pH, and temperature are also reported and discussed. The adsorption mechanisms such as electrostatic interaction, π-π interaction, hydrogen bonding and synergistic interaction between metal particles and carbon materials are proposed for organic dyes adsorption on metal-doped porous carbon with the help of related works from the literature. Finally, few suggestions for future studies on metal-doped porous carbon materials are proposed.

CBF Related Papers
Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

Robotics2120 citations2019-03-27arXiv ->

Control Barrier Functions: Theory and Applications

A. Ames, S. Coogan, M. Egerstedt, Gennaro Notomista, K. Sreenath et al.

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Robotics342 citations2017-07-12Paper ->

Discrete Control Barrier Functions for Safety-Critical Control of Discrete Systems with Application to Bipedal Robot Navigation

Ayush Agrawal, K. Sreenath

Other568 citations2016-07-06Paper ->

Exponential Control Barrier Functions for enforcing high relative-degree safety-critical constraints

Quan Nguyen, K. Sreenath

CBF Related Papers
Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Robotics0 citations2026-03-25arXiv ->

MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics

Junheng Li, Lizhi Yang, Aaron D. Ames

Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.

Robotics0 citations2026-03-25arXiv ->

MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics

Junheng Li, Lizhi Yang, Aaron D. Ames

Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.

Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

A. Kiss, Ersin Daş, T. G. Molnár, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Das, Tamas G. Molnar, Aaron D. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key challenge in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, the standard bCBF method utilizes the same backup controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative dynamic behavior. In this study, we generalize the bCBF framework by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Moreover, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2026-03-19arXiv ->

Topological Obstructions to the Existence of Control Barrier Functions

Massimiliano de Sa, Aaron D. Ames

In 1983, Brockett developed a topological necessary condition for the existence of continuous, asymptotically stabilizing control laws. Building upon recent work on necessary conditions for set stabilization, we develop Brockett-like necessary conditions for the existence of control barrier functions (CBFs). By leveraging the unique geometry of CBF safe sets, we provide simple and self-contained derivations of necessary conditions for the existence of CBFs and their safe, continuous controllers. We demonstrate the application of these conditions to instructive examples and kinematic nonholonomic systems, and discuss their relationship to Brockett's necessary condition.

Theory0 citations2026-03-18arXiv ->

Dynamical Properties of Safety Filters for Linear Systems and Affine Control Barrier Functions

Pol Mestres, Shima Sadat Mousavi, Aaron D. Ames

This letter studies the dynamical properties of safety filters designed based on Control Barrier Functions (CBF). This mechanism, which is popular in safety-critical applications, takes a nominal controller and minimally modifies it to render it safe. Although CBF-based safety filters make the closed-loop system safe, characterizing their additional dynamical properties, such as stability, boundedness, or existence of spurious equilibria, remains a challenging problem. Here, we address this problem for the case of linear systems and an affine CBF constraint. We provide conditions under which the closed-loop system presents undesired equilibria, unbounded trajectories, or the origin is globally exponentially stable.

Theory0 citations2026-03-18arXiv ->

Dynamical Properties of Safety Filters for Linear Systems and Affine Control Barrier Functions

Pol Mestres, S. Mousavi, Aaron D. Ames

This letter studies the dynamical properties of safety filters designed based on Control Barrier Functions (CBF). This mechanism, which is popular in safety-critical applications, takes a nominal controller and minimally modifies it to render it safe. Although CBF-based safety filters make the closed-loop system safe, characterizing their additional dynamical properties, such as stability, boundedness, or existence of spurious equilibria, remains a challenging problem. Here, we address this problem for the case of linear systems and an affine CBF constraint. We provide conditions under which the closed-loop system presents undesired equilibria, unbounded trajectories, or the origin is globally exponentially stable.

Robotics0 citations2026-03-05arXiv ->

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes et al.

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

Robotics0 citations2025-10-16arXiv ->

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames

Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety -- traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy -- both enforcing safer actions and biasing towards safer rewards -- enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on navigation tasks and on the Unitree G1 humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.

Robotics0 citations2025-10-01arXiv ->

Probabilistic Control Barrier Functions: Safety in Probability for Discrete-Time Stochastic Systems

Pol Mestres, Blake Werner, Ryan K. Cosner, Aaron D. Ames

Control systems operating in the real world face countless sources of unpredictable uncertainties. These random disturbances can render deterministic guarantees inapplicable and cause catastrophic safety failures. To overcome this, this paper proposes a method for designing safe controllers for discrete-time stochastic systems that retain probabilistic guarantees of safety. To do this we modify the traditional notion of a control barrier function (CBF) to explicitly account for these stochastic uncertainties and call these new modified functions probabilistic CBFs. We show that probabilistic CBFs can be used to design controllers that guarantee safety over a finite number of time steps with a prescribed probability. Next, by leveraging various uncertainty quantification methods, such as concentration inequalities and the scenario approach, we provide a variety of sufficient conditions that result in computationally tractable controllers with tunable probabilistic guarantees across a plethora of practical scenarios. Finally, we showcase the applicability of our results in simulation and hardware for the control of a quadruped robot.

MPC/Planning0 citations2025-09-04arXiv ->

Compatibility of Multiple Control Barrier Functions for Constrained Nonlinear Systems

Max H. Cohen, Eugene Lavretsky, Aaron D. Ames

Control barrier functions (CBFs) are a powerful tool for the constrained control of nonlinear systems; however, the majority of results in the literature focus on systems subject to a single CBF constraint, making it challenging to synthesize provably safe controllers that handle multiple state constraints. This paper presents a framework for constrained control of nonlinear systems subject to box constraints on the systems’ vector-valued outputs using multiple CBFs. Our results illustrate that when the output has a vector relative degree, the CBF constraints encoding these box constraints are compatible, and the resulting optimization-based controller is locally Lipschitz continuous and admits a closed-form expression. Additional results are presented to characterize the degradation of nominal tracking objectives in the presence of safety constraints. Simulations of a planar quadrotor are presented to demonstrate the efficacy of the proposed framework.

Robotics0 citations2025-08-15arXiv ->

Geometry-Aware Predictive Safety Filters on Humanoids: From Poisson Safety Functions to CBF Constrained MPC

Ryan M. Bena, Gilbert Bahati, Blake Werner, Ryan K. Cosner, Lizhi Yang et al.

Autonomous navigation through unstructured and dynamically-changing environments is a complex task that continues to present many challenges for modern roboticists. In particular, legged robots typically possess manipulable asymmetric geometries which must be considered during safetycritical trajectory planning. This work proposes a predictive safety filter: a nonlinear model predictive control (MPC) algorithm for online trajectory generation with geometry-aware safety constraints based on control barrier functions (CBFs). Critically, our method leverages Poisson safety functions to numerically synthesize CBF constraints directly from perception data. We extend the theoretical framework for Poisson safety functions to incorporate temporal changes in the domain by reformulating the static Dirichlet problem for Poisson's equation as a parameterized moving boundary value problem. Furthermore, we employ Minkowski set operations to lift the domain into a configuration space that accounts for robot geometry. Finally, we implement our real-time predictive safety filter on humanoid and quadruped robots in various safetycritical scenarios. The results highlight the versatility of Poisson safety functions, as well as the benefit of CBF constrained model predictive safety-critical controllers.

Robotics3 citations2025-05-16arXiv ->

SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics

Lizhi Yang, Blake Werner, Ryan K. Cosner, David Fridovich-Keil, Preston Culbertson et al.

Robot learning has produced remarkably effective "black-box" controllers for complex tasks such as dynamic locomotion on humanoids. Yet ensuring dynamic safety, i.e., constraint satisfaction, remains challenging for such policies. Reinforcement learning (RL) embeds constraints heuristically through reward engineering, and adding or modifying constraints requires retraining. Model-based approaches, like control barrier functions (CBFs), enable runtime constraint specification with formal guarantees but require accurate dynamics models. This paper presents SHIELD, a layered safety framework that bridges this gap by: (1) training a generative, stochastic dynamics residual model using real-world data from hardware rollouts of the nominal controller, capturing system behavior and uncertainties; and (2) adding a safety layer on top of the nominal (learned locomotion) controller that leverages this model via a stochastic discrete-time CBF formulation enforcing safety constraints in probability. The result is a minimally-invasive safety layer that can be added to the existing autonomy stack to give probabilistic guarantees of safety that balance risk and performance. In hardware experiments on an Unitree G1 humanoid, SHIELD enables safe navigation (obstacle avoidance) through varied indoor and outdoor environments using a nominal (unknown) RL controller and onboard perception.

Learning0 citations2025Paper ->

Learning for Layered Safety-Critical Control with Predictive Control Barrier Functions

William D. Compton, Max H. Cohen, Aaron D. Ames

Robotics8 citations2024-12-05arXiv ->

Learning for Layered Safety-Critical Control with Predictive Control Barrier Functions

William D. Compton, Max H. Cohen, Aaron D. Ames

Safety filters leveraging control barrier functions (CBFs) are highly effective for enforcing safe behavior on complex systems. It is often easier to synthesize CBFs for a Reduced order Model (RoM), and track the resulting safe behavior on the Full order Model (FoM) -- yet gaps between the RoM and FoM can result in safety violations. This paper introduces \emph{predictive CBFs} to address this gap by leveraging rollouts of the FoM to define a predictive robustness term added to the RoM CBF condition. Theoretically, we prove that this guarantees safety in a layered control implementation. Practically, we learn the predictive robustness term through massive parallel simulation with domain randomization. We demonstrate in simulation that this yields safe FoM behavior with minimal conservatism, and experimentally realize predictive CBFs on a 3D hopping robot.

Robotics0 citations2024-11-25arXiv ->

Safety-Critical Controller Synthesis with Reduced-Order Models

Max H. Cohen, Noel Csomay-Shanklin, William D. Compton, T. Molnár, Aaron D. Ames

Reduced-order models (ROMs) provide lower dimensional representations of complex systems, capturing their salient features while simplifying control design. Building on previous work, this paper presents an overarching framework for the integration of ROMs and control barrier functions, enabling the use of simplified models to construct safety-critical controllers while providing safety guarantees for complex full-order models. To achieve this, we formalize the connection between full and ROMs by defining projection mappings that relate the states and inputs of these models and leverage simulation functions to establish conditions under which safety guarantees may be transferred from a ROM to its corresponding full-order model. The efficacy of our framework is illustrated through simulation results on a drone and hardware demonstrations on ARCHER, a 3D hopping robot.

Robotics3 citations2024-11-12arXiv ->

Robust Adaptive Safe Robotic Grasping with Tactile Sensing

Yitaek Kim, Jeeseop Kim, Albert H. Li, Aaron D. Ames, Christoffer Sloth

Robotic grasping requires safe force interaction to prevent a grasped object from being damaged or slipping out of the hand. In this vein, this paper proposes an integrated framework for grasping with formal safety guarantees based on Control Barrier Functions. We first design contact force and force closure constraints, which are enforced by a safety filter to accomplish safe grasping with finger force control. For sensory feedback, we develop a technique to estimate contact point, force, and torque from tactile sensors at each finger. We verify the framework with various safety filters in a numerical simulation under a two-finger grasping scenario. We then experimentally validate the framework by grasping multiple objects, including fragile lab glassware, in a real robotic setup, showing that safe grasping can be successfully achieved in the real world. We evaluate the performance of each safety filter in the context of safety violation and conservatism, and find that disturbance observer-based control barrier functions provide superior performance for safety guarantees with minimum conservatism.

Robotics7 citations2024-07-10Paper ->

Receding Horizon CBF-Based Multi-Layer Controllers for Safe Trajectory Generation

Lorenzo Sforni, G. Notarstefano, Aaron D. Ames

In this paper, we present a safe trajectory generation strategy for multi-layer control architectures. We develop a high-level, continuous-time trajectory generation strategy based on optimal control, which ensures the satisfaction of safety-critical constraints via Control Barrier Functions (CBFs). The proposed strategy leverages a receding horizon CBF-based optimal control problem formulation that, as the prediction horizon goes to infinity, generates system trajectories equivalent to the solution of the original (constrained) optimal control problem. Conversely, as the horizon approaches zero, the resulting trajectory is equivalent to the one obtained by applying a safety filter to the optimal (unconstrained) controller. Instrumental to our results is a novel characterization of CBFs in the context of control invariance of safe sets. The proposed approach is realized through a multi-layer implementation on a unicycle system in the context of autonomous navigation.

Theory2 citations2024-07-10Paper ->

Approximating Regions of Attraction via Flow-Control Barrier Functions and Constrained Polytope Expansion

Wyatt Ubellacker, Noel Csomay-Shanklin, Aaron D. Ames

Regions of attraction are a fundamental and extensively researched concept in control theory—their accurate characterization is essential to establishing the robustness of equilibria to perturbations since they quantify the set of initial conditions that converge to a given stable equilibrium point. They are of special interest for nonlinear dynamical systems, as they often lack analytical solutions and therefore require the use of numerical methods to obtain useful approximations. In this paper, we leverage recent results in control barrier function theory to propose a novel method to approximate regions of attraction about stable fixed points. First, we establish connections between the region of attraction and the idea of an “explicit region of attraction” for dynamical systems. This motivates an extension of control barrier functions termed flow-control barrier functions $(\phi-\boldsymbol{CBF})$, and we introduce the idea of an “auxiliary dynamical system” connected to a target system via a $\phi-\mathbf{CBF}$. We construct a time-varying polytope governed by expansion dynamics, but bounded to lie within the desired region of attraction. The main result establishes that as the number of polytope vertices increases, this polytope approximates the region of attraction with arbitrary accuracy. We illustrate our method through various compelling examples.

Robotics0 citations2024-03-09arXiv ->

Bounding Stochastic Safety: Leveraging Freedman’s Inequality With Discrete-Time Control Barrier Functions

Ryan K. Cosner, Preston Culbertson, Aaron D. Ames

When deployed in the real world, safe control methods must be robust to unstructured uncertainties such as modeling error and external disturbances. Typical robust safety methods achieve their guarantees by always assuming that the worst-case disturbance will occur. In contrast, this letter utilizes Freedman’s inequality in the context of discrete-time control barrier functions (DTCBFs) and c-martingales to provide stronger (less conservative) safety guarantees for stochastic systems. Our approach accounts for the underlying disturbance distribution instead of relying exclusively on its worst-case bound and does not require the barrier function to be upper-bounded, which makes the resulting safety probability bounds more useful for intuitive safety constraints such as signed distance. We compare our results with existing safety guarantees, such as input-to-state safety (ISSf) and martingale results that rely on Ville’s inequality. When the assumptions for all methods hold, we provide a range of parameters for which our guarantee is stronger. Finally, we present simulation examples, including a bipedal walking robot, that demonstrate the utility and tightness of our safety guarantee.

MPC/Planning0 citations2023-11-03arXiv ->

Safe Online Dynamics Learning with Initially Unknown Models and Infeasible Safety Certificates

A. Capone, Ryan K. Cosner, Aaron D. Ames, Sandra Hirche

Safety-critical control tasks with high levels of uncertainty are becoming increasingly common. Typically, techniques that guarantee safety during learning and control utilize constraint-based safety certificates, which can be leveraged to compute safe control inputs. However, excessive model uncertainty can render robust safety certification methods or infeasible, meaning no control input satisfies the constraints imposed by the safety certificate. This paper considers a learning-based setting with a robust safety certificate based on a control barrier function (CBF) second-order cone program. If the control barrier function certificate is feasible, our approach leverages it to guarantee safety. Otherwise, our method explores the system dynamics to collect data and recover the feasibility of the control barrier function constraint. To this end, we employ a method inspired by well-established tools from Bayesian optimization. We show that if the sampling frequency is high enough, we recover the feasibility of the robust CBF certificate, guaranteeing safety. Our approach requires no prior model and corresponds, to the best of our knowledge, to the first algorithm that guarantees safety in settings with occasionally infeasible safety certificates without requiring a backup non-learning-based controller.

Non-CBF Papers
Other0 citationsPaper ->

Towards Dynamical Safety on Humanoids with Stochastic Controllers with SHIELD

∗. LizhiYang, ∗. BlakeWerner, Ryan K. Cosner, David Fridovich-Keil, Preston Culbertson et al.

Robotics0 citations2026-01-09arXiv ->

Walk the PLANC: Physics-Guided RL for Agile Humanoid Locomotion on Constrained Footholds

Min Dai, William D. Compton, Junheng Li, Lizhi Yang, Aaron D. Ames

Bipedal humanoid robots must precisely coordinate balance, timing, and contact decisions when locomoting on constrained footholds such as stepping stones, beams, and planks -- even minor errors can lead to catastrophic failure. Classical optimization and control pipelines handle these constraints well but depend on highly accurate mathematical representations of terrain geometry, making them prone to error when perception is noisy or incomplete. Meanwhile, reinforcement learning has shown strong resilience to disturbances and modeling errors, yet end-to-end policies rarely discover the precise foothold placement and step sequencing required for discontinuous terrain. These contrasting limitations motivate approaches that guide learning with physics-based structure rather than relying purely on reward shaping. In this work, we introduce a locomotion framework in which a reduced-order stepping planner supplies dynamically consistent motion targets that steer the RL training process via Control Lyapunov Function (CLF) rewards. This combination of structured footstep planning and data-driven adaptation produces accurate, agile, and hardware-validated stepping-stone locomotion on a humanoid robot, substantially improving reliability compared to conventional model-free reinforcement-learning baselines.

Other0 citations2025-10-16arXiv ->

Architecture Is All You Need: Diversity-Enabled Sweet Spots for Robust Humanoid Locomotion

Blake Werner, Lizhi Yang, Aaron D. Ames

Robust humanoid locomotion in unstructured environments requires architectures that balance fast low-level stabilization with slower perceptual decision-making. We show that a simple layered control architecture (LCA), a proprioceptive stabilizer running at high rate, coupled with a compact low-rate perceptual policy, enables substantially more robust performance than monolithic end-to-end designs, even when using minimal perception encoders. Through a two-stage training curriculum (blind stabilizer pretraining followed by perceptual fine-tuning), we demonstrate that layered policies consistently outperform one-stage alternatives in both simulation and hardware. On a Unitree G1 humanoid, our approach succeeds across stair and ledge tasks where one-stage perceptual policies fail. These results highlight that architectural separation of timescales, rather than network scale or complexity, is the key enabler for robust perception-conditioned locomotion.

Robotics0 citations2025-09-23arXiv ->

RoMoCo: Robotic Motion Control Toolbox for Reduced-Order Model-Based Locomotion on Bipedal and Humanoid Robots

Min Dai, Aaron D. Ames

We present RoMoCo, an open-source C++ toolbox for the synthesis and evaluation of reduced-order model-based planners and whole-body controllers for bipedal and humanoid robots. RoMoCo's modular architecture unifies state-of-the-art planners and whole-body locomotion controllers under a consistent API, enabling rapid prototyping and reproducible benchmarking. By leveraging reduced-order models for platform-agnostic gait generation, RoMoCo enables flexible controller design across diverse robots. We demonstrate its versatility and performance through extensive simulations on the Cassie, Unitree H1, and G1 robots, and validate its real-world efficacy with hardware experiments on the Cassie and G1 humanoids.

Robotics0 citations2025-09-23arXiv ->

Chasing Stability: Humanoid Running via Control Lyapunov Function Guided Reinforcement Learning

Zachary Olkin, Kejun Li, William D. Compton, Aaron D. Ames

Achieving highly dynamic behaviors on humanoid robots, such as running, requires controllers that are both robust and precise, and hence difficult to design. Classical control methods offer valuable insight into how such systems can stabilize themselves, but synthesizing real-time controllers for nonlinear and hybrid dynamics remains challenging. Recently, reinforcement learning (RL) has gained popularity for locomotion control due to its ability to handle these complex dynamics. In this work, we embed ideas from nonlinear control theory, specifically control Lyapunov functions (CLFs), along with optimized dynamic reference trajectories into the reinforcement learning training process to shape the reward. This approach, CLF-RL, eliminates the need to handcraft and tune heuristic reward terms, while simultaneously encouraging certifiable stability and providing meaningful intermediate rewards to guide learning. By grounding policy learning in dynamically feasible trajectories, we expand the robot's dynamic capabilities and enable running that includes both flight and single support phases. The resulting policy operates reliably on a treadmill and in outdoor environments, demonstrating robustness to disturbances applied to the torso and feet. Moreover, it achieves accurate global reference tracking utilizing only on-board sensors, making a critical step toward integrating these dynamic motions into a full autonomy stack.

Robotics2 citations2025-09-05arXiv ->

Hierarchical Reduced-Order Model Predictive Control for Robust Locomotion on Humanoid Robots

Adrian B. Ghansah, Sergio A. Esteban, Aaron D. Ames

As humanoid robots enter real-world environments, ensuring robust locomotion across diverse environments is crucial. This paper presents a computationally efficient hierarchical control framework for humanoid robot locomotion based on reduced-order models—enabling versatile step planning and incorporating arm and torso dynamics to better stabilize the walking. At the high level, we use the step-to-step dynamics of the ALIP model to simultaneously optimize over step periods, step lengths, and ankle torques via nonlinear MPC. The ALIP trajectories are used as references to a linear MPC framework that extends the standard SRB-MPC to also include simplified arm and torso dynamics. We validate the performance of our approach through simulation and hardware experiments on the Unitree G1 humanoid robot. In the proposed framework the high-level step planner runs at 40 Hz and the mid-level MPC at 500 Hz using the onboard mini-PC. Adaptive step timing increased the push recovery success rate by 36%, and the upper body control improved the yaw disturbance rejection. We also demonstrate robust locomotion across diverse indoor and outdoor terrains, including grass, stone pavement, and uneven gym mats.

Robotics1 citations2025-08-30arXiv ->

A Layered Control Perspective on Legged Locomotion: Embedding Reduced Order Models via Hybrid Zero Dynamics

Sergio A. Esteban, Max H. Cohen, Adrian B. Ghansah, Aaron D. Ames

Reduced-order models (ROMs) provide a powerful means of synthesizing dynamic walking gaits on legged robots. Yet this approach lacks the formal guarantees enjoyed by methods that utilize the full-order model (FOM) for gait synthesis, e.g., hybrid zero dynamics. This paper aims to unify these approaches through a layered control perspective. In particular, we establish conditions on when a ROM of locomotion yields stable walking on the full-order hybrid dynamics. To achieve this result, given an ROM we synthesize a zero dynamics manifold encoding the behavior of the ROM—controllers can be synthesized that drive the FOM to this surface, yielding hybrid zero dynamics. We prove that a stable periodic orbit in the ROM implies an input-to-state stable periodic orbit of the FOM’s hybrid zero dynamics, and hence the FOM dynamics. This result is demonstrated in simulation on a linear inverted pendulum ROM and a 5-link planar walking FOM.

Robotics0 citations2025-08-12arXiv ->

CLF-RL: Control Lyapunov Function Guided Reinforcement Learning

Kejun Li, Zachary Olkin, Yisong Yue, Aaron D. Ames

Reinforcement learning (RL) has shown promise in generating robust locomotion policies for bipedal robots, but often suffers from tedious reward design and sensitivity to poorly shaped objectives. In this work, we propose a structured reward shaping framework that leverages model-based trajectory generation and control Lyapunov functions (CLFs) to guide policy learning. We explore two model-based planners for generating reference trajectories: a reduced-order linear inverted pendulum (LIP) model for velocity-conditioned motion planning, and a precomputed gait library based on hybrid zero dynamics (HZD) using full-order dynamics. These planners define desired end-effector and joint trajectories, which are used to construct CLF-based rewards that penalize tracking error and encourage rapid convergence. This formulation provides meaningful intermediate rewards, and is straightforward to implement once a reference is available. Both the reference trajectories and CLF shaping are used only during training, resulting in a lightweight policy at deployment. We validate our method both in simulation and through extensive real-world experiments on a Unitree G1 robot. CLF-RL demonstrates significantly improved robustness relative to the baseline RL policy and better performance than a classic tracking reward RL formulation.

Robotics0 citations2025-06-20arXiv ->

Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Control

Albert H. Li, Brandon Hung, Aaron D. Ames, Jiuguang Wang, Simon Le Cleac'h et al.

Recent advancements in parallel simulation and successful robotic applications are spurring a resurgence in sampling-based model predictive control. To build on this progress, however, the robotics community needs common tooling for prototyping, evaluating, and deploying sampling-based controllers. We introduce Judo, a software package designed to address this need. To facilitate rapid prototyping and evaluation, Judo provides robust implementations of common sampling-based MPC algorithms and standardized benchmark tasks. It further emphasizes usability with simple but extensible interfaces for controller and task definitions, asynchronous execution for straightforward simulation-to-hardware transfer, and a highly customizable interactive GUI for tuning controllers interactively. While written in Python, the software leverages MuJoCo as its physics backend to achieve real-time performance, which we validate across both consumer and server-grade hardware. Code at https://github.com/bdaiinstitute/judo.

Robotics0 citations2025-06-11arXiv ->

Locomotion on Constrained Footholds via Layered Architectures and Model Predictive Control

Zachary Olkin, Aaron D. Ames

Computing stabilizing and optimal control actions for legged locomotion in real time is difficult due to the nonlinear, hybrid, and high dimensional nature of these robots. The hybrid nature of the system introduces a combination of discrete and continuous variables which causes issues for numerical optimal control. To address these challenges, we propose a layered architecture that separates the choice of discrete variables and a smooth Model Predictive Controller (MPC). The layered formulation allows for online flexibility and optimality without sacrificing real-time performance through a combination of gradient-free and gradient-based methods. The architecture leverages a sampling-based method for determining discrete variables, and a classical smooth MPC formulation using these fixed discrete variables. We demonstrate the results on a quadrupedal robot stepping over gaps and onto terrain with varying heights. In simulation, we demonstrate the controller on a humanoid robot for gap traversal. The layered approach is shown to be more optimal and reliable than common heuristic-based approaches and faster to compute than pure sampling methods.

Robotics0 citations2025-05-16arXiv ->

Bracing for Impact: Robust Humanoid Push Recovery and Locomotion with Reduced Order Models

Lizhi Yang, Blake Werner, Adrian B. Ghansah, Aaron D. Ames

Push recovery during locomotion will facilitate the deployment of humanoid robots in human-centered environments. In this paper, we present a unified framework for walking control and push recovery for humanoid robots, leveraging the arms for push recovery while dynamically walking. The key innovation is to use the environment, such as walls, to facilitate push recovery by combining Single Rigid Body model predictive control (SRB-MPC) with Hybrid Linear Inverted Pendulum (HLIP) dynamics to enable robust locomotion, push detection, and recovery by utilizing the robot's arms to brace against such walls and dynamically adjusting the desired contact forces and stepping patterns. Extensive simulation results on a humanoid robot demonstrate improved perturbation rejection and tracking performance compared to HLIP alone, with the robot able to recover from pushes up to 100 N for 0.2 s while walking at commanded speeds up to $0.5 ~\mathrm{m} / \mathrm{s}$. Robustness is further validated in scenarios with angled walls and multi-directional pushes.

Robotics0 citations2025-04-25arXiv ->

Robust Push Recovery on Bipedal Robots: Leveraging Multi-Domain Hybrid Systems with Reduced-Order Model Predictive Control

Min Dai, Aaron D. Ames

In this paper, we present a novel control framework to achieve robust push recovery on bipedal robots while locomoting. The key contribution is the unification of hybrid system models of locomotion with a reduced-order model predictive controller determining: foot placement, step timing, and ankle control. The proposed reduced-order model is an augmented Linear Inverted Pendulum model with zero moment point coordinates; this is integrated within a model predictive control framework for robust stabilization under external disturbances. By explicitly leveraging the hybrid dynamics of locomotion, our approach significantly improves stability and robustness across varying walking heights, speeds, step durations, and is effective for both flat-footed and more complex multi-domain heel-to-toe walking patterns. The framework is validated with high-fidelity simulation on Cassie, a 3D underactuated robot, showcasing real-time feasibility and substantially improved stability. The results demonstrate the robustness of the proposed method in dynamic environments.

Robotics0 citations2025-03-17arXiv ->

Layered Nonlinear Model Predictive Control for Robust Stabilization of Hybrid Systems

Zachary Olkin, Aaron D. Ames

Computing the receding horizon optimal control of nonlinear hybrid systems is typically prohibitively slow, limiting real-time implementation. To address this challenge, we propose a layered Model Predictive Control (MPC) architecture for robust stabilization of hybrid systems. A high level "hybrid" MPC is solved at a slow rate to produce a stabilizing hybrid trajectory, potentially sub-optimally, including a domain and guard sequence. This domain and guard sequence is passed to a low level "fixed mode" MPC which is a traditional, time-varying, state-constrained MPC that can be solved rapidly, e.g., using nonlinear programming (NLP) tools. A robust version of the fixed mode MPC is constructed by using tracking error tubes that are not guaranteed to have finite size for all time. Using these tubes, we demonstrate that the speed at which the fixed mode MPC is re-calculated is directly tied to the robustness of the system, thereby justifying the layered approach. Finally, simulation examples of a five link bipedal robot and a controlled nonlinear bouncing ball are used to illustrate the formal results.

Robotics0 citations2025-02-21arXiv ->

Reduced-Order Model Guided Contact-Implicit Model Predictive Control for Humanoid Locomotion

Sergio A. Esteban, Vince Kurtz, Adrian B. Ghansah, Aaron D. Ames

Humanoid robots have great potential for real-world applications due to their ability to operate in environments built for humans, but their deployment is hindered by the challenge of controlling their underlying high-dimensional nonlinear hybrid dynamics. While reduced-order models like the Hybrid Linear Inverted Pendulum (HLIP) are simple and computationally efficient, they lose whole-body expressiveness. Meanwhile, recent advances in Contact-Implicit Model Predictive Control (CI-MPC) enable robots to plan through multiple hybrid contact modes, but remain vulnerable to local minima and require significant tuning. We propose a control framework that combines the strengths of HLIP and CI-MPC. The reduced-order model generates a nominal gait, while CI-MPC manages the whole-body dynamics and modifies the contact schedule as needed. We demonstrate the effectiveness of this approach in simulation with a novel 24 degree-of-freedom humanoid robot: Achilles. Our proposed framework achieves rough terrain walking, disturbance recovery, robustness under model and state uncertainty, and allows the robot to interact with obstacles in the environment, all while running online in real-time at 50 Hz.

Robotics0 citations2024-11-22arXiv ->

Dynamic Tube MPC: Learning Tube Dynamics with Massively Parallel Simulation for Robust Safety in Practice

William D. Compton, Noel Csomay-Shanklin, Cole Johnson, Aaron D. Ames

Safe navigation of cluttered environments is a critical challenge in robotics. It is typically approached by separating the planning and tracking problems, with planning executed on a reduced order model to generate reference trajectories, and control techniques used to track these trajectories on the full order dynamics. Inevitable tracking error necessitates robustification of the nominal plan to ensure safety; in many cases, this is accomplished via worst-case bounding, which ignores the fact that some trajectories of the planning model may be easier to track than others. In this work, we present a novel method leveraging massively parallel simulation to learn a dynamic tube representation, which characterizes tracking performance as a function of actions taken by the planning model. Planning model trajectories are then optimized such that the dynamic tube lies in the free space, allowing a balance between performance and safety to be traded off in real time. The resulting Dynamic Tube MPC is applied to the 3D hopping robot ARCHER, enabling agile and performant navigation of cluttered environments, and safe collision-free traversal of narrow corridors.

Robotics0 citations2024-11-20arXiv ->

Dynamically Feasible Path Planning in Cluttered Environments via Reachable BéZier Polytopes

Noel Csomay-Shanklin, William D. Compton, Aaron D. Ames

The deployment of robotic systems in real world environments requires the ability to quickly produce paths through cluttered, non-convex spaces. These planned trajectories must be both kinematically feasible (i.e., collision free) and dynamically feasible (i.e., satisfy the underlying system dynamics), necessitating a consideration of both the free space and the dynamics of the robot in the path planning phase. In this work, we explore the application of reachable Bézier polytopes as an efficient tool for generating trajectories satisfying both kinematic and dynamic requirements. Furthermore, we demonstrate that by offloading specific computation tasks to the GPU, such an algorithm can meet tight real time requirements. We propose a layered control architecture that efficiently produces collision free and dynamically feasible paths for nonlinear control systems, and demonstrate the framework on the tasks of 3D hopping in a cluttered environment.

MPC/Planning0 citations2024-11-20arXiv ->

Bézier Reachable Polytopes: Efficient Certificates for Robust Motion Planning with Layered Architectures

Noel Csomay-Shanklin, Aaron D. Ames

Control architectures are often implemented in a layered fashion, combining independently designed blocks to achieve complex tasks. Providing guarantees for such hierarchical frameworks requires considering the capabilities and limitations of each layer and their interconnections at design time. To address this holistic design challenge, we introduce the notion of Bézier Reachable Polytopes – certificates of reachable points in the space of Bézier polynomial reference trajectories. This approach captures the set of trajectories that can be tracked by a low-level controller while satisfying state and input constraints, and leverages the geometric properties of Bézier polynomials to maintain an efficient polytopic representation. As a result, these certificates serve as a constructive tool for layered architectures, enabling long-horizon tasks to be reasoned about in a computationally tractable manner.

Learning0 citations2024-10-31arXiv ->

Get a Grip: Multi-Finger Grasp Evaluation at Scale Enables Robust Sim-to-Real Transfer

Tyler Ga Wei Lum, Albert H. Li, Preston Culbertson, K. Srinivasan, Aaron D. Ames et al.

This work explores conditions under which multi-finger grasping algorithms can attain robust sim-to-real transfer. While numerous large datasets facilitate learning generative models for multi-finger grasping at scale, reliable real-world dexterous grasping remains challenging, with most methods degrading when deployed on hardware. An alternate strategy is to use discriminative grasp evaluation models for grasp selection and refinement, conditioned on real-world sensor measurements. This paradigm has produced state-of-the-art results for vision-based parallel-jaw grasping, but remains unproven in the multi-finger setting. In this work, we find that existing datasets and methods have been insufficient for training discriminitive models for multi-finger grasping. To train grasp evaluators at scale, datasets must provide on the order of millions of grasps, including both positive and negative examples, with corresponding visual data resembling measurements at inference time. To that end, we release a new, open-source dataset of 3.5M grasps on 4.3K objects annotated with RGB images, point clouds, and trained NeRFs. Leveraging this dataset, we train vision-based grasp evaluators that outperform both analytic and generative modeling-based baselines on extensive simulated and real-world trials across a diverse range of objects. We show via numerous ablations that the key factor for performance is indeed the evaluator, and that its quality degrades as the dataset shrinks, demonstrating the importance of our new dataset. Project website at: https://sites.google.com/view/get-a-grip-dataset.

Robotics0 citations2024-10-14Paper ->

Learned Regions of Attraction for Safe Motion Primitive Transitions

Wyatt Ubellacker, Aaron D. Ames

Estimating regions of attraction (ROAs) of dynamical systems is critical for understanding the operational bounds within which a system will converge to a desired state. In this paper, we introduce a neural network-based approach to approximating ROAs that leverages labeled data generated by offline sampling and simulation of initial conditions, with labels determined by flow membership in an "explicit region of attraction." This framework is designed to estimate ROAs with a level of precision suitable for integration into a motion primitive transition framework as conditions to switch between candidate primitive behaviors. To account for gaps between the simulated environment and the real world, online learning is employed; this refines the offline-learned model of the ROA based on observed discrepancies between predicted and actual system behaviors. We validate this methodology on a quadrupedal robot, demonstrating that our ROA estimates can effectively model regions of attraction for a high-dimensional system. We show this for multiple primitive behaviors and in environments different from the training data. The outcomes highlight the usefulness of our method in estimating regions of attraction and informing transition conditions between primitive behaviors.

Robotics0 citations2024-09-23arXiv ->

A Contract Theory for Layered Control Architectures

Manuel Mazo, William D. Compton, Max H. Cohen, Aaron D. Ames

Autonomous systems typically leverage layered control architectures with a combination of discrete and continuous models operating at different timescales. As a result, layered systems form a new class of hybrid systems composed of systems operating on a diverse set of continuous and discrete signals. This paper formalizes the notion of a layered (hierarchical) control architecture through a theory of relations between its layers. This theory enables us to formulate contracts within layered control systems -- these define interfaces between layers and isolate the design of each layer, guaranteeing that composition of contracts at each layer results in a contract capturing the desired system-wide specification. Thus, the proposed theory yields the ability to analyze layered control architectures via a compositional approach.

CBF Related Papers
Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Robotics0 citations2020-10-30arXiv ->

Multi-Layered Safety for Legged Robots via Control Barrier Functions and Model Predictive Control

R. Grandia, Andrew J. Taylor, A. Ames, Marco Hutter

The problem of dynamic locomotion over rough terrain requires both accurate foot placement together with an emphasis on dynamic stability. Existing approaches to this problem prioritize immediate safe foot placement over longer term dynamic stability considerations, or relegate the coordination of foot placement and dynamic stability to heuristic methods. We propose a multi-layered locomotion framework that unifies Control Barrier Functions (CBFs) with Model Predictive Control (MPC) to simultaneously achieve safe foot placement and dynamic stability. Our approach incorporates CBF based safety constraints both in a low frequency kinodynamic MPC formulation and a high frequency inverse dynamics tracking controller. This ensures that safety-critical execution is considered when optimizing locomotion over a longer horizon. We validate the proposed method in a 3D stepping-stone scenario in simulation and experimentally on the ANYmal quadruped platform.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Learning0 citations2019-10-01arXiv ->

Adaptive Safety with Control Barrier Functions

Andrew J. Taylor, A. Ames

Adaptive Control Lyapunov Functions (aCLFs) were introduced 20 years ago, and provided a Lyapunov-based methodology for stabilizing systems with parameter uncertainty. The goal of this paper is to revisit this classic formulation in the context of safety-critical control. This will motivate a variant of aCLFs in the context of safety: adaptive Control Barrier Functions (aCBFs). Our proposed approach adaptively achieves safety by keeping the system’s state within a safe set even in the presence of parametric model uncertainty. We unify aCLFs and aCBFs into a single control methodology for systems with uncertain parameters in the context of a Quadratic Program (QP) based framework. We validate the ability of this unified framework to achieve stability and safety in an Adaptive Cruise Control (ACC) simulation.

CBF Related Papers
Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Das, Tamas G. Molnar, Aaron D. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key challenge in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, the standard bCBF method utilizes the same backup controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative dynamic behavior. In this study, we generalize the bCBF framework by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Moreover, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2026-03-17arXiv ->

Enforcing Mixed State-Input Constraints with Multiple Backup Control Barrier Functions: A Projection-based Approach

Laszlo Gacsi, Adam K. Kiss, Ersin Das, Tamas G. Molnar

Ensuring the safety of control systems often requires the satisfaction of constraints on states (such as position or velocity), control inputs (such as force), and a mixture of states and inputs (such as power that depends on both velocity and force). This paper presents a safety-critical control framework for enforcing mixed state-input constraints through a generalization of backup control barrier functions (backup CBFs). First, we extend the backup CBF approach to maintain multiple decoupled state and input constraints using a single backup set-backup controller pair. Second, we address mixed state-input constraints by converting them into state constraints using a projection from the state-input space to the state space along the backup controller. In the special case of decoupled state and input constraints, the proposed method simplifies the synthesis of backup CBFs by eliminating the need for saturating backup control laws. Finally, we demonstrate the efficacy of the proposed method on an inverted pendulum example, where constraints on the angle (state), torque (input), and power (mixture of state and input) are satisfied simultaneously.

CBF Related Papers
Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Das, Tamas G. Molnar, Aaron D. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key challenge in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, the standard bCBF method utilizes the same backup controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative dynamic behavior. In this study, we generalize the bCBF framework by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Moreover, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2026-03-17arXiv ->

Enforcing Mixed State-Input Constraints with Multiple Backup Control Barrier Functions: A Projection-based Approach

Laszlo Gacsi, Adam K. Kiss, Ersin Das, Tamas G. Molnar

Ensuring the safety of control systems often requires the satisfaction of constraints on states (such as position or velocity), control inputs (such as force), and a mixture of states and inputs (such as power that depends on both velocity and force). This paper presents a safety-critical control framework for enforcing mixed state-input constraints through a generalization of backup control barrier functions (backup CBFs). First, we extend the backup CBF approach to maintain multiple decoupled state and input constraints using a single backup set-backup controller pair. Second, we address mixed state-input constraints by converting them into state constraints using a projection from the state-input space to the state space along the backup controller. In the special case of decoupled state and input constraints, the proposed method simplifies the synthesis of backup CBFs by eliminating the need for saturating backup control laws. Finally, we demonstrate the efficacy of the proposed method on an inverted pendulum example, where constraints on the angle (state), torque (input), and power (mixture of state and input) are satisfied simultaneously.

CBF Related Papers
MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

MPC/Planning0 citations2026-03-18arXiv ->

Robust Dynamic Pricing and Admission Control with Fairness Guarantees

Yingqing Chen, Anni Li, Christos G. Cassandras, Homayoun Hamedmoghadam, Fabian Wirth et al.

Dynamic pricing is commonly used to regulate congestion in shared service systems. This paper is motivated by the fact that in the presence of users with varying price sensitivity (responsiveness), conventional monotonic pricing can lead to unfair outcomes by disproportionately excluding price-elastic users, particularly under high or uncertain demand. We therefore develop a fairness-oriented mechanism under demand uncertainty. The paper's contributions are twofold. First, we show that when fairness is imposed as a hard state constraint, the optimal (revenue maximizing) pricing policy is generally non-monotonic in demand. This structural result departs fundamentally from standard surge pricing rules and reveals that price reduction under heavy load may be necessary to maintain equitable access. Second, we address the problem that price elasticity among heterogeneous users is unobservable. To solve it, we develop a robust dynamic pricing and admission control framework that enforces capacity and fairness constraints for all user type distributions consistent with aggregate measurements. By integrating integral High Order Control Barrier Functions (iHOCBFs) with a robust optimization framework under uncertain user-type distribution, we obtain a controller that guarantees forward invariance of safety and fairness constraints while optimizing revenue. Numerical experiments demonstrate improved fairness and revenue performance relative to monotonic surge pricing policies.

Robotics0 citations2024-03-15arXiv ->

Robust Optimal Lane-changing Control for Connected Autonomous Vehicles in Mixed Traffic

Anni Li, Andres S. Chavez Armijos, Christos G. Cassandras

We derive time and energy-optimal policies for a Connected Autonomous Vehicle (CAV) to execute lane change maneuvers in mixed traffic, i.e., in the presence of both CAVs and Human Driven Vehicles (HDVs). These policies are also shown to be robust with respect to the unpredictable behavior of HDVs by exploiting CAV cooperation which can eliminate or greatly reduce the interaction between CAVs and HDVs. We derive a simple threshold-based criterion on the initial relative distance between two cooperating CAVs based on which an optimal policy is selected such that the lane-changing CAV merges ahead of a cooperating CAV in the target lane; in this case, the lane-changing CAV's trajectory becomes independent of HDV behavior. Otherwise, the interaction between CAVs and neighboring HDVs is formulated as a bilevel optimization problem with an appropriate behavioral model for an HDV, and an iterated best response (IBR) method is used to determine an equilibrium. We demonstrate the convergence of the IBR process under certain conditions. Furthermore, Control Barrier Functions (CBFs) are implemented to ensure the robustness of lane-changing behaviors by guaranteeing safety in both longitudinal and lateral directions despite HDV disturbances. Simulation results validate the effectiveness of our CAV controllers in terms of cost, safety guarantees, and limited disruption to traffic flow. Additionally, we demonstrate the robustness of the lane-changing behaviors in the presence of uncontrollable HDVs.

Theory0 citations2023-10-01arXiv ->

Safe Optimal Interactions Between Automated and Human-Driven Vehicles in Mixed Traffic with Event-Triggered Control Barrier Functions

Anni Li, Christos G. Cassandras, Wei Xiao

This paper studies safe driving interactions between Human-Driven Vehicles (HDVs) and Connected and Automated Vehicles (CAVs) in mixed traffic where the dynamics and control policies of HDVs are unknown and hard to predict. In order to address this challenge, we employ event-triggered Control Barrier Functions (CBFs) to estimate the HDV model online, construct data-driven and state-feedback safety controllers, and transform constrained optimal control problems for CAVs into a sequence of event-triggered quadratic programs. We show that we can ensure collision-free interactions between HDVs and CAVs and demonstrate the robustness and flexibility of our framework on different types of human drivers in lane-changing scenarios while guaranteeing the satisfaction of safety constraints.

Non-CBF Papers
MPC/Planning8 citationsPaper ->

Resource limited event-triggered model predictive control for continuous-time nonlinear systems based on first-order hold

Anni Li, Jitao Sun

Other3 citations2025-07-17Paper ->

Discovery of a polyethylene biodegradable laccase from Acinetobacter dijkshoorniae

Luxuan Wu, Xiufeng Wang, Anni Li, Haiyang Cui, Xiujuan Li

Plastic waste management, especially polyethylene (PE), is a global challenge due to its chemical inertness and resistance to degradation. Herein, we isolated a bacterial strain, Acinetobacter dijkshoorniae PE‐9, which can degrade PE films. Over 40 days, the strain reduced the film weight by 5.1%, with degradation confirmed by SEM, FTIR, water contact angle (WCA), and GPC analysis. Using whole‐genome sequencing, transcriptomics, and sequence similarity network analysis, we identified the key degradation enzyme, a multicopper oxidase (AcMCO). The crude AcMCO reduced the WCA of PE films from 97.0° to 60.1%, with its effect supported by SEM and GC–MS analysis. Molecular dynamics simulations revealed the AcMCO‐PE interaction pattern, identifying a methionine‐rich region (AcMCO‐MetRich, residues 328–446) crucial for binding to the PE surface. These findings provide insights into microbial PE degradation and the potential of AcMCO in enhancing plastic recycling.

Other5 citations2025-05-20Paper ->

Recent Advances in Electrochemical Benzylic C(sp3)−H Functionalization

Anni Li, Zhengjun He, Qiang Huang, Hongji Li

Direct benzylic C(sp3)–H functionalization has emerged as a topic in organic synthesis due to its critic role in constructing complex and valuable molecules. Among the various methodologies employed, electroorganic synthesis has garnered considerable attention in diversifying benzylic C(sp3)–H functionalization. In recent years, substantial progress has been made in electrochemical benzylic C(sp3)–H functionalization. However, a comprehensive review summarizing recent advancements in this area is still lacking. This review provides an overview of the latest developments (2021–2025) in electrochemical benzylic C(sp3)–H functionalization, with a particular emphasis on mechanistic insights and practical applications in the synthesis of biologically active molecules. Additionally, current challenges and future perspectives in this field are discussed.

Other4 citations2025-05-01Paper ->

Protein language model empowered the robust ASR-driven PET hydrolase featured with two PET binding motifs

Yibo Song, Anni Li, Haiyang Cui, Bo Zhou, Jie Qiao et al.

Learning3 citations2025-04-06Paper ->

Dynamic SpikFormer: Low-Latency & Energy-Efficient Spiking Neural Networks with Dynamic Time Steps for Vision Transformers

G. Datta, Zeyu Liu, Anni Li, P. Beerel

Spiking Neural Networks (SNNs) have emerged as a popular spatio-temporal computing paradigm for complex vision tasks. Recently proposed SNN training algorithms have significantly reduced the number of time steps (down to 1) for improved latency and energy efficiency, however, they target only convolutional neural networks (CNN). These algorithms, when applied to the recently spotlighted vision transformers (ViT), either require a large number of time steps or fail to converge. Based on the analysis of the histograms of the ANN and SNN activation maps, we hypothesize that each ViT block has a different sensitivity to the number of time steps. We propose a novel training framework that dynamically allocates the number of time steps to each ViT module depending on a trainable score assigned to each timestep. In particular, we generate a scalar binary time step mask that filters spikes emitted by each neuron in a leaky-integrate-and-fire (LIF) layer. The resulting SNNs have high activation sparsity and require only accumulate operations (AC), except for the input embedding layer, in contrast to expensive multiply-and-accumulates (MAC) needed in traditional ViTs. This yields significant improvements in energy efficiency. We evaluate our training framework and resulting SNNs on image recognition tasks including CIFAR10, CIFAR100, and ImageNet with different ViT architectures. We obtain a test accuracy of 95.97% with 4.97 time steps with direct encoding on CIFAR10.

Robotics11 citations2025-04-01Paper ->

Robust optimal lane-changing control for Connected Autonomous Vehicles in mixed traffic

Anni Li, Andres S. Chavez Armijos, Christos G. Cassandras

Learning0 citations2025-03-28arXiv ->

A Cooperative Compliance Control Framework for Socially Optimal Mixed Traffic Routing

Anni Li, Ting Bai, Yingqing Chen, Christos G. Cassandras, Andreas A. Malikopoulos

In this paper, we propose a Cooperative Compliance Control framework for mixed traffic routing, where a Social Planner optimizes vehicle routes for system-wide optimality while a compliance controller incentivizes human drivers to align their behavior with route guidance from the Social Planner through a "refundable toll" scheme. A key challenge arises from the heterogeneous and unknown response models of different human driver types to these tolls, making it difficult to design a proper controller and achieve desired compliance probabilities over the traffic network. To address this challenge, we employ Control Lyapunov Functions to adaptively correct crucial components of our compliance probability model online, construct data-driven feedback controllers, and demonstrate that we can achieve the desired compliance probability for HDVs, thereby contributing to the social optimality of the traffic network.

Other14 citations2025-03-17Paper ->

Climate warming may undermine sleep duration and quality in repeated-measure study of 23 million records

Anni Li, Huihuan Luo, Yixiang Zhu, Zheqi Zhang, Binbin Liu et al.

The impact of rising ambient temperatures on sleep and its phases under climate change is becoming increasingly concerning but remains underexplored. Sleep, consisting of non-rapid eye movement and rapid eye movement phases, is crucial for health, and insufficient sleep in either phase could have significant implications. Based on sleep monitoring data of 23 million days from 214,445 participants across mainland China, we investigated how daily average temperature affected sleep. For each 10 °C increase in ambient temperature, the odds of sleep insufficiency increased by 20.1%, while total sleep duration decreased by 9.67 minutes, with deep sleep declining the most (by 2.82%). Projections under the unrestricted (SSP5-8.5) greenhouse gas emission scenario suggest that by the end of the century, sleep insufficiency could rise by 10.50%, with an annual loss of 33.28 hours of sleep per person. These findings highlight the potential of climate warming to exacerbate sleep deprivation and degrade sleep quality, especially for the elderly, women, individuals with obesity, and regions of South, Centre and East. The impact of rising temperatures on sleep and its components under climate change remains underexplored. Here, authors show that climate warming can significantly exacerbate sleep deprivation, with a pronounced effect on duration of deep sleep.

MPC/Planning0 citations2025-03-16arXiv ->

Routing Guidance for Emerging Transportation Systems with Improved Dynamic Trip Equity

Ting Bai, Anni Li, Gehui Xu, Christos G. Cassandras, Andreas A. Malikopoulos

This paper presents a dynamic routing guidance system that optimizes route recommendations for individual vehicles in an emerging transportation system while enhancing travelers’ trip equity. We develop a framework to quantify trip quality and equity in dynamic travel environments, providing new insights into how routing guidance influences equity in road transportation. Our approach enables real-time routing by incorporating both monitored and anticipated traffic congestion. We provide conditions that ensure perfect trip equity for all travelers in a free-flow network. Simulation studies on 1,000 vehicles traversing an urban road network in Boston demonstrate that our method improves trip equity by approximately 11.4% compared to the shortest-route strategy. In addition, the results reveal that our approach redistributes travel costs across vehicle types through route optimization, contributing to a more equitable transportation system.

Other3 citations2025-01-26Paper ->

Ancestral Sequence Reconstruction and Comprehensive Computational Simulations Unmask an Efficient PET Hydrolase with the Wobbled Catalytic Triad.

Yibo Song, Anni Li, Haiyang Cui, Luxuan Wu, Bo Zhou et al.

Beyond directed evolution, ancestral sequence reconstruction (ASR) has emerged as a powerful strategy for engineering proteins with superior functional properties. Herein, we harnessed ASR to uncover robust PET hydrolase variants, expanding the repertoire of PET-degrading enzymes and providing deeper insights into the underlying mechanisms of PET hydrolysis. As a result, ASR1-PETase, featuring a unique cysteine catalytic site, was discovered. Despite having only 19.3% sequence identity with IsPETase, ASR1-PETase demonstrated improved PET degradation efficiency, with a finely-tuned substrate-binding cleft. Comprehensive experimental validation, including mutagenesis studies and comparisons with six state-of-the-art PET hydrolases, combined with microsecond-scale molecular dynamics (MD) simulations and QM-cluster calculations, revealed that ASR1-PETase's C161 catalytic residue assisted with the wobbled H242 can simultaneously cleave both ester bonds of BHET-a feature not commonly observed in other PET hydrolases. This mechanism may serve as the primary driving force for accelerating PET hydrolysis while minimizing the accumulation of the intermediate MHET, thereby enhancing the efficiency of TPA production.

MPC/Planning15 citations2024-12-18Paper ->

Global, regional, and national burden of early-onset colorectal cancer and projection to 2050: An analysis based on the Global Burden of Disease Study 2021.

Xinyi Li, Xueyan Xiao, Zenghong Wu, Anni Li, Weijun Wang et al.

OBJECTIVES Early-onset colorectal cancer (EO-CRC) is becoming increasingly concerning due to its impact on individuals under 50 years old. We explored the burden of EO-CRC to provide information for planning effective management and prevention strategies. STUDY DESIGN We conducted secondary analyses to assess the burden of EO-CRC using data from GBD 2021. METHODS The incidence, prevalence, deaths, disability-adjusted life years (DALYs) and their rates across 204 countries and territories were obtained from GBD 2021 database. The estimated annual percentage change (EAPC) calculation was used to assess temporal trends in these metrics. Additionally, we reported the proportion of DALYs attributable to risk factors and projected future disease burden till 2050. RESULTS The global number of new EO-CRC cases increased from 107,310 in 1990 to 211,890 in 2021. Both age-standardized incidence rate (ASIR) and prevalence rate (ASPR) of EO-CRC showed overall increases over the study period (ASIR: EAPC = 0.96 (0.9-1.02), ASPR: EAPC = 1.5 (1.44-1.55)). However, a decline in ASIR and ASPR was observed in 2020 and 2021. Males consistently showed higher EO-CRC indicators compared to females. Furthermore, projections indicated that deaths and DALYs cases are likely to fluctuate but generally increase by 2050, reaching 85,602 and 4,283,093, respectively. CONCLUSIONS The global impact of EO-CRC has increased significantly from 1990 to 2021, revealing notable variations across SDI regions, countries, age groups, and sexes. Besides, deaths and DALYs are predicted to rise by 2050. These results highlight the importance of implementing measures to address the growing burden of EO-CRC globally.

Other4 citations2024-08-27Paper ->

Electrochemical N‐Centered Radical‐Triggered Intramolecular N‐N Coupling for the Cyclization of o‐Aminyl Azobenzenes

Anna Gao, Kangjia Chen, Fang Ma, Anni Li, Hongji Li

An electrochemical radical cyclization of o‐aminyl azobenzenes via N‐centered radical generation has been developed for the synthesis of benzotriazoles. The cyclization of o‐aminyl azobenzenes bearing a sulfonyl protection on amine readily proceeds in the absence of any external transition metal catalyst or chemical oxidant, and exhibits good tolerance towards functional groups.

Other7 citations2024-07-22Paper ->

Electrochemical Cyclization of o-Aminyl Azobenzenes: Roles of Aldehydes in N-N Bond Cleavage.

Anni Li, Anna Gao, Kangjia Chen, Hongji Li

Direct functionalization of azobenzenes provides an approach to obtaining valuable molecules in synthetic chemistry. However, an efficient method for the cleavage of the N═N bond of azobenzenes, which is a key process for this transformation, is still lacking. We herein disclose an electrochemical reduction-induced cyclization of azobenzenes with aldehydes via N═N bond cleavage. This electrochemical cyclization of azobenzenes proceeds well in the absence of any transition metals or external chemical oxidants, leading to the formation of N-protected benzimidazoles in moderate to good yields.

Other0 citations2024-07-18arXiv ->

0.7 MW Yb:YAG pumped degenerate optical parametric oscillator at 2.06 μm

Anni Li, Mehran Bahri, R. Gray, Seowon Choi, Sajjad Hoseinkhani et al.

Frequency comb spectroscopy and field-resolved broadband absorption spectroscopy are promising techniques for rapid, precise, and sensitive detection of short-lived atmospheric pollutants on-site. Enhancing detection sensitivity in absorption spectroscopy hinges on bright sources that cover molecular resonances and fast signal modulation techniques to implement lock-in detection schemes efficiently. Yb:YAG thin-disk lasers, combined with optical parametric oscillators (OPOs), present a compelling solution to fulfill these requirements. In this work, we report on a bright OPO pumped using a Yb:YAG thin-disk Kerr-lens mode-locked oscillator delivering 2.8 W, 114 fs pulses at 2.06 μm with an averaged energy of 90 nJ. The OPO cavity operates at 30.9 MHz repetition rate—twice the repetition rate of the pump laser—allowing for a broadband, efficient, and dispersion-free modulation of the OPO output pulses at a 15.45 MHz rate. With 13% optical-to-optical conversion efficiency and a high-frequency intra-cavity modulation, this scalable scheme holds promise to advance the detection sensitivity and frontiers of field-resolved spectroscopy.

Other17 citations2024-05-01Paper ->

Higher ambient temperatures may worsen obstructive sleep apnea: A nationwide smartwatch-based analysis of 6.2 million person-days.

Anni Li, Qingli Zhang, Yuan Yao, Xinlei Zhu, Cong Liu et al.

Obstructive sleep apnea (OSA) is a serious type of sleep disorder that can lead to cardiometabolic and neurocognitive diseases. We utilized smart device-based photoplethysmography technology to collect sleep data from the Chinese population from 2019 to 2022. Distributed lag nonlinear models combined with a generalized nonlinear model or a linear mixed effects model were used to investigate the short-term associations between daily temperature and indicators of OSA severity. We included a total of 6,232,056 d of sleep monitoring data from 51,842 participants with moderate to severe risk of OSA from 313 Chinese cities. The relationships between ambient temperature and OSA exacerbation, apnea-hypopnea index (AHI), and minimum oxygen saturation (MinSpO2) were almost linear and present only on the same day. Higher temperatures were associated with a greater risk of OSA exacerbation, with an 8.4% (95% confidence interval (CI): 7.6%-9.3%) increase per 10 °C increase in temperature. A 10 °C increase in daily temperature corresponded to an AHI increase of 0.70 events h-1 (95% CI: 0.65-0.76) and a MinSpO2 decrease of 0.18% (95% CI: 0.16%-0.19%). Exposure to elevated temperatures during the night can also lead to adverse effects. The effects of higher temperatures on OSA severity were stronger among men, participants with a body mass index ≥24 kg m-2, those aged 45 years and older, individuals with a history of hypertension and diabetes, and during the cold season. This large-scale, nationwide, longitudinal study provides robust evidence suggesting that higher ambient temperatures may immediately worsen OSA.

Other7 citations2024-05-01Paper ->

Air pollutants, genetic susceptibility, and incident schizophrenia in later life: A prospective study in the UK Biobank.

Qingli Zhang, Xia Meng, Huihuan Luo, Kexin Yu, Anni Li et al.

OBJECTIVE Air pollution has been linked to multiple psychiatric disorders, but little is known on its long-term association with schizophrenia. The interaction between air pollution and genetic susceptibility on incident schizophrenia has never been reported. We aimed to explore the associations between long-term air pollution exposure and late-onset schizophrenia and evaluate whether genetic susceptibility could modify the association. METHODS This population-based prospective cohort study included 437,802 middle-aged and elderly individuals free of schizophrenia at baseline in the UK Biobank. Land use regression models were applied in the estimation of the annual average concentrations of nitrogen dioxide (NO2), nitrogen oxides (NOx), fine particulate matter (PM2.5), and inhalable particulate matter (PM10) at residence. The associations between air pollutants and schizophrenia were evaluated by using Cox proportional hazard models. A polygenic risk score of schizophrenia was constructed for exploring potential interaction of air pollutants with genetic susceptibility. RESULTS An interquartile range increase in PM2.5, PM10, NO2, and NOx was associated with the hazard ratios (HR) for incident schizophrenia at 1.19, 1.16, 1.22, and 1.09, respectively. The exposure-response curves for the association of air pollution with incident schizophrenia were approximately linear. There are additive interactions of air pollution score (APS), PM10, NO2, and NOx with genetic risk. Specifically, compared with participants with low genetic susceptibility and low APS, the HR was 3.23 for individuals with high genetic risk and high APS, among which 0.49 excess risk could be attributed to the additive interaction, accounting for 15 % of the schizophrenia risk. CONCLUSION This large-scale, prospective cohort study conveys the first-hand evidence that long-term air pollution exposure could elevate schizophrenia incidence in later life, especially for individuals with higher genetic risks. The findings highlight the importance of improving air quality for preventing the late-onset schizophrenia in an aging era, especially among those with high genetic risks.

Other15 citations2024-04-20Paper ->

InstructPLM: Aligning Protein Language Models to Follow Protein Structure Instructions

Jiezhong Qiu, Junde Xu, Jie Hu, Hanqun Cao, Liya Hou et al.

Large language models are renowned for their efficacy in capturing intricate patterns, including co-evolutionary relationships, and underlying protein languages. However, current methodologies often fall short in illustrating the emergence of genomic insertions, duplications, and insertion/deletions (indels), which account for approximately 14% of human pathogenic mutations. Given that structure dictates function, mutated proteins with similar structures are more likely to persist throughout biological evolution. Motivated by this, we leverage crossmodality alignment and instruct fine-tuning techniques inspired by large language models to align a generative protein language model with protein structure instructions. Specifically, we present a method for generating variable-length and diverse proteins to explore and simulate the complex evolution of life, thereby expanding the repertoire of options for protein engineering. Our proposed protein LM-based approach, InstructPLM, demonstrates significant performance enhancements both in silico and in vitro. On native protein backbones, it achieves a perplexity of 2.68 and a sequence recovery rate of 57.51, surpassing Protein-MPNN by 39.2% and 25.1%, respectively. Furthermore, we validate the efficacy of our model by redesigning PETase and L-MDH. For PETase, all fifteen designed variable-length PETase exhibit depolymerization activity, with eleven surpassing the activity levels of the wild type. Regarding L-MDH, an enzyme lacking an experimentally determined structure, InstructPLM is able to design functional enzymes with an AF2-predicted structure. Code and model weights of InstructPLM are publicly available*.

Learning0 citations2024-03-20arXiv ->

AFLoRA: Adaptive Freezing of Low Rank Adaptation in Parameter Efficient Fine-Tuning of Large Models

Zeyu Liu, Souvik Kundu, Anni Li, Jun Wan, Lianghao Jiang et al.

We present a novel Parameter-Efficient Fine-Tuning (PEFT) method, dubbed as Adaptive Freezing of Low Rank Adaptation (AFLoRA). Specifically, for each pre-trained frozen weight tensor, we add a parallel path of trainable low-rank matrices, namely a down-projection and an up-projection matrix, each of which is followed by a feature transformation vector. Based on a novel freezing score, we the incrementally freeze these projection matrices during fine-tuning to reduce the computation and alleviate over-fitting. Our experimental results demonstrate that we can achieve state-of-the-art performance with an average improvement of up to $0.85\%$ as evaluated on GLUE benchmark while yeilding up to $9.5\times$ fewer average trainable parameters. While compared in terms of runtime, AFLoRA can yield up to $1.86\times$ improvement as opposed to similar PEFT alternatives. Besides the practical utility of our approach, we provide insights on the trainability requirements of LoRA paths at different modules and the freezing schedule for the different projection matrices. Code will be released.

Other8 citations2024-02-22Paper ->

Unlocking a Sustainable Future for Plastics: A Chemical-Enzymatic Pathway for Efficient Conversion of Mixed Waste to MHET and Energy-Saving PET Recycling.

Anni Li, Luxuan Wu, Haiyang Cui, Yibo Song, Xing Zhang et al.

The heterogeneous monomers obtained from plastic waste degradation are unfavorable for PET recondensation and high-value derivative synthesis. Herein, we developed an efficient chemical-enzymatic approach to convert mixed plastic wastes into homogeneous mono-2-hydroxyethyl terephthalate (MHET) without downstream purification, benefiting from three discovered BHETases (KbEst, KbHyd, and BrevEst) in nature. Towards the mixed plastic waste, integrating the chemical K2CO3-driven glycolysis process with the BHETase depolymerization technique resulted in an MHET yield of up to 98.26% in 40 h. Remarkably, BrevEst accomplished the highest BHET hydrolysis (~87% efficiency in 12 h) for yielding analytical-grade MHET compared to seven state-of-the-art PET hydrolases (18%-40%). In an investigation combining quantum theoretical computations and experimental validations, we established a MHET-initiated PET repolymerization pathway. This shortcut approach with MHET promises to strengthen the valorization of mixed plastics, offering a substantially more efficient and energy-saving route for PET recycling.

Other7 citations2024-02-01Paper ->

Long-term exposure to ambient air pollution and incident gout: A prospective cohort study in the UK Biobank.

Anni Li, Qingli Zhang, Lu Zhou, Huihuan Luo, Kexin Yu et al.

Gout is a chronic disorder characterized by the accumulation of uric acid in the body, leading to recurrent episodes of joint inflammation and pain. There remains a lack of studies investigating the association between long-term exposure to ambient air pollution and the incidence of gout. We conducted this prospective cohort study involving participants aged 38-70 from the UK Biobank who were enrolled in 2006-2010 and followed until 2023. Baseline residential concentrations of fine particulate matter (PM2.5), inhalable particulate matter (PM10), nitrogen dioxide (NO2) and nitrogen oxides (NOx) were predicted using land-use regression models. Cox proportional hazards models were employed to examine the relationship between air pollution and incident gout events. A total of 443,587 individuals were included in the analyses and a total of 6589 incident gout cases were identified over a follow-up of 6,130,439 person-years. There were significant associations between higher levels of air pollution and an increased incidence risk of gout. Higher risk of incident gout was associated with each interquartile range increase in concentrations of PM2.5 (hazard ratio:1.05, 95% confidence intervals: 1.02-1.09), PM10 (1.04, 1.00-1.07), NO2 (1.08, 1.05-1.12) and NOx (1.04, 1.02-1.07). The magnitude of associations was larger at higher concentrations. The association was more prominent among older adults, smokers, and individuals with lower and moderate physical activity. This prospective cohort study provides novel and compelling evidence of increased risk of incident gout associated with long-term air pollution exposures.

CBF Related Papers
MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

MPC/Planning0 citations2026-03-18arXiv ->

Robust Dynamic Pricing and Admission Control with Fairness Guarantees

Yingqing Chen, Anni Li, Christos G. Cassandras, Homayoun Hamedmoghadam, Fabian Wirth et al.

Dynamic pricing is commonly used to regulate congestion in shared service systems. This paper is motivated by the fact that in the presence of users with varying price sensitivity (responsiveness), conventional monotonic pricing can lead to unfair outcomes by disproportionately excluding price-elastic users, particularly under high or uncertain demand. We therefore develop a fairness-oriented mechanism under demand uncertainty. The paper's contributions are twofold. First, we show that when fairness is imposed as a hard state constraint, the optimal (revenue maximizing) pricing policy is generally non-monotonic in demand. This structural result departs fundamentally from standard surge pricing rules and reveals that price reduction under heavy load may be necessary to maintain equitable access. Second, we address the problem that price elasticity among heterogeneous users is unobservable. To solve it, we develop a robust dynamic pricing and admission control framework that enforces capacity and fairness constraints for all user type distributions consistent with aggregate measurements. By integrating integral High Order Control Barrier Functions (iHOCBFs) with a robust optimization framework under uncertain user-type distribution, we obtain a controller that guarantees forward invariance of safety and fairness constraints while optimizing revenue. Numerical experiments demonstrate improved fairness and revenue performance relative to monotonic surge pricing policies.

CBF Related Papers
MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

MPC/Planning0 citations2026-03-18arXiv ->

Robust Dynamic Pricing and Admission Control with Fairness Guarantees

Yingqing Chen, Anni Li, Christos G. Cassandras, Homayoun Hamedmoghadam, Fabian Wirth et al.

Dynamic pricing is commonly used to regulate congestion in shared service systems. This paper is motivated by the fact that in the presence of users with varying price sensitivity (responsiveness), conventional monotonic pricing can lead to unfair outcomes by disproportionately excluding price-elastic users, particularly under high or uncertain demand. We therefore develop a fairness-oriented mechanism under demand uncertainty. The paper's contributions are twofold. First, we show that when fairness is imposed as a hard state constraint, the optimal (revenue maximizing) pricing policy is generally non-monotonic in demand. This structural result departs fundamentally from standard surge pricing rules and reveals that price reduction under heavy load may be necessary to maintain equitable access. Second, we address the problem that price elasticity among heterogeneous users is unobservable. To solve it, we develop a robust dynamic pricing and admission control framework that enforces capacity and fairness constraints for all user type distributions consistent with aggregate measurements. By integrating integral High Order Control Barrier Functions (iHOCBFs) with a robust optimization framework under uncertain user-type distribution, we obtain a controller that guarantees forward invariance of safety and fairness constraints while optimizing revenue. Numerical experiments demonstrate improved fairness and revenue performance relative to monotonic surge pricing policies.

CBF Related Papers
Robotics436 citations2021-08-18Paper ->

High-Order Control Barrier Functions

Wei Xiao, C. Belta

We approach the problem of stabilizing a dynamical system while optimizing a cost and satisfying safety constraints and control limitations. For (nonlinear) affine control systems and quadratic costs, it has been shown that control barrier functions (CBFs) guaranteeing safety and control Lyapunov functions (CLFs) enforcing convergence can be used to (conservatively) reduce the optimal control problem to a sequence of quadratic programs (QPs). Existing works in this category have two main limitations. First, with one exception, they are based on the assumption that the relative degree of the system with respect to a function enforcing a safety constraint is one. Second, the QPs can easily become infeasible, in particular for problems with many safety constraints and tight control limitations. We propose high-order CBFs (HOCBFs), which can accommodate systems of arbitrary relative degrees. For each safety constraint, by using Lyapunov-like conditions, we construct a set of controls that renders the intersection of a set of sets forward invariant, which implies the satisfaction of the original constraint. We formulate optimal control problems with constraints given by HOCBF and CLF, and propose two methods—the penalty method and the parameterization method—to address the feasibility problem. Finally, we show how our methodology can be extended for safe navigation in unknown environments with long-term feasibility. We illustrate the proposed framework on adaptive cruise control and robot control problems.

MPC/Planning172 citations2021-04-21Paper ->

Adaptive Control Barrier Functions

Wei Xiao, C. Belta, C. Cassandras

It has been shown that optimizing quadratic costs while stabilizing affine control systems to desired (sets of) states subject to state and control constraints can be reduced to a sequence of quadratic programs (QPs) by using control barrier functions (CBFs) and control Lyapunov functions (CLFs). In this article, we introduce adaptive CBFs (aCBFs) that can accommodate time-varying control bounds and noise in the system dynamics while also guaranteeing the feasibility of the QPs if the original quadratic cost optimization problem itself is feasible, which is a challenging problem in current approaches. We propose two different types of aCBFs: parameter-adaptive CBF (PACBF) and relaxation-adaptive CBF (RACBF). Central to aCBFs is the introduction of appropriate time-varying functions to modify the definition of a common CBF. These time-varying functions are treated as high-order CBFs with their own auxiliary dynamics, which are stabilized by CLFs. We demonstrate the advantages of using aCBFs over the existing CBF techniques by applying both the PACBF-based method and the RACBF-based method to a cruise control problem with time-varying road conditions and noise in the system dynamics, and compare their relative performance.

Learning0 citations2019-03-12arXiv ->

Control Barrier Functions for Systems with High Relative Degree

Wei Xiao, C. Belta

This paper extends control barrier functions (CBFs) to high order control barrier functions (HOCBFs) that can be used for high relative degree constraints. The proposed HOCBFs are more general than recently proposed (exponential) HOCBFs. We introduce high order barrier functions (HOBFs), and show that their satisfaction of Lyapunov-like conditions implies the forward invariance of the intersection of a series of sets. We then introduce HOCBF, and show that any control input that satisfies the HOCBF constraint renders the intersection of a series of sets forward invariant. We formulate optimal control problems with constraints given by HOCBF and control Lyapunov functions (CLF), and provide a promising method to address the conflict between HOCBF constraints and control limitations by penalizing the class $\mathcal{K}$ functions. We illustrate the proposed method on an adaptive cruise control problem.

CBF Related Papers
Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

Other0 citations2026-03-17arXiv ->

Enforcing Mixed State-Input Constraints with Multiple Backup Control Barrier Functions: A Projection-based Approach

Laszlo Gacsi, Adam K. Kiss, Ersin Das, Tamas G. Molnar

Ensuring the safety of control systems often requires the satisfaction of constraints on states (such as position or velocity), control inputs (such as force), and a mixture of states and inputs (such as power that depends on both velocity and force). This paper presents a safety-critical control framework for enforcing mixed state-input constraints through a generalization of backup control barrier functions (backup CBFs). First, we extend the backup CBF approach to maintain multiple decoupled state and input constraints using a single backup set-backup controller pair. Second, we address mixed state-input constraints by converting them into state constraints using a projection from the state-input space to the state space along the backup controller. In the special case of decoupled state and input constraints, the proposed method simplifies the synthesis of backup CBFs by eliminating the need for saturating backup control laws. Finally, we demonstrate the efficacy of the proposed method on an inverted pendulum example, where constraints on the angle (state), torque (input), and power (mixture of state and input) are satisfied simultaneously.

CBF Related Papers
Robotics0 citations2026-03-25arXiv ->

MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics

Junheng Li, Lizhi Yang, Aaron D. Ames

Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.

Robotics0 citations2026-03-05arXiv ->

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes et al.

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

MPC/Planning0 citations2025-12-10arXiv ->

Explicit Control Barrier Function-based Safety Filters and their Resource-Aware Computation

Pol Mestres, S. Mousavi, Pio Ong, Lizhi Yang, Ersin Daş et al.

This paper studies the efficient implementation of safety filters that are designed using control barrier functions (CBFs), which minimally modify a nominal controller to render it safe with respect to a prescribed set of states. Although CBF-based safety filters are often implemented by solving a quadratic program (QP) in real time, the use of off-the-shelf solvers for such optimization problems poses a challenge in applications where control actions need to be computed efficiently at very high frequencies. In this paper, we introduce a closed-form expression for controllers obtained through CBF-based safety filters. This expression is obtained by partitioning the state-space into different regions, with a different closed-form solution in each region. We leverage this formula to introduce a resource-aware implementation of CBF-based safety filters that detects changes in the partition region and uses the closed-form expression between changes. We showcase the applicability of our approach in examples ranging from aerospace control to safe reinforcement learning.

Robotics0 citations2025-10-16arXiv ->

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames

Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety -- traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy -- both enforcing safer actions and biasing towards safer rewards -- enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on navigation tasks and on the Unitree G1 humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.

Robotics0 citations2025-08-15arXiv ->

Geometry-Aware Predictive Safety Filters on Humanoids: From Poisson Safety Functions to CBF Constrained MPC

Ryan M. Bena, Gilbert Bahati, Blake Werner, Ryan K. Cosner, Lizhi Yang et al.

Autonomous navigation through unstructured and dynamically-changing environments is a complex task that continues to present many challenges for modern roboticists. In particular, legged robots typically possess manipulable asymmetric geometries which must be considered during safetycritical trajectory planning. This work proposes a predictive safety filter: a nonlinear model predictive control (MPC) algorithm for online trajectory generation with geometry-aware safety constraints based on control barrier functions (CBFs). Critically, our method leverages Poisson safety functions to numerically synthesize CBF constraints directly from perception data. We extend the theoretical framework for Poisson safety functions to incorporate temporal changes in the domain by reformulating the static Dirichlet problem for Poisson's equation as a parameterized moving boundary value problem. Furthermore, we employ Minkowski set operations to lift the domain into a configuration space that accounts for robot geometry. Finally, we implement our real-time predictive safety filter on humanoid and quadruped robots in various safetycritical scenarios. The results highlight the versatility of Poisson safety functions, as well as the benefit of CBF constrained model predictive safety-critical controllers.

Robotics3 citations2025-05-16arXiv ->

SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics

Lizhi Yang, Blake Werner, Ryan K. Cosner, David Fridovich-Keil, Preston Culbertson et al.

Robot learning has produced remarkably effective "black-box" controllers for complex tasks such as dynamic locomotion on humanoids. Yet ensuring dynamic safety, i.e., constraint satisfaction, remains challenging for such policies. Reinforcement learning (RL) embeds constraints heuristically through reward engineering, and adding or modifying constraints requires retraining. Model-based approaches, like control barrier functions (CBFs), enable runtime constraint specification with formal guarantees but require accurate dynamics models. This paper presents SHIELD, a layered safety framework that bridges this gap by: (1) training a generative, stochastic dynamics residual model using real-world data from hardware rollouts of the nominal controller, capturing system behavior and uncertainties; and (2) adding a safety layer on top of the nominal (learned locomotion) controller that leverages this model via a stochastic discrete-time CBF formulation enforcing safety constraints in probability. The result is a minimally-invasive safety layer that can be added to the existing autonomy stack to give probabilistic guarantees of safety that balance risk and performance. In hardware experiments on an Unitree G1 humanoid, SHIELD enables safe navigation (obstacle avoidance) through varied indoor and outdoor environments using a nominal (unknown) RL controller and onboard perception.

Non-CBF Papers
MPC/Planning5 citations2025-09-15Paper ->

Biomimetic Nanoregulators Mediated Tyrosine Hydroxylase mRNA and Stimulator of Interferon Genes Antagonist Codelivery for Synergistic Therapy on Parkinson's Disease.

Lizhi Yang, Shuo Li, Chao Hou, Yukang Zhang, Ling-gang Cheng et al.

Degeneration of dopaminergic neurons in substantia nigra and neuroinflammation caused by microglia is one of the basic pathological features of Parkinson's disease (PD). Currently, therapeutic strategies that enhance dopaminergic neuronal function while simultaneously mitigating neuroinflammation hold great promise but face significant challenges in clinical application. To address these challenges, we developed a neuron-derived exosome biomimetic multifunctional nanoregulator codelivered tyrosine hydroxylase (TH) mRNA and stimulator of interferon genes (STING) antagonist. This nanoregulator system simultaneously delivers TH mRNA to enhance dopaminergic neuronal function and activity while incorporating the STING antagonist H-151 to promote microglial polarization from the pro-inflammatory M1 phenotype to the anti-inflammatory M2 phenotype, effectively suppressing neuroinflammation. Both in vitro and in vivo studies demonstrate that via mRNA therapy can precisely target and regulate dopamine (DA) synthesis, and that combined anti-inflammatory treatment effectively enhances this effect, significantly alleviating motor dysfunction in PD mice. Our findings present an effective approach for the development of PD medications and the advanced delivery of mRNA nanomedicines. This innovative nanoregulator represents a promising therapeutic strategy for managing neuroinflammation and improving dopaminergic neuronal function in PD by merging mRNA-based gene therapy with neuroinflammation modulation, addressing DA deficiency at its root and overcoming the current treatment obstacles in PD.

Other5 citations2025-04-01Paper ->

Polysaccharides from Ganoderma lucidum attenuate cognitive impairment in 5xFAD mice by inhibiting oxidative stress and modulating mitochondrial dynamics via the Nrf2/antioxidative axis activation

Xiaoqin Liu, Yanbing Li, Jiwei Wang, Tao Meng, Lijuan Song et al.

Biomedical6 citations2025-01-03Paper ->

Recent advances in mRNA-based therapeutics for neurodegenerative diseases and brain tumors.

Lizhi Yang, Shuo Li, Chao Hou, Zihua Wang, Wen He et al.

Messenger RNA (mRNA) therapy is an innovative approach that delivers specific protein-coding information. By promoting the ribosomal synthesis of target proteins within cells, it supplements functional or antigenic proteins to treat diseases. Unlike traditional gene therapy, mRNA does not need to enter the cell nucleus, reducing the risks associated with gene integration. Moreover, protein expression levels can be regulated by adjusting the dosage and degradation rates of mRNA. As a new generation gene therapy strategy, mRNA therapy represents the latest advancements and trends in the field. It offers advantages such as precision, safety, and ease of modification. It has been widely used in the prevention of COVID-19. Unlike acute conditions such as cerebral hemorrhage and stroke that often require immediate surgical or interventional treatments, neurodegenerative diseases (NDs) and brain tumors progress relatively slowly and face challenges such as the blood-brain barrier and complex pathogenesis. These characteristics make them particularly suitable for mRNA therapy. With continued research, mRNA-based therapeutics are expected to play a significant role in the prevention and treatment of NDs and brain tumors. This paper reviews the preparation and delivery of mRNA drugs and summarizes the research progress of mRNA gene therapy in treating NDs and brain tumors. It also discusses the current challenges, providing a theoretical basis and reference for future research in this field.

Other19 citations2025-01-01Paper ->

Optimal scheduling of park-level integrated energy system considering multiple uncertainties: A comprehensive risk strategy-information gap decision theory method

Zhengxiong Ji, Jianyan Tian, Shuwei Liu, Lizhi Yang, Yuanyuan Dai et al.

Learning3 citations2024-11-01Paper ->

Exploring the neural mechanisms underlying cooperation and competition behavior: Insights from stereo-electroencephalography hyperscanning

Xiaojun Qiao, Rui Li, Huimin Huang, Yang Hong, Xiaoran Li et al.

Summary Cooperation and competition are essential social behaviors in human society. This study utilized hyperscanning and stereo-electroencephalography (SEEG) to investigate intra- and inter-brain neural dynamics underlying these behaviors within the insula and inferior frontal gyrus (IFG), regions critical for executive function and mentalizing. We found distinct high-gamma responses and connectivity patterns, with a stronger influence from IFG to insula during competition and more balanced interactions during cooperation. Inter-brain synchronization shows significantly higher insula gamma synchronization during competition and higher IFG gamma synchronization during cooperation. Cross-frequency coupling suggests that these gamma synchronizations result from intra- and inter-brain interactions. Competition stems from intra-brain alpha-gamma coupling from IFG to insula and inter-brain IFG alpha synchronization, while cooperation is driven by intra-brain beta-gamma coupling from insula to IFG and inter-brain insula beta synchronization. Our findings provide insights into the neural basis of cooperation and competition, highlighting the roles of both insula and IFG.

Other3 citations2024-08-14Paper ->

Study on the resilience recovery of civil airport infrastructure under weather extremes

Xin Huang, Lizhi Yang, Kun Wu, Cheng-song Tan, Lin Qi et al.

Other17 citations2024-06-25Paper ->

Ultrasonic-responsive piezoelectric stimulation enhances sonodynamic therapy for HER2-positive breast cancer

Zhiguang Chen, Lizhi Yang, Zhimin Yang, Zihua Wang, Wenzhan He et al.

Breast cancer ranks second as the most common malignancy globally, after lung cancer. Among the various subtypes of breast cancer, HER2 positive breast cancer (HER2 BC)poses a particularly challenging prognosis due to its heightened invasiveness and metastatic potential. The objective of this study was to construct a composite piezoelectric nanoparticle based on poly(vinylidene fluoride-trifluoroethylene) (P(VDF-TrFE)) for imaging and treatment of HER2 BC. By reshaping the crystal structure of P(VDF-TrFE) piezoelectric nanoparticles, improving hydrophilicity, and incorporating imaging capabilities, we developed piezoelectric composite nanoparticles (PGd@tNBs) that integrate imaging and therapeutic functions. The in vitro characterization encompassed the assessment of piezoelectric properties, hydrophilicity, imaging performance, and therapeutic efficacy of these particles. The targeting and therapeutic effectiveness of PGd@tNBs particles were further validated in the SK-BR3 cell line and subsequently confirmed in HER2-positive tumor-bearing mice. The nanoparticle demonstrated excellent biocompatibility and impressive multimodal imaging performance. Magnetic resonance imaging (MRI) observations revealed significant accumulation of PGd@tNBs particles in the HER2 positive tumor, exhibiting superior contrast-enhanced ultrasound performance compared to traditional ultrasound contrast agents, and small animal in vivo imaging showed that PGd@tNBs particles were primarily excreted through respiration and urinary metabolism. Piezoforce Microscopy characterization highlighted the outstanding piezoelectric properties of PGd@tNBs particles. Upon targeted binding to HER2-BC, ultrasound stimulation influenced the cell membrane potential, leading to reversible electroporation. This, in turn, affected the balance of calcium ions inside and outside the cells and the mitochondrial membrane potential. Following ingestion by cells, PGd@tNBs, when exposed to ultrasound, triggered the generation of reactive oxygen species (ROS), resulting in the consumption of glutathione and superoxide dismutase and achieving sonodynamic therapy. Notably, repeated ultrasound stimulation, post PGd@tNBs particles binding and entry into cells, increased ROS production and elevated the apoptosis rate by approximately 45%. In conclusion, the PGd@tNBs particles developed exhibit outstanding imaging and therapeutic efficacy, holding potential for precise diagnosis and personalized treatment of HER2 BC.

Other12 citations2024-06-15Paper ->

Comprehensive investigations of 2-phenylethanol production by the filamentous fungus Annulohypoxylon stygium

Qianwen Tong, Lizhi Yang, Jinxiang Zhang, Yue Zhang, Yuji Jiang et al.

Abstract 2-Phenylethanol (2-PE) is an aromatic compound with a rose-like fragrance that is widely used in food and other industries. Yeasts have been implicated in the biosynthesis of 2-PE; however, few studies have reported the involvement of filamentous fungi. In this study, 2-PE was detected in Annulohypoxylon stygium mycelia grown in both potato dextrose broth (PDB) and sawdust medium. Among the 27 A. stygium strains investigated in this study, the strain “Jinjiling” (strain S20) showed the highest production of 2-PE. Under optimal culture conditions, the concentration of 2-PE was 2.33 g/L. Each of the key genes in Saccharomyces cerevisiae shikimate and Ehrlich pathways was found to have homologous genes in A. stygium . Upon the addition of L-phenylalanine to the medium, there was an upregulation of all key genes in the Ehrlich pathway of A. stygium , which was consistent with that of S. cerevisiae . A. stygium as an associated fungus provides nutrition for the growth of Tremella fuciformis and most spent composts of T. fuciformis contain pure A. stygium mycelium. Our study on the high-efficiency biosynthesis of 2-PE in A. stygium offers a sustainable solution by utilizing the spent compost of T. fuciformis and provides an alternative option for the production of natural 2-PE. Key points • Annulohypoxylon stygium can produce high concentration of 2-phenylethanol. • The pathways of 2-PE biosynthesis in Annulohypoxylon stygium were analyzed. • Spent compost of Tremella fuciformis is a potential source for 2-phenylethanol.

Theory11 citations2023-11-10Paper ->

Disordered Convolution Region of P(VDF-TrFE) Piezoelectric Nanoparticles: The Core of Sono-Piezo Dynamic Therapy.

Zhiguang Chen, Lizhi Yang, Zhimin Yang, Zihua Wang, Wenzhan He et al.

The recent focus on P(VDF-TrFE) material in biomedical engineering stems from its outstanding mechanical properties and biocompatibility. However, its application in sono-piezo dynamic therapy (SPDT) has been relatively unexplored. In this study, we developed composite piezoelectric nanoparticles (rPGd NPs@RGD) based on recrystallized P(VDF-TrFE) particles, which offer dual capabilities of MRI imaging and targeted treatment for brain gliomas. SEM observations of P(VDF-TrFE) particles in the disordered convolution region (DCR) revealed recrystallization, representing the polymer chain structure and particle polarity. In comparison to nonrecrystallized nanoparticles, rPGd NPs@RGD exhibited remarkable stability and biocompatibility. Under ultrasound excitation, they generated significantly higher levels of reactive oxygen species, effectively inhibiting tumor cell proliferation, invasion, and migration. rPGd NPs@RGD demonstrated excellent MRI imaging capabilities and antitumor activity in U87 tumor-bearing mice. This study highlights the remarkable SPDT abilities of the developed nanoparticles, attributed to the microscopic morphological changes in the DCR that increase the nanoparticle's polarity and thus boost its potential for SPDT. This research opens new possibilities for utilizing P(VDF-TrFE) materials in advanced biomedical applications.

Other4 citations2023-03-15Paper ->

Decorin inhibits the formation of hard nodules after microwave ablation by inhibiting the TGF-β1/SMAD and MAPK signaling pathways: in a Bama miniature pig model of mammary gland hyperplasia

Yue-Hua Du, Xinyao Liu, Kai Du, Wenkai Zhang, Rui Li et al.

Abstract Background Benign breast lesions are often associated with hard nodule formation after microwave ablation (MWA), which persists for a long time and causes problems in patients. The aim of this study was to evaluate the efficacy of decorin in the treatment of hard nodule formation and its potential mechanism of action. Methods Using a Bama miniature pig model of mammary gland hyperplasia, immunohistochemistry, Masson’s trichrome and western blotting were firstly applied to compare the extent of fibrosis and activation of key members of the TGF-β1/SMAD and MAPK signaling pathways of hard nodule in the control and MWA groups, and then the extent of fibrosis and expression of signaling pathways in hard nodule were examined after application of decorin. Results The results showed that the MWA group had increased levels of TGF-β1, p-SMAD2/3, p-ERK1/2, and collagen I proteins and increased fibrosis at 2 weeks, 4 weeks, and 3 months after MWA. After decorin treatment, the expression levels of each protein were significantly downregulated, and the degree of fibrosis was reduced at 2 weeks, 4 weeks, and 3 months after MWA compared with the MWA group. Conclusion In conclusion, these results suggest that activation of TGF-β1 may play an important role in hard nodule formation and that decorin may reduce hard nodule formation after MWA in a model of mammary gland hyperplasia by inhibiting the TGF-β1/SMAD and MAPK signaling pathways.

Other31 citations2023-01-26Paper ->

Genes related to osmoregulation and antioxidation play important roles in the response of Trollius chinensis seedlings to saline-alkali stress

R. Hou, Lizhi Yang, T. Wuyun, Shiyao Chen, Lu Zhang

Saline-alkali stress is one of the main abiotic stress factors affecting plant growth and development. Trollius chinensis is a perennial herbal medicinal plant with high values for garden application. However, its response and tolerance to saline-alkali stress is unclear. In this study, we mixed four salts (NaCl: Na2SO4: NaHCO3: Na2CO3) with a concentration ratio of 1:9:9:1, and applied low (40 and 80 mM) and high (120 and 160 mM) saline-alkali stress to analyze osmotic regulation substances, antioxidant systems and the gene expression of T. chinensis. Along with higher saline-alkali stress, the leaf relative water content (RWC) started to decrease only from high stress, while the malondialdehyde (MDA) content in leaves decreased continuously, and the contents of proline (Pro), soluble sugar (SS) and soluble protein (SP) increased compared with control. The activities of antioxidant enzymes and the contents of non-enzymatic antioxidants were increased positively with the accumulation of superoxide anion (O2 •–) and hydrogen peroxide (H2O2). For instance, the ascorbic acid-glutathione (AsA-GSH) cycle was enhanced in T. chinensis seedling leaves subject to saline-alkali stress. Principal Component Analysis (PCA) indicates that MDA, Pro, SS, SP, H2O2, O2 •–, and GSH are important indexes to evaluate the response and tolerance of T. chinensis to saline-alkali stress. Through RNA-Seq, a total of 474 differentially expressed genes (DEGs) were found in plant under low saline-alkaline stress (40 mM, MSA1) vs. control. Among them, 364 genes were up-regulated and 110 genes were down-regulated. DEGs were extensively enriched in carbohydrate transport, transferase activity, zeatin biosynthesis, ABC transporters, and spliceosome. The transcription factor family MYB, BZIP, WRKY, and NAC were related to its saline-alkali tolerance. In addition, some DEGs encode key enzymes in the processes of osmoregulation and antioxidation, including betaine aldehyde dehydrogenase (BADH), inositol monophosphatase (IMP), chloroperoxidase (CPO), thioredoxin (Trx), and germin-like protein (GLPs) were found. Overall, these findings provide new insights into the physiological changes and molecular mechanism of T. chinensis to saline-alkali stress and lay a foundation for application of T. chinensis in saline-alkali environment.

Other6 citations2022-11-22Paper ->

Comparison of Pharmacokinetic Similarity, Immunogenicity, and Safety of Ustekinumab and BAT2206 in Healthy Chinese Male Subjects in a Double-Blind, Randomized, Single-Dose, Parallel-Group Phase I Trial

Min Wu, Xiaojiao Li, Deming Yang, Meng Wang, Hong Zhang et al.

Objective We aimed to evaluate the similarity of BAT2206 to its originator, ustekinumab, including pharmacokinetic profiles, immunogenicity, and safety in healthy Chinese male subjects. Methods This was a double-blinded, randomized, single-dose, parallel-group clinical trial, in which 270 healthy male subjects were enrolled to receive a single subcutaneous injection (45 mg) of either BAT2206 or ustekinumab (European Union or USA) at a 1:1:1 ratio. The pairwise pharmacokinetic similarities and the safety and immunogenicity of both drugs were evaluated and compared. Results The results showed that the 90% confidence interval of the geometric mean ratio for primary pharmacokinetic parameters (maximum plasma concentration and area under the plasma concentration–time curve from time zero to infinity) among BAT2206 and ustekinumab (USA or European Union sourced) groups were all within the predefined equivalent interval of 80–125%. Furthermore, all the groups had similar incidences of treatment-emergent adverse events, in which the majority of cases belonged to Common Terminology Criteria for the Classification of Adverse Events Grade 1 or 2. Anti-drug antibodies were detected in 54 (20.1%) subjects, namely 24 (26.7%), 13 (14.8%), and 17 (18.9%) patients in the BAT2206, ustekinumab (European Union), and ustekinumab (USA) groups, respectively. In contrast, the incidences of positive neutralizing antibodies were similar among the three groups. Conclusions Pharmacokinetic similarity between BAT2206 and ustekinumab (USA or European Union sourced) was confirmed. The three groups had similar safety profiles, and the investigational drugs were well tolerated by subjects. Clinical Trial Registration This study was registered with ClinicalTrials.gov (NCT04371185).

Robotics0 citations2022-10-10arXiv ->

Creating a Dynamic Quadrupedal Robotic Goalkeeper with Reinforcement Learning

Xiaoyu Huang, Zhongyu Li, Yan-Ling Xiang, Yiming Ni, Yufeng Chi et al.

We present a reinforcement learning (RL) framework that enables quadrupedal robots to perform soccer goalkeeping tasks in the real world. Soccer goalkeeping with quadrupeds is a challenging problem, that combines highly dynamic locomotion with precise and fast non-prehensile object (ball) manipulation. The robot needs to react to and intercept a potentially flying ball using dynamic locomotion maneuvers in a very short amount of time, usually less than one second. In this paper, we propose to address this problem using a hierarchical model-free RL framework. The first component of the framework contains multiple control policies for distinct locomotion skills, which can be used to cover different regions of the goal. Each control policy enables the robot to track random parametric end-effector trajectories while performing one specific locomotion skill, such as jump, dive, and sidestep. These skills are then utilized by the second part of the framework which is a high-level planner to determine a desired skill and end-effector trajectory in order to intercept a ball flying to different regions of the goal. We deploy the proposed framework on a Mini Cheetah quadrupedal robot and demonstrate the effectiveness of our framework for various agile interceptions of a fast-moving ball in the real world.

Robotics0 citations2022-09-12arXiv ->

GenLoco: Generalized Locomotion Controllers for Quadrupedal Robots

Gilbert Feng, Hongbo Zhang, Zhongyu Li, Xue Bin Peng, Bhuvan Basireddy et al.

Recent years have seen a surge in commercially-available and affordable quadrupedal robots, with many of these platforms being actively used in research and industry. As the availability of legged robots grows, so does the need for controllers that enable these robots to perform useful skills. However, most learning-based frameworks for controller development focus on training robot-specific controllers, a process that needs to be repeated for every new robot. In this work, we introduce a framework for training generalized locomotion (GenLoco) controllers for quadrupedal robots. Our framework synthesizes general-purpose locomotion controllers that can be deployed on a large variety of quadrupedal robots with similar morphologies. We present a simple but effective morphology randomization method that procedurally generates a diverse set of simulated robots for training. We show that by training a controller on this large set of simulated robots, our models acquire more general control strategies that can be directly transferred to novel simulated and real-world robots with diverse morphologies, which were not observed during training.

Learning24 citations2022-07-16Paper ->

Visibility Prediction Based on Machine Learning Algorithms

Yu Zhang, Yangjun Wang, Yinqian Zhu, Lizhi Yang, Li-Na Ge et al.

In this study, ground observation data were selected from January 2016 to January 2020. First, six machine learning methods were used to predict visibility. We verified the accuracy of the method with and without principal components analysis (PCA) by combining actual examples with the European Centre for Medium-Range Weather Forecast (ECMWF) data and National Centers for Environmental Prediction (NECP) data. The results show that PCA can improve visibility prediction. Neural networks have high accuracy in machine learning algorithms. The initial visibility data plays an important role in the visibility forecast and can effectively improve forecast accuracy.

Robotics0 citations2022-06-29arXiv ->

Collaborative Navigation and Manipulation of a Cable-Towed Load by Multiple Quadrupedal Robots

Chenyu Yang, Guo Ning Sue, Zhongyu Li, Lizhi Yang, Haotian Shen et al.

This letter tackles the problem of robots collaboratively towing a load with cables to a specified goal location while avoiding collisions in real time. The introduction of cables (as opposed to rigid links) enables the robotic team to travel through narrow spaces by changing its intrinsic dimensions through slack/taut switches of the cable. However, this is a challenging problem because of the hybrid mode switches and the dynamical coupling among multiple robots and the load. Previous attempts at addressing such a problem were performed offline and do not consider avoiding obstacles online. In this letter, we introduce a cascaded planning scheme with a parallelized centralized trajectory optimization that deals with hybrid mode switches. We additionally develop a set of decentralized planners per robot, which enables our approach to solve the problem of collaborative load manipulation online. We develop and demonstrate one of the first collaborative autonomy framework that is able to move a cable-towed load, which is too heavy to move by a single robot, through narrow spaces with real-time feedback and reactive planning in experiments.

Other4 citations2022-05-19Paper ->

First-In-Human Study on Pharmacokinetics, Safety, and Tolerability of Single and Multiple Escalating Doses of Hepenofovir, a Novel Hepatic Targeting Prodrug of Tenofovir in Healthy Chinese Subjects

Hong Zhang, Lei Gao, Jinfeng Lou, Min Wu, Hong Chen et al.

Objective: Hepenofovir, a novel hepatic targeting prodrug of tenofovir, has been developed for the treatment of chronic hepatitis B (CHB). This is a first-in-human study to evaluate the pharmacokinetics (PK) and tolerability of single and multiple escalating doses of hepenofovir in healthy Chinese subjects. Methods: This phase Ia study included two parts: a double-blinded, randomized, placebo-controlled single-ascending-dose (SAD) (25–200 mg) study under fasted conditions comprising a food-effect investigation (200 mg) and a multiple-ascending-dose (MAD) (25 mg) study under fasted conditions. Results: Hepenofovir was well tolerated in healthy Chinese subjects. There was no significant difference in adverse reaction rates between hepenofovir and placebo groups. Hepenofovir was rapidly absorbed and metabolized into tenofovir after dosing. In healthy participants, the median Tmax of hepenofovir and tenofovir was 0.33–0.50 h and 0.62–0.75 h, respectively, and their mean half-life was 2.5–12.3 h and 49.7–53.8 h, respectively. Systemic exposure to tenofovir increased in proportion to the dose. The mean accumulation indexes of hepenofovir and tenofovir were 1.1 vs. 1.8. Moreover, food could reduce the Cmax of both hepenofovir and tenofovir, but did not affect their area under the curve (AUC). Conclusions: Hepenofovir has shown a favorable safety and PK profile, which support the further evaluation of its safety and efficacy in CHB patients. Clinical trial registration number: The trial is registered at Chinese Clinical Trial website (http://www.chinadrugtrials.org.cn/index.html # CTR20191953).

Robotics0 citations2022-03-04arXiv ->

Bayesian Optimization Meets Hybrid Zero Dynamics: Safe Parameter Learning for Bipedal Locomotion Control

Lizhi Yang, Zhongyu Li, Jun Zeng, K. Sreenath

In this paper, we propose a multi-domain control parameter learning framework that combines Bayesian Optimization (BO) and Hybrid Zero Dynamics (HZD) for locomotion control of bipedal robots. We leverage BO to learn the control parameters used in the HZD-based controller. The learning process is firstly deployed in simulation to optimize different control parameters for a large repertoire of gaits. Next, to tackle the discrepancy between the simulation and the real world, the learning process is applied on the physical robot to learn for corrections to the control parameters learned in simulation while also respecting a safety constraint for gait stability. This method empowers an efficient sim-to-real transition with a small number of samples in the real world, and does not require a valid controller to initialize the training in simulation. Our proposed learning framework is experimentally deployed and validated on a bipedal robot Cassie to perform versatile locomotion skills with improved performance on smoothness of walking gaits and reduction of steady-state tracking errors.

Other31 citations2022-01-24Paper ->

Dual-responsive nanodroplets combined with ultrasound-targeted microbubble destruction suppress tumor growth and metastasis via autophagy blockade.

Xiaoxuan Wang, Mengmeng Shang, Xiao Sun, Lu Guo, Shan Xiao et al.

The inhibition of autophagy is a feasible clinical strategy in tumor therapy. Traditional autophagy inhibitors are limited in clinical tumor therapy due to nonspecific biodistribution, systemic toxicity and limited antitumor effect. Herein, the autophagy inhibitor hydroxychloroquine (HCQ)-loaded nanodroplets (NDs) are synthesized to overcome these drawbacks. HCQ-NDs are endowed with endogenous pH- and exogenous ultrasound-responsive drug release and contrast enhanced ultrasound imaging performance. The combined application of ultrasound-targeted microbubble destruction (UTMD) and HCQ-NDs can severely break the homeostasis of tumor cells, simultaneously releasing HCQ rapidly to block autophagic flux and thus abolish the cytoprotective function. This strategy presents strong synergistic antitumor efficacy with the tumor growth inhibition value of 80.02% and synchronously inhibits tumor lung metastasis by inhibition of MMP2 and MMP9 production, eventually leading to tumor suppression. In addition, HCQ-NDs show excellent tumor-targeting, biocompatibility, biosafety and contrast-enhanced ultrasound imaging properties. Based on the above findings, this combined strategy rationally regulates the autophagic process of tumor cells and could be instructive for the design of clinical treatment modalities.

Robotics0 citations2022-01-11arXiv ->

Drone Object Detection Using RGB/IR Fusion

Lizhi Yang, Ruhang Ma, A. Zakhor

Object detection using aerial drone imagery has received a great deal of attention in recent years. While visible light images are adequate for detecting objects in most scenarios, thermal cameras can extend the capabilities of object detection to night-time or occluded objects. As such, RGB and Infrared (IR) fusion methods for object detection are useful and important. One of the biggest challenges in applying deep learning methods to RGB/IR object detection is the lack of available training data for drone IR imagery, especially at night. In this paper, we develop several strategies for creating synthetic IR images using the AIRSim simulation engine and CycleGAN. Furthermore, we utilize an illumination-aware fusion framework to fuse RGB and IR images for object detection on the ground. We characterize and test our methods for both simulated and actual data. Our solution is implemented on an NVIDIA Jetson Xavier running on an actual drone, requiring about 28 milliseconds of processing per RGB/IR image pair.

CBF Related Papers
MPC/Planning0 citations2026-03-24arXiv ->

Universal Formula Families for Safe Stabilization of Single-Input Nonlinear Systems

Bo Wang, Miroslav Krstic

We develop an optimization-free framework for safe stabilization of single-input control-affine nonlinear systems with a given control Lyapunov function (CLF) and a given control barrier function (CBF), where the desired equilibrium lies in the interior of the safe set. An explicit compatibility condition is derived that is necessary and sufficient for the pointwise simultaneous satisfaction of the CLF and CBF inequalities. When this condition holds, two closed-form continuous state-feedback laws are constructed from the Lie-derivative data of the CLF and CBF via standard universal stabilizer formulas, yielding asymptotic stabilization of the origin and forward invariance of the interior of the safe set, without online quadratic programming. The two laws belong to broader families parametrized by a free nondecreasing function, providing additional design flexibility. When the compatibility condition fails, a safety-prioritizing modification preserves forward invariance and drives the state toward the safe-set boundary until a compatible region is reached, whereupon continuity at the origin and asymptotic stabilization are recovered. The framework produces families of explicit constructive alternatives to CLF-CBF quadratic programming for scalar-input nonlinear systems.

MPC/Planning0 citations2026-03-17arXiv ->

Eliminating Persistent Boundary Residence via Matrosov-Type Auxiliary Functions

Tianyu Han, Guangwei Wang, Bo Wang

Control barrier functions enforce safety by guaranteeing forward invariance of an admissible set. Under standard (non-strict) barrier conditions, however, forward invariance alone does not prevent trajectories from remaining on the boundary of the safe set for arbitrarily long time intervals, potentially leading to boundary sticking or deadlock phenomena. This paper studies the elimination of persistent boundary residence under forward-invariant barrier conditions. Inspired by Matrosov-type arguments, we introduce an auxiliary function framework that preserves forward invariance while excluding infinite-time residence within boundary layers. Sufficient conditions are established under which any trajectory can only remain in a prescribed neighborhood of the boundary for finite time, thereby restoring boundary-level liveness without altering forward invariance. The proposed construction does not rely on singular barrier formulations or controller-specific modifications, and can be incorporated into standard safety-critical control architectures. Numerical examples illustrate the removal of boundary sticking behaviors while maintaining safety across representative systems.

CBF Related Papers
Robotics0 citations2026-03-22arXiv ->

Koopman Meets Discrete-Time Control Barrier Functions: A Linear Model Predictive Control Framework

Shuo Liu, Liang Wu, Dawei Zhang, Jan Drgona, Calin. A. Belta

This paper proposes a Koopman-based linear model predictive control (LMPC) framework for safety-critical control of nonlinear discrete-time systems. Existing MPC formulations based on discrete-time control barrier functions (DCBFs) enforce safety through barrier constraints but typically result in computationally demanding nonlinear programming. To address this challenge, we construct a DCBF-augmented dynamical system and employ Koopman operator theory to lift the nonlinear dynamics into a higher-dimensional space where both the system dynamics and the barrier function admit a linear predictor representation. This enables the transformation of the nonlinear safety-constrained MPC problem into a quadratic program (QP). To improve feasibility while preserving safety, a relaxation mechanism with slack variables is introduced for the barrier constraints. The resulting approach combines the modeling capability of Koopman operators with the computational efficiency of QP. Numerical simulations on a navigation task for a robot with nonlinear dynamics demonstrate that the proposed framework achieves safe trajectory generation and efficient real-time control.

Robotics0 citations2026-03-06arXiv ->

Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes

Shuo Liu, Zhe Huang, Calin A. Belta

Obstacle avoidance of polytopic obstacles by polytopic robots is a challenging problem in optimization-based control and trajectory planning. Many existing methods rely on smooth geometric approximations, such as hyperspheres or ellipsoids, which allow differentiable distance expressions but distort the true geometry and restrict the feasible set. Other approaches integrate exact polytope distances into nonlinear model predictive control (MPC), resulting in nonconvex programs that limit real-time performance. In this paper, we construct linear discrete-time control barrier function (DCBF) constraints by deriving supporting hyperplanes from exact closest-point computations between convex polytopes. We then propose a novel iterative convex MPC-DCBF framework, where local linearization of system dynamics and robot geometry ensures convexity of the finite-horizon optimization at each iteration. The resulting formulation reduces computational complexity and enables fast online implementation for safety-critical control and trajectory planning of general nonlinear dynamics. The framework extends to multi-robot and three-dimensional environments. Numerical experiments demonstrate collision-free navigation in cluttered maze scenarios with millisecond-level solve times.

Non-CBF Papers
Learning0 citations2026-01-06arXiv ->

MiMo-V2-Flash Technical Report

Xi Xiao, Bing Xia, Bo Yang, Bofei Gao, Bowen Shen et al.

We present MiMo-V2-Flash, a Mixture-of-Experts (MoE) model with 309B total parameters and 15B active parameters, designed for fast, strong reasoning and agentic capabilities. MiMo-V2-Flash adopts a hybrid attention architecture that interleaves Sliding Window Attention (SWA) with global attention, with a 128-token sliding window under a 5:1 hybrid ratio. The model is pre-trained on 27 trillion tokens with Multi-Token Prediction (MTP), employing a native 32k context length and subsequently extended to 256k. To efficiently scale post-training compute, MiMo-V2-Flash introduces a novel Multi-Teacher On-Policy Distillation (MOPD) paradigm. In this framework, domain-specialized teachers (e.g., trained via large-scale reinforcement learning) provide dense and token-level reward, enabling the student model to perfectly master teacher expertise. MiMo-V2-Flash rivals top-tier open-weight models such as DeepSeek-V3.2 and Kimi-K2, despite using only 1/2 and 1/3 of their total parameters, respectively. During inference, by repurposing MTP as a draft model for speculative decoding, MiMo-V2-Flash achieves up to 3.6 acceptance length and 2.6x decoding speedup with three MTP layers. We open-source both the model weights and the three-layer MTP weights to foster open research and community collaboration.

Learning0 citations2025-12-29arXiv ->

MiMo-Audio: Audio Language Models are Few-Shot Learners

X. Zhang, Gang Wang, Jinlong Xue, Kai Fang, Liang Zhao et al.

Existing audio language models typically rely on task-specific fine-tuning to accomplish particular audio tasks. In contrast, humans are able to generalize to new audio tasks with only a few examples or simple instructions. GPT-3 has shown that scaling next-token prediction pretraining enables strong generalization capabilities in text, and we believe this paradigm is equally applicable to the audio domain. By scaling MiMo-Audio's pretraining data to over one hundred million of hours, we observe the emergence of few-shot learning capabilities across a diverse set of audio tasks. We develop a systematic evaluation of these capabilities and find that MiMo-Audio-7B-Base achieves SOTA performance on both speech intelligence and audio understanding benchmarks among open-source models. Beyond standard metrics, MiMo-Audio-7B-Base generalizes to tasks absent from its training data, such as voice conversion, style transfer, and speech editing. MiMo-Audio-7B-Base also demonstrates powerful speech continuation capabilities, capable of generating highly realistic talk shows, recitations, livestreaming and debates. At the post-training stage, we curate a diverse instruction-tuning corpus and introduce thinking mechanisms into both audio understanding and generation. MiMo-Audio-7B-Instruct achieves open-source SOTA on audio understanding benchmarks (MMSU, MMAU, MMAR, MMAU-Pro), spoken dialogue benchmarks (Big Bench Audio, MultiChallenge Audio) and instruct-TTS evaluations, approaching or surpassing closed-source models. Model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-Audio.

Robotics0 citations2025-08-11arXiv ->

MolmoAct: Action Reasoning Models that can Reason in Space

Jason Lee, Jiafei Duan, Haoquan Fang, Yuquan Deng, Shuo Liu et al.

Reasoning is central to purposeful action, yet most robotic foundation models map perception and instructions directly to control, which limits adaptability, generalization, and semantic grounding. We introduce Action Reasoning Models (ARMs), a class of robotic foundation models that integrate perception, planning, and control through a structured three-stage pipeline. Our model, MolmoAct, encodes observations and instructions into depth-aware perception tokens, generates mid-level spatial plans as editable trajectory traces, and predicts precise low-level actions, enabling explainable and steerable behavior. MolmoAct-7B-D achieves strong performance across simulation and real-world settings: 70.5% zero-shot accuracy on SimplerEnv Visual Matching tasks, surpassing closed-source Pi-0 and GR00T N1.5; 86.6% average success on LIBERO, including an additional 6.3% gain over ThinkAct on long-horizon tasks; and in real-world fine-tuning, an additional 10% (single-arm) and an additional 22.7% (bimanual) task progression over Pi-0-FAST. It also outperforms baselines by an additional 23.3% on out-of-distribution generalization and achieves top human-preference scores for open-ended instruction following and trajectory steering. Furthermore, we release, for the first time, the MolmoAct Dataset -- a mid-training robot dataset comprising over 10,000 high quality robot trajectories across diverse scenarios and tasks. Training with this dataset yields an average 5.5% improvement in general performance over the base model. We release all model weights, training code, our collected dataset, and our action reasoning dataset, establishing MolmoAct as both a state-of-the-art robotics foundation model and an open blueprint for building ARMs that transform perception into purposeful action through structured reasoning. Blogpost: https://allenai.org/blog/molmoact

MPC/Planning0 citations2025-08-06arXiv ->

LLM Collaboration With Multi-Agent Reinforcement Learning

Shuo Liu, Zeyu Liang, Xueguang Lyu, Christopher Amato

A large amount of work has been done in Multi-Agent Systems (MAS) for modeling and solving problems with multiple interacting agents. However, most LLMs are pretrained independently and not specifically optimized for coordination. Existing LLM fine-tuning frameworks rely on individual rewards, which require complex reward designs for each agent to encourage collaboration. To address these challenges, we model LLM collaboration as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. We develop a multi-agent, multi-turn algorithm, Multi-Agent Group Relative Policy Optimization (MAGRPO), to solve it, building on current RL approaches for LLMs as well as MARL techniques. Our experiments on LLM writing and coding collaboration demonstrate that fine-tuning MAS with MAGRPO enables agents to generate high-quality responses efficiently through effective cooperation. Our approach opens the door to using other MARL methods for LLMs and highlights the associated challenges. Our code is available at https://github.com/OpenMLRL/CoMLRL.

Other0 citations2025-07-02arXiv ->

Quantum Mpemba effects from symmetry perspectives

Hui Yu, Shuo Liu, Shi-Xin Zhang

Non-equilibrium dynamics have become a central research focus, exemplified by the counterintuitive Mpemba effect where initially hotter systems can cool faster than colder ones. Studied extensively in both classical and quantum regimes, this phenomenon reveals diverse and complex behaviors across different systems. This review provides a concise overview of the quantum Mpemba effect (QME), specifically emphasizing its connection to symmetry breaking and restoration in closed quantum many-body systems. We begin by outlining the classical Mpemba effect and its quantum counterparts, summarizing key findings. Subsequently, we introduce entanglement asymmetry and charge variance as key metrics for probing the QME from symmetry perspectives. Leveraging these tools, we analyze the early- and late-time dynamics of these quantities under Hamiltonian evolution and random unitary circuits. We conclude by discussing significant challenges and promising avenues for future research.

MPC/Planning0 citations2025-06-04arXiv ->

MiMo-VL Technical Report

X. Yue, Zhenrui Lin, Yi-Hao Song, Weikun Wang, Shu-Qin Ren et al.

We open-source MiMo-VL-7B-SFT and MiMo-VL-7B-RL, two powerful vision-language models delivering state-of-the-art performance in both general visual understanding and multimodal reasoning. MiMo-VL-7B-RL outperforms Qwen2.5-VL-7B on 35 out of 40 evaluated tasks, and scores 59.4 on OlympiadBench, surpassing models with up to 78B parameters. For GUI grounding applications, it sets a new standard with 56.1 on OSWorld-G, even outperforming specialized models such as UI-TARS. Our training combines four-stage pre-training (2.4 trillion tokens) with Mixed On-policy Reinforcement Learning (MORL) integrating diverse reward signals. We identify the importance of incorporating high-quality reasoning data with long Chain-of-Thought into pre-training stages, and the benefits of mixed RL despite challenges in simultaneous multi-domain optimization. We also contribute a comprehensive evaluation suite covering 50+ tasks to promote reproducibility and advance the field. The model checkpoints and full evaluation suite are available at https://github.com/XiaomiMiMo/MiMo-VL.

MPC/Planning0 citations2025-05-12arXiv ->

MiMo: Unlocking the Reasoning Potential of Language Model - From Pretraining to Posttraining

Xi Xia, Bowen Shen, Cici, Dawei Zhu, Di Zhang et al.

We present MiMo-7B, a large language model born for reasoning tasks, with optimization across both pre-training and post-training stages. During pre-training, we enhance the data preprocessing pipeline and employ a three-stage data mixing strategy to strengthen the base model's reasoning potential. MiMo-7B-Base is pre-trained on 25 trillion tokens, with additional Multi-Token Prediction objective for enhanced performance and accelerated inference speed. During post-training, we curate a dataset of 130K verifiable mathematics and programming problems for reinforcement learning, integrating a test-difficulty-driven code-reward scheme to alleviate sparse-reward issues and employing strategic data resampling to stabilize training. Extensive evaluations show that MiMo-7B-Base possesses exceptional reasoning potential, outperforming even much larger 32B models. The final RL-tuned model, MiMo-7B-RL, achieves superior performance on mathematics, code and general reasoning tasks, surpassing the performance of OpenAI o1-mini. The model checkpoints are available at https://github.com/xiaomimimo/MiMo.

Learning15 citations2025-04-14Paper ->

Hydroxyapatite microspheres encapsulated within hybrid hydrogel promote skin regeneration through the activation of Calcium Signaling and Motor Protein pathway

Shuo Liu, Lu Song, Shuwen Huang, Zhanhong Liu, Yang Xu et al.

Hydroxyapatite (HAp), traditionally recognized for its efficacy in bone regeneration, has rarely been explored for skin regeneration applications. This investigation explored HAp microspheres with distinct physicochemical properties tailored away from conventional bone regeneration parameters, and the capacity promoting skin regeneration and mitigating the aging process were investigated when encapsulated in hyaluronate hydrogels. By benchmarking against well-established dermal fillers like PMMA and PLLA, it was revealed the specific attributes of HAp that were conducive to skin regeneration, providing initial insights into the underlying mechanism. HAp enhanced the fibroblast functionality by triggering minimal adaptive immune responses and enhancing the Calcium Signaling and Motor Protein Signaling pathways. This modulation supported the production of normal collagen fibers, essential for ECM maturation and skin structural integrity. The significant ECM regeneration and remodeling capabilities exhibited by the HAp-encapsulated hybrid hydrogels suggested promising application in facial rejuvenation procedures, potentially making a breakthrough in aesthetic and reconstructive surgery.

Other10 citations2025-03-17Paper ->

Characterization of fog microphysics and their relationships with visibility at a mountain site in China

Quan Liu, Xiaojing Shen, Junying Sun, Yangmei Zhang, Bing Qi et al.

Abstract. Enhancing the understanding of fog microphysical processes is essential for reducing uncertainty in fog forecasts, particularly in predicting fog visibility and duration. To investigate the complex interactions between aerosols and fog microphysics and their impacts on visibility degradation, simultaneous measurements of aerosol and fog microphysical characteristics were conducted from April to May 2023 at a mountain site (1483 m a.s.l.) in the Yangtze River Delta (YRD) region, China. In this study, eight fog events were investigated during the campaign, revealing significantly higher fog droplet number concentrations (Nd) compared to those observed in clean areas. A strong correlation was found between pre-fog aerosol number concentration (Na) and the peak Nd of each fog event, indicating the substantial influence of pre-existing aerosol levels on fog microphysics. Water vapor supersaturation ratio (SS) within fogs was estimated to 0.07 % ± 0.02 %, slightly higher than previous estimates in urban and suburban areas. The broadening of the droplet size distribution (DSD) at formation, development, and mature stages was dominantly driven by activation, condensation, and collision–coalescence mechanisms, respectively. This evolution process often led DSD to a shift from a unimodal to a trimodal distribution, with peaks around 6, 12, and 23 µm. For fog events occurring under high Na background, a notable decrease in temperature during the mature stage promoted a secondary activation-dominated process, resulting in the formation of numerous small fog droplets and a reduction in the large droplet size. The evolution of DSD can significantly influence visibility (VIS) in fogs. Detailed comparison of several visibility calculation methods suggests that estimating visibility based on the extinction of fog droplets only led to considerable overprediction when 100 m

Theory22 citations2025-03-01Paper ->

Enhanced oxygen evolution reaction performance of Cr-CoFe-layered double hydroxide via the synergistic roles of Fe etching, Cr doping, and anion intercalation.

Shuo Liu, Yufan Zhang, Lin Hao, Wei Shen, Anaclet Nsabimana et al.

The development of cost-effective and efficient electrocatalysts for water electrolysis is crucial for sustainable hydrogen production. In this study, we designed a hierarchical Cr-CoFe-LDH composite using a tailored etching and doping strategy to enhance catalytic performance. By integrating mesoporous CoFe-LDH layers with C2O42- anions and Cr dopants, we engineered a structure that optimizes mass transport, strengthens electronic interactions at active sites, and stabilizes key catalytic species. In situ spectroscopic analysis provided direct evidence of active species evolution, offering insights into the underlying reaction mechanisms. As a result, the Cr-CoFe-LDH catalyst exhibited excellent oxygen evolution reaction (OER) activity, demonstrating enhanced intrinsic performance and long-term stability. This work presents a novel approach to designing high-performance LDH-based catalysts and advances the understanding of active site modulation for efficient water electrolysis.

Other41 citations2025-02-21Paper ->

Integrated sensing and communication based on space-time-coding metasurfaces

X. Q. Chen, Lei Zhang, Y. Zheng, Shuo Liu, Zhuo Ran Huang et al.

Programmable metasurfaces (PMs), also called reconfigurable intelligent surfaces (RISs), are planar structures capable of dynamically manipulating electromagnetic waves in real-time. Regarded as a key enabling technology for implementing smart wireless propagation environments, PMs/RISs also serve as an ideal supporting platform for integrated sensing and communication (ISAC). Here, we propose two ISAC schemes based on a special type of PMs/RISs: space-time-coding metasurfaces (STCMs). By leveraging space-time-coding strategies, STCMs simultaneously control the propagation at the fundamental (carrier) frequency for reliable wireless communication and generate spatially distributed harmonics for sensing. The proposed schemes seamlessly integrate both communication and sensing on a shared hardware platform, eliminating the need for additional sensors. For experimental validation, we implemented an ISAC system using a 2-bit STCM operating at microwave frequencies. Experimental results align with theoretical predictions, confirming the practical viability and effectiveness of the proposed ISAC schemes for applications in communication, imaging, radar, and sensing systems. This study proposes an integrated sensing and communication (ISAC) scheme leveraging space-timecoding metasurfaces (STCMs), which enables concurrent wireless communication and sensing on a shared platform.

Other19 citations2025-02-11Paper ->

SIRT1 Regulates Fumonisin B1-Induced LMH Cell PANoptosis and Antagonism of Lycopene.

Xue-Qi Wang, Yuan-Hang Chang, Xiao-Chun Wang, Rui-Qi Liu, Shang-Jia Yang et al.

Mycotoxin contamination is a universal agricultural problem and a critical health issue. Fumonisin B1 (FB1) is one of the most toxic and extensive fumonisins that exist in various agro-products and foods. Lycopene (LYC), as a natural carotenoid, is becoming increasingly favored owing to its oxidation resistance. Here, we aim to explore the mechanism of FB1-induced hepatotoxicity and the antagonism of LYC. In this study, our findings indicated that FB1 induced mitochondrial structure damage and loss of mitochondrial function in chicken hepatocytes. Furthermore, FB1 upregulated the expression of PANoptosis-related signal molecules. FB1 also reduced the levels of SIRT1 and Ac-FOXO1 protein expression, which then inhibited mitophagy. However, LYC relieved these FB1-induced alterations. Most importantly, SIRT1 knockdown inhibited the protective effects of LYC in FB1-induced mitochondrial damage and PANoptosis. Our study provides evidence for the role of LYC in mycotoxin-induced chicken hepatocyte injury and points to SIRT1 as a potential target for liver protection.

Theory91 citations2025-01-20Paper ->

Palmitoylation-dependent regulation of GPX4 suppresses ferroptosis

Bin Huang, Hui Wang, Shuo Liu, Meng Hao, Dan Luo et al.

S-palmitoylation is a reversible and widespread post-translational modification, but its role in the regulation of ferroptosis has been poorly understood. Here, we elucidate that GPX4, an essential regulator of ferroptosis, is reversibly palmitoylated on cysteine 66. The acyltransferase ZDHHC20 palmitoylates GPX4 and increases its protein stability. ZDHHC20 depletion or inhibition of protein palmitoylation by 2-BP sensitizes cancer cells to ferroptosis. Moreover, we identify APT2 as the depalmitoylase of GPX4. Genetic silencing or pharmacological inhibition of APT2 with ML349 increases GPX4 palmitoylation, thereby stabilizing the protein and conferring resistance to ferroptosis. Notably, disrupting GPX4 palmitoylation markedly potentiates ferroptosis in xenografted and orthotopically implanted tumor models, and inhibits tumor metastasis through blood vessels. In the chemically induced colorectal cancer model, knockout of APT2 significantly aggravates cancer progression. Furthermore, pharmacologically modulating GPX4 palmitoylation impacts liver ischemia–reperfusion injury. Overall, our findings uncover the intricate network regulating GPX4 palmitoylation, highlighting its pivotal role in modulating ferroptosis sensitivity. Ferroptosis is crucial in tumor growth, metastasis, and cancer therapy response. Here, the authors reveal that reversible palmitoylation of GPX4 by ZDHHC20 and APT2 regulates ferroptosis sensitivity, offering a potential target for therapeutic intervention.

Other44 citations2025Paper ->

Face-on Oriented Self-Assembled Molecules with Enhanced π-π Stacking for Highly Efficient Inverted Perovskite Solar Cells on Rough FTO Substrate

Jiajun Du, Jinling Chen, Beilin Ouyang, Anxin Sun, Congcong Tian et al.

Self-assembled molecules (SAMs) as hole transport layers (HTLs) on light-managing textured substrates promise great commercial potential for high-efficiency inverted perovskite solar cells (PSCs). However, the inhomogeneous distribution and disordered packing...

Other0 citations2024-11-16arXiv ->

Bias in Large Language Models: Origin, Evaluation, and Mitigation

Yufei Guo, Muzhe Guo, Juntao Su, Zhou Yang, Mengqiu Zhu et al.

Large Language Models (LLMs) have revolutionized natural language processing, but their susceptibility to biases poses significant challenges. This comprehensive review examines the landscape of bias in LLMs, from its origins to current mitigation strategies. We categorize biases as intrinsic and extrinsic, analyzing their manifestations in various NLP tasks. The review critically assesses a range of bias evaluation methods, including data-level, model-level, and output-level approaches, providing researchers with a robust toolkit for bias detection. We further explore mitigation strategies, categorizing them into pre-model, intra-model, and post-model techniques, highlighting their effectiveness and limitations. Ethical and legal implications of biased LLMs are discussed, emphasizing potential harms in real-world applications such as healthcare and criminal justice. By synthesizing current knowledge on bias in LLMs, this review contributes to the ongoing effort to develop fair and responsible AI systems. Our work serves as a comprehensive resource for researchers and practitioners working towards understanding, evaluating, and mitigating bias in LLMs, fostering the development of more equitable AI technologies.

Biomedical95 citations2024-11-01Paper ->

Microbiota-derived lysophosphatidylcholine alleviates Alzheimer's disease pathology via suppressing ferroptosis.

Xu Zha, Xicheng Liu, Mengping Wei, Huanwei Huang, Jiaqi Cao et al.

Alzheimer's disease (AD) is a pervasive neurodegenerative disorder, and new approaches for its prevention and therapy are critically needed. Here, we elucidate a gut-microbiome-brain axis that offers actionable perspectives for achieving this objective. Using the 5xFAD mouse model, we identify increased Clostridium abundance and decreased Bacteroides abundance as key features associated with β-amyloid (Aβ) burden. Treatment with Bacteroides ovatus, or its associated metabolite lysophosphatidylcholine (LPC), significantly reduces Aβ load and ameliorates cognitive impairment. Mechanistically, LPC acts through the orphan receptor GPR119, inhibiting ACSL4 expression, thereby suppressing ferroptosis and ameliorating AD pathologies. Analysis of fecal and serum samples from individuals with AD also reveals diminished levels of Bacteroides and LPC. This study thus identifies a B.ovatus-triggered pathway regulating AD pathologies and indicates that the use of single gut microbiota, metabolite, or small molecule compound may complement current prevention and treatment approaches for AD.

Learning32 citations2024-10-18Paper ->

Ultrasensitive dim-light neuromorphic vision sensing via momentum-conserved reconfigurable van der Waals heterostructure

Lei Xu, Junling Liu, Xinrui Guo, Shuo Liu, Xilin Lai et al.

Reconfigurable phototransistors featuring bipolar photoresponses are favorable for manipulating high-performance neuromorphic vision sensory. Here, we present a momentum-conserved reconfigurable phototransistor based on the van der Waals heterojunction between methylammonium lead iodide perovskite and two-dimensional Bi2O2Se semiconductor, which exhibits a synergistic interplay of interband hot-carrier transitions and reconfigurable heterointerface band alignments, eventually achieving the ultrahigh bipolar optoelectronic performances with the photoresponsivity of 6×107 AW−1, accompanied by the specific detectivity of 5.2×1011 Jones, and the dynamic range of 110 dB. Moreover, A 3×3 heterotransistor array is fabricated to perform in-sensor analog multiply-accumulate operations even under the challenging dim illumination of 0.1 μWcm−2 that comparable to natural moonlight. The reconfigurable heterotransistor array can be further adopted to enhance the traffic-light detection under dim-light conditions. Our advancement in momentum-conserved reconfigurable heterotransistor signifies a leap forward in real-time, energy-efficient, and low-light image processing for neuromorphic vision sensors. Xu et al. report reconfigurable phototransistors based on MAPbI3/Bi2O2Se heterostructure, with momentum conservation promotes hot carrier extraction and interlayer carrier transport. Heterotransistor array enables traffic light signal detection under dim light, assisted by YOLOv4 neural network.

Biomedical51 citations2024-10-08Paper ->

AHR activation relieves deoxynivalenol-induced disruption of porcine intestinal epithelial barrier functions.

Zi-Yan Hu, Shang-Jia Yang, Yuan-Hang Chang, Xue-Qi Wang, Rui-Qi Liu et al.

Mycotoxins are ubiquitous natural pollutants that pose a serious threat to public health. Deoxynivalenol (DON) as one of the most prominent mycotoxins has a noticeable adverse effect on intestinal barrier function, which depends on the intestinal barrier integrity. However, the potential mechanisms and effective therapeutic strategies remain unclear. Aryl hydrocarbon receptor (AHR) has been implicated in the modulation of intestinal barrier function and inflammation. The study aims to investigate the unique role of AHR in mediating DON-induced intestinal epithelial barrier function. In the current study, we revealed that DON triggered mitochondrial structural damage and functional impairment, leading to oxidative stress and apoptosis in porcine jejunal epithelial cells (IPEC-J2). DON altered the integrity of IPEC-J2 cells by disrupting the distribution and function of tight junction proteins. Additionally, DON activated TNF-α/NF-κB/MLCK signaling pathway, thereby eliciting inflammatory response. Notably, DON inhibited AHR nuclear translocation and attenuated xenobiotic response element promoter activity and its target genes. However, overexpression of AHR mitigated DON-induced disruption of intestinal epithelial barrier functions by suppressing TNF-α/NF-κB/MLCK pathway in IPEC-J2 cells. Our findings indicate that AHR regulates intestinal epithelial barrier function and therefore is a novel therapeutic molecule for intestinal disorders.

Theory45 citations2024-09-24Paper ->

Designing ternary Co-Ni-Fe layered double hydroxides within a novel 3D cross-flower framework for efficient catalytic performance in oxygen evolution reaction.

Shuo Liu, Yufan Zhang, Lin Hao, Anaclet Nsabimana, Shigang Shen

In this study, we synthesized novel three-dimensional (3D) cross-flowered Co-Ni metal-organic framework (Co-Ni-MOF) precursors using the chemical precipitation method. Subsequently, we obtained Co-Ni-Fe layered double hydroxides (Co-Ni-Fe-LDHs) through an ion exchange strategy, which preserved their original morphology while consisting of ultrathin layered hydroxide nanosheets. The interlayer spacing of the LDH lamellar structure was finely tuned by varying the ratios of Co to Ni. The results demonstrated that Co-Ni-Fe LDHs, characterized by a unique three-dimensional cross-shaped structure and an optimal composition ratio of Co2+:Ni2+ = 2:1, exhibited increased interlayer spacing. This structural characteristic contributed to their excellent electrochemical performance, positioning them as optimal electrode materials for catalytic oxygen evolution reactions (OER). Our observations revealed that Co-Ni-Fe-LDHs exhibited remarkable OER activity, characterized by a low Tafel slope of 41.82 mV dec-1, a low overpotential of 322 mV at a current density of 10 mA cm-2, and outstanding stability over a 48-hour period. In-situ Raman spectroscopy results indicated that the active site of the composite was γ-CoOOH. Additionally, the room temperature stirring and standing strategy employed in this study is easier to scale up and yields a higher quantity of reaction products compared to traditional high-temperature and high-pressure conditions. This investigation provides novel insights into the design and fabrication of Co-Ni-Fe-LDHs catalyst with 3D cross-flower structures, demonstrating enhanced electrocatalytic activity and commendable stability. These findings suggest promising applications in the field of electrolyzed water.

Other39 citations2024-08-29Paper ->

Unraveling the Trade‐Off Between Oxygen Vacancy Concentration and Ordering of Perovskite Oxides for Efficient Lattice Oxygen Evolution

Lin-Bo Liu, Yu‐Feng Tang, Shuo Liu, Mulin Yu, Yifei Sun et al.

Oxygen evolution reaction (OER) over perovskite oxides, upon undergoing a lattice oxygen oxidation mechanism, is strongly oxygen vacancy‐correlated as determined by the oxygen ion diffusivity. Despite substantial efforts having been devoted to tuning the oxygen vacancy concentration in perovskite oxides, the impact of the concomitant altering of oxygen vacancy ordering is often underestimated. In particular, the underlying mechanism of how the ordering and the concentration of oxygen vacancy affect the lattice OER, and how to well balance them still remain inadequately understood. Herein, a series of Sr1−xCaxCo0.5Fe0.5O3−δ with gradually increased oxygen vacancy concentration and ordering are synthesized. Theoretical calculations indicated that a higher oxygen vacancy concentration promoted the lattice oxygen migration, whereas a higher oxygen vacancy ordering impeded it. Particularly, Sr0.5Ca0.5Co0.5Fe0.5O3−δ with a relatively higher oxygen vacancy concentration and a lower ordering displayed the maximum oxygen diffusion rate and the optimal OER activity, affording a current density of 10 mA cm−2 at a quite low overpotential of 310.2 mV, together with a small Tafel slope of 55.87 mV dec−1. This study sheds light on the critical influence of oxygen vacancy configuration on the lattice OER, and paves a compromised avenue to screen and design advanced electrocatalysts for various electrochemical devices.

CBF Related Papers
Robotics0 citations2026-03-19arXiv ->

A Closed-Form CLF-CBF Controller for Whole-Body Continuum Soft Robot Collision Avoidance

Kiwan Wong, Maximillian Stölzle, Wei Xiao, Daniela Rus

Safe operation is essential for deploying robots in human-centered 3D environments. Soft continuum manipulators provide passive safety through mechanical compliance, but still require active control to achieve reliable collision avoidance. Existing approaches, such as sampling-based planning, are often computationally expensive and lack formal safety guarantees, which limits their use for real-time whole-body avoidance. This paper presents a closed-form Control Lyapunov Function--Control Barrier Function (CLF--CBF) controller for real-time 3D obstacle avoidance in soft continuum manipulators without online optimization. By analytically embedding safety constraints into the control input, the proposed method ensures stability and safety under the stated modeling assumptions, while avoiding feasibility issues commonly encountered in online optimization-based methods. The resulting controller is up to $10\times$ faster than standard CLF--CBF quadratic-programming approaches and up to $100\times$ faster than traditional sampling-based planners. Simulation and hardware experiments on a tendon-driven soft manipulator demonstrate accurate 3D trajectory tracking and robust obstacle avoidance in cluttered environments. These results show that the proposed framework provides a scalable and provably safe control strategy for soft robots operating in dynamic, safety-critical settings.

Robotics151 citations2023-06-01Paper ->

BarrierNet: Differentiable Control Barrier Functions for Learning of Safe Robot Control

Wei Xiao, Tsun-Hsuan Wang, Ramin M. Hasani, Makram Chahine, Alexander Amini et al.

Many safety-critical applications of neural networks, such as robotic control, require safety guarantees. This article introduces a method for ensuring the safety of learned models for control using differentiable control barrier functions (dCBFs). dCBFs are end-to-end trainable and guarantee safety. They improve over classical control barrier functions (CBFs), which are usually overly conservative. Our dCBF solution relaxes the CBF definitions by: 1) using environmental dependencies; 2) embedding them into differentiable quadratic programs. These novel safety layers are called a BarrierNet. They can be used in conjunction with any neural network-based controller. They are trained by gradient descent. With BarrierNet, the safety constraints of a neural controller become adaptable to changing environments. We evaluate BarrierNet on the following several problems: 1) robot traffic merging; 2) robot navigation in 2-D and 3-D spaces; 3) end-to-end vision-based autonomous driving in a sim-to-real environment and in physical experiments; 4) demonstrate their effectiveness compared to state-of-the-art approaches.

CBF Related Papers
Theory0 citations2026-03-19arXiv ->

Mean-field control barrier functions for stochastic multi-agent systems

Cinzia Tomaselli, Gian Carlo Maffettone, Samy Wu Fung, Levon Nurbekyan, Mario di Bernardo

Many applications involving multi-agent systems require fulfilling safety constraints. Control barrier functions offer a systematic framework to enforce forward invariance of safety sets. Recent work extended this paradigm to mean-field scenarios, where the number of agents is large enough to make density-space descriptions a reasonable workaround for the curse of dimensionality. However, an open gap in the recent literature concerns the development of mean-field control barrier functions for Fokker-Planck (advection-diffusion) equations. In this work, we address this gap, enabling safe mean-field control of agents with stochastic microscopic dynamics. We provide bounded stability guarantees under safety corrections and corroborate our results through numerical simulations in two representative scenarios, coverage and shepherding control of multi-agent systems.

Learning0 citations2026-03-16arXiv ->

Multi-Scale Control of Large Agent Populations: From Density Dynamics to Individual Actuation

Mario di Bernardo

We review a body of recent work by the author and collaborators on controlling the spatial organisation of large agent populations across multiple scales. A central theme is the systematic bridging of microscopic agent-level dynamics and macroscopic density descriptions, enabling control design at the most natural level of abstraction and subsequent translation across scales. We show how this multi-scale perspective provides a unified approach to both \emph{direct control}, where every agent is actuated, and \emph{indirect control}, where few leaders or herders steer a larger uncontrolled population. The review covers continuification-based control with robustness under limited sensing and decentralised implementation via distributed density estimation; leader--follower density regulation with dual-feedback stability guarantees and bio-inspired plasticity; optimal-transport methods for coverage control and macro-to-micro discretisation; nonreciprocal field theory for collective decision-making; mean-field control barrier functions for population-level safety; and hierarchical reinforcement learning for settings where closed-form solutions are intractable. Together, these results demonstrate the breadth and versatility of a multi-scale control framework that integrates analytical methods, learning, and physics-inspired approaches for large agent populations.

CBF Related Papers
Learning0 citations2026-03-15arXiv ->

Robust Safety Filters for Lipschitz-Bounded Adaptive Closed-Loop Systems with Structured Uncertainties

Johannes Autenrieb, Peter A. Fisher, Anuradha Annaswamy

Adaptive control provides closed-loop stability and reference tracking for uncertain dynamical systems through online parameter adaptation. These properties alone, however, do not ensure safety in the sense of forward invariance of state constraints, particularly during transient phases of adaptation. Control barrier function (CBF)-based safety filters have been proposed to address this limitation, but existing approaches often rely on conservative constraint tightening or static safety margins within quadratic program formulations. This paper proposes a reference-based adaptive safety framework for systems with structured parametric uncertainty that explicitly accounts for transient plant-reference mismatch. Safety is enforced at the reference level using a barrier-function-based filter, while adaptive control drives the plant to track the safety-certified reference. By exploiting Lipschitz bounds on the closed-loop error dynamics, a robust CBF condition is derived and reformulated as a convex second-order cone program (SOCP). The resulting approach reduces conservatism while preserving formal guarantees of forward invariance, stability, and tracking.

Other0 citations2026-03-05arXiv ->

Combinatorial Safety-Critical Coordination of Multi-Agent Systems via Mixed-Integer Responsibility Allocation and Control Barrier Functions

Johannes Autenrieb, Mark Spiller, Hyo-Sang Shin, Namhoon Cho

This paper presents a hybrid safety-critical coordination architecture for multi-agent systems operating in dense environments. While control barrier functions (CBFs) provide formal safety guarantees, decentralized implementations typically rely on ego-centric safety filtering and may lead to redundant constraint enforcement and conservative collective behavior. To address this limitation, we introduce a combinatorial coordination layer formulated as a mixed-integer linear program (MILP) that assigns collision-avoidance responsibilities among agents. By explicitly distributing enforcement tasks, redundant reactions are eliminated and computational complexity is reduced. Each agent subsequently solves a reduced local quadratic program enforcing only its assigned constraints.

CBF Related Papers
Robotics0 citations2026-03-06arXiv ->

Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions

Simiao Zhuang, Bingkun Huang, Zewen Yang

Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneously enforcing strict safety constraints in varying environments with limited communication and real-time computation budgets. This paper presents a distributed control framework that achieves consensus coordination with safety guarantees via hierarchical event-triggered control barrier functions (CBFs). We first develop a consensus-based protocol that relies solely on local neighbor information to enforce both translational and rotational consistency in task space. Building on this coordination layer, we propose a three-level hierarchical event-triggered safety architecture with CBFs, which is integrated with a risk-aware leader selection and smooth switching strategy to reduce online computation. The proposed approach is validated through real-world hardware experiments using two Franka manipulators operating with static obstacles, as well as comprehensive simulations demonstrating scalable multi-arm cooperation with dynamic obstacles. Results demonstrate higher precision cooperation under strict safety constraints, achieving substantially reduced computational cost and communication frequency compared to baseline methods.

Robotics0 citations2026-03-06arXiv ->

Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions

Si-Xuan Zhuang, Bingkun Huang, Zewen Yang

Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneously enforcing strict safety constraints in varying environments with limited communication and real-time computation budgets. This paper presents a distributed control framework that achieves consensus coordination with safety guarantees via hierarchical event-triggered control barrier functions (CBFs). We first develop a consensus-based protocol that relies solely on local neighbor information to enforce both translational and rotational consistency in task space. Building on this coordination layer, we propose a three-level hierarchical event-triggered safety architecture with CBFs, which is integrated with a risk-aware leader selection and smooth switching strategy to reduce online computation. The proposed approach is validated through real-world hardware experiments using two Franka manipulators operating with static obstacles, as well as comprehensive simulations demonstrating scalable multi-arm cooperation with dynamic obstacles. Results demonstrate higher precision cooperation under strict safety constraints, achieving substantially reduced computational cost and communication frequency compared to baseline methods.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qing Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Non-CBF Papers
Other48 citationsPaper ->

Unraveling the discriminative mechanisms for peroxy activation via atomically dispersed Fe-N5 sites for tunable water decontamination

Xinyu Song, Yangguang Shi, Zelin Wu, Bingkun Huang, Xinhao Wang et al.

Other1 citationsPaper ->

Constructing Reversible Zn/MnO2 Dual‐Electrodeposition‐Based Smart Window with Wide Modulation Range by an Iodide Mediator in Near‐Neutral Electrolyte

Bingkun Huang, Bin Wang, Feifei Zhao, Yukai Xu, Haizeng Li et al.

Other1 citations2026-02-06Paper ->

Proximity Engineering of Fe‒N4 Twins for Oriented Generation of Singlet Oxygen for Hospital Wastewater Treatment

Xinhao Wang, Z. Xiong, Shuai Yang, Hongyu Zhou, Yanbiao Shi et al.

ABSTRACT Precisely tailoring the molecular configurations of single‐atom sites and elucidating their correlation with generated specific reactive species is crucial for advancing Fenton‐like chemistry toward targeted remediation. Herein, we developed a facile approach to precisely modulate the distances between isolated Fe‒N4 sites (dFe–Fe) from nanometer (0.95 nm) to subnanometer (0.43 nm) to construct a family of well‐defined Fe‒N4 twins with manipulated ligand‐field strength and spin states. Different Fe‒N4 twin sites trigger a metal‐loading‐independent volcano‐shaped Fenton‐like activity trend. The optimal configuration, achieved at an Fe‒Fe distance of 0.43 nm (Fed0.43SA), induces an intermediate‐spin (t2g4eg1) configuration that optimizes eg orbital occupancy, thereby promoting peroxymonosulfate (PMS) adsorption to form *HSO5 − and subsequently lowers the energy barrier for coupling with another PMS to selectively generate singlet oxygen (1O2). The robust molecular catalyst with Fe‒N4 twin sites sustains over 120 h of continuous treatment of organic wastewater and demonstrates simultaneous disinfection and pharmaceutical removal of actual hospital wastewater. This work presents an advanced strategy for engineering single‐atom sites with multi‐site cooperativity to regulate Fenton‐like catalysis, enabling rapid and real‐world water purification.

Robotics0 citations2026-02-04arXiv ->

A Unified Complementarity-based Approach for Rigid-Body Manipulation and Motion Prediction

Bingkun Huang, Xin Ma, Nilanjan Chakraborty, Riddhiman Laha

Robotic manipulation in unstructured environments requires planners to reason jointly about free-space motion and sustained, frictional contact with the environment. Existing (local) planning and simulation frameworks typically separate these regimes or rely on simplified contact representations, particularly when modeling non-convex or distributed contact patches. Such approximations limit the fidelity of contact-mode transitions and hinder the robust execution of contact-rich behaviors in real time. This paper presents a unified discrete-time modeling framework for robotic manipulation that consistently captures both free motion and frictional contact within a single mathematical formalism (Unicomp). Building on complementarity-based rigid-body dynamics, we formulate free-space motion and contact interactions as coupled linear and nonlinear complementarity problems, enabling principled transitions between contact modes without enforcing fixed-contact assumptions. For planar patch contact, we derive a frictional contact model from the maximum power dissipation principle in which the set of admissible contact wrenches is represented by an ellipsoidal limit surface. This representation captures coupled force-moment effects, including torsional friction, while remaining agnostic to the underlying pressure distribution across the contact patch. The resulting formulation yields a discrete-time predictive model that relates generalized velocities and contact wrenches through quadratic constraints and is suitable for real-time optimization-based planning. Experimental results show that the proposed approach enables stable, physically consistent behavior at interactive speeds across tasks, from planar pushing to contact-rich whole-body maneuvers.

Other4 citations2026-01-01Paper ->

Zn Anode‐Based Electrochromic Devices: Progress & Challenges

Bingkun Huang, Feifei Zhao, Pengcheng Liu, Yukai Xu, Bin Wang et al.

Other0 citations2026Paper ->

Redirecting ROS oxidation to targeted interfacial electron transfer via Fe atom-cluster tandem for reactant-tailored Fenton-like processes

Zelin Wu, Z. Xiong, Xinhao Wang, Bingkun Huang, Yu Zhang et al.

Other2 citations2025-11-29Paper ->

Multicolored Dual‐Band Zinc Anode‐Based Electrochromic Device with Four‐Mode Conversion Based on Phytic Acid‐Doped Polyaniline

Bingkun Huang, Feifei Zhao, Yukai Xu, Jia‐Yue Yang, Litao Kang et al.

Dual‐band electrochromic devices (DECDs) can regulate the transmittance of visible (VIS) and near‐infrared (NIR) light, representing a significant advancement for smart windows. However, current DECDs are limited by a dearth of color options and the inherent challenges in achieving independent control over VIS and NIR transmission. Herein, this study develops a multi‐color, multi‐mode dual‐band zinc anode electrochromic device (ZECD) using phytic acid‐doped polyaniline (PANI). Due to PANI's unique redox properties, this device produces colors of bright yellow, yellow, blue, and purple, enhancing visual appeal. More importantly, by leveraging the nonlinear relationship between polariton/bipolaron concentration in PANI and applied potential, the device can operate in bright, cool, dark, and warm modes, allowing independent control of VIS and NIR lights. Additionally, introducing phytic acid effectively reduces PANI's bandgap, optimizes its molecular electrostatic potential distribution, and significantly improves the redox reaction reversibility. Therefore, the ZECD shows high transmittance modulating ability (49.9% at 530 nm, 22.1% at 1000 nm), fast response times (61.4 and 19.2 s at 530 nm, 51.6 and 26.0 s at 1000 nm for bleaching and coloring, respectively) and excellent cycling durability (10 000 cycles with 63.2% retention at 530 nm, 70.9% retention at 1000 nm).

Robotics0 citations2025-11-17arXiv ->

Contact-Safe Reinforcement Learning with ProMP Reparameterization and Energy Awareness

Bingkun Huang, Yuhe Gong, Zewen Yang, Tianyu Ren, Luis Figueredo

Reinforcement learning (RL) approaches based on Markov Decision Processes (MDPs) are predominantly applied in the robot joint space, often relying on limited task-specific information and partial awareness of the 3D environment. In contrast, episodic RL has demonstrated advantages over traditional MDP-based methods in terms of trajectory consistency, task awareness, and overall performance in complex robotic tasks. Moreover, traditional step-wise and episodic RL methods often neglect the contact-rich information inherent in task-space manipulation, especially considering the contact-safety and robustness. In this work, contact-rich manipulation tasks are tackled using a task-space, energy-safe framework, where reliable and safe task-space trajectories are generated through the combination of Proximal Policy Optimization (PPO) and movement primitives. Furthermore, an energy-aware Cartesian Impedance Controller objective is incorporated within the proposed framework to ensure safe interactions between the robot and the environment. Our experimental results demonstrate that the proposed framework outperforms existing methods in handling tasks on various types of surfaces in 3D environments, achieving high success rates as well as smooth trajectories and energy-safe interactions.

Other0 citations2025-10-23Paper ->

Genetic diversity analysis of the natural regeneration loci of Liriodendron chinense in artificial mixed forests in the rocky desertification area of Western Hunan

Ziying Jia, Yixuan Wang, Bingkun Huang, Miao Liang, C. Ge et al.

Liriodendron chinense plays a crucial role in improving the ecological environment and combating soil erosion in the rocky desertification area of Western Hunan, China. However, there is still a lack of systematic research on the genetic diversity of natural populations of the L. chinense in rocky desertification areas. This study employed 11 simple sequence repeat (SSR) markers to analyze genetic diversity and spatial genetic structure in a population of 318 L. chinense individuals. We conducted parentage analysis on individuals from a limited area of natural regeneration to quantify pollen and seed-mediated gene flow separately. Based on diameter classification, L. chinense individuals in the large diameter class can be considered as potential parents. The results show that there is moderate genetic diversity in the natural populations of the L. chinense. The spatial genetic patterns of the adult individuals indicate that significant gene flow occurs primarily at short to medium distances, with about 70% occurring within a range of less than 80 m. Among the 318 L. chinense individuals analyzed, 201 were predominantly assigned to the parental generation, with 41 showing closest genetic similarity to the maternal parent. These results indicate that the majority of pollen (63.2%) originated from within the sampling area, which suggests a substantial proportion of natural regeneration occurred within the 2.5 hm2 stand. These findings further elucidate the natural regeneration process of L. chinense and provide a theoretical foundation for ecological restoration efforts in rocky desertification areas.

Robotics0 citations2025-09-17arXiv ->

Prompt2Auto: From Motion Prompt to Automated Control via Geometry-Invariant One-Shot Gaussian Process Learning

Zewen Yang, X. Dai, Dongfa Zhang, Yu Li, Ziyang Meng et al.

Learning from demonstration allows robots to acquire complex skills from human demonstrations, but conventional approaches often require large datasets and fail to generalize across coordinate transformations. In this paper, we propose Prompt2Auto, a geometry-invariant one-shot Gaussian process (GeoGP) learning framework that enables robots to perform human-guided automated control from a single motion prompt. A dataset-construction strategy based on coordinate transformations is introduced that enforces invariance to translation, rotation, and scaling, while supporting multi-step predictions. Moreover, GeoGP is robust to variations in the user's motion prompt and supports multi-skill autonomy. We validate the proposed approach through numerical simulations with the designed user graphical interface and two real-world robotic experiments, which demonstrate that the proposed method is effective, generalizes across tasks, and significantly reduces the demonstration burden. Project page is available at: https://prompt2auto.github.io

Other3 citations2025-09-01Paper ->

Layered mesoporous TiO2 loaded CQDs activation of periodate to remove sulfamethoxazole: Key role of CQDs

Tao Wei, Jialong Yin, Heng Zhang, Mengfan Luo, Jia Zhao et al.

Robotics0 citations2025-08-09arXiv ->

Manipulator for people with limited abilities

Bingkun Huang, Evgeniy Kotov, A. Yuschenko

The topic of this final qualification work was chosen due to the importance of developing robotic systems designed to assist people with disabilities. Advances in robotics and automation technologies have opened up new prospects for creating devices that can significantly improve the quality of life for these people. In this context, designing a robotic hand with a control system adapted to the needs of people with disabilities is a major scientific and practical challenge. This work addresses the problem of developing and manufacturing a four-degree-of-freedom robotic hand suitable for practical manipulation. Addressing this issue requires a comprehensive approach, encompassing the design of the hand's mechanical structure, the development of its control system, and its integration with a technical vision system and software based on the Robot Operating System (ROS).

Learning0 citations2025-08-05arXiv ->

Streaming Generated Gaussian Process Experts for Online Learning and Control

Zewen Yang, Dongfa Zhang, X. Dai, Fengyi Yu, Chi Zhang et al.

Gaussian Processes (GPs), as a nonparametric learning method, offer flexible modeling capabilities and calibrated uncertainty quantification for function approximations. Additionally, GPs support online learning by efficiently incorporating new data with polynomial-time computation, making them well-suited for safety-critical dynamical systems that require rapid adaptation. However, the inference and online updates of exact GPs, when processing streaming data, incur cubic computation time and quadratic storage memory complexity, limiting their scalability to large datasets in real-time settings. In this paper, we propose a streaming kernel-induced progressively generated expert framework of Gaussian processes (SkyGP) that addresses both computational and memory constraints by maintaining a bounded set of experts, while inheriting the learning performance guarantees from exact Gaussian processes. Furthermore, two SkyGP variants are introduced, each tailored to a specific objective, either maximizing prediction accuracy (SkyGP-Dense) or improving computational efficiency (SkyGP-Fast). The effectiveness of SkyGP is validated through extensive benchmarks and real-time control experiments demonstrating its superior performance compared to state-of-the-art approaches.

Other4 citations2025-07-16Paper ->

Thermal-Driven Coordination Microenvironment Reconstruction in Single-Atom Catalysts Unlocks Ultrafast Water Remediation.

Lei Yang, Zelin Wu, Tao Tian, Bingkun Huang, Xinhao Wang et al.

Other12 citations2025-07-01Paper ->

Is the choice of quencher appropriate for exploring reactive oxygen species in advanced oxidation processes?

Bingkun Huang, Zelin Wu, Jing Zhang, Yanbiao Shi, Chuan-Shu He et al.

Other1 citations2025-07-01Paper ->

Matching molecular scale with active site spacing induces distinct mechanisms in single-atom catalysts for persulfate activation

Ying Li, Zelin Wu, Xiaoyu Liu, Bingkun Huang, Jing Zhang et al.

Other28 citations2025-05-19Paper ->

Inorganic electrochromic smart windows for advancing building energy efficiency

Feifei Zhao, Bin Wang, Bingkun Huang, Wu Zhang, Jingwei Chen et al.

Learning0 citations2025-05-16Paper ->

ACACM: Autoencoder and Confidence-Assisted Classification Model for Network Anomaly Detection

Guolou Ping, Xinan Liu, Bingkun Huang, Runzi Guo, Wentao Wu et al.

In order to deal with the security threats that inevitably exist on the Internet, network anomaly detection technology based on deep learning is widely used to detect potential network attacks. However, the lack of labeled data, imbalanced traffic categories and the existence of unknown attack categories make this problem more challenging. In this work, we propose an autoencoder and confidence-assisted classification model for semi-supervised anomaly detection. First, a stacked autoencoder was introduced to deal with the unlabeled data and to alleviate the problem of insufficient labeled data. Since unlabeled traffic data usually contain more normal samples than anomalous samples, this module makes the reconstruction loss of anomalous samples much higher than normal ones, therefore it can help the classification module for anomaly detection. Second, we propose a classification module with confidence estimator and classifier. The confidence estimator part is used to solve the problem of unknown attack detection. At the same time, the classifier part using focal loss function is to deal with the problem of imbalanced traffic categories. Finally, based on the autoencoder and the confidence-assisted classification module, we design a joint training method and a joint discrimination method, which can detect both known and unknown network attacks. Extensive experiments on the two benchmark data sets CICIDS2017 and ISCXIDS2012 show that our model is robust and effective for network anomaly detection, and is superior to existing methods.

Theory4 citations2025-05-02Paper ->

Integrating Transparent Zinc Mesh and Anti‐Freezing Hydrogel Electrolyte Toward Durable Zinc Anode‐Based Electrochromic Devices

Yukai Xu, Bin Wang, Bingkun Huang, Pengcheng Liu, Lanxin Ma et al.

Emerging zinc‐anode‐based electrochromic devices (ZECDs) significantly contribute to displays or smart windows. However, the majority of existing ZECDs employ opaque zinc sheets and liquid electrolytes, posing key limitations of restricted light transmission capacity, possible electrolyte leakage, and poor frost resistance, while the issue of zinc dendrites is also overlooked in ZECDs. Here, a flexible and transparent zinc mesh is developed for the zinc‐anode‐based electrochromic device (ZECD). The effect of zinc dendrites on the cycling process of ZECDs is investigated by controlling different zinc deposition morphologies. Additionally, a hydrogel electrolyte suitable for the ZECD smart window has been developed with excellent frost resistance, water‐retention capability, and electrical conductivity. Finally, the ZECD smart window is assembled based on the transparent zinc mesh and the hydrogel electrolyte. The window has excellent cyclic stability (94.4% retention after 1000 cycles), high optical contrast (78.7% at 633 nm), and high energy‐recovery efficiency (61.6%). It is foreseeable that these results will provide a boost to the future development of ZECDs and energy efficiency in buildings.

Other11 citations2025-05-01Paper ->

Catalytic ozonation for hospital wastewater treatment: Challenge of simultaneous removal of pharmaceutical contaminants and pathogenic microorganisms

Qian Wen, Xingxing An, Bingkun Huang, Jing Zhang, Chuanshu He et al.

CBF Related Papers
Robotics0 citations2026-03-06arXiv ->

Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions

Simiao Zhuang, Bingkun Huang, Zewen Yang

Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneously enforcing strict safety constraints in varying environments with limited communication and real-time computation budgets. This paper presents a distributed control framework that achieves consensus coordination with safety guarantees via hierarchical event-triggered control barrier functions (CBFs). We first develop a consensus-based protocol that relies solely on local neighbor information to enforce both translational and rotational consistency in task space. Building on this coordination layer, we propose a three-level hierarchical event-triggered safety architecture with CBFs, which is integrated with a risk-aware leader selection and smooth switching strategy to reduce online computation. The proposed approach is validated through real-world hardware experiments using two Franka manipulators operating with static obstacles, as well as comprehensive simulations demonstrating scalable multi-arm cooperation with dynamic obstacles. Results demonstrate higher precision cooperation under strict safety constraints, achieving substantially reduced computational cost and communication frequency compared to baseline methods.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Robotics0 citations2025-04-11arXiv ->

SafeFlow: Safe Robot Motion Planning with Flow Matching via Control Barrier Functions

X. Dai, Zewen Yang, Dian Yu, Fangzhou Liu, Hamid Sadeghian et al.

Recent advances in generative modeling have led to promising results in robot motion planning, particularly through diffusion and flow matching (FM)-based models that capture complex, multimodal trajectory distributions. However, these methods are typically trained offline and remain limited when faced with new environments with constraints, often lacking explicit mechanisms to ensure safety during deployment. In this work, safe flow matching (SafeFlow), a motion planning framework, is proposed for trajectory generation that integrates flow matching with safety guarantees. SafeFlow leverages our proposed flow matching barrier functions (FMBF) to ensure the planned trajectories remain within safe regions across the entire planning horizon. Crucially, our approach enables training-free, real-time safety enforcement at test time, eliminating the need for retraining. We evaluate SafeFlow on a diverse set of tasks, including planar robot navigation and 7-DoF manipulation, demonstrating superior safety and planning performance compared to state-of-the-art generative planners. Comprehensive resources are available on the project website: https://safeflowmatching.github.io.

Non-CBF Papers
Other2 citationsPaper ->

Pri-GP: Prior-Aware Distributed Gaussian Process Regression

Zewen Yang, X. Dai, Akshat Dubey, Sandra Hirche, Georges Hattab

Learning0 citations2025-08-05arXiv ->

Streaming Generated Gaussian Process Experts for Online Learning and Control

Zewen Yang, Dongfa Zhang, X. Dai, Fengyi Yu, Chi Zhang et al.

Gaussian Processes (GPs), as a nonparametric learning method, offer flexible modeling capabilities and calibrated uncertainty quantification for function approximations. Additionally, GPs support online learning by efficiently incorporating new data with polynomial-time computation, making them well-suited for safety-critical dynamical systems that require rapid adaptation. However, the inference and online updates of exact GPs, when processing streaming data, incur cubic computation time and quadratic storage memory complexity, limiting their scalability to large datasets in real-time settings. In this paper, we propose a streaming kernel-induced progressively generated expert framework of Gaussian processes (SkyGP) that addresses both computational and memory constraints by maintaining a bounded set of experts, while inheriting the learning performance guarantees from exact Gaussian processes. Furthermore, two SkyGP variants are introduced, each tailored to a specific objective, either maximizing prediction accuracy (SkyGP-Dense) or improving computational efficiency (SkyGP-Fast). The effectiveness of SkyGP is validated through extensive benchmarks and real-time control experiments demonstrating its superior performance compared to state-of-the-art approaches.

Robotics2 citations2025-08-01Paper ->

Safe event-triggered control of unmanned surface vehicles with Gaussian processes: Resilience in denial of service attacks and uncertain dynamics

Zewen Yang, X. Dai, Liang Fang, Jiajia Zhou, Zheping Yan

Other2 citations2025-04-30Paper ->

Holistic forecasting for future pandemics: a review of pathogens, models, and data

L. R. E. Gomez, N. Malysheva, Juliane Pfeil, Zewen Yang, Sandra M. Bütow et al.

Pandemics challenge the capacity and resilience of healthcare systems around the world. A rapid and effective response to the sudden spread of a pathogen is therefore key to minimising the burden of a disease. Epidemic forecasting generates possible future scenarios of disease spread that can inform the decision-making process of public health authorities, leading to the timely implementation of efficient control strategies. Here, we provide an overview of the pathogens that possess the potential to cause future pandemics, the different models, and the data sources that can be employed to generate prognoses about their spread. Existing efforts focus mainly on one or two different sources, failing to account for multiple factors that influence disease transmission. We discuss recent developments that can lead us towards a holistic forecasting system capable of integrating different data sources, which, we argue, is needed to make reliable predictions and ensure a timely response by public health authorities at a global scale.

Learning2 citations2025-04-11Paper ->

Asynchronous Distributed Gaussian Process Regression

Zewen Yang, X. Dai, Sandra Hirche

In this paper, we address a practical distributed Bayesian learning problem with asynchronous measurements and predictions due to diverse computational conditions. To this end, asynchronous distributed Gaussian process (AsyncDGP) regression is proposed, which is the first effective online distributed Gaussian processes (GPs) approach to improve the prediction accuracy in real-time learning tasks. By leveraging the devised evaluation criterion and established prediction error bounds, AsyncDGP enables the distinction of contributions of each model for prediction ensembling using aggregation strategy. Furthermore, we extend its utility to dynamic systems by introducing a learning-based control law, ensuring guaranteed control performance in safety-critical applications. Additionally, a networked online learning simulation platform for distributed GPs, namely online GP gym (GPgym), is introduced for testing the performance of learning and control of dynamical systems. Numerical simulations within GPgym across regression tasks with real-world data sets and dynamical control scenarios demonstrate the effectiveness and applicability of AsyncDGP.

Theory4 citations2025-04-03Paper ->

Association between triglyceride-glucose index and all-cause mortality in patients with congestive heart failure and atrial fibrillation

Fuqiang Kan, Zewen Yang, Donglai Bao, M. Tang, Ningning Ji

Background The role of the triglyceride-glucose (TyG) index in critically ill patients with congestive heart failure (CHF) and atrial fibrillation (AF), requiring intensive care unit (ICU) admission, remains unclear. This study aimed to investigate the association between the TyG index and the clinical prognosis of critically ill patients with CHF and AF. Methods This retrospective observational cohort study utilized data from the Medical Information Mart for Intensive Care-IV (MIMIC IV2.2) database. Participants were categorized into four groups based on TyG index level. The primary outcome was hospital all-cause mortality. Multivariable logistic proportional regression analysis and restricted cubic spline regression were employed to assess the TyG index's association with hospital mortality in patients with CHF and AF. Sensitivity analysis included determining the TyG index's feature importance through subgroup analysis in different subgroups. Results A total of 787 patients were included in the study, with hospital and ICU mortalities of 14.2% and 8.3%, respectively. Multivariate logistic regression analysis demonstrated that the TyG index was independently associated with an increased risk of hospital mortality (odds ratio (OR), 1.59 [95% confidence interval (CI) 1.15–2.19], P = 0.005) and ICU mortality [OR 1.9; (95% CI 1.28–2.83), P = 0.001] after adjusting for confounders. The restricted cubic spline regression model indicated a linear increase in the risks of in-hospital and ICU mortality with a higher TyG index. Sensitivity analysis revealed consistent effect sizes and directions in different subgroups, ensuring result stability. Conclusions The results of our study suggest a significant association between the TyG index and hospital and ICU all-cause mortality in critically ill patients with CHF and AF. This finding implies that the TyG index could potentially serve as a valuable tool for identifying patients with CHF and AF at an elevated risk of all-cause mortality.

Learning6 citations2025-04-01Paper ->

Torque-Induced-Overshoot Reduction Inspired Compensator for PMSMs Using Motor-Physics Embedded Gaussian Process Regression

Zhenxiao Yin, X. Dai, Zewen Yang, Yang Shen, Fang Li et al.

In safety-critical control for permanent magnet synchronous motors (PMSMs), the overshoot after adding a spontaneous load is a crucial metric, leading to the unexpected motion of driving equipment, which induces potential unsafe problems. Therefore, it is necessary to develop a control method that effectively reduces overshoot in PMSMs. Recognizing the nature of overshoot effects, a data-driven approach, Gaussian process regression (GPR), is employed to generate the prediction. With a focus on maintaining the advantage of the GPR method while preserving the physical properties of PMSM, an overshoot reduction-inspired motor physics embedded GPR method (OR-MPE-GPR) is proposed. Inspired by the shape of the overshoot, the squared exponential (SQE) kernel function is chosen for GPR. Furthermore, by using sufficient conditions to achieve stability, the dynamic stable range and static stable range of the updating rate are derived to guarantee the stability of the proposed machine learning control algorithm. Finally, comprehensive simulations and experiments compared with the state-of-the-art methods are conducted, showcasing the good performance of the proposed method in reducing overshoot while preserving static performance within a stable region.

Other4 citations2025-02-01Paper ->

Dammed lake chronology in the middle Yarlung Tsangpo River: Tracing the origin of late Holocene megafloods

A. Yang, Wei-ming Liu, Hao Wang, Kaiheng Hu, Xuemei Li et al.

Other6 citations2025-01-09Paper ->

The predictive value of triglyceride-glucose index combined with non–high-density lipoprotein cholesterol in coronary heart disease

Chunge Zhang, Hui Zhang, Zewen Yang, Yao Sheng, Ningning Ji

To explore the predictive value of the triglyceride-glucose(TyG)index combined with non–high-density lipoprotein cholesterol (Non-HDL-C) in coronary atherosclerotic heart disease (CHD). We retrospectively collected patients who were suspected of CHD and underwent coronary angiography in Yiwu Central Hospital and collected medical history, other serum biochemical evaluation and echocardiography from the enrolled population, Non-HDL-C and TyG indices were calculated, and their correlation with Gensini score was analyzed. Logistic regression analysis was used to analyze the risk factors of coronary heart disease, and ROC curves were plotted to assess the predictive value of CHD in subjects with single or multiple indices. TyG index and Non-HDL-C were higher in patients with CHD than in patients without CHD (P < 0.05), and they were independent risk factors for the development of CHD after logistic regression analysis. Diabetes, Non-HDL-C, TyG index, and Gensini score were positively correlated. The areas under the ROC curves for TyG index and Non-HDL-C for the diagnosis of coronary heart disease were 0.719 (95% CI 0.675–0.763) and 0.652 (95% CI 0.605-0.700), respectively, and the area under the ROC curve plotted with the joint equation of the two was 0.724 (95% CI 0.681–0.768), which can better predict the occurrence of coronary heart disease. TyG index and Non-HDL-C are independent risk factors for the occurrence of coronary heart disease, and the combination of the two can better predict the occurrence of coronary heart disease.

Other4 citations2025-01-01Paper ->

Optimizing FBG sensor layout of tunnel monitoring using improved multi-objective snow ablation optimizer based on radial basis function

R. Xing, Zhongchao Zhao, Chuan He, P. Xu, Daiqiang Zhu et al.

Other2 citations2024-12-13Paper ->

Persona Adaptable Strategies Make Large Language Models Tractable

Georges Hattab, A. Anžel, Akshat Dubey, Chisom Ezekannagha, Zewen Yang et al.

Explainable artificial intelligence for language models varies widely, using techniques like visualization, model-generated text samples, and data analysis. Explanations often overlook the human perspective, leaving the public in the dark about these powerful artificial intelligence systems. Ten persona-adaptable strategies are proposed to help large language models explain their functionality to everyday users. These strategies are designed to be implemented by the model itself and allow it to tailor explanations based on user archetypes, adjusting complexity and style accordingly. The strategies incorporate both technical and human-centered considerations. Technical considerations include the training data, the model architecture used for training, its behavior, and efficiency. Human-centered considerations make the understanding of large language models tractable. These include explaining the sheer volume of text and digital storage a language model requires, the time required to read and computationally process the text, the universality and multilingual properties of the text, the energy required for processing and abstract reasoning, and how the model matches natural language experience. The persona-adaptable strategies serve as a template for the creation of audience-centric explanations powered by the use of large language models. The result can make complex language models more transparent and understandable to the general public.

Other3 citations2024-12-09Paper ->

Refractive Index Morphology Imaging Microscope System Utilizing Polarization Multiplexing for Label-Free Single Living Cells.

Huijun Wang, Lu Zhang, Chen Fan, Jie Huang, Weihao Zhao et al.

Detections of internal substances and morphologies for label-free living cells are crucial for revealing malignant diseases. With the phase serving as a coupling of refractive index (RI) (marker for substances) and thickness (morphology), existing decoupling methods mainly rely on complex integrated systems or extensive optical field information. Developing simple and rapid decoupling methods remains a challenge. This study introduces a refractive index morphology imaging microscope (RIMIM) system utilizing polarization multiplexing for label-free single living cells. By simultaneous degree of circular polarization (DOCP) imaging and noninterferometric quantitative phase imaging (QPI), the intracellular refractive index distribution (IRID) and morphology can be decoupled. The optical thickness calculated from the phase is input into the circular depolarization decay model (CDDM) of degree of circular polarization to retrieve IRID. Subsequently, the thickness can be decoupled from phase result using retrieved IRID. Experiments conducted on mouse forestomach carcinoma (MFC) cells and human kidney-2 cells (HK-2) demonstrated the RIMIM system's ability to retrieve IRID and decouple fine morphology. Additionally, the RIMIM system effectively detected membrane damage and changes in erastin-induced ferroptotic HK-2 cells, with average and root-mean-square of surface folds 65.5% and 70.0% higher than those of normal HK-2 cells. Overall, the RIMIM system provides a simple and rapid method for decoupling RI and fine morphology, showing great potential for label-free live cells' cytopathology detection.

Other17 citations2024-11-24Paper ->

Stress hyperglycemia ratio association with all-cause mortality in critically ill patients with coronary heart disease: an analysis of the MIMIC-IV database

Xiaofang Chen, Zewen Yang, Rui Shi, Xiaoyan Wang, Xuhua Li

Background The stress hyperglycemia ratio (SHR) indicates relative hyperglycemia levels. Research on the impact of SHR on mortality in coronary heart disease (CHD) patients in intensive care is limited. This study explores the predictive accuracy of SHR for the prognosis of CHD patients in the ICU. Methods This study included 2,059 CHD patients from the American Medical Information Mart for Intensive Care (MIMIC-IV) database. SHR was determined using the formula: SHR = (admission glucose) (mmol/L) / (1.59 * HbA1c [%] – 2.59). Subjects were stratified into quartiles based on SHR levels to examine the correlation between SHR and in-hospital mortality. The restricted cubic splines and Cox proportional hazards models were employed to assess this association, while Kaplan-Meier survival analysis was executed to ascertain the mortality rates across the SHR quartiles. Results Among the 2059 participants (1358 men), the rates of in-hospital and ICU mortality were 8.5% and 5.25%, respectively. Analysis showed SHR as a significant predictor of increased risk for both in-hospital (HR,1.16, 95% CI: 1.02–1.32, P = 0.022) and ICU mortality (HR, 1.16, 95% CI: 1.01–1.35, P = 0.040) after adjustments. A J-shaped relationship was noted between SHR and mortality risks (p for non-linearity = 0.002, respectively). Kaplan-Meier analysis confirmed substantial differences in in-hospital and ICU mortality across SHR quartiles. Conclusions SHR significantly predicts in-hospital and ICU mortality in critically ill CHD patients, indicating that higher SHR levels correlate with longer ICU stays and increased mortality. This underscores the potential of SHR as a prognostic marker for ICU CHD patients.

Other2 citations2024-11-01Paper ->

Transient geomorphic response after landslide-induced river damming in the eastern margin of the Tibetan plateau

Yanlian Zhou, Weiming Liu, B. Yanites, Liqin Zhou, Xuemei Li et al.

Learning0 citations2024-10-24arXiv ->

AI Readiness in Healthcare through Storytelling XAI

Akshat Dubey, Zewen Yang, Georges Hattab

Artificial Intelligence is rapidly advancing and radically impacting everyday life, driven by the increasing availability of computing power. Despite this trend, the adoption of AI in real-world healthcare is still limited. One of the main reasons is the trustworthiness of AI models and the potential hesitation of domain experts with model predictions. Explainable Artificial Intelligence (XAI) techniques aim to address these issues. However, explainability can mean different things to people with different backgrounds, expertise, and goals. To address the target audience with diverse needs, we develop storytelling XAI. In this research, we have developed an approach that combines multi-task distillation with interpretability techniques to enable audience-centric explainability. Using multi-task distillation allows the model to exploit the relationships between tasks, potentially improving interpretability as each task supports the other leading to an enhanced interpretability from the perspective of a domain expert. The distillation process allows us to extend this research to large deep models that are highly complex. We focus on both model-agnostic and model-specific methods of interpretability, supported by textual justification of the results in healthcare through our use case. Our methods increase the trust of both the domain experts and the machine learning experts to enable a responsible AI.

Other8 citations2024-07-12Paper ->

Association between the triglyceride glucose index and the risk of acute kidney injury in critically ill patients with hypertension: analysis of the MIMIC-IV database

Wenbin Zhang, Zewen Yang

Background The triglyceride glucose (TyG) index, a metric computed from the levels of fasting triglyceride (TG) and fasting plasma glucose (FPG), has emerged as a simple surrogate measure for insulin resistance (IR) in recent years. In multiple critical care scenarios, such as contrast-induced acute kidney injury (AKI) and cardiorenal syndrome, a high TyG index levels shows a notable correlation with AKI incidence. However, its predictive value for AKI in critically ill hypertensive patients remains uncertain. Methods Participants were selected from the Medical Information Mart for Intensive Care IV (MIMIC-IV) database and divided into quartiles based on the TyG index. The primary focus of the study was to investigate the risk of acute kidney injury (AKI), with in-hospital mortality as a secondary endpoint, assessed among all study subjects as well as specifically among AKI patients. The use of renal replacement therapy (RRT), indicative of AKI progression, was also considered a secondary endpoint reflecting renal outcomes. To explore the correlation between the TyG index and AKI risk in critically ill hypertensive patients, the study employed a restricted cubic splines model and Cox proportional hazards (CPH) models. Additionally, Kaplan-Meier survival analysis was utilized to assess differences in primary and secondary outcomes across groups categorized by their TyG index. Analyses were conducted to ensure the consistency of the predictive capability of TyG index across various subgroups. Results Our study included 4,418 participants, with 57% being male patients. AKI occurred in 56.1% of cases. Through the CPH analysis, we identified a significant association between the TyG index and AKI occurrence in critically ill hypertensive patients. With the help of a restricted cubic splines model, we observed a direct relationship between an elevated TyG index and an increased AKI. Subgroup examinations consistently proved the predictive value of the TyG index across categories. Furthermore, Kaplan-Meier survival analysis revealed notable differences in RRT among AKI patients. Conclusion The findings underscore the importance of the TyG index as a reliable predictor for the occurrence of AKI and adverse renal outcomes among hypertensive patients in critical ill states. Nevertheless, validating causality mandates extensive prospective investigations.

Robotics5 citations2024-07-01Paper ->

Hierarchical Trajectory Deformation Algorithm With Hybrid Controller for Active Lower Limb Rehabilitation

Zewen Yang, Hu Jin, Wei Gao, Erlong Wang, Yang Shu et al.

Robot-aided active rehabilitation has shown to be an effective treatment approach for hemiplegic patients. This letter presents an active control framework for lower limb rehabilitation, combining an interaction layer with a hierarchical trajectory deformation algorithm (HTDA), and an assist-as-needed (AAN) layer with a hybrid controller. The HTDA uses constrained optimization in both position and velocity domains to continuously generate smooth reference trajectories based on virtual interaction forces during physical human-robot interaction (pHRI). An additional optimization loop is also implemented to achieve adaptive parameter adjustment for HTDA. Meanwhile, the hybrid controller relies on a force field term and a velocity field term to provide AAN feature. The proposed method is validated on a two-degree-of-freedom lower limb rehabilitation robot for walking with variable step height and step length. The experimental results demonstrate that compared to previously developed admittance model (AM) and trajectory deformation algorithm (TDA), under four different evaluation metrics, HTDA can improve dimensionless squared jerk (DSJ) by 73.6% comparing to AM and improve constraint force percentage (CFP) by 20.4% comparing to TDA. This demonstrate the effectiveness of the proposed framework in reducing human-robot confrontation, especially in improving robot actuation compliance and movement smoothness.

Other0 citations2024-06-08arXiv ->

A nested model for AI design and validation

Akshat Dubey, Zewen Yang, Georges Hattab

Summary The growing AI field faces trust, transparency, fairness, and discrimination challenges. Despite the need for new regulations, there is a mismatch between regulatory science and AI, preventing a consistent framework. A five-layer nested model for AI design and validation aims to address these issues and streamline AI application design and validation, improving fairness, trust, and AI adoption. This model aligns with regulations, addresses AI practitioners’ daily challenges, and offers prescriptive guidance for determining appropriate evaluation approaches by identifying unique validity threats. We have three recommendations motivated by this model: (1) Authors should distinguish between layers when claiming contributions to clarify the specific areas in which the contribution is made and to avoid confusion; (2) authors should explicitly state upstream assumptions to ensure that the context and limitations of their AI system are clearly understood, (3) AI venues should promote thorough testing and validation of AI systems and their compliance with regulatory requirements.

Learning11 citations2024-06-01Paper ->

Decentralized event-triggered online learning for safe consensus control of multi-agent systems with Gaussian process regression

X. Dai, Zewen Yang, Mengtian Xu, Sihua Zhang, Fangzhou Liu et al.

Other11 citations2024-05-02Paper ->

Smart Designs of Zeolite-Based Catalysts for Dry Reforming of Methane: A Review

Shuxian Qiu, Xinyan Zhong, Zewen Yang, Yiyu Deng, Yilan Lai et al.

CBF Related Papers
Other0 citations2025-08-11arXiv ->

When are safety filters safe? On minimum phase conditions of control barrier functions

Jason J. Choi, Claire J. Tomlin, S. Sastry, K. Sreenath

In emerging control applications involving multiple and complex tasks, safety filters are gaining prominence as a modular approach to enforcing safety constraints. Among various methods, control barrier functions (CBFs) are widely used for designing safety filters due to their simplicity, imposing a single linear constraint on the control input at each state. In this work, we focus on the internal dynamics of systems governed by CBF-constrained control laws. Our key observation is that, although CBFs guarantee safety by enforcing state constraints, they can inadvertently be"unsafe"by causing the internal state to diverge. We investigate the conditions under which the full system state, including the internal state, can remain bounded under a CBF-based safety filter. Drawing inspiration from the input-output linearization literature, where boundedness is ensured by minimum phase conditions, we propose a new set of CBF minimum phase conditions tailored to the structure imposed by the CBF constraint. A critical distinction from the original minimum phase conditions is that the internal dynamics in our setting is driven by a nonnegative virtual control input, which reflects the enforcement of the safety constraint. We include a range of numerical examples, including single-input, multi-input, linear, and nonlinear systems, validating both our analysis and the necessity of the proposed CBF minimum phase conditions.

Robotics0 citations2025-05-04arXiv ->

Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety

Jason J. Choi, J. J. Aloor, Jingqi Li, Maria G. Mendoza, Hamsa Balakrishnan et al.

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety guarantees. Traditional control methods, such as reachability and control barrier functions, can provide rigorous safety guarantees when interactions are limited only to a small number of robots. However, conflicts between the constraints faced by different agents pose a challenge to safe multi-agent coordination. To overcome this challenge, we propose a method that integrates multiple layers of safety by combining MARL with safety filters. First, MARL is used to learn strategies that minimize multiple agent interactions, where multiple indicates more than two. Particularly, we focus on interactions likely to result in conflicting constraints within the engagement distance. Next, for agents that enter the engagement distance, we prioritize pairs requiring the most urgent corrective actions. Finally, a dedicated safety filter provides tactical corrective actions to resolve these conflicts. Crucially, the design decisions for all layers of this framework are grounded in reachability analysis and a control barrier-value function-based filtering mechanism. We validate our Layered Safe MARL framework in 1) hardware experiments using Crazyflie drones and 2) high-density advanced aerial mobility (AAM) operation scenarios, where agents navigate to designated waypoints while avoiding collisions. The results show that our method significantly reduces conflict while maintaining safety without sacrificing much efficiency (i.e., shorter travel time and distance) compared to baselines that do not incorporate layered safety. The project website is available at https://dinamo-mit.github.io/Layered-Safe-MARL/

Learning0 citations2024-02-07arXiv ->

Safety Filters for Black-Box Dynamical Systems by Learning Discriminating Hyperplanes

Will Lavanakul, Jason J. Choi, K. Sreenath, Claire J. Tomlin

Learning-based approaches are emerging as an effective approach for safety filters for black-box dynamical systems. Existing methods have relied on certificate functions like Control Barrier Functions (CBFs) and Hamilton-Jacobi (HJ) reachability value functions. The primary motivation for our work is the recognition that ultimately, enforcing the safety constraint as a control input constraint at each state is what matters. By focusing on this constraint, we can eliminate dependence on any specific certificate function-based design. To achieve this, we define a discriminating hyperplane that shapes the half-space constraint on control input at each state, serving as a sufficient condition for safety. This concept not only generalizes over traditional safety methods but also simplifies safety filter design by eliminating dependence on specific certificate functions. We present two strategies to learn the discriminating hyperplane: (a) a supervised learning approach, using pre-verified control invariant sets for labeling, and (b) a reinforcement learning (RL) approach, which does not require such labels. The main advantage of our method, unlike conventional safe RL approaches, is the separation of performance and safety. This offers a reusable safety filter for learning new tasks, avoiding the need to retrain from scratch. As such, we believe that the new notion of the discriminating hyperplane offers a more generalizable direction towards designing safety filters, encompassing and extending existing certificate-function-based or safe RL methodologies.

MPC/Planning0 citations2023-10-26arXiv ->

A Forward Reachability Perspective on Control Barrier Functions and Discount Factors in Reachability Analysis

Jason J. Choi, Donggun Lee, Boyang Li, Jonathan P. How, K. Sreenath et al.

Control invariant sets are crucial for various methods that aim to design safe control policies for systems whose state constraints must be satisfied over an indefinite time horizon. In this article, we explore the connections among reachability, control invariance, and Control Barrier Functions (CBFs). Unlike prior formulations based on backward reachability concepts, we establish a strong link between these three concepts by examining the inevitable Forward Reachable Tube (FRT), which is the set of states such that every trajectory reaching the FRT must have passed through a given initial set of states. First, our findings show that the inevitable FRT is a robust control invariant set if it has a continuously differentiable boundary. If the boundary is not differentiable, the FRT may lose invariance. We also show that any robust control invariant set including the initial set is a superset of the FRT if the boundary of the invariant set is differentiable. Next, we formulate a differential game between the control and disturbance, where the inevitable FRT is characterized by the zero-superlevel set of the value function. By incorporating a discount factor in the cost function of the game, the barrier constraint of the CBF naturally arises in the Hamilton-Jacobi (HJ) equation and determines the optimal policy. The resulting FRT value function serves as a CBF-like function, and conversely, any valid CBF is also a forward reachability value function. We further prove that any $C^1$ supersolution of the HJ equation for the FRT value functions is a valid CBF and characterizes a robust control invariant set that outer-approximates the FRT. Building on this property, finally, we devise a novel method that learns neural control barrier functions, which learn an control invariant superset of the FRT of a given initial set.

Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Other4 citations2023-07-29Paper ->

Short‐ and Long‐Term MRI Assessed Hemodynamic Changes in Pediatric Moyamoya Patients After Revascularization

Moss Y. Zhao, Elizabeth Tong, Rui Duarte Armindo, Ates Fettahoglu, Jason J. Choi et al.

Cerebrovascular reserve (CVR) reflects the capacity of cerebral blood flow (CBF) to change following a vasodilation challenge. Decreased CVR is associated with a higher stroke risk in patients with cerebrovascular diseases. While revascularization can improve CVR and reduce this risk in adult patients with vasculopathy such as those with Moyamoya disease, its impact on hemodynamics in pediatric patients remains to be elucidated. Arterial spin labeling (ASL) is a quantitative MRI technique that can measure CBF, CVR, and arterial transit time (ATT) non‐invasively.

Learning0 citations2022-08-23arXiv ->

Recursively Feasible Probabilistic Safe Online Learning With Control Barrier Functions

F. Castañeda, Jason J. Choi, Wonsuhk Jung, Bike Zhang, C. Tomlin et al.

Learning-based control has demonstrated great promise for handling complex tasks in various applications. However, ensuring system safety under uncertain dynamics remains a significant challenge. Control Barrier Functions (CBFs) offer mathematical tools for enforcing safety constraints given known system dynamics, yet their guarantees can be lost in the presence of model errors. In this article, we present a framework that combines model-based safety methods with data-driven techniques to guarantee safety recursively for systems with uncertain dynamics. We build upon our previous work, where Gaussian Process (GP) regression was utilized to quantify uncertainty in model-based CBF constraints, resulting in a second-order cone program (SOCP) controller. When the SOCP is feasible at a state, it provides a pointwise probabilistic safety guarantee. A critical innovation we develop further in this work is an event-triggered online data collection algorithm that actively and safely gathers data to provide the recursive feasibility of the SOCP-based controller. By continuously assessing the sufficiency of data based on the feasibility measure of the SOCP, our method triggers safe exploratory actions when necessary to reduce the uncertainty in critical control directions. This approach ensures that a feasible, safety-preserving control input is always available, thereby establishing forward invariance of the safe set with high probability, even in previously unexplored regions. We validate the proposed framework through two numerical simulation experiments.

Learning15 citations2022Paper ->

Probabilistic Safe Online Learning with Control Barrier Functions

F. Castañeda, Jason J. Choi, Wonsuhk Jung, Bike Zhang, C. Tomlin et al.

MPC/Planning0 citations2021-06-13arXiv ->

Pointwise Feasibility of Gaussian Process-based Safety-Critical Control under Model Uncertainty

F. Castañeda, Jason J. Choi, Bike Zhang, C. Tomlin, K. Sreenath

Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) are popular tools for enforcing safety and stability of a controlled system, respectively. They are commonly utilized to build constraints that can be incorpo-rated in a min-norm quadratic program (CBF-CLF-QP) which solves for a safety-critical control input. However, since these constraints rely on a model of the system, when this model is inaccurate the guarantees of safety and stability can be easily lost. In this paper, we present a Gaussian Process (GP)-based approach to tackle the problem of model uncertainty in safety-critical controllers that use CBFs and CLFs. The considered model uncertainty is affected by both state and control input. We derive probabilistic bounds on the effects that such model uncertainty has on the dynamics of the CBF and CLF. We then use these bounds to build safety and stability chance constraints that can be incorporated in a min-norm convex optimization-based controller, called GP-CBF-CLF-SOCP. As the main theoretical result of the paper, we present necessary and sufficient conditions for pointwise feasibility of the proposed optimization problem. We believe that these conditions could serve as a starting point towards understanding what are the minimal requirements on the distribution of data collected from the real system in order to guarantee safety. Finally, we validate the proposed framework with numerical simulations of an adaptive cruise controller for an automotive system.

MPC/Planning0 citations2021-04-06arXiv ->

Robust Control Barrier–Value Functions for Safety-Critical Control

Jason J. Choi, Donggun Lee, K. Sreenath, C. Tomlin, Sylvia L. Herbert

This paper works towards unifying two popular approaches in the safety control community: Hamilton-Jacobi (HJ) reachability and Control Barrier Functions (CBFs). HJ Reachability has methods for direct construction of value functions that provide safety guarantees and safe controllers, however the online implementation can be overly conservative and/or rely on chattering bang-bang control. The CBF community has methods for safe-guarding controllers in the form of point-wise optimization using quadratic programs (CBF-QP), where the CBF-based safety certificate is used as a constraint. However, finding a valid CBF for a general dynamical system is challenging. This paper unifies these two methods by introducing a new reachability formulation inspired by the structure of CBFs to construct a Control Barrier-Value Function (CBVF). We verify that CBVF is a viscosity solution to a novel Hamilton-Jacobi-Isaacs Variational Inequality and preserves the same safety guarantee as the original reachability formulation. Finally, inspired by the CBF-QP, we propose a QP-based online control synthesis for systems affine in control and disturbance, whose solution is always the CBVF’s optimal control signal robust to bounded disturbance. We demonstrate the benefit of using the CBVFs for double-integrator and Dubins car systems by comparing it to previous methods.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

Non-CBF Papers
Learning0 citations2025-09-29arXiv ->

Multi-Agent Guided Policy Search for Non-Cooperative Dynamic Games

Jingqi Li, Gechen Qu, Jason J. Choi, S. Sojoudi, Claire J. Tomlin

Multi-agent reinforcement learning (MARL) optimizes strategic interactions in non-cooperative dynamic games, where agents have misaligned objectives. However, data-driven methods such as multi-agent policy gradients (MA-PG) often suffer from instability and limit-cycle behaviors. Prior stabilization techniques typically rely on entropy-based exploration, which slows learning and increases variance. We propose a model-based approach that incorporates approximate priors into the reward function as regularization. In linear quadratic (LQ) games, we prove that such priors stabilize policy gradients and guarantee local exponential convergence to an approximate Nash equilibrium. We then extend this idea to infinite-horizon nonlinear games by introducing Multi-agent Guided Policy Search (MA-GPS), which constructs short-horizon local LQ approximations from trajectories of current policies to guide training. Experiments on nonlinear vehicle platooning and a six-player strategic basketball formation show that MA-GPS achieves faster convergence and more stable learning than existing MARL methods.

Robotics0 citations2025-08-13arXiv ->

Whole-Body Bilateral Teleoperation with Multi-Stage Object Parameter Estimation for Wheeled Humanoid Locomanipulation

D. Baek, Amartya Purushottam, Jason J. Choi, João Ramos

This paper presents an object-aware whole-body bilateral teleoperation framework for wheeled humanoid loco-manipulation. This framework combines whole-body bilateral teleoperation with an online multi-stage object inertial parameter estimation module, which is the core technical contribution of this work. The multi-stage process sequentially integrates a vision-based object size estimator, an initial parameter guess generated by a large vision-language model (VLM), and a decoupled hierarchical sampling strategy. The visual size estimate and VLM prior offer a strong initial guess of the object's inertial parameters, significantly reducing the search space for sampling-based refinement and improving the overall estimation speed. A hierarchical strategy first estimates mass and center of mass, then infers inertia from object size to ensure physically feasible parameters, while a decoupled multi-hypothesis scheme enhances robustness to VLM prior errors. Our estimator operates in parallel with high-fidelity simulation and hardware, enabling real-time online updates. The estimated parameters are then used to update the wheeled humanoid's equilibrium point, allowing the operator to focus more on locomotion and manipulation. This integration improves the haptic force feedback for dynamic synchronization, enabling more dynamic whole-body teleoperation. By compensating for object dynamics using the estimated parameters, the framework also improves manipulation tracking while preserving compliant behavior. We validate the system on a customized wheeled humanoid with a robotic gripper and human-machine interface, demonstrating real-time execution of lifting, delivering, and releasing tasks with a payload weighing approximately one-third of the robot's body weight.

MPC/Planning0 citations2025-04-04arXiv ->

Data-Driven Hamiltonian for Direct Construction of Safe Set from Trajectory Data

Jason J. Choi, C. Strong, K. Sreenath, Namhoon Cho, Claire J. Tomlin

In continuous-time optimal control, evaluating the Hamiltonian requires solving a constrained optimization problem using the system’s dynamics model. Hamilton-Jacobi reachability analysis for safety verification has demonstrated practical utility only when efficient evaluation of the Hamiltonian over a large state-time grid is possible. In this study, we introduce the concept of a data-driven Hamiltonian (DDH), which circumvents the need for an explicit dynamics model by relying only on mild prior knowledge (e.g., Lipschitz constants), thus enabling the construction of reachable sets directly from trajectory data. Recognizing that the Hamiltonian is the optimal inner product between a given costate and realizable state velocities, the DDH estimates the Hamiltonian using the worstcase realization of the velocity field based on the observed state trajectory data. This formulation ensures a conservative approximation of the true Hamiltonian for uncertain dynamics. The reachable set computed based on the DDH is also ensured to be a conservative approximation of the true reachable set. Next, we propose a data-efficient safe experiment framework for gradual expansion of safe sets using the DDH. This is achieved by iteratively conducting experiments within the computed data-driven safe set and updating the set using newly collected trajectory data. To demonstrate the capabilities of our approach, we showcase its effectiveness in safe flight envelope expansion for a tiltrotor vehicle transitioning from near-hover to forward flight.

Robotics0 citations2024-09-10arXiv ->

Gait Switching and Enhanced Stabilization of Walking Robots with Deep Learning-based Reachability: A Case Study on Two-link Walker

Xingpeng Xia, Jason J. Choi, Ayush Agrawal, K. Sreenath, Claire J. Tomlin et al.

Learning-based approaches have recently shown notable success in legged locomotion. However, these approaches often lack accountability, necessitating empirical tests to determine their effectiveness. In this work, we are interested in designing a learning-based locomotion controller whose stability can be examined and guaranteed. This can be achieved by verifying regions of attraction (RoAs) of legged robots to their stable walking gaits. This is a non-trivial problem for legged robots due to their hybrid dynamics. Although previous work has shown the utility of Hamilton-Jacobi (HJ) reachability to solve this problem, its practicality was limited by its poor scalability. The core contribution of our work is the employment of a deep learning-based HJ reachability solution to the hybrid legged robot dynamics, which overcomes the previous work’s limitation. With the learned reachability solution, first, we can estimate a library of RoAs for various gaits. Second, we can design a one-step predictive controller that effectively stabilizes to an individual gait within the verified RoA. Finally, we can devise a strategy that switches gaits, in response to external perturbations, whose feasibility is guided by the RoA analysis. We demonstrate our method in a two-link walker simulation, whose mathematical model is well established. Our method achieves improved stability than previous model-based methods, while ensuring transparency that was not present in the existing learning-based approaches.

Robotics0 citations2023-11-23arXiv ->

Constraint-Guided Online Data Selection for Scalable Data-Driven Safety Filters in Uncertain Robotic Systems

Jason J. Choi, F. Castañeda, Wonsuhk Jung, Bike Zhang, Claire J. Tomlin et al.

As the use of autonomous robots expands in tasks that are complex and challenging to model, the demand for robust data-driven control methods that can certify safety and stability in uncertain conditions is increasing. However, the practical implementation of these methods often faces scalability issues due to the growing amount of data points with system complexity and a significant reliance on high-quality training data. In response to these challenges, this study presents a scalable data-driven controller that efficiently identifies and infers from the most informative data points for implementing data-driven safety filters. Our approach is grounded in the integration of a model-based certificate function-based method and Gaussian Process regression, reinforced by a novel online data selection algorithm that reduces time complexity from quadratic to linear relative to dataset size. Empirical evidence, gathered from successful real-world cart–pole swing-up experiments and simulated locomotion of a five-link bipedal robot, demonstrates the efficacy of our approach. Our findings reveal that our efficient online data selection algorithm, which strategically selects key data points, enhances the practicality and efficiency of data-driven certifying filters in complex robotic systems, significantly mitigating scalability concerns inherent in nonparametric learning-based control methods.

Theory5 citations2023-05-16Paper ->

Towards Flight Envelope Protection for the NASA Tiltwing eVTOL Flight Mode Transition using Hamilton-Jacobi Reachability

T. Hsu, Jason J. Choi, Shaun C. McWherter, Divyang Amin, M. Piedmonte et al.

This paper presents a collaborative research effort between authors from Bechamo LLC, UC Berkeley, and NASA to establish a framework for applying Hamilton-Jacobi Reachability Analysis to the full 6-DOF dynamics of the NASA Tiltwing vehicle, verifying the safe flight envelope during the flight mode transition between hover and cruise flight, which prevents loss of control of the vehicle and ensures recoverability to safe trim conditions. This involved first verifying the nominal flight mode transition path as a series of trim points, defining the safe flight envelope using reachability, and decomposing the system dynamics into longitudinal and lateral subsystems. Our formulation guarantees the computed envelope's robustness against modeling errors and uncertainty, and the usage of state decomposition significantly improved the tractability of the reachability computation. The framework's success is validated through 6-DOF Monte Carlo nonlinear simulation of vehicle dynamics, demonstrating that the vehicle states within the flight envelope can successfully recover to trim states and continue a safe flight mode transition.

Theory2 citations2023Paper ->

Towards Flight Envelope Protection for the NASA Tiltwing eVTOL Flight Mode Transition Using Hamilton–Jacobi Reachability

T.-W. Hsu, Jason J. Choi, Divyang Amin, Claire J. Tomlin, Shaun C. McWherter et al.

Innovative electric vertical take-off and landing (eVTOL) aircraft designs and operational concepts, driven by advancements in battery and electric motor technologies, seek to achieve superior safety records with increased system redundancy. Validating safe flight operations within verified flight envelope regions for passenger flights in densely populated urban environments remains a primary challenge. This paper establishes a framework for applying Hamilton–Jacobi reachability analysis to the full six-degree-of-freedom (6-DOF) dynamics of the NASA Tiltwing vehicle, verifying the flight envelope during the flight mode transition between near-hover and cruise flight, which prevents loss of control of the vehicle and ensures recoverability to safe trim conditions. This involves first verifying the nominal flight mode transition path as a series of trim points, defining the safe flight envelope using reachability, and decomposing the system dynamics into longitudinal and lateral subsystems. Our formulation guarantees the computed envelope's robustness against modeling errors and uncertainties, and the usage of state decomposition significantly improves the tractability of the reachability computation. The result is validated through Monte Carlo 6-DOF nonlinear simulation of vehicle dynamics, demonstrating that the vehicle states within the flight envelope can successfully recover to trim states and continue the flight mode transition safely.

MPC/Planning0 citations2022-06-21arXiv ->

Lyapunov Density Models: Constraining Distribution Shift in Learning-Based Control

Katie Kang, Paula Gradu, Jason J. Choi, Michael Janner, C. Tomlin et al.

Learned models and policies can generalize effectively when evaluated within the distribution of the training data, but can produce unpredictable and erroneous outputs on out-of-distribution inputs. In order to avoid distribution shift when deploying learning-based control algorithms, we seek a mechanism to constrain the agent to states and actions that resemble those that it was trained on. In control theory, Lyapunov stability and control-invariant sets allow us to make guarantees about controllers that stabilize the system around specific states, while in machine learning, density models allow us to estimate the training data distribution. Can we combine these two concepts, producing learning-based control algorithms that constrain the system to in-distribution states using only in-distribution actions? In this work, we propose to do this by combining concepts from Lyapunov stability and density estimation, introducing Lyapunov density models: a generalization of control Lyapunov functions and density models that provides guarantees on an agent's ability to stay in-distribution over its entire trajectory.

Robotics0 citations2022-01-21arXiv ->

Computation of Regions of Attraction for Hybrid Limit Cycles Using Reachability: An Application to Walking Robots

Jason J. Choi, Ayush Agrawal, K. Sreenath, C. Tomlin, Somil Bansal

Contact-rich robotic systems, such as legged robots and manipulators, are often represented as hybrid systems. However, the stability analysis and region-of-attraction computation for these systems are often challenging because of the discontinuous state changes upon contact (also referred to as state resets). In this work, we cast the computation of region-of-attraction as a Hamilton-Jacobi (HJ) reachability problem. This enables us to leverage HJ reachability tools that are compatible with general nonlinear system dynamics, and can formally deal with state and input constraints as well as bounded disturbances. Our main contribution is the generalization of HJ reachability framework to account for the discontinuous state changes originating from state resets, which has remained a challenge until now. We apply our approach for computing region-of-attractions for several underactuated walking robots and demonstrate that the proposed approach can (a) recover a bigger region-of-attraction than state-of-the-art approaches, (b) handle state resets, nonlinear dynamics, external disturbances, and input constraints, and (c) also provides a stabilizing controller for the system that can leverage the state resets for enhancing system stability.

Other5 citations2021-04-12Paper ->

Improving the performance of AI models in tactical environments using a hybrid cloud architecture

Eric M. Sturzinger, Christopher J. Lowrance, Isaac J. Faber, Jason J. Choi, Alex D. MacCalman

As the Department of Defense (DoD) looks to exploit and scale Artificial Intelligence (AI) capabilities across the warfighting domains, the Army plans to integrate advanced features into many of its combat systems. The benefits of cloud technologies offer promising solutions to these needs. While cloud-based AI-enabled capabilities leverage flexibility, common interfaces, and virtually infinite scale of resources, they suffer from their lack of proximity to the tactical edge. Tactical AI-enabled systems cannot reliably leverage advantages provided by cloud resources due to limited standardized practices for integration of on-premise/edge systems required by the deployed military. Future high-intensity conflict will be fought in a degraded, denied, intermittent, and lowbandwidth (DDIL) digital environment. As a result, tactical AI-enabled systems will be required to operate in a scenario where high speed, reliable cloud access is unavailable. This paper proposes a hybrid-cloud architecture that leverages resources of the cloud, when available, while also maintaining the capability to retrain tactical AI models in the field environment, using on-site computation and storage. The hybrid cloud construct consists of tactical cloud nodes that reside in closer proximity to AI-enabled systems at the edge. They may retain connectivity to the enterprise cloud yet have the ability to provide the common AI development platform and tool sets to support continuous integration, delivery, and deployment. Thus, its ultimate objective is to enable the seamless and expeditious operation of a distributed AI development environment for the Army and DoD that bridges the tactical edge and enterprise cloud.

Robotics0 citations2021-01-15arXiv ->

Scalable Learning of Safety Guarantees for Autonomous Systems using Hamilton-Jacobi Reachability

Sylvia L. Herbert, Jason J. Choi, Suvansh Qazi, Marsalis T. Gibson, K. Sreenath et al.

Autonomous systems like aircraft and assistive robots often operate in scenarios where guaranteeing safety is critical. Methods like Hamilton-Jacobi reachability can provide guaranteed safe sets and controllers for such systems. However, often these same scenarios have unknown or uncertain environments, system dynamics, or predictions of other agents. As the system is operating, it may learn new knowledge about these uncertainties and should therefore update its safety analysis accordingly. However, work to learn and update safety analysis is limited to small systems of about two dimensions due to the computational complexity of the analysis. In this paper we synthesize several techniques to speed up computation: decomposition, warm-starting, and adaptive grids. Using this new framework we can update safe sets by one or more orders of magnitude faster than prior work, making this technique practical for many realistic systems. We demonstrate our results on simulated 2D and 10D near-hover quadcopters operating in a windy environment.

MPC/Planning0 citations2020-11-14arXiv ->

Gaussian Process-based Min-norm Stabilizing Controller for Control-Affine Systems with Uncertain Input Effects and Dynamics

F. Castañeda, Jason J. Choi, Bike Zhang, C. Tomlin, K. Sreenath

This paper presents a method to design a min-norm Control Lyapunov Function (CLF)-based stabilizing controller for a control-affine system with uncertain dynamics using Gaussian Process (GP) regression. In order to estimate both state and input-dependent model uncertainty, we propose a novel compound kernel that captures the control-affine nature of the problem. Furthermore, by the use of GP Upper Confidence Bound analysis, we provide probabilistic bounds of the regression error, leading to the formulation of a CLF-based stability chance constraint which can be incorporated in a min-norm optimization problem. We show that this resulting optimization problem is convex, and we call it “Gaussian Process-based Control Lyapunov Function Second-Order Cone Program” (GP-CLF-SOCP). The data-collection process and the training of the GP regression model are carried out in an episodic learning fashion. We validate the proposed algorithm and controller in numerical simulations of an inverted pendulum and a kinematic bicycle model, resulting in stable trajectories which are very similar to the ones obtained if we actually knew the true plant dynamics.

Robotics2 citations2019-06-24Paper ->

Online Social Touch Pattern Recognition with Multi-modal-sensing Modular Tactile Interface

Hyunjin Ku, Jason J. Choi, Sunho Jang, Wonkyung Do, Soomin Lee et al.

The capability of recognizing various social touch patterns is necessary for robots functioning for touch-based social interaction, which is effective in many robot applications. Literature has focused on the novelty of the recognition system or improvements in classification accuracy based on publicly available datasets. In this paper, we propose an integrated framework of implementing social touch recognition system for various robots, which consists of three complementary principles: 1) multi-modal tactile sensing, 2) a modular design, and 3) a social touch pattern classifier capable of learning temporal features. The approach is evaluated by an implemented Multi-modal-sensing Modular Tactile Interface prototype, while for the classifiers, three learning methods—HMM, LSTM, and 3D-CNN—have been tested. The trained classifiers, which can run online in robot’s embedded system, predict 18 classes of social touch pattern. Results of the online validation test offer that all three methods are promising with the best accuracy of 88.86%. Especially, the stable performance of 3D-CNN indicates that learning ‘spatiotemporal’ features from tactile data would be more effective. Through this validation process, we have confirmed that our framework can be easily adopted and secures robust performance for social touch pattern recognition.

Robotics19 citations2018-03-01Paper ->

Designing Shelly, a Robot Capable of Assessing and Restraining Children's Robot Abusing Behaviors

Hyunjin Ku, Jason J. Choi, Soomin Lee, Sunho Jang, Wonkyung Do

Robotics6 citations2018-03-01Paper ->

Shelly, a Tortoise-Like Robot for One-to-Many Interaction with Children

Hyunjin Ku, Jason J. Choi, Soomin Lee, Sunho Jang, Wonkyung Do

Other90 citations2014-05-01Paper ->

Opening Injection Pressure Consistently Detects Needle–Nerve Contact during Ultrasound-guided Interscalene Brachial Plexus Block

J. Gadsden, Jason J. Choi, Emily Lin, Allegra Robinson

Other126 citations2013-12-01Paper ->

Continuous Interscalene Block in Patients Having Outpatient Rotator Cuff Repair Surgery: A Prospective Randomized Trial

E. Şalvız, Daquan Xu, Ashton P. Frulla, K. Kwofie, U. Shastri et al.

Other38 citations2013-08-01Paper ->

Regional anesthesia for trauma outside the operating theatre

Jason J. Choi, Emily Lin, J. Gadsden

Other34 citations2013-07-01Paper ->

Peripheral nerve blocks for outpatient surgery: evidence-based indications

Emily Lin, Jason J. Choi, A. Hadžić

CBF Related Papers
Robotics200 citations2023-10-01Paper ->

Data-Driven Safety Filters: Hamilton-Jacobi Reachability, Control Barrier Functions, and Predictive Methods for Uncertain Systems

K. P. Wabersich, Andrew J. Taylor, Jason J. Choi, K. Sreenath, C. Tomlin et al.

Today’s control engineering problems exhibit an unprecedented complexity, with examples including the reliable integration of renewable energy sources into power grids [1], safe collaboration between humans and robotic systems [2], and dependable control of medical devices [3] offering personalized treatment [4]. In addition to compliance with safety criteria, the corresponding control objective is often multifaceted. It ranges from relatively simple stabilization tasks to unknown objective functions, which are, for example, accessible only through demonstrations from interactions between robots and humans [5]. Classical control engineering methods are, however, often based on stability criteria with respect to set points and reference trajectories, and they can therefore be challenging to apply in such unstructured tasks with potentially conflicting safety specifications [6, Secs. 3 and 6]. While numerous efforts have started to address these challenges, missing safety certificates often still prohibit the widespread application of innovative designs outside research environments. As described in “Summary,” this article presents safety filters and advanced data-driven enhancements as a flexible framework for overcoming these limitations by ensuring that safety requirements codified as static state constraints are satisfied under all physical limitations of the system.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

CBF Related Papers
Other0 citations2025-10-24arXiv ->

Predictive control barrier functions for piecewise affine systems with non-smooth constraints

Kanghui He, Anil Alan, Shengling Shi, T. Boom, B. D. Schutter

Obtaining control barrier functions (CBFs) with large safe sets for complex nonlinear systems and constraints is a challenging task. Predictive CBFs address this issue by using an online finite-horizon optimal control problem that implicitly defines a large safe set. The optimal control problem, also known as the predictive safety filter (PSF), involves predicting the system's flow under a given backup control policy. However, for non-smooth systems and constraints, some key elements, such as CBF gradients and the sensitivity of the flow, are not well-defined, making the current methods inadequate for ensuring safety. Additionally, for control-non-affine systems, the PSF is generally nonlinear and non-convex, posing challenges for real-time computation. This paper considers piecewise affine systems, which are usually control-non-affine, under nonlinear state and polyhedral input constraints. We solve the safety issue by incorporating set-valued generalized Clarke derivatives in the PSF design. We show that enforcing CBF constraints across all elements of the generalized Clarke derivatives suffices to guarantee safety. Moreover, to lighten the computational overhead, we propose an explicit approximation of the PSF. The resulting control methods are demonstrated through numerical examples.

Learning0 citations2025-08-11arXiv ->

Robust Adaptive Discrete-Time Control Barrier Certificate

Changrui Liu, Anil Alan, Shengling Shi, B. D. Schutter

This work develops a robust adaptive control strategy for discrete-time systems using Control Barrier Functions (CBFs) to ensure safety under parametric model uncertainty and disturbances. A key contribution of this work is establishing a barrier function certificate in discrete time for general online parameter estimation algorithms. This barrier function certificate guarantees positive invariance of the safe set despite disturbances and parametric uncertainty without access to the true system parameters. In addition, real-time implementation and inherent robustness guarantees are provided. The proposed robust adaptive safe control framework demonstrates that the parameter estimation module can be designed separately from the CBF-based safety filter, simplifying the development of safe adaptive controllers for discrete-time systems. The resulting safe control approach guarantees that the system remains within the safe set while adapting to model uncertainties, making it a promising strategy for discrete-time safety-critical systems.

Other0 citations2025-03-19arXiv ->

Uncertainty Estimators for Robust Backup Control Barrier Functions

D. V. Wijk, Ersin Daş, Anil Alan, Samuel Coogan, T. G. Molnár et al.

Designing safe controllers is crucial and notoriously challenging for input-constrained safety-critical control systems. Backup control barrier functions offer an approach for the construction of safe controllers online by considering the flow of the system under a backup controller. However, in the presence of model uncertainties, the flow cannot be accurately computed, making this method insufficient for safety assurance. To tackle this shortcoming, we integrate backup control barrier functions with uncertainty estimators and calculate the flow under a reconstruction of the model uncertainty while refining this estimate over time. We prove that the controllers resulting from the proposed Uncertainty Estimator Backup Control Barrier Function (UE-bCBF) approach guarantee safety, are robust to unknown disturbances, and satisfy input constraints.

Other16 citations2024-01-01Paper ->

Integrating Safety With Performance in Connected Automated Truck Control: Experimental Validation

Anil Alan, C. He, T. Molnár, Johaan C. Mathew, A. Bell et al.

Combining efficiency with safety is one of the most important design challenges for connected automated trucks. In order to address this challenge for longitudinal control problems, we propose a scheme that integrates a performance-based controller with a safety-oriented controller in a seamless manner. This safe integration scheme operates instantaneously, and it is compatible with a large class of controllers. We first link this practical integration method to the theoretical framework of control barrier functions that endows controllers with formal safety guarantees. Then, through this scheme we safely integrate a predictive-type controller minimizing energy consumption (predictive cruise control—PCC) with a safety-oriented cruise controller structure relying on connectivity (connected cruise control—CCC). Importantly, the efficacy of the safe and seamless integration between the PCC and the CCC is demonstrated using on-road experiments with a full-scale connected automated truck. Initial experimental campaign is held on a closed test track, and safe driving is achieved thanks to the CCC while up to 18% energy saving is obtained thanks to the PCC. Finally, experiments are extended to a public highway, and similar results are obtained with up to 4.3% energy saving.

Other0 citations2023-03-20arXiv ->

Parameterized Barrier Functions to Guarantee Safety Under Uncertainty

Anil Alan, T. Molnár, A. Ames, G. Orosz

Deploying safety-critical controllers in practice necessitates the ability to modulate uncertainties in control systems. In this context, robust control barrier functions—in a variety of forms—have been used to obtain safety guarantees for uncertain systems. Yet the differing types of uncertainty experienced in practice have resulted in a fractured landscape of robustification—with a variety of instantiations depending on the structure of the uncertainty. This letter proposes a framework for generalizing these variations into a single form: parameterized barrier functions (PBFs), which yield safety guarantees for a wide spectrum of uncertainty types. This leads to controllers that enforce robust safety guarantees while their conservativeness scales by the parameterization. To illustrate the generality of this approach, we show that input-to-state safety (ISSf) is a special case of the PBF framework, whereby improved safety guarantees can be given relative to ISSf.

Theory0 citations2022-09-16arXiv ->

Disturbance Observers for Robust Safety-Critical Control With Control Barrier Functions

Anil Alan, T. Molnár, Ersin Daş, A. Ames, G. Orosz

This letter provides formal safety guarantees for control systems with disturbance. A disturbance observer-based robust safety-critical controller is proposed, that estimates the effect of the disturbance on safety and utilizes this estimate with control barrier functions to attain provably safe dynamic behavior. The observer error bound – which consists of transient and steady-state parts – is quantified, and the system is endowed with robustness against this error via the proposed controller. A connected cruise control problem is used as illustrative example through simulations including real disturbance data.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Other0 citations2022-05-29arXiv ->

Input-to-State Safety with Input Delay in Longitudinal Vehicle Control

T. Molnár, Anil Alan, A. Kiss, A. Ames, G. Orosz

Safe longitudinal control is discussed for a connected automated truck traveling behind a preceding connected vehicle. A controller is proposed based on control barrier function theory and predictor feedback for provably safe, collision-free behavior by taking into account the significant response time of the truck as input delay and the uncertainty of its dynamical model as input disturbance. The benefits of the proposed controller compared to control designs that neglect the delay or treat the delay as disturbance are shown by numerical simulations.

Robotics0 citations2021-12-15arXiv ->

Safety-Aware Preference-Based Learning for Safety-Critical Control

Ryan K. Cosner, Maegan Tucker, Andrew J. Taylor, Kejun Li, Tam'as G. Moln'ar et al.

Bringing dynamic robots into the wild requires a tenuous balance between performance and safety. Yet controllers designed to provide robust safety guarantees often result in conservative behavior, and tuning these controllers to find the ideal trade-off between performance and safety typically requires domain expertise or a carefully constructed reward function. This work presents a design paradigm for systematically achieving behaviors that balance performance and robust safety by integrating safety-aware Preference-Based Learning (PBL) with Control Barrier Functions (CBFs). Fusing these concepts -- safety-aware learning and safety-critical control -- gives a robust means to achieve safe behaviors on complex robotic systems in practice. We demonstrate the capability of this design paradigm to achieve safe and performant perception-based autonomous operation of a quadrupedal robot both in simulation and experimentally on hardware.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Non-CBF Papers
MPC/Planning0 citations2025-10-22arXiv ->

Approximate Model Predictive Control for Microgrid Energy Management via Imitation Learning

Changrui Liu, Shengling Shi, Anil Alan, G. K. Venayagamoorthy, B. D. Schutter

Efficient energy management is essential for reliable and sustainable microgrid operation amid increasing renewable integration. This paper proposes an imitation learning-based framework to approximate mixed-integer Economic Model Predictive Control (EMPC) for microgrid energy management. The proposed method trains a neural network to imitate expert EMPC control actions from offline trajectories, enabling fast, real-time decision making without solving optimization problems online. To enhance robustness and generalization, the learning process includes noise injection during training to mitigate distribution shift and explicitly incorporates forecast uncertainty in renewable generation and demand. Simulation results demonstrate that the learned policy achieves economic performance comparable to EMPC while only requiring $10\%$ of the computation time of optimization-based EMPC in practice.

Other0 citations2022-12-07arXiv ->

Experimental Validation of a Safe Controller Integration Scheme for Connected Automated Trucks

Anil Alan, C. He, T. Molnár, Johaan C. Mathew, A. H. Bell et al.

Accomplishing safe and efficient driving is one of the predominant challenges in the controller design of connected automated vehicles (CAVs). It is often more convenient to address these goals separately and integrate the resulting controllers. In this study, we propose a controller integration scheme to fuse performance-based controllers and safety-oriented controllers safely for the longitudinal motion of a CAV. The resulting structure is compatible with a large class of controllers, and offers flexibility to design each controller individually without affecting the performance of the others. We implement the proposed safe integration scheme on a connected automated truck using an optimal-in-energy controller and a safety-oriented connected cruise controller. We validate the premise of the safe integration through experiments with a full-scale truck in two scenarios: a controlled experiment on a test track and a real-world experiment on a public highway. In both scenarios, we achieve energy efficient driving without violating safety.

Other7 citations2020-07-01Paper ->

Improving fuel economy of heavy-duty vehicles in daily driving

C. He, Anil Alan, T. Molnár, S. Avedisov, A. Bell et al.

In this work, we integrate two once separate concepts for longitudinal control of heavy duty vehicles: responding to elevation changes to improve fuel economy using preview and reacting to the motion of preceding vehicles using feedback. The two concepts are unified to provide a safe yet fuel efficient connected and automated technology for heavy duty vehicles. First, we establish an integrated control framework of the two concepts based on barrier function theory and then we discuss the detailed control design of each concept. Finally, we demonstrate the benefits of the proposed design against a naive switching controller by experimentally evaluating the performance of a connected automated truck.

Learning16 citations2018-09-18Paper ->

High-Performance Adaptive Pressure Control in the Presence of Time Delays: Pressure Control for Use in Variable-Thrust Rocket Development

Anil Alan, Y. Yildiz, U. Poyraz

Smart defense systems using missiles that can fine-tune their velocity profiles have significant technological superiority over their conventional counterparts. This tuning is possible, in part, due to the deployment of advanced sensing, actuation, and computation capabilities and sophisticated guidance, navigation, and control algorithms. The capability to alter velocity during operation helps sustain optimum performance for different flight conditions. In addition, it makes it possible to slow down while turning and then speed up along a straight path, rendering the maneuvers more efficient. This ability to modify velocity (known as throttleability) is also known to increase a missile's no-escape zone, which is the maximum range that the missile can outrun its target [1]. As presented in "Summary," this article discusses the advanced control technologies needed to obtain throttleability.

Learning10 citations2017-08-01Paper ->

Adaptive pressure control experiment: Controller design and implementation

Anil Alan, Y. Yildiz, U. Poyraz

Learning0 citations2017-06-01Paper ->

Pressure control of gas generator in throttleable ducted rockets: a time delay resistant adaptive control approach

Anil Alan

Learning2 citations2017-01-09Paper ->

Pressure control of cold air testing plant with delay resistant closed-loop reference model adaptive control

Anil Alan, Y. Yildiz, U. Poyraz

Learning8 citations2015-07-27Paper ->

Gas Generator Pressure Control in Throttleable Ducted Rockets: A Classical and Adaptive Control Approach

Anil Alan, Y. Yildiz, U. Poyraz

CBF Related Papers
Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Non-CBF Papers
Other37 citations2023-07-18Paper ->

Chiral PSiSi-Ligand Enabled Iridium-Catalyzed Atroposelective Intermolecular C-H Silylation.

Bo Yang, Jihui Gao, Xing-wu Tan, Yicong Ge, C. He

Catalytic enantioselective intermolecular C-H silylation offers an efficient approach for the rapid construction of chiral organosilicon compounds, but remains a significant challenge. Herein, a new type of chiral silyl ligand is developed, which enables the first iridium-catalyzed atroposelective intermolecular C-H silylation reaction of 2-arylisoquinolines. This protocol features mild reaction conditions, high atom economy, and remarkable yield with excellent stereoselectivity (up to 99% yield, 99% ee), delivering enantioenriched axially chiral silane platform molecules with facile convertibility. Key to the success of this unprecedented transformation relies on a novel chiral PSiSi-ligand, which facilitates the intermolecular C-H silylation process with perfect chem-, regio- and stereo-control via a multi-coordinated silyl iridium complex.

Theory166 citations2023-01-26Paper ->

Exon architecture controls mRNA m6A suppression and gene expression

P. He, Jiangbo Wei, Xiaoyang Dou, Bryan T. Harada, Zijie Zhang et al.

N6-methyladenosine (m6A) is the most abundant messenger RNA (mRNA) modification and plays crucial roles in diverse physiological processes. Using a massively parallel assay for m6A (MPm6A), we discover that m6A specificity is globally regulated by suppressors that prevent m6A deposition in unmethylated transcriptome regions. We identify exon junction complexes (EJCs) as m6A suppressors that protect exon junction–proximal RNA within coding sequences from methylation and regulate mRNA stability through m6A suppression. EJC suppression of m6A underlies multiple global characteristics of mRNA m6A specificity, with the local range of EJC protection sufficient to suppress m6A deposition in average-length internal exons but not in long internal and terminal exons. EJC-suppressed methylation sites colocalize with EJC-suppressed splice sites, which suggests that exon architecture broadly determines local mRNA accessibility to regulatory complexes. Description Methylation suppression Methylation of the N6 position of adenine (m6A) is a chemical tag for many messenger RNAs (mRNAs) added by m6A “writer” proteins. Tagged mRNAs are marked for regulation through m6A “reader” proteins, which bind methylated mRNAs and alter their expression. However, how the cell selects specific regions on mRNAs to be marked has remained unclear. He et al. identified a new function for the exon junction complex as an m6A “suppressor” that packages nearby mRNA and protects these regions from m6A marking. Exon architecture controls mRNA accessibility to m6A methylation, as well as potentially a broader set of regulatory complexes. —DJ Exon junction complexes are m6A suppressors that control global mRNA m6A specificity by protecting proximal RNA from methylation.

Other125 citations2021-04-30Paper ->

Microwave absorption enhancement of 2-dimensional CoZn/C@MoS2@PPy composites derived from metal-organic framework.

Yuxin Bi, M. Ma, Yanyan Liu, Zhouyu Tong, Rongzhen Wang et al.

Other81 citations2018-09-01Paper ->

Chapter 2: Mitigation pathways compatible with 1.5°C in the context of sustainable development

J. Rogelj, D. Shindell, K. Jiang, S. Fifita, P. Forster et al.

Other1144 citations2018-07-01Paper ->

China’s response to a national land-system sustainability emergency

B. Bryan, Lei Gao, Yan-mei Ye, Xiufeng Sun, J. Connor et al.

Other241 citations2017-07-17Paper ->

Auto-Conditioned Recurrent Networks for Extended Complex Human Motion Synthesis

Yi Zhou, Zimo Li, Shuangjiu Xiao, C. He, Zeng Huang et al.

Other269 citations2014-10-01Paper ->

Near wake flow analysis of a vertical axis wind turbine by stereoscopic particle image velocimetry

G. Tescione, D. Ragni, C. He, C. Ferreira, G. Bussel

Other183 citations2014-09-01Paper ->

Long cycle life lithium ion battery with lithium nickel cobalt manganese oxide (NCM) cathode

Shuang Liu, L. Xiong, C. He

Other52 citations2014-03-01Paper ->

Treatment of melasma with oral administration of compound tranexamic acid: a preliminary clinical trial

Y. Li, Q. Sun, Z. He, L. Fu, C. He et al.

Other76 citations2013-08-01Paper ->

Melting behaviour and homogeneity range of B2 CoAl and updated thermodynamic description of the Al–Co system

F. Stein, C. He, N. Dupin

Other82 citations2013-01-31Paper ->

China's role in attaining the global 2°C target

K. Jiang, Zhuang Xing, R. Miao, C. He

Other183 citations2011-05-01Paper ->

Chrysanthemum leaf epidermal surface morphology and antioxidant and defense enzyme activity in response to aphid infestation.

Junping He, Fadi Chen, Sumei Chen, Guosheng Lv, Yanming Deng et al.

Other45 citations2011-02-01Paper ->

The I/D polymorphism of angiotensin‐converting enzyme gene and asthma risk: a meta‐analysis

Y-G Zhang, X-B Li, J. Zhang, J. Huang, C. He et al.

Other118 citations2010-03-26Paper ->

Potentials of phototrophic bacteria in treating pharmaceutical wastewater

E. I. Madukasi, X. Dai, C. He, J. Zhou

Other366 citations2009Paper ->

Gold Nanoparticles: Clinical Nanomedicine, Radiation Oncology Enhancement of radiation effects by gold nanoparticles for superficial radiation therapy

W. N. Rahman, N. B. Bishara, T. Ackerly, C. He, C. Wong et al.

Other188 citations2008-08-21Paper ->

Anomalous transport properties and phase diagram of the FeAs-based SmFeAsO1-xFx superconductors.

Rui Liu, Gang Wu, Tao Wu, D. F. Fang, H. Chen et al.

Other0 citations2008-04-23arXiv ->

Specific heat of the iron-based high- T c superconductor SmO 1 − x F x FeAs

L. Ding, C. He, J. Dong, Tao Wu, Rui Liu et al.

The specific heat $C(T)$ of new iron-based high-$T_c$ superconductor SmO$_{1-x}$F$_x$FeAs ($0 \leq x \leq 0.2$) was systematically studied. For undoped $x$ = 0 sample, a specific heat jump was observed at 130 K. This is attributed to the structural or spin-density-wave (SDW) transition, which also manifests on resistivity as a rapid drop. However, this jump disappears with slight F doping in $x$ = 0.05 sample, although the resistivity drop still exists. The specific heat $C/T$ shows clear anomaly near $T_c$ for $x$ = 0.15 and 0.20 superconducting samples. Such anomaly has been absent in LaO$_{1-x}$F$_x$FeAs. For the parent compound SmOFeAs, $C(T)$ shows a sharp peak at 4.6 K, and with electron doping in $x$ = 0.15 sample, this peak shifts to 3.7 K. It is interpreted that such a sharp peak results from the antiferromagnetic ordering of Sm$^{3+}$ ions in this system, which mimics the electron-doped high-$T_c$ cuprate Sm$_{2-x}$Ce$_x$CuO$_{4-\delta}$.

Other359 citations2007-04-20Paper ->

An Approach to Obtaining Homogeneously Dispersed Carbon Nanotubes in Al Powders for Preparing Reinforced Al‐Matrix Composites

C. He, N. Zhao, C. Shi, X. Du, J. Li et al.

Other57 citations2004-12-01Paper ->

New microstructural features occurring during transformation from austenite to ferrite under the kinetic influence of magnetic field in a medium carbon steel

Yudong Zhang, C. He, Xiang Zhao, L. Zuo, C. Esling et al.

Other96 citations2004-07-12Paper ->

High temperature tempering behaviors in a structural steel under high magnetic field

Yudong Zhang, N. Gey, C. He, Xiang Zhao, L. Zuo et al.

CBF Related Papers
Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

CBF Related Papers
Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

CBF Related Papers
Robotics0 citations2020-10-19arXiv ->

Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance

Andrew W. Singletary, Karl Klingebiel, Joseph R. Bourne, Andrew W. Browning, P. Tokumaru et al.

Artificial potential fields (APFs) and their variants have been a staple for collision avoidance of mobile robots and manipulators for almost 40 years. Its model-independent nature, ease of implementation, and real-time performance have played a large role in its continued success over the years. Control barrier functions (CBFs), on the other hand, are a more recent development, commonly used to guarantee safety for nonlinear systems in real-time in the form of a filter on a nominal controller. In this paper, we address the connections between APFs and CBFs. At a theoretic level, we show that given a broad class of APFs, one can construct a CBF that guarantees safety. Additionally, we prove that CBFs obtained from these APFs have additional beneficial properties and can be applied to nonlinear systems. Practically, we compare the performance of APFs and CBFs in the context of obstacle avoidance on simple illustrative examples and for a quadrotor with unknown dynamics, both in simulation and on hardware using onboard sensing.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

CBF Related Papers
Robotics0 citations2025-06-09arXiv ->

Deep Equivariant Multi-Agent Control Barrier Functions

N. Bousias, Lars Lindemann, G. Pappas

With multi-agent systems increasingly deployed autonomously at scale in complex environments, ensuring safety of the data-driven policies is critical. Control Barrier Functions have emerged as an effective tool for enforcing safety constraints, yet existing learning-based methods often lack in scalability, generalization and sampling efficiency as they overlook inherent geometric structures of the system. To address this gap, we introduce symmetries-infused distributed CBFs, enforcing the satisfaction of intrinsic symmetries on learnable graph-based safety certificates. We theoretically motivate the need for equivariant parametrization of CBFs and policies, and propose a simple, yet efficient and adaptable methodology for constructing such equivariant group-modular networks via the compatible group actions. This approach encodes safety constraints in a distributed data-efficient manner, enabling zero-shot generalization to larger and denser swarms. Through extensive simulations on multi-robot navigation tasks, we demonstrate that our method outperforms state-of-the-art baselines in terms of safety, scalability, and task success rates, highlighting the importance of embedding symmetries in safe distributed neural policies.

Robotics0 citations2025-04-12arXiv ->

Nonconvex Obstacle Avoidance using Efficient Sampling-Based Distance Functions

Paul Lutkus, Michelle S. Chong, Lars Lindemann

We consider nonconvex obstacle avoidance where a robot described by nonlinear dynamics and a nonconvex shape has to avoid nonconvex obstacles. Obstacle avoidance is a fundamental problem in robotics and well studied in control. However, existing solutions are computationally expensive (e.g., model predictive controllers), neglect nonlinear dynamics (e.g., graph-based planners), use diffeomorphic transformations into convex domains (e.g., for star shapes), or are conservative due to convex overapproximations. The key challenge here is that the computation of the distance between the shapes of the robot and the obstacles is a nonconvex problem. We propose efficient computation of this distance via sampling-based distance functions. We quantify the sampling error and show that, for certain systems, such sampling-based distance functions are valid nonsmooth control barrier functions. We also study how to deal with disturbances on the robot dynamics in our setting. Finally, we illustrate our method on a robot navigation task involving an omnidirectional robot and nonconvex obstacles. We also analyze performance and computational efficiency of our controller as a function of the number of samples.

MPC/Planning0 citations2024-09-19arXiv ->

Incremental Composition of Learned Control Barrier Functions in Unknown Environments

Paul Lutkus, Deepika Anantharaman, Stephen Tu, Lars Lindemann

We consider the problem of safely exploring a static and unknown environment while learning valid control barrier functions (CBFs) from sensor data. Existing works either assume known environments, target specific dynamics models, or use a-priori valid CBFs, and thus provide limited safety guarantees for general control-affine systems during exploration. We present a method for safely exploring by incrementally composing a global CBF from local CBFs. The challenge here is that local CBFs may not have well-defined end behavior outside their training domain, i.e. local CBFs may be positive (indicating safety) in regions where no training data is available. We show that well-defined end behavior can be obtained when local CBFs are parameterized by compactly-supported radial basis functions. For learning local CBFs, we collect sensor data, e.g. LiDAR capturing obstacles in the environment, and augment it with simulated data from a safe oracle controller. Our work complements recent efforts to learn CBFs from safe demonstrations, where learned safe sets are limited to their training domains, by demonstrating how to grow the safe set over time as more data becomes available. We evaluate our approach on two simulated systems, where our method successfully explores an unknown environment while maintaining safety throughout the entire execution.

Robotics0 citations2024-04-30arXiv ->

Reactive Temporal Logic-based Planning and Control for Interactive Robotic Tasks

Farhad Nawaz, Shaoting Peng, Lars Lindemann, Nadia Figueroa, Nikolai Matni

Robots interacting with humans must be safe, reactive and adapt online to unforeseen environmental and task changes. Achieving these requirements concurrently is a challenge as interactive planners lack formal safety guarantees, while safe motion planners lack flexibility to adapt. To tackle this, we propose a modular control architecture that generates both safe and reactive motion plans for human-robot interaction by integrating temporal logic-based discrete task level plans with continuous Dynamical System (DS)-based motion plans. We formulate a reactive temporal logic formula that enables users to define task specifications through structured language, and propose a planning algorithm at the task level that generates a sequence of desired robot behaviors while being adaptive to environmental changes. At the motion level, we incorporate control Lyapunov functions and control barrier functions to compute stable and safe continuous motion plans for two types of robot behaviors: (i) complex, possibly periodic motions given by autonomous DS and (ii) time-critical tasks specified by Signal Temporal Logic (STL). Our methodology is demonstrated on the Franka robot arm performing wiping tasks on a whiteboard and a mannequin that is compliant to human interactions and adaptive to environmental changes.

Learning0 citations2023-04-01arXiv ->

Safe Perception-Based Control Under Stochastic Sensor Uncertainty Using Conformal Prediction

Shuo Yang, George Pappas, Rahul Mangharam, Lars Lindemann

We consider perception-based control using state estimates that are obtained from high-dimensional sensor measurements via learning-enabled perception maps. However, these perception maps are not perfect and result in state estimation errors that can lead to unsafe system behavior. Stochastic sensor noise can make matters worse and result in estimation errors that follow unknown distributions. We propose a perception-based control framework that i) quantifies estimation uncertainty of perception maps, and ii) integrates these uncertainty representations into the control design. To do so, we use conformal prediction to compute valid state estimation regions, which are sets that contain the unknown state with high probability. We then devise a sampled-data controller for continuous-time systems based on the notion of measurement robust control barrier functions. Our controller uses idea from self-triggered control and enables us to avoid using stochastic calculus. Our framework is agnostic to the choice of the perception map, independent of the noise distribution, and to the best of our knowledge the first to provide probabilistic safety guarantees in such a setting. We demonstrate the effectiveness of our proposed perception-based controller for a LiDAR-enabled F1/10th car.

MPC/Planning14 citations2022-06-08Paper ->

Corridor MPC: Towards Optimal and Safe Trajectory Tracking

Pedro Roque, Wenceslao Shaw-Cortez, Lars Lindemann, Dimos V. Dimarogonas

We present a framework for safe and optimal trajectory tracking by combining Model Predictive Control and Sampled-Data Control Barrier functions. This framework, which we call Corridor MPC, safely and robustly keeps the state of the system within a corridor that is defined as a permissible error around a reference trajectory. By incorporating Sampled-Data Control Barrier functions into an MPC framework, we guarantee safety for the continuous-time system in the sense of staying within the corridor and practical stability in the sense of converging to the reference trajectory. The proposed framework is evaluated with a free-flyer kinematics system.

Robotics0 citations2021-11-18arXiv ->

Learning Robust Output Control Barrier Functions From Safe Expert Demonstrations

Lars Lindemann, Alexander Robey, Lejun Jiang, Stephen Tu, N. Matni

This paper addresses learning safe output feedback control laws from partial observations of expert demonstrations. We assume that a model of the system dynamics and a state estimator are available along with corresponding error bounds, e.g., estimated from data in practice. We first propose robust output control barrier functions (ROCBFs) as a means to guarantee safety, as defined through controlled forward invariance of a safe set. We then formulate an optimization problem to learn ROCBFs from expert demonstrations that exhibit safe system behavior, e.g., data collected from a human operator or an expert controller. When the parametrization of the ROCBF is linear, then we show that, under mild assumptions, the optimization problem is convex. Along with the optimization problem, we provide verifiable conditions in terms of the density of the data, smoothness of the system model and state estimator, and the size of the error bounds that guarantee validity of the obtained ROCBF. Towards obtaining a practical control algorithm, we propose an algorithmic implementation of our theoretical framework that accounts for assumptions made in our framework in practice. We validate our algorithm in the autonomous driving simulator CARLA and demonstrate how to learn safe control laws from simulated RGB camera images.

MPC/Planning0 citations2021-01-17arXiv ->

Learning Robust Hybrid Control Barrier Functions for Uncertain Systems

Alexander Robey, Lars Lindemann, Stephen Tu, N. Matni

The need for robust control laws is especially important in safety-critical applications. We propose robust hybrid control barrier functions as a means to synthesize control laws that ensure robust safety. Based on this notion, we formulate an optimization problem for learning robust hybrid control barrier functions from data. We identify sufficient conditions on the data such that feasibility of the optimization problem ensures correctness of the learned robust hybrid control barrier functions. Our techniques allow us to safely expand the region of attraction of a compass gait walker that is subject to model uncertainty.

Robotics0 citations2020-12-01arXiv ->

Barrier Function Based Collaborative Control of Multiple Robots Under Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

Motivated by the recent interest in cyber-physical and autonomous robotic systems, we study the problem of dynamically coupled multiagent systems under a set of signal temporal logic tasks. In particular, the satisfaction of each of these signal temporal logic tasks depends on the behavior of a distinct set of agents. Instead of abstracting the agent dynamics and the temporal logic tasks into a discrete domain and solving the problem therein or using optimization-based methods, we derive collaborative feedback control laws.These control laws are based on a decentralized control barrier function condition that results in discontinuous control laws, as opposed to a centralized condition resembling the single-agent case. The benefits of our approach are inherent robustness properties typically present in feedback control as well as satisfaction guarantees for continuous-time multiagent systems. More specifically, time-varying control barrier functions are used that account for the semantics of the signal temporal logic tasks at hand. For a certain fragment of signal temporal logic tasks, we further propose a systematic way to construct such control barrier functions. Finally, we show the efficacy and robustness of our framework in an experiment, including a group of three omnidirectional robots.

MPC/Planning0 citations2020-11-08arXiv ->

Learning Hybrid Control Barrier Functions from Data

Lars Lindemann, Haimin Hu, Alexander Robey, Hanwen Zhang, Dimos V. Dimarogonas et al.

Motivated by the lack of systematic tools to obtain safe control laws for hybrid systems, we propose an optimization-based framework for learning certifiably safe control laws from data. In particular, we assume a setting in which the system dynamics are known and in which data exhibiting safe system behavior is available. We propose hybrid control barrier functions for hybrid systems as a means to synthesize safe control inputs. Based on this notion, we present an optimization-based framework to learn such hybrid control barrier functions from data. Importantly, we identify sufficient conditions on the data such that feasibility of the optimization problem ensures correctness of the learned hybrid control barrier functions, and hence the safety of the system. We illustrate our findings in two simulations studies, including a compass gait walker.

MPC/Planning0 citations2020-09-04arXiv ->

Provably Safe Control of Lagrangian Systems in Obstacle-Scattered Environments

Fernando S Barbosa, Lars Lindemann, Dimos V. Dimarogonas, Jana Tumova

We propose a hybrid feedback control law that guarantees both safety and asymptotic stability for a class of Lagrangian systems in environments with obstacles. Rather than performing trajectory planning and implementing a trajectory-tracking feedback control law, our approach requires a sequence of locations in the environment (a path plan) and an abstraction of the obstacle-free space. The problem of following a path plan is then interpreted as a sequence of reach-avoid problems: the system is required to consecutively reach each location of the path plan while staying within safe regions. Obstacle-free ellipsoids are used as a way of defining such safe regions, each of which encloses two consecutive locations. Feasible Control Barrier Functions (CBFs) are created directly from geometric constraints, the ellipsoids, ensuring forward-invariance, and therefore safety. Reachability to each location is guaranteed by asymptotically stabilizing Control Lyapunov Functions (CLFs). Both CBFs and CLFs are then encoded into quadratic programs (QPs) without the need of relaxation variables. Furthermore, we also propose a switching mechanism that guarantees the control law is correct and well-defined even when transitioning between QPs. Simulations show the effectiveness of the proposed approach in two complex scenarios.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Other0 citations2020-04-05arXiv ->

Control Barrier Functions for Nonholonomic Systems under Risk Signal Temporal Logic Specifications

Lars Lindemann, George Pappas, Dimos V. Dimarogonas

Temporal logics provide a formalism for expressing complex system specifications. A large body of literature has addressed the verification and the control synthesis problem for deterministic systems under such specifications. For stochastic systems or systems operating in unknown environments, however, only the probability of satisfying a specification has been considered so far, neglecting the risk of not satisfying the specification. Towards addressing this shortcoming, we consider, for the first time, risk metrics, such as (but not limited to) the Conditional Value-at-Risk, and propose risk signal temporal logic. Specifically, we compose risk metrics with stochastic predicates to consider the risk of violating certain spatial specifications. As a particular instance of such stochasticity, we consider control systems in unknown environments and present a determinization of the risk signal temporal logic specification to transform the stochastic control problem into a deterministic one. For unicycle-like dynamics, we then extend our previous work on deterministic time-varying control barrier functions.

Other0 citations2019-06-01arXiv ->

Decentralized Control Barrier Functions for Coupled Multi-Agent Systems under Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

We study the problem of controlling multi-agent systems under a set of signal temporal logic tasks. Signal temporal logic is a formalism that is used to express time and space constraints for dynamical systems. Recent methods to solve the control synthesis problem for single-agent systems under signal temporal logic tasks are, however, subject to a high computational complexity. Methods for multi-agent systems scale at least linearly with the number of agents and induce even higher computational burdens. We propose a computationally-efficient control strategy to solve the multi-agent control synthesis problem that results in a robust satisfaction of a set of signal temporal logic tasks. In particular, a decentralized feedback control law is proposed that is based on time-varying control barrier functions. The obtained control law is discontinuous and formal guarantees are provided by nonsmooth analysis. Simulations show the efficacy of the presented method.

MPC/Planning16 citations2019-06-01Paper ->

Integrated Motion Planning and Control Under Metric Interval Temporal Logic Specifications

Fernando S Barbosa, Lars Lindemann, Dimos V. Dimarogonas, Jana Tumova

This paper proposes an approach that combines motion planning and hybrid feedback control design in order to find and follow trajectories fulfilling a given complex mission involving time constraints. We use Metric Interval Temporal Logic (MITL) as a rich and rigorous formalism to specify such missions. The solution builds on three main steps: (i) using sampling-based motion planning methods and the untimed version of the mission specification in the form of Zone automaton, we find a sequence of waypoints in the workspace; (ii) based on the clock zones from the satisfying run on the Zone automaton, we compute time-stamps at which these waypoints should be reached; and (iii) to control the system to connect two waypoints in the desired time, we design a low-level feedback controller leveraging Time-varying Control Barrier Functions. Illustrative simulation results are included.

Robotics115 citations2019-05-21Paper ->

Control Barrier Functions for Multi-Agent Systems Under Conflicting Local Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

Motivated by the recent interest in cyber-physical and interconnected autonomous systems, we study the problem of dynamically coupled multi-agent systems under conflicting local signal temporal logic (STL) tasks. Each agent is assigned a local STL task regardless of the tasks that the other agents are assigned to. Such a task may be dependent, i.e., the satisfaction of the task may depend on the behavior of more than one agent, so that the satisfaction of the conjunction of all local tasks may be conflicting. We propose a hybrid feedback control strategy using time-varying control barrier functions. Our control strategy finds least violating solutions in the aforementioned conflicting situations based on a suitable robustness notion and by initiating collaboration among agents.

Robotics347 citations2019-01-01Paper ->

Control Barrier Functions for Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

The need for computationally-efficient control methods of dynamical systems under temporal logic tasks has recently become more apparent. Existing methods are computationally demanding and hence often not applicable in practice. Especially with respect to multi-robot systems, these methods do not scale computationally. In this letter, we propose a framework that is based on control barrier functions and signal temporal logic. In particular, time-varying control barrier functions are considered where the temporal properties are used to satisfy signal temporal logic tasks. The resulting controller is given by a switching strategy between a computationally-efficient convex quadratic program and a local feedback control law.

Non-CBF Papers
Robotics0 citations2026-02-26arXiv ->

V-MORALS: Visual Morse Graph-Aided Estimation of Regions of Attraction in a Learned Latent Space

Faiz Aladin, A. Balasubramanian, Lars Lindemann, Daniel Seita

Reachability analysis has become increasingly important in robotics to distinguish safe from unsafe states. Unfortunately, existing reachability and safety analysis methods often fall short, as they typically require known system dynamics or large datasets to estimate accurate system models, are computationally expensive, and assume full state information. A recent method, called MORALS, aims to address these shortcomings by using topological tools to estimate Regions of Attraction (ROA) in a low-dimensional latent space. However, MORALS still relies on full state knowledge and has not been studied when only sensor measurements are available. This paper presents Visual Morse Graph-Aided Estimation of Regions of Attraction in a Learned Latent Space (V-MORALS). V-MORALS takes in a dataset of image-based trajectories of a system under a given controller, and learns a latent space for reachability analysis. Using this learned latent space, our method is able to generate well-defined Morse Graphs, from which we can compute ROAs for various systems and controllers. V-MORALS provides capabilities similar to the original MORALS architecture without relying on state knowledge, and using only high-level sensor data. Our project website is at: https://v-morals.onrender.com.

Robotics0 citations2026-02-19arXiv ->

Multi-Agent Temporal Logic Planning via Penalty Functions and Block-Coordinate Optimization

E. Vlahakis, Arash Bahari Kordabad, Lars Lindemann, Pantelis Sopasakis, Sadegh Soudjani et al.

Multi-agent planning under Signal Temporal Logic (STL) is often hindered by collaborative tasks that lead to computational challenges due to the inherent high-dimensionality of the problem, preventing scalable synthesis with satisfaction guarantees. To address this, we formulate STL planning as an optimization program under arbitrary multi-agent constraints and introduce a penalty-based unconstrained relaxation that can be efficiently solved via a Block-Coordinate Gradient Descent (BCGD) method, where each block corresponds to a single agent's decision variables, thereby mitigating complexity. By utilizing a quadratic penalty function defined via smooth STL semantics, we show that BCGD iterations converge to a stationary point of the penalized problem under standard regularity assumptions. To enforce feasibility, the BCGD solver is embedded within a two-layer optimization scheme: inner BCGD updates are performed for a fixed penalty parameter, which is then increased in an outer loop to progressively improve multi-agent STL robustness. The proposed framework enables scalable computations and is validated through various complex multi-robot planning scenarios.

Robotics0 citations2026-02-13arXiv ->

When Environments Shift: Safe Planning with Generative Priors and Robust Conformal Prediction

Kaizer Rahaman, Jyotirmoy V. Deshmukh, Ashish R. Hota, Lars Lindemann

Autonomous systems operate in environments that may change over time. An example is the control of a self-driving vehicle among pedestrians and human-controlled vehicles whose behavior may change based on factors such as traffic density, road visibility, and social norms. Therefore, the environment encountered during deployment rarely mirrors the environment and data encountered during training -- a phenomenon known as distribution shift -- which can undermine the safety of autonomous systems. Conformal prediction (CP) has recently been used along with data from the training environment to provide prediction regions that capture the behavior of the environment with a desired probability. When embedded within a model predictive controller (MPC), one can provide probabilistic safety guarantees, but only when the deployment and training environments coincide. Once a distribution shift occurs, these guarantees collapse. We propose a planning framework that is robust under distribution shifts by: (i) assuming that the underlying data distribution of the environment is parameterized by a nuisance parameter, i.e., an observable, interpretable quantity such as traffic density, (ii) training a conditional diffusion model that captures distribution shifts as a function of the nuisance parameter, (iii) observing the nuisance parameter online and generating cheap, synthetic data from the diffusion model for the observed nuisance parameter, and (iv) designing an MPC that embeds CP regions constructed from such synthetic data. Importantly, we account for discrepancies between the underlying data distribution and the diffusion model by using robust CP. Thus, the plans computed using robust CP enjoy probabilistic safety guarantees, in contrast with plans obtained from a single, static set of training data. We empirically demonstrate safety under diverse distribution shifts in the ORCA simulator.

MPC/Planning0 citations2026-02-03arXiv ->

eCP: Informative uncertainty quantification via Equivariantized Conformal Prediction with pre-trained models

N. Bousias, Lars Lindemann, G. Pappas

We study the effect of group symmetrization of pre-trained models on conformal prediction (CP), a post-hoc, distribution-free, finite-sample method of uncertainty quantification that offers formal coverage guarantees under the assumption of data exchangeability. Unfortunately, CP uncertainty regions can grow significantly in long horizon missions, rendering the statistical guarantees uninformative. To that end, we propose infusing CP with geometric information via group-averaging of the pretrained predictor to distribute the non-conformity mass across the orbits. Each sample now is treated as a representative of an orbit, thus uncertainty can be mitigated by other samples entangled to it via the orbit inducing elements of the symmetry group. Our approach provably yields contracted non-conformity scores in increasing convex order, implying improved exponential-tail bounds and sharper conformal prediction sets in expectation, especially at high confidence levels. We then propose an experimental design to test these theoretical claims in pedestrian trajectory prediction.

Robotics9 citations2025-12-01Paper ->

Formal Verification and Control With Conformal Prediction: Practical Safety Guarantees For Autonomous Systems

Lars Lindemann, Yiqi Zhao, Xinyi Yu, G. Pappas, Jyotirmoy V. Deshmukh

The design of autonomous systems, which are becoming increasingly learning enabled, has attracted much attention within the research community. Research in this area promises to enable many future technologies, such as autonomous driving, intelligent transportation, and robotics. In recent years, great progress has been made in the design of learning-enabled components (LECs), for example, with neural networks for perception tasks, such as object detection [1], [2], localization and state estimation [3], [4], and trajectory prediction [5], [6], [7]; for decision-making tasks, such as motion and behavior planning [8], [9]; and for low-level control [10], [11], [12]. However, the integration of LECs into safety-critical autonomous systems is limited by their fragility and can result in unsafe behavior, for example, inaccurate and nonrobust object detectors in self-driving cars. The fragility of LECs is the result of highly nonconvex learning problems, distribution shifts from training to the deployment domain, and a lack of model robustness [13], [14]. Unfortunately, these safety challenges are further amplified by the complexity of modern autonomous systems that operate in uncertain and dynamic environments, where traditional approaches for localization and mapping may fail to provide guarantees, for example, simultaneous localization and mapping techniques [4], [15] or Kalman/particle filters [16], [17], [18].

Other0 citations2025-12-01Paper ->

Special Issue on the Internal Model Principle

A. Annaswamy, Jyotirmoy V. Deshmukh, Yizhou Gong, Jie Huang, A. Isidori et al.

Robotics0 citations2025-11-29arXiv ->

Sample-Efficient Expert Query Control in Active Imitation Learning via Conformal Prediction

Arad Firouzkouhi, Omid Mirzaeedodangeh, Lars Lindemann

Active imitation learning (AIL) combats covariate shift by querying an expert during training. However, expert action labeling often dominates the cost, especially in GPU-intensive simulators, human-in-the-loop settings, and robot fleets that revisit near-duplicate states. We present Conformalized Rejection Sampling for Active Imitation Learning (CRSAIL), a querying rule that requests an expert action only when the visited state is under-represented in the expert-labeled dataset. CRSAIL scores state novelty by the distance to the $K$-th nearest expert state and sets a single global threshold via conformal prediction. This threshold is the empirical $(1-\alpha)$ quantile of on-policy calibration scores, providing a distribution-free calibration rule that links $\alpha$ to the expected query rate and makes $\alpha$ a task-agnostic tuning knob. This state-space querying strategy is robust to outliers and, unlike safety-gate-based AIL, can be run without real-time expert takeovers: we roll out full trajectories (episodes) with the learner and only afterward query the expert on a subset of visited states. Evaluated on MuJoCo robotics tasks, CRSAIL matches or exceeds expert-level reward while reducing total expert queries by up to 96% vs. DAgger and up to 65% vs. prior AIL methods, with empirical robustness to $\alpha$ and $K$, easing deployment on novel systems with unknown dynamics.

Robotics0 citations2025-11-13arXiv ->

Safe Planning in Interactive Environments via Iterative Policy Updates and Adversarially Robust Conformal Prediction

Omid Mirzaeedodangeh, Eliot Shekhtman, Nikolai Matni, Lars Lindemann

Safe planning of an autonomous agent in interactive environments -- such as the control of a self-driving vehicle among pedestrians and human-controlled vehicles -- poses a major challenge as the behavior of the environment is unknown and reactive to the behavior of the autonomous agent. This coupling gives rise to interaction-driven distribution shifts where the autonomous agent's control policy may change the environment's behavior, thereby invalidating safety guarantees in existing work. Indeed, recent works have used conformal prediction (CP) to generate distribution-free safety guarantees using observed data of the environment. However, CP's assumption on data exchangeability is violated in interactive settings due to a circular dependency where a control policy update changes the environment's behavior, and vice versa. To address this gap, we propose an iterative framework that robustly maintains safety guarantees across policy updates by quantifying the potential impact of a planned policy update on the environment's behavior. We realize this via adversarially robust CP where we perform a regular CP step in each episode using observed data under the current policy, but then transfer safety guarantees across policy updates by analytically adjusting the CP result to account for distribution shifts. This adjustment is performed based on a policy-to-trajectory sensitivity analysis, resulting in a safe, episodic open-loop planner. We further conduct a contraction analysis of the system providing conditions under which both the CP results and the policy updates are guaranteed to converge. We empirically demonstrate these safety and convergence guarantees on a two-dimensional car-pedestrian case study. To the best of our knowledge, these are the first results that provide valid safety guarantees in such interactive settings.

Robotics0 citations2025-09-24arXiv ->

Latent Activation Editing: Inference-Time Refinement of Learned Policies for Safer Multirobot Navigation

Satyajeet Das, D. Chiu, Zhehui Huang, Lars Lindemann, Gaurav S. Sukhatme

Reinforcement learning has enabled significant progress in complex domains such as coordinating and navigating multiple quadrotors. However, even well-trained policies remain vulnerable to collisions in obstacle-rich environments. Addressing these infrequent but critical safety failures through retraining or fine-tuning is costly and risks degrading previously learned skills. Inspired by activation steering in large language models and latent editing in computer vision, we introduce a framework for inference-time Latent Activation Editing (LAE) that refines the behavior of pre-trained policies without modifying their weights or architecture. The framework operates in two stages: (i) an online classifier monitors intermediate activations to detect states associated with undesired behaviors, and (ii) an activation editing module that selectively modifies flagged activations to shift the policy towards safer regimes. In this work, we focus on improving safety in multi-quadrotor navigation. We hypothesize that amplifying a policy's internal perception of risk can induce safer behaviors. We instantiate this idea through a latent collision world model trained to predict future pre-collision activations, thereby prompting earlier and more cautious avoidance responses. Extensive simulations and real-world Crazyflie experiments demonstrate that LAE achieves statistically significant reduction in collisions (nearly 90% fewer cumulative collisions compared to the unedited baseline) and substantially increases the fraction of collision-free trajectories, while preserving task completion. More broadly, our results establish LAE as a lightweight paradigm, feasible on resource-constrained hardware, for post-deployment refinement of learned robot policies.

Learning0 citations2025-09-23arXiv ->

Metriplectic Conditional Flow Matching for Dissipative Dynamics

Ali Baheri, Lars Lindemann

Metriplectic conditional flow matching (MCFM) learns dissipative dynamics without violating first principles. Neural surrogates often inject energy and destabilize long-horizon rollouts; MCFM instead builds the conservative-dissipative split into both the vector field and a structure preserving sampler. MCFM trains via conditional flow matching on short transitions, avoiding long rollout adjoints. In inference, a Strang-prox scheme alternates a symplectic update with a proximal metric step, ensuring discrete energy decay; an optional projection enforces strict decay when a trusted energy is available. We provide continuous and discrete time guarantees linking this parameterization and sampler to conservation, monotonic dissipation, and stable rollouts. On a controlled mechanical benchmark, MCFM yields phase portraits closer to ground truth and markedly fewer energy-increase and positive energy rate events than an equally expressive unconstrained neural flow, while matching terminal distributional fit.

Learning0 citations2025-09-04arXiv ->

Split Conformal Prediction in the Function Space with Neural Operators

David Millard, Lars Lindemann, Ali Baheri

Uncertainty quantification for neural operators remains an open problem in the infinite-dimensional setting due to the lack of finite-sample coverage guarantees over functional outputs. While conformal prediction offers finite-sample guarantees in finite-dimensional spaces, it does not directly extend to function-valued outputs. Existing approaches (Gaussian processes, Bayesian neural networks, and quantile-based operators) require strong distributional assumptions or yield conservative coverage. This work extends split conformal prediction to function spaces following a two step method. We first establish finite-sample coverage guarantees in a finite-dimensional space using a discretization map in the output function space. Then these guarantees are lifted to the function-space by considering the asymptotic convergence as the discretization is refined. To characterize the effect of resolution, we decompose the conformal radius into discretization, calibration, and misspecification components. This decomposition motivates a regression-based correction to transfer calibration across resolutions. Additionally, we propose two diagnostic metrics (conformal ensemble score and internal agreement) to quantify forecast degradation in autoregressive settings. Empirical results show that our method maintains calibrated coverage with less variation under resolution shifts and achieves better coverage in super-resolution tasks.

Robotics0 citations2025-09-01arXiv ->

Conformal Predictive Monitoring for Multi-modal Scenarios

Francesca Cairoli, Luca Bortolussi, Jyotirmoy V. Deshmukh, Lars Lindemann, Nicola Paoletti

We consider the problem of quantitative predictive monitoring (QPM) of stochastic systems, i.e., predicting at runtime the degree of satisfaction of a desired temporal logic property from the current state of the system. Since computational efficiency is key to enable timely intervention against predicted violations, several state-of-the-art QPM approaches rely on fast machine-learning surrogates to provide prediction intervals for the satisfaction values, using conformal inference to offer statistical guarantees. However, these QPM methods suffer when the monitored agent exhibits multi-modal dynamics, whereby certain modes may yield high satisfaction values while others critically violate the property. Existing QPM methods are mode-agnostic and so would yield overly conservative and uninformative intervals that lack meaningful mode-specific satisfaction information. To address this problem, we present GenQPM, a method that leverages deep generative models, specifically score-based diffusion models, to reliably approximate the probabilistic and multi-modal system dynamics without requiring explicit model access. GenQPM employs a mode classifier to partition the predicted trajectories by dynamical mode. For each mode, we then apply conformal inference to produce statistically valid, mode-specific prediction intervals. We demonstrate the effectiveness of GenQPM on a benchmark of agent navigation and autonomous driving tasks, resulting in prediction intervals that are significantly more informative (less conservative) than mode-agnostic baselines.

Robotics0 citations2025-08-11arXiv ->

Neuro-Symbolic Acceleration of MILP Motion Planning with Temporal Logic and Chance Constraints

Junyang Cai, Weimin Huang, Jyotirmoy V. Deshmukh, Lars Lindemann, B. Dilkina

Autonomous systems must solve motion planning problems subject to increasingly complex, time-sensitive, and uncertain missions. These problems often involve high-level task specifications, such as temporal logic or chance constraints, which require solving large-scale Mixed-Integer Linear Programs (MILPs). However, existing MILP-based planning methods suffer from high computational cost and limited scalability, hindering their real-time applicability. We propose to use a neuro-symbolic approach to accelerate MILP-based motion planning by leveraging machine learning techniques to guide the solver's symbolic search. Focusing on two representative classes of planning problems, namely, those with Signal Temporal Logic (STL) specifications and those with chance constraints formulated via Conformal Predictive Programming (CPP). We demonstrate how graph neural network-based learning methods can guide traditional symbolic MILP solvers in solving challenging planning problems, including branching variable selection and solver parameter configuration. Through extensive experiments, we show that neuro-symbolic search techniques yield scalability gains. Our approach yields substantial improvements, achieving an average performance gain of about 20% over state-of-the-art solver across key metrics, including runtime and solution quality.

Other0 citations2025-07-29arXiv ->

Multi-Agent Path Finding Among Dynamic Uncontrollable Agents with Statistical Safety Guarantees

Kegan J. Strawn, Thomy Phan, Eric Wang, Nora Ayanian, Sven Koenig et al.

Existing multi-agent path finding (MAPF) solvers do not account for uncertain behavior of uncontrollable agents. We present a novel variant of Enhanced Conflict-Based Search (ECBS), for both one-shot and lifelong MAPF in dynamic environments with uncontrollable agents. Our method consists of (1) training a learned predictor for the movement of uncontrollable agents, (2) quantifying the prediction error using conformal prediction (CP), a tool for statistical uncertainty quantification, and (3) integrating these uncertainty intervals into our modified ECBS solver. Our method can account for uncertain agent behavior, comes with statistical guarantees on collision-free paths for one-shot missions, and scales to lifelong missions with a receding horizon sequence of one-shot instances. We run our algorithm, CP-Solver, across warehouse and game maps, with competitive throughput and reduced collisions.

Robotics0 citations2025-07-20arXiv ->

STL-GO: Spatio-Temporal Logic with Graph Operators for Distributed Systems with Multiple Network Topologies

Yiqi Zhao, Xinyi Yu, Bardh Hoxha, Georgios Fainekos, J. Deshmukh et al.

Multi-agent systems (MASs) consisting of a number of autonomous agents that communicate, coordinate, and jointly sense the environment to achieve complex missions can be found in a variety of applications such as robotics, smart cities, and internet-of-things applications. Modeling and monitoring MAS requirements to guarantee overall mission objectives, safety, and reliability is an important problem. Such requirements implicitly require reasoning about diverse sensing and communication modalities between agents, analysis of the dependencies between agent tasks, and the spatial or virtual distance between agents. To capture such rich MAS requirements, we model agent interactions via multiple directed graphs, and introduce a new logic – Spatio-Temporal Logic with Graph Operators (STL-GO). The key innovation in STL-GO are graph operators that enable us to reason about the number of agents along either the incoming or outgoing edges of the underlying interaction graph that satisfy a given property of interest; for example, the requirement that an agent should sense at least two neighboring agents whose task graphs indicate the ability to collaborate. We then propose novel distributed monitoring conditions for individual agents that use only local information to determine whether or not an STL-GO specification is satisfied. We compare the expressivity of STL-GO against existing spatio-temporal logic formalisms, and demonstrate the utility of STL-GO and our distributed monitors in a bike-sharing and a multi-drone case study.

Robotics0 citations2025-06-12arXiv ->

Sampling-Based Planning Under STL Specifications: A Forward Invariance Approach

Gregorio Marchesini, Siyuan Liu, Lars Lindemann, Dimos V. Dimarogonas

We propose a variant of the Rapidly Exploring Random Tree Star (RRT$^{\star}$) algorithm to synthesize trajectories satisfying a given spatio-temporal specification expressed in a fragment of Signal Temporal Logic (STL) for linear systems. Previous approaches for planning trajectories under STL specifications using sampling-based methods leverage either mixed-integer or non-smooth optimization techniques, with poor scalability in the horizon and complexity of the task. We adopt instead a control-theoretic perspective on the problem, based on the notion of set forward invariance. Specifically, from a given STL task defined over polyhedral predicates, we develop a novel algorithmic framework by which the task is efficiently encoded into a time-varying set via linear programming, such that trajectories evolving within the set also satisfy the task. Forward invariance properties of the resulting set with respect to the system dynamics and input limitations are then proved via non-smooth analysis. We then present a modified RRT$^{\star}$ algorithm to synthesize asymptotically optimal and dynamically feasible trajectories satisfying a given STL specification, by sampling a tree of trajectories within the previously constructed time-varying set. We showcase two use cases of our approach involving an autonomous inspection of the International Space Station and room-servicing task requiring timed revisit of a charging station.

Learning0 citations2025-05-29arXiv ->

Latent Representations for Control Design with Provable Stability and Safety Guarantees

Paul Lutkus, Kaiyuan Wang, Lars Lindemann, Stephen Tu

We initiate a formal study on the use of low-dimensional latent representations of dynamical systems for verifiable control synthesis. Our main goal is to enable the application of verification techniques—such as Lyapunov or barrier functions—that might otherwise be computationally prohibitive when applied directly to the full state representation. Towards this goal, we first provide dynamics-aware, approximate conjugacy conditions which formalize the notion of reconstruction error necessary for systems analysis. We then utilize our conjugacy conditions to transfer the stability and invariance guarantees of a latent certificate function (e.g., a Lyapunov or barrier function) for a latent space controller back to the original system. Importantly, our analysis contains several important implications for learning latent spaces and dynamics, by highlighting the necessary geometric properties which need to be preserved by the latent space, in addition to providing concrete loss functions for dynamics reconstruction that are directly related to control design. We conclude by demonstrating the applicability of our theory to two case studies: (1) stabilization of a cartpole system, and (2) collision avoidance for a two-vehicle system.

MPC/Planning0 citations2025-05-20arXiv ->

PCA-DDReach: Efficient Statistical Reachability Analysis of Stochastic Dynamical Systems via Principal Component Analysis

Navid Hashemi, Lars Lindemann, J. Deshmukh

This study presents a scalable data-driven algorithm designed to efficiently address the challenging problem of reachability analysis. Analysis of cyber-physical systems (CPS) relies typically on parametric physical models of dynamical systems. However, identifying parametric physical models for complex CPS is challenging due to their complexity, uncertainty, and variability, often rendering them as black-box oracles. As an alternative, one can treat these complex systems as black-box models and use trajectory data sampled from the system (e.g., from high-fidelity simulators or the real system) along with machine learning techniques to learn models that approximate the underlying dynamics. However, these machine learning models can be inaccurate, highlighting the need for statistical tools to quantify errors. Recent advancements in the field include the incorporation of statistical uncertainty quantification tools such as conformal inference (CI) that can provide probabilistic reachable sets with provable guarantees. Recent work has even highlighted the ability of these tools to address the case where the distribution of trajectories sampled during training time are different from the distribution of trajectories encountered during deployment time. However, accounting for such distribution shifts typically results in more conservative guarantees. This is undesirable in practice and motivates us to present techniques that can reduce conservatism. Here, we propose a new approach that reduces conservatism and improves scalability by combining conformal inference with Principal Component Analysis (PCA). We show the effectiveness of our technique on various case studies, including a 12-dimensional quadcopter and a 27-dimensional hybrid system known as the powertrain.

Other9 citations2025-04-26Paper ->

Trust Dynamics in AI-Assisted Development: Definitions, Factors, and Implications

Sadra Sabouri, Philipp Eibl, Xinyi Zhou, Morteza Ziyadi, Nenad Medvidovic et al.

Software developers increasingly rely on AI code generation utilities. To ensure that “good” code is accepted into the code base and “bad” code is rejected, developers must know when to trust an AI suggestion. Understanding how developers build this intuition is crucial to enhancing developer-AI collaborative programming. In this paper, we seek to understand how developers (1) define and (2) evaluate the trustworthiness of a code suggestion and (3) how trust evolves when using AI code assistants. To answer these questions, we conducted a mixed method study consisting of an in-depth exploratory survey with (n=29) developers followed by an observation study (n=10). We found that comprehensibility and perceived correctness were the most frequently used factors to evaluate code suggestion trustworthiness. However, the gap in developers' definition and evaluation of trust points to a lack of support for evaluating trustworthy code in real-time. We also found that developers often alter their trust decisions, keeping only 52% of original suggestions. Based on these findings, we extracted four guidelines to enhance developer-AI interactions. We validated the guidelines through a survey with (n=7) domain experts and survey members (n=8). We discuss the validated guidelines, how to apply them, and tools to help adopt them.

MPC/Planning0 citations2025-04-06arXiv ->

Conformal Data-driven Control of Stochastic Multi-Agent Systems under Collaborative Signal Temporal Logic Specifications

E. Vlahakis, Lars Lindemann, Dimos V. Dimarogonas

We address control synthesis of stochastic discrete-time linear multi-agent systems under jointly chance-constrained collaborative signal temporal logic specifications in a distribution-free manner using available disturbance samples, which are partitioned into training and calibration sets. Leveraging linearity, we decompose each agent’s system into deterministic nominal and stochastic error parts, and design disturbance feedback controllers to bound the stochastic errors by solving a tractable optimization problem over the training data. We then quantify prediction regions (PRs) for the aggregate error trajectories corresponding to agent cliques, involved in collaborative tasks, using conformal prediction and calibration data. This enables us to address the specified joint chance constraint via Lipschitz tightening and the computed PRs, and relax the centralized stochastic optimal control problem to a deterministic one, whose solution represents feedforward inputs. To enhance scalability, we decompose the deterministic problem into agent-level subproblems solved in an MPC fashion, yielding a distributed control policy. Finally, we present an illustrative example and a comparison with [1].

CBF Related Papers
Other0 citations2025-12-09arXiv ->

Decoupled Design of Time-Varying Control Barrier Functions via Equivariances

A. Wiltz, Dimos V. Dimarogonas

This article presents a systematic method for designing time-varying Control Barrier Functions (CBF) composed of a time-invariant component and multiple time-dependent components, leveraging structural properties of the system dynamics. The method involves the construction of a specific class of time-invariant CBFs that encode the system's dynamic capabilities with respect to a given constraint, and augments them subsequently with appropriately designed time-dependent transformations. While transformations uniformly varying the time-invariant CBF can be applied to arbitrary systems, transformations exploiting structural properties in the dynamics - equivariances in particular - enable the handling of a broader and more expressive class of time-varying constraints. The article shows how to leverage such properties in the design of time-varying CBFs. The proposed method decouples the design of time variations from the computationally expensive construction of the underlying CBFs, thereby providing a computationally attractive method to the design of time-varying CBFs. The method accounts for input constraints and under-actuation, and requires only qualitative knowledge on the time-variation of the constraints making it suitable to the application in uncertain environments.

Theory0 citations2025-09-18arXiv ->

On Uniformly Time-Varying Control Barrier Functions

A. Wiltz, Dimos V. Dimarogonas

This paper investigates the design of a subclass of time-varying Control Barrier Functions (CBFs), specifically that of uniformly time-varying CBFs. Leveraging the fact that CBFs encode a system's dynamic capabilities relative to a state constraint, we decouple the design of uniformly time-varying CBFs into a time-invariant and a time-varying component. We characterize the subclass of time-invariant CBFs that yield a uniformly time-varying CBF when combined with a specific type of time-varying function. A detailed analysis of those conditions under which the time-varying function preserves the CBF property of the time-invariant component is provided. These conditions allow for selecting the time-varying function such that diverse variations in the state constraints can be captured while avoiding the redesign of the time-invariant component. From a technical point of view, the analysis requires the derivation of novel relations for comparison functions, not previously reported in the literature. We further relax the requirements on the time-varying function, showing that forward invariance can still be ensured even when the uniformly time-varying value function does not strictly constitute a CBF. Finally, we discuss how existing CBF construction methods can be applied to design suitable time-invariant CBFs, and demonstrate the effectiveness of the approach through detailed numerical examples.

Other0 citations2025-09-04arXiv ->

Leveraging Equivariances and Symmetries in the Control Barrier Function Synthesis

A. Wiltz, Dimos V. Dimarogonas

The synthesis of Control Barrier Functions (CBFs) often involves demanding computations or a meticulous construction. However, structural properties of the system dynamics and constraints have the potential to mitigate these challenges. In this paper, we explore how equivariances in the dynamics, loosely speaking a form of symmetry, can be leveraged in the CBF synthesis. Although CBFs are generally not inherently symmetric, we show how equivariances in the dynamics and symmetries in the constraints induce symmetries in CBFs derived through reachability analysis. This insight allows us to infer their CBF values across the entire domain from their values on a subset, leading to significant computational savings. Interestingly, equivariances can be even leveraged to the CBF synthesis for non-symmetric constraints. Specifically, we show how a partially known CBF can be leveraged together with equivariances to construct a CBF for various new constraints. Throughout the paper, we provide examples illustrating the theoretical findings. Furthermore, a numerical study investigates the computational gains from invoking equivariances into the CBF synthesis.

Other0 citations2025-04-22arXiv ->

Predictive Synthesis of Control Barrier Functions and its Application to Time-Varying Constraints

A. Wiltz, Dimos V. Dimarogonas

This paper presents a systematic method for synthesizing a Control Barrier Function (CBF) that encodes predictive information into a CBF. Unlike other methods, the synthesized CBF can account for changes and time-variations in the constraints even when constructed for time-invariant constraints. This avoids recomputing the CBF when the constraint specifications change. The method provides an explicit characterization of the extended class K function {\alpha} that determines the dynamic properties of the CBF, and {\alpha} can even be explicitly chosen as a design parameter in the controller synthesis. The resulting CBF further accounts for input constraints, and its values can be determined at any point without having to compute the CBF over the entire domain. The synthesis method is based on a finite horizon optimal control problem inspired by Hamilton-Jacobi reachability analysis and does not rely on a nominal control law. The synthesized CBF is time-invariant if the constraints are. The method poses mild assumptions on the controllability of the dynamic system and assumes the knowledge of at least a subset of some control invariant set. The paper provides a detailed analysis of the properties of the synthesized CBF, including its application to time-varying constraints. A simulation study applies the proposed approach to various dynamic systems in the presence of time-varying constraints. The paper is accompanied by an online available parallelized implementation of the proposed synthesis method.

Robotics0 citations2025-04-16arXiv ->

Robust Visual Servoing under Human Supervision for Assembly Tasks

Victor Nan Fernandez-Ayala, J. Silva, Meng Guo, Dimos V. Dimarogonas

We propose a framework enabling mobile manipulators to reliably complete pick-and-place tasks for assembling structures from construction blocks. The picking uses an eye-in-hand visual servoing controller for object tracking with Control Barrier Functions (CBFs) to ensure fiducial markers in the blocks remain visible. An additional robot with an eye-to-hand setup ensures precise placement, critical for structural stability. We integrate human-in-the-loop capabilities for flexibility and fault correction and analyze robustness to camera pose errors, proposing adapted barrier functions to handle them. Lastly, experiments validate the framework on 6-DoF mobile arms.

Theory0 citations2024-08-23arXiv ->

From Time-Invariant to Uniformly Time-Varying Control Barrier Functions: A Constructive Approach

A. Wiltz, Dimos V. Dimarogonas

In this paper, we define and analyze a subclass of (time-invariant) Control Barrier Functions (CBF) that have favorable properties for the construction of uniformly time-varying CBFs and thereby for the satisfaction of uniformly time-varying constraints. We call them $\Lambda$-shiftable CBFs where $\Lambda$ states the extent by which the CBF can be varied by adding a time-varying function. Moreover, we derive sufficient conditions under which a time-varying CBF can be obtained from a time-invariant one, and we propose a systematic construction method. Advantageous about our approach is that a $\Lambda$-shiftable CBF, once constructed, can be reused for various control objectives. In the end, we relate the class of $\Lambda$-shiftable CBFs to Control Lyapunov Functions (CLF), and we illustrate the application of our results with a relevant simulation example.

Theory7 citations2024-07-10Paper ->

On the Equivalence Between Prescribed Performance Control and Control Barrier Functions

Ryo Namerikawa, A. Wiltz, Farhad Mehdifar, Toru Namerikawa, Dimos V. Dimarogonas

In this paper, we show that Prescribed Performance Control (PPC) is a model-free Control Barrier Function (CBF)-based control approach. Specifically, we establish that a function utilized in the PPC design is a Time-Varying Reciprocal Control Barrier Function (TVRCBF). We demonstrate that PPC satisfies the same gradient condition that is well-known in the CBF literature, ensuring forward invariance. As a result, the control inputs generated by the PPC law belong to the input set characterized by the TVRCBF. Apart from assuming a certain controllability property, no further knowledge on the system dynamics is required. Our theoretical findings improve the understanding of the relationship between PPC and other CBF-based controllers. The theoretical results are validated through numerical simulations.

Robotics2 citations2024-05-13Paper ->

Multi-robot Human-in-the-loop Control under Spatiotemporal Specifications

Yixiao Zhang, Victor Nan Fernandez-Ayala, Dimos V. Dimarogonas

In this work, we present a coordination strategy tailored for scenarios involving multiple agents and tasks. We devise a range of tasks using signal temporal logic (STL), each earmarked for specific agents. These tasks are then imposed through control barrier function (CBF) constraints to ensure completion. To extend existing methodologies, our framework adeptly manages interactions among multiple agents. This extension is facilitated by leveraging nonlinear model predictive control (NMPC) to compute trajectories that avoid collisions. An integral aspect of our approach is the integration of a human-in-the-loop (HIL) model. This model enables real-time integration of human directives into the coordination process. A novel task allocation protocol is embedded within the frame-work to guide this process. We substantiate our methodology through a series of experiments, which corroborate the viability and relevance of our algorithms.

MPC/Planning0 citations2024-04-11arXiv ->

A Continuous-Time Violation-Free Multiagent Optimization Algorithm and Its Applications to Safe Distributed Control

Xiao Tan, Changxin Liu, Karl H. Johansson, Dimos V. Dimarogonas

In this work, we propose a continuous-time distributed optimization algorithm with guaranteed zero coupling constraint violation and apply it to safe distributed control in the presence of multiple control barrier functions (CBFs). The optimization problem is defined over a network that collectively minimizes a separable cost function with coupled linear constraints. An equivalent optimization problem with auxiliary decision variables and a decoupling structure is proposed. A sensitivity analysis demonstrates that the subgradient information can be computed using local information. This then leads to a subgradient algorithm for updating the auxiliary variables. A case with sparse coupling constraints is further considered, and it is shown to have better memory and communication efficiency. For the specific case of a CBF-induced time-varying quadratic program (QP), an update law is proposed that achieves finite-time convergence. Numerical results involving a static resource allocation problem and a safe coordination problem for a multiagent system demonstrate the efficiency and effectiveness of our proposed algorithms.

Theory49 citations2024-02-01Paper ->

Prescribed performance formation control for second-order multi-agent systems with connectivity and collision constraints

Yi Huang, Ziyang Meng, Dimos V. Dimarogonas

This paper studies the distributed formation control problem of second-order multi-agent systems (MASs) with limited communication ranges and collision avoidance constraints. A novel connectivity preservation and collision-free distributed control algorithm is proposed by combining prescribed performance control (PPC) and exponential zeroing control barrier Lyapunov functions (EZCBFs). In particular, we impose the time-varying performance constraints on the relative position and velocity errors between the neighboring agents, and then a PPC-based formation control algorithm is developed such that the connectivity of the communication graph can be preserved at all times, and the prescribed transient and steady performance on the relative position and velocity error can be achieved. Subsequently, by introducing the EZCBFs method, an inequality constraint condition on the control input is derived to guarantee the collision-free formation motion. By regarding the PPC-based formation controller as a nominal input, an actual formation control input is given by solving the quadratic programming (QP) problem such that each agent achieves collision-free formation motion while guaranteeing the connectivity and prescribed performance as much as possible. Finally, numerical simulation is carried out to validate the effectiveness of the proposed algorithm.

Other0 citations2023-09-17arXiv ->

Continuous-Time Control Synthesis Under Nested Signal Temporal Logic Specifications

Pian Yu, Xiao Tan, Dimos V. Dimarogonas

In this work, we propose a novel approach for the continuous-time control synthesis of nonlinear systems under nested signal temporal logic (STL) specifications. While the majority of existing literature focuses on control synthesis for STL specifications without nested temporal operators, addressing nested temporal operators poses a notably more challenging scenario and requires new theoretical advancements. Our approach hinges on the concepts of STL tree (sTLT) and control barrier function (CBF). Specifically, we detail the construction of an sTLT from a given STL formula and a continuous-time dynamical system, the sTLT semantics (i.e., satisfaction condition), and the equivalence or underapproximation relation between sTLT and STL. Leveraging the fact that the satisfaction condition of an sTLT is essentially keeping the state within certain sets during certain time intervals, it provides explicit guidelines for the CBF design. The resulting controller is obtained through the utilization of an online CBF-based program coupled with an event-triggered scheme for online updating the activation time interval of each CBF, with which the correctness of the system behavior can be established by construction. We demonstrate the efficacy of the proposed method for single-integrator and unicycle models under nested STL formulas.

Robotics17 citations2023-06-01Paper ->

Receding Horizon Control With Online Barrier Function Design Under Signal Temporal Logic Specifications

Maria Charitidou, Dimos V. Dimarogonas

Signal temporal logic (STL) has been found to be an expressive language for describing complex, time-constrained tasks in several robotic applications. Existing methods encode such specifications by either using integer constraints or by employing set invariance techniques. While in the first case this results in a mixed integer linear program (MILP), control problems, in the latter case, designer-specific choices may induce conservatism in the robot's performance and the satisfaction of the task. In this article, a continuous-time receding horizon control scheme (RHS) is proposed that exploits the tradeoff between task satisfaction and performance costs such as actuation and state costs, traditionally considered in RHS schemes. The satisfaction of the STL tasks is encoded using time-varying control barrier functions that are designed online, thus avoiding the integer expressions that are often used in literature. The recursive feasibility of the proposed scheme is guaranteed by the satisfaction of a time-varying terminal constraint that ensures the satisfaction of the task with predetermined robustness. The effectiveness of the method is illustrated in a multirobot simulation scenario.

Robotics15 citations2023-05-29Paper ->

Distributed barrier function-enabled human-in-the-loop control for multi-robot systems

Victor Nan Fernandez-Ayala, Xiao Tan, Dimos V. Dimarogonas

In this work, we propose a distributed control scheme for multi-robot systems in the presence of multiple constraints using control barrier functions. The proposed scheme expands previous work where only one single constraint can be handled. Here we show how to transform multiple constraints to a collective one using a smoothly approximated minimum function. Additionally, human-in-the-loop control is also incorporated seamlessly to our control design, both through the nominal control in the optimization objective as well as a safety condition in the constraints. Possible failure regions are identified and a suitable fix is proposed. Two types of human-in- the-loop scenarios are tested on real multi-robot systems with multiple constraints, including collision avoidance, connectivity maintenance, and arena range limits.

Other0 citations2022-09-06arXiv ->

Compatibility checking of multiple control barrier functions for input constrained systems

Xiao Tan, Dimos V. Dimarogonas

State and input constraints are ubiquitous in control system design. One recently developed tool to deal with these constraints is control barrier functions (CBF) which transform state constraints into conditions in the input space. CBF-based controller design thus incorporates both the CBF conditions and input constraints in a quadratic program. However, the CBF-based controller is well-defined only if the CBF conditions are compatible. In the case of perturbed systems, robust compatibility is of relevance. In this work, we propose an algorithmic solution to verify or falsify the (robust) compatibility of given CBFs a priori. Leveraging the Lipschitz properties of the CBF conditions, a grid sampling and refinement method with theoretical analysis and guarantees is proposed.

MPC/Planning0 citations2022-05-27arXiv ->

A Robust, Multiple Control Barrier Function Framework for Input Constrained Systems

Wenceslao Shaw Cortez, Xiao Tan, Dimos V. Dimarogonas

We propose a novel (Type-II) zeroing control barrier function (ZCBF) for safety-critical control, which generalizes the original ZCBF approach. Our method allows for applications to a larger class of systems (e.g., passivity-based) while still ensuring robustness, for which the construction of conventional ZCBFs is difficult. We also propose a locally Lipschitz continuous control law that handles multiple ZCBFs, while respecting input constraints, which is not currently possible with existing ZCBF methods. We apply the proposed concept for unicycle navigation in an obstacle-rich environment.

Theory0 citations2022-04-26arXiv ->

Razumikhin and Krasovskii Approaches for Safe Stabilization

W. Ren, R. Jungers, Dimos V. Dimarogonas

This paper studies the stabilization and safety problems of nonlinear time-delay systems. Following both Razumikhin and Krasovskii approaches, we propose novel control Lyapunov functions/functionals for the stabilization problem and novel control barrier functions/functionals for the safety problem. The proposed control Lyapunov and barrier functions/functionals extend the existing ones from the delay-free case to the time-delay case, and allow for designing the stabilizing and safety controllers in closed-form. Since analytical solutions to time-delay optimal control problems are hard to be achieved, a sliding mode control based approach is developed to merge the proposed control Lyapunov and barrier functions/functionals. Based on the sliding surface functional, a feedback control law is established to investigate the stabilization and safety objectives simultaneously. In particular, the properties of the sliding surface functional are analyzed, and further how to construct the sliding surface functional is discussed. Finally, the proposed approaches are illustrated via two numerical examples from the connected cruise control problem of automotive systems and the synchronization problem of multi-agent systems.

Other50 citations2022Paper ->

Distributed Implementation of Control Barrier Functions for Multi-agent Systems

Xiao Tan, Dimos V. Dimarogonas

In this letter, we propose a distributed implementation framework for control barrier functions induced quadratic programs for multi-agent systems. The quadratic program aims at minimally modifying nominal local controllers, which relate to the underlying system tasks, while always respecting a single coupling constraint which relates to system safety. Unlike previous implementations, no approximation or pre-allocation of the coupling constraint over the agents is needed. Instead, to solve the quadratic problem exactly, an auxiliary variable is assigned to each agent and then locally updated and transmitted among agents. The proposed distributed implementation ensures that the control barrier function constraint is enforced at every time instant, and the optimal to the quadratic program control signal is achieved in finite time. The efficacy of our method is demonstrated through two numerical examples.

Theory0 citations2021-04-30arXiv ->

On the Undesired Equilibria Induced by Control Barrier Function Based Quadratic Programs

Xiao Tan, Dimos V. Dimarogonas

In this paper, we analyze the system behavior for general nonlinear control-affine systems when a control barrier function-induced quadratic program-based controller is employed for feedback. In particular, we characterize the existence and locations of possible equilibrium points of the closed-loop system and also provide analytical results on how design parameters affect them. Based on this analysis, a simple modification on the existing quadratic program-based controller is provided, which, without any assumptions other than those taken in the original program, inherits the safety set forward invariance property, and further guarantees the complete elimination of undesired equilibrium points in the interior of the safety set as well as one type of boundary equilibrium points, and local asymptotic stability of the origin. Numerical examples are given alongside the theoretical discussions.

Robotics0 citations2020-12-01arXiv ->

Barrier Function Based Collaborative Control of Multiple Robots Under Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

Motivated by the recent interest in cyber-physical and autonomous robotic systems, we study the problem of dynamically coupled multiagent systems under a set of signal temporal logic tasks. In particular, the satisfaction of each of these signal temporal logic tasks depends on the behavior of a distinct set of agents. Instead of abstracting the agent dynamics and the temporal logic tasks into a discrete domain and solving the problem therein or using optimization-based methods, we derive collaborative feedback control laws.These control laws are based on a decentralized control barrier function condition that results in discontinuous control laws, as opposed to a centralized condition resembling the single-agent case. The benefits of our approach are inherent robustness properties typically present in feedback control as well as satisfaction guarantees for continuous-time multiagent systems. More specifically, time-varying control barrier functions are used that account for the semantics of the signal temporal logic tasks at hand. For a certain fragment of signal temporal logic tasks, we further propose a systematic way to construct such control barrier functions. Finally, we show the efficacy and robustness of our framework in an experiment, including a group of three omnidirectional robots.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Robotics347 citations2019-01-01Paper ->

Control Barrier Functions for Signal Temporal Logic Tasks

Lars Lindemann, Dimos V. Dimarogonas

The need for computationally-efficient control methods of dynamical systems under temporal logic tasks has recently become more apparent. Existing methods are computationally demanding and hence often not applicable in practice. Especially with respect to multi-robot systems, these methods do not scale computationally. In this letter, we propose a framework that is based on control barrier functions and signal temporal logic. In particular, time-varying control barrier functions are considered where the temporal properties are used to satisfy signal temporal logic tasks. The resulting controller is given by a switching strategy between a computationally-efficient convex quadratic program and a local feedback control law.

Non-CBF Papers
Other0 citations2026-03-25arXiv ->

A Modular Platooning and Vehicle Coordination Simulator for Research and Education

Kevin Jamsahar, A. Wiltz, Maria Charitidou, Dimos V. Dimarogonas

This work presents a modular, Python-based simulator that simplifies the evaluation of novel vehicle control and coordination algorithms in complex traffic scenarios while keeping the implementation overhead low. It allows researchers to focus primarily on developing the control and coordination strategies themselves, while the simulator manages the setup of complex road networks, vehicle configuration, execution of the simulation and the generation of video visualizations of the results. It is thereby also well-suited to support control education by allowing instructors to create interactive exercises providing students with direct visual feedback. Thanks to its modular architecture, the simulator remains easily customizable and extensible, lowering the barrier for conducting advanced simulation studies in vehicle and traffic control research.

Theory0 citations2026-03-08arXiv ->

Tunable Input-to-State Safety with Input Constraints

Ming Li, Jin Chen, Dimos V. Dimarogonas

Tunable input-to-state safety (TISSf) generalizes the input-to-state safety (ISSf) framework by incorporating a tuning function that regulates safety conservatism while preserving robustness against perturbations. Despite its flexibility, the TISSf tuning function is often designed without explicitly incorporating actuator limits, which can lead to incompatibility with input constraints. To address this gap, this paper proposes a framework that integrates general compact input constraints into tuning function synthesis. Leveraging a geometric perspective, we characterize the TISSf condition as a state-dependent half-space constraint and derive a verifiable certificate for input compatibility using support functions. This characterization transforms the compatibility requirement into a design constraint on the tuning function, yielding a prescriptive lower bound that defines an admissible family of tunings under input constraints. These results are specialized to norm-bounded, polyhedral, and box constraints, yielding tractable control design conditions. We show that these conditions, combined with tuning function monotonicity, guarantee input compatibility and recursive feasibility of the resulting quadratic program (QP)-based safety filter. Furthermore, an offline parameter selection procedure using a covering-based sampling strategy ensures compatibility across the entire safe set via a linear program (LP). A connected cruise control (CCC) application demonstrates robust safety under TISSf while enforcing input constraints by design.

MPC/Planning1 citations2026-03-01Paper ->

Cooperative Stochastic MPC Under Hard Input Constraints and Event-Triggered Communication

Irene Perez-Salesa, Dimos V. Dimarogonas, Carlos Sagüés, Rodrigo Aldana‐López

In this work, we develop a new distributed output-feedback stochastic model-predictive control (SMPC) proposal for a plant that is cooperatively regulated by a set of actuator nodes. Contrary to most approaches, we consider hard constraints on the actuators, and we appropriately tighten the constraints to ensure recursive feasibility with a given probability, despite the stochastic noise present in the system. To lighten the communication load, the constraint design is performed offline, and an event-triggering mechanism is included, so that the nodes only need to transmit their local state estimates to neighbors at event instants during online execution. We prove constraint satisfaction and stability of our proposal, and we include simulation results showing that similar control performance to the centralized case can be achieved by our distributed SMPC with reduced communication.

MPC/Planning0 citations2026-03-01Paper ->

Achieving violation-free distributed optimization under coupling constraints

Changxin Liu, Xiao Tan, Xuyang Wu, Dimos V. Dimarogonas, Karl H. Johansson

Robotics0 citations2026-02-28arXiv ->

Validation of Space Robotics in Underwater Environments via Disturbance Robustness Equivalency

Joris Verhagen, Elias Krantz, Chelsea Sidrane, David Dorner, N. D. Carli et al.

We present an experimental validation framework for space robotics that leverages underwater environments to approximate microgravity dynamics. While neutral buoyancy conditions make underwater robotics an excellent platform for space robotics validation, there are still dynamical and environmental differences that need to be overcome. Given a high-level space mission specification, expressed in terms of a Signal Temporal Logic specification, we overcome these differences via the notion of maximal disturbance robustness of the mission. We formulate the motion planning problem such that the original space mission and the validation mission achieve the same disturbance robustness degree. The validation platform then executes its mission plan using a near-identical control strategy to the space mission where the closed-loop controller considers the spacecraft dynamics. Evaluating our validation framework relies on estimating disturbances during execution and comparing them to the disturbance robustness degree, providing practical evidence of operation in the space environment. Our evaluation features a dual-experiment setup: an underwater robot operating under near-neutral buoyancy conditions to validate the planning and control strategy of either an experimental planar spacecraft platform or a CubeSat in a high-fidelity space dynamics simulator.

Robotics0 citations2026-02-26arXiv ->

Marinarium: a New Arena to Bring Maritime Robotics Closer to Shore

Ignacio Torroba, David Dorner, Victor Nan Fernandez-Ayala, Mart Kartašev, Joris Verhagen et al.

This paper presents the Marinarium, a modular and stand-alone underwater research facility designed to provide a realistic testbed for maritime and space-analog robotic experimentation in a resource-efficient manner. The Marinarium combines a fully instrumented underwater and aerial operational volume, extendable via a retractable roof for real-weather conditions, a digital twin in the SMaRCSim simulator and tight integration with a space robotics laboratory. All of these result from design choices aimed at bridging simulation, laboratory validation, and field conditions. We compare the Marinarium to similar existing infrastructures and illustrate how its design enables a set of experiments in four open research areas within field robotics. First, we exploit high-fidelity dynamics data from the tank to demonstrate the potential of learning-based system identification approaches applied to underwater vehicles. We further highlight the versatility of the multi-domain operating volume via a rendezvous mission with a heterogeneous fleet of robots across underwater, surface, and air. We then illustrate how the presented digital twin can be utilized to reduce the reality gap in underwater simulation. Finally, we demonstrate the potential of underwater surrogates for spacecraft navigation validation by executing spatiotemporally identical inspection tasks on a planar space-robot emulator and a neutrally buoyant \gls{rov}. In this work, by sharing the insights obtained and rationale behind the design and construction of the Marinarium, we hope to provide the field robotics research community with a blueprint for bridging the gap between controlled and real offshore and space robotics experimentation.

Theory0 citations2026-02-25arXiv ->

Stability of Open Multi-agent Systems over Dynamic Signed Digraphs

Pelin Şekercioğlu, Angela Fontan, Dimos V. Dimarogonas

We address the synchronization problem in open multi-agent systems (OMAS) containing both cooperative and antagonistic interactions. In these systems, agents can join or leave the network over time, and the interaction structure may evolve accordingly. To capture these dynamical structural changes, we represent the network as a switched system interconnected over a dynamic and directed signed graph. Additionally, the network may contain one or multiple leader groups that influence the behavior of the remaining agents. In general, we show that the OMAS exhibit a more general form of synchronization, including trivial consensus, bipartite consensus and containment. Our approach uses the signed edge-based agreement protocol, and constructs strict Lyapunov functions for signed networks described by signed edge-Laplacian matrices containing multiple zero eigenvalues. Numerical simulations validate our theoretical results.

Theory0 citations2026-02-23arXiv ->

Edge-based Synchronization over Signed Digraphs with Multiple Leaders

Pelin Şekercioğlu, Angela Fontan, Dimos V. Dimarogonas

This work addresses the edge-based synchronization problem in first-order multi-agent systems containing both cooperative and antagonistic interactions with one or multiple leader groups. The presence of multiple leaders and antagonistic interactions means that the multi-agent system typically does not achieve consensus, unless specific conditions (on the number of leaders and on the signed graph) are met, in which case the agents reach a trivial form of consensus. In general, we show that the multi-agent system exhibits a more general form of synchronization, including bipartite consensus and containment. Our approach proposes a signed edge-based agreement protocol for signed networks described by signed edge-Laplacian matrices. In particular, in this work, we present new spectral properties of signed edge-Laplacian matrices containing multiple zero eigenvalues and establish global exponential stability of the synchronization errors. Moreover, we explicitly compute the equilibrium to which all edge states converge, thereby characterizing the resulting synchronization behavior. Numerical simulations validate our theoretical results.

Robotics0 citations2026-02-19arXiv ->

Multi-Agent Temporal Logic Planning via Penalty Functions and Block-Coordinate Optimization

E. Vlahakis, Arash Bahari Kordabad, Lars Lindemann, Pantelis Sopasakis, Sadegh Soudjani et al.

Multi-agent planning under Signal Temporal Logic (STL) is often hindered by collaborative tasks that lead to computational challenges due to the inherent high-dimensionality of the problem, preventing scalable synthesis with satisfaction guarantees. To address this, we formulate STL planning as an optimization program under arbitrary multi-agent constraints and introduce a penalty-based unconstrained relaxation that can be efficiently solved via a Block-Coordinate Gradient Descent (BCGD) method, where each block corresponds to a single agent's decision variables, thereby mitigating complexity. By utilizing a quadratic penalty function defined via smooth STL semantics, we show that BCGD iterations converge to a stationary point of the penalized problem under standard regularity assumptions. To enforce feasibility, the BCGD solver is embedded within a two-layer optimization scheme: inner BCGD updates are performed for a fixed penalty parameter, which is then increased in an outer loop to progressively improve multi-agent STL robustness. The proposed framework enables scalable computations and is validated through various complex multi-robot planning scenarios.

Theory0 citations2026-02-05arXiv ->

Observer-based Control of Multi-agent Systems under STL Specifications

Tommaso Zaccherini, Siyuan Liu, Dimos V. Dimarogonas

This paper proposes a decentralized controller for large-scale heterogeneous multi-agent systems subject to bounded external disturbances, where agents must satisfy Signal Temporal Logic (STL) specifications requiring cooperation among non-communicating agents. To address the lack of direct communication, we employ a decentralized k-hop Prescribed Performance State Observer (k-hop PPSO) to provide each agent with state estimates of those agents it cannot communicate with. By leveraging the performance bounds on the state estimation errors guaranteed by the k-hop PPSO, we first modify the space robustness of the STL tasks to account for these errors, and then exploit the modified robustness to design a decentralized continuous-time feedback controller that ensures satisfaction of the STL tasks even under worst-case estimation errors. A simulation result is provided to validate the proposed framework.

Robotics0 citations2026Paper ->

Quality of Control-Based Control-Communication Co-Design for Collaborative Robotics

Neelabhro Roy, Mani H. Dhullipalla, Gourav Prateek Sharma, Sara Sandberg, Dimos V. Dimarogonas et al.

Robotics0 citations2025-12-16arXiv ->

Trajectory Tracking for Multi-Manipulator Systems in Constrained Environments

Mayank Sewlia, Christos K. Verginis, Dimos V. Dimarogonas

We consider the problem of cooperative manipulation by a mobile multi-manipulator system operating in obstacle-cluttered and highly constrained environments under spatio-temporal task specifications. The task requires transporting a grasped object while respecting both continuous robot dynamics and discrete geometric constraints arising from obstacles and narrow passages. To address this hybrid structure, we propose a multi-rate planning and control framework that combines offline generation of an STL-satisfying object trajectory and collision-free base footprints with online constrained inverse kinematics and continuous-time feedback control. The resulting closed-loop system enables coordinated reconfiguration of multiple manipulators while tracking the desired object motion. The approach is evaluated in high-fidelity physics simulations using three Franka Emika Panda mobile manipulators rigidly grasping an object.

MPC/Planning0 citations2025-12-11arXiv ->

Distribution-Free Stochastic MPC for Joint-in-Time Chance-Constrained Linear Systems

Lukas Vogel, Andrea Carron, E. Vlahakis, Dimos V. Dimarogonas

This work presents a stochastic model predictive control (MPC) framework for linear systems subject to joint-in-time chance constraints under unknown disturbance distributions. Unlike existing stochastic MPC formulations that rely on parametric or Gaussian assumptions or require expensive offline computations, the proposed method leverages conformal prediction (CP) as a streamlined tool to construct finite-sample confidence regions for the system's stochastic error trajectories with minimal computational effort. These regions enable the relaxation of probabilistic constraints while providing formal guarantees. By employing an indirect feedback mechanism and a probabilistic set-based formulation, we prove recursive feasibility of the relaxed optimization problem and establish chance constraint satisfaction in closed-loop. Furthermore, we extend the approach to the more general output feedback setting with unknown measurement noise distributions. Given available noise samples, we establish satisfaction of the joint chance constraints and recursive feasibility via output measurements alone. Numerical examples demonstrate the effectiveness and advantages of the proposed method compared to existing approaches.

Other0 citations2025-12-09Paper ->

Leader selection and control design for topology estimation of dynamical networks

Nana Wang, Dimos V. Dimarogonas

We propose a framework for selecting leaders and employing active control to guarantee accurate topology estimation in finite time for dynamical networks. After determining the optimal or suboptimal solution of the minimum leader number which renders strongly structurally controllable, two topology estimation algorithms with active control design schemes are proposed. The first, employing the integral of the states and control input and building an equation of its topology matrix, based on the dynamics of the original network, gives a unique solution for a symmetric topological matrix and the subspace of an asymmetric topological matrix. The second, building upon an auxiliary network and comparing the difference with the original network, provides a guarantee for accurate topology estimation for both stable and unstable dynamical networks in finite time. Finally, a relevant simulation example verifies the performance of the proposed methods.

MPC/Planning1 citations2025-12-01Paper ->

Distributed Adaptive Prescribed Performance Control for Interconnected Euler–Lagrange Systems Under Input Constraints

Tian Tao, Charalampos P. Bechlioulis, Dimos V. Dimarogonas

This article proposes a novel distributed adaptive prescribed performance control scheme with low complexity for interconnected multi-input multi-output Euler–Lagrange systems subject to structural uncertainty in dynamics, input saturation, and external disturbances without employing any approximation structures. In addition to the coupling caused by the control protocol, uncertain nonlinear interconnection terms intrinsically existing in the dynamics are also considered. The control scheme is implemented in a distributed manner among multiple agents, utilizing only local information. Adaptive control tools are employed to introduce flexible prescribed performance functions, which serve as a trade-off between input and output constraints, effectively dampening the input saturation and eliminating the need for an auxiliary system. The proposed approach is analyzed using Lyapunov techniques and is validated by simulation results on a leader–follower multiagent trajectory tracking control problem.

Other0 citations2025-11-28arXiv ->

Resistant Topology Inference in Consensus Networks: A Feedback-Based Design

Yushan Li, Jiabao He, Dimos V. Dimarogonas

Consensus networks are widely deployed in numerous civil and industrial applications. However, the process of reaching a common consensus among nodes can unintentionally reveal the network’s topology to external observers by appropriate inference techniques. This paper investigates a feedback-based resistant inference design to prevent the topology from being inferred using data, while preserving the original consensus convergence. First, we characterize the conditions to preserve the original consensus, and introduce the "accurate inference" notion, which accounts for both the uniqueness of the solution to topology inference (solvability) and the deviation from the original topology (accuracy). Then, we employ invariant subspace analysis to characterize the solvability. Even when unique inference remains possible, we provide necessary and sufficient conditions for the feedback design to induce inaccurate inference, and give a Laplacian structure based distributed design. Simulations validate the effectiveness of the method.

Robotics0 citations2025-11-27arXiv ->

Switching control of underactuated multi-channel systems with input constraints for cooperative manipulation

Dongjae Lee, Dimos V. Dimarogonas, H. J. Kim

This work presents an event-triggered switching control framework for a class of nonlinear underactuated multi-channel systems with input constraints. These systems are inspired by cooperative manipulation tasks involving underactuation, where multiple underactuated agents collaboratively push or pull an object to a target pose. Unlike existing approaches for multi-channel systems, our method addresses underactuation and the potential loss of controllability by additionally addressing channel assignment of agents. To simultaneously account for channel assignment, input constraints, and stabilization, we formulate the control problem as a Mixed Integer Linear Programming and derive sufficient conditions for its feasibility. To improve real-time computation efficiency, we introduce an event-triggered control scheme that maintains stability even between switching events through a quadratic programming-based stabilizing controller. We theoretically establish the semi-global exponential stability of the proposed method and the asymptotic stability of its extension to nonprehensile cooperative manipulation under noninstantaneous switching. The proposed framework is further validated through numerical simulations on 2D and 3D free-flyer systems and multi-robot nonprehensile pushing tasks.

Other0 citations2025-11-12arXiv ->

Robust Estimation and Control for Heterogeneous Multi-agent Systems Based on Decentralized k-hop Prescribed Performance Observers

Tommaso Zaccherini, Siyuan Liu, Dimos V. Dimarogonas

We propose decentralized k-hop Prescribed Performance State and Input Observers for heterogeneous multi-agent systems subject to bounded external disturbances. In the proposed input/state observer, each agent estimates the state and input of agents located two or more hops away using only local information exchanged with 1-hop neighbors, while guaranteeing that transient estimation errors satisfy predefined performance bounds. Conditions are established under which the input observer can be omitted, allowing the state observer convergence to be independent of the input estimates. Theoretical analysis demonstrates that if a closed-loop controller with full state knowledge achieves the control objective and the estimation-based closed-loop system is set-Input to State Stable (set-ISS) with respect to the goal set, then the estimated states can be used to achieve the system objective with an arbitrarily small worst-case error governed by the accuracy of the states estimates. Simulation results are provided to validate the proposed approach.

Other0 citations2025-10-13arXiv ->

Robust Closed-Form Control for MIMO Nonlinear Systems under Conflicting Time-Varying Hard and Soft Constraints (extended version)

Farhad Mehdifar, Charalampos P. Bechlioulis, Dimos V. Dimarogonas

This paper introduces a novel robust closed-form control law to handle time-varying hard and soft constraints in uncertain high-relative-degree nonlinear MIMO systems. These constraints represent spatiotemporal specifications in mechanical systems'operational space, with hard constraints ensuring safety-critical requirements and soft constraints encoding performance or task objectives. Initially, all constraints are consolidated into two separate scalar time-varying hard and soft constraint functions, whose positive level sets define feasible regions. A closed-form control law is developed to enforce these constraints using appropriately designed reciprocal barriers and nonlinear transformation functions. When conflicts between hard and soft constraints arise, the control law prioritizes hard constraints by virtually relaxing soft constraints via a dynamic relaxation law. Notably, the proposed control law maintains low complexity by avoiding approximation schemes for coping with system uncertainties. Simulation results confirm the effectiveness of the proposed method.

MPC/Planning0 citations2025-09-02arXiv ->

Fault-tolerant Model Predictive Control for Spacecraft

Raphael Stöckner, Pedro Roque, Maria Charitidou, Dimos V. Dimarogonas

Given the cost and critical functions of satellite constellations, ensuring mission longevity and safe decommissioning is essential for space sustainability. This article presents a Model Predictive Control for spacecraft trajectory and setpoint stabilization under multiple actuation failures. The proposed solution allows us to efficiently control the faulty spacecraft enabling safe navigation towards servicing or collision-free trajectories. The proposed scheme ensures closedloop asymptotic stability and is shown to be recursively feasible. We demonstrate its efficacy through open-source numerical results and realistic experiments using the ATMOS platform.

CBF Related Papers
Robotics1 citations2023-01-19Paper ->

A ROS Package for UAV Run Time Assurance with In-the-Loop Reachability

Christian Llanes, S. Coogan

This work describes an open source software package for run time assurance (RTA) of UAVs to verify safety in the form of collision avoidance. An operator designs a primary controller with possible learning-enabled components or with human inputs. Learning-based control design is inherently unverified and the RTA supervises the control behavior during the learning process. The proposed RTA package guarantees collision avoidance of obstacles while acting as a supervisor for an operator’s primary controller. The RTA mechanism uses control barrier functions (CBFs) with reachability analysis of the UAV dynamics to detect unsafe control actions from the primary controller and solves an optimization problem to minimally adjust desired control inputs to ensure that collision-bound trajectories are avoided. We use the Robot Operating System (ROS) middleware as a framework for designing the software package. We describe the main underlying algorithm and its implementation as a ROS2 package, and we demonstrate its use in hardware experiments.

MPC/Planning12 citations2022-05-01Paper ->

Safety from Fast, In-the-Loop Reachability with Application to UAVs

Christian Llanes, Matthew Abate, S. Coogan

We present a runtime assurance (RTA) mechanism for ensuring safety of a controlled dynamical system and an application to collision avoidance of two unmanned aerial vehicles (UAVs). We consider a dynamical system controlled by an unverified and potentially unsafe primary controller that might, e.g., lead to collision. The proposed RTA mechanism computes at each time the reachable set of the system under a backup control law. We then develop a novel optimization problem based on control barrier functions that filters the primary controller when necessary in order to keep the system's reachable set within reach of a known, but conservative, safe region. The theory of mixed monotone systems is leveraged for efficient reachable set computation and to achieve a tractable optimization formulation. We demonstrate the proposed RTA mechanism on a dual multirotor UAV case study which requires a fast controller update rate as a result of the small time-scale rotational dynamics. In implementation, the algorithm computes the reachable set of an eight dimensional dynamical system in less than five milliseconds and solves the optimization problem in under one millisecond, yielding a controller update rate of 100Hz.

MPC/Planning6 citations2021-05-19Paper ->

Safety from in-the-loop reachability for cyber-physical systems

Christian Llanes, Matthew Abate, S. Coogan

We demonstrate a methodology for achieving safe autonomy that relies on computing reachable sets at runtime. Given a system subject to disturbances controlled by an unverified and potentially faulty controller, this methodology computes at each time the reachable set of the system under a backup control law to ensure the system is within reach of a known a priori safe region. Control barrier functions are then used in conjunction with the reachable set to adjust potentially unsafe control actions that would otherwise move the system beyond reach of this safe set. This approach faces several computational challenges: reachable sets for the dynamics must be computed at runtime; sensitivity of the reachable set to initial conditions is required for the control barrier optimization formulation; and the presence of disturbances introduces a large number of constraints in the resulting optimization. The proposed methodology leverages the theory of mixed monotone systems to address these challenges, and the main contribution of this paper is an application of this methodology to a ten dimensional dual planar multirotor system that is implemented on embedded hardware with a controller update rate up to 100Hz.

Other0 citations2020-08-16arXiv ->

Enforcing Safety at Runtime for Systems with Disturbances

Matthew Abate, S. Coogan

An assured controller is one that enforces safety online by filtering a desired control input at runtime, and control barrier functions (CBFs) provide an assured controller that renders a safe subset of the statespace forward invariant. In this work, we present a problem formulation for CBF-based runtime assurance for systems with disturbances, and controllers that solve this problem must, in some way, incorporate the online computation of reachable sets. In general, computing reachable sets in the presence of disturbances is computationally costly and cannot be directly incorporated in a CBF framework. To that end, we present a particular solution to the problem, whereby reachable sets are approximated via the mixed-monotonicity property. Efficient algorithms exist for over-approximating reachable sets for mixed-monotone systems with hyperrectangles, and we show that such approximations are suitable for incorporating into a CBF-based runtime assurance framework.

Robotics0 citations2020-05-25arXiv ->

Continuous Reachability Task Transition Using Control Barrier Functions

M. Srinivasan, Cesar Santoyo, S. Coogan

In this paper, a method to achieve smooth transitions between sequential reachability tasks for a continuous time mobile robotic system is presented. Control barrier functions provide formal guarantees of forward invariance of safe sets and finite-time reachability and are able to enforce task execution. Barrier functions used in quadratic programs result in implementation of controllers with real-time performance guarantees. Existing approaches for multi-objective task execution using control barrier functions leverage discretely switched, sequential quadratic programs to achieve successive tasks. However, discrete switching can lead to control input discontinuities which can affect a robot's performance. Hence, we propose a method which ensures continuous transitions between sequential quadratic programs. In particular, a time varying component to the barrier function constraint is introduced which allows for a smooth transition between objectives. Robotic implementation results are also provided.

Robotics0 citations2020-03-10arXiv ->

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach

M. Srinivasan, A. Dabholkar, S. Coogan, P. Vela

Control barrier functions are mathematical constructs used to guarantee safety for robotic systems. When integrated as constraints in a quadratic programming optimization problem, instantaneous control synthesis with real-time performance demands can be achieved for robotics applications. Prevailing use has assumed full knowledge of the safety barrier functions, however there are cases where the safe regions must be estimated online from sensor measurements. In these cases, the corresponding barrier function must be synthesized online. This paper describes a learning framework for estimating control barrier functions from sensor data. Doing so affords system operation in unknown state space regions without compromising safety. Here, a support vector machine classifier provides the barrier function specification as determined by sets of safe and unsafe states obtained from sensor measurements. Theoretical safety guarantees are provided. Experimental ROS-based simulation results for an omnidirectional robot equipped with LiDAR demonstrate safe operation.

Robotics0 citations2020-01-20arXiv ->

Extent-Compatible Control Barrier Functions

M. Srinivasan, Matthew Abate, Gustav Nilsson, S. Coogan

Safety requirements in dynamical systems are commonly enforced with set invariance constraints over a safe region of the state space. Control barrier functions, which are Lyapunov-like functions for guaranteeing set invariance, are an effective tool to enforce such constraints and guarantee safety when the system is represented as a point in the state space. In this paper, we introduce extent-compatible control barrier functions as a tool to enforce safety for the system including its volume (extent) in the physical world. In order to implement the extent-compatible control barrier functions framework, a sum-of-squares based optimization program is proposed. Since sum-of-squares programs can be computationally prohibitive, we additionally introduce a sampling based method in order to retain the computational advantage of a traditional barrier function based quadratic program controller. We prove that the proposed sampling based controller retains the guarantee for safety. Simulation and robotic implementation results are also provided.

Robotics5 citations2019-12-01Paper ->

Weighted Polar Finite Time Control Barrier Functions With Applications To Multi-Robot Systems

M. Srinivasan, N. P. Hyun, S. Coogan

In this paper, we introduce a class of functions inspired by the weighted Lp norm which is used for the control of unicycle robots in planar space. In particular, we prove that these functions are valid finite time control barrier functions. Finite time control barrier functions (FCBFs) provide a formal guarantee for finite time convergence to desired sets in the state space. Traditionally, these barrier functions consider only the position of the robot and not the heading, which makes it difficult to apply this framework in cases where the heading is important in addition to the position. In this paper, a new barrier function defined with the full state of the robot is proposed to achieve finite time convergence to the desired set in the state space and the desired heading angle with controllable error bounds. We propose a quadratic program (QP) based controller, which guarantees finite time convergence to a desired region in the state space. We show that there exists singular sets in the state space where the QP is infeasible. By virtue of the structure of the proposed barrier function, feasibility of the QP is guaranteed. A multi-robot case study is presented, along with simulation and experimental results.

MPC/Planning0 citations2019-09-10arXiv ->

A Barrier Function Approach to Finite-Time Stochastic System Verification and Control

Cesar Santoyo, Maxence Dutreix, S. Coogan

This paper studies the problem of enforcing safety of a stochastic dynamical system over a finite-time horizon. We use stochastic control barrier functions as a means to quantify the probability that a system exits a given safe region of the state space in finite time. A barrier certificate condition that bounds the expected value of the barrier function over the time horizon is recast as a sum-of-squares optimization problem for efficient numerical computation. Unlike prior works, the proposed certificate condition includes a state-dependent upper bound on the evolution of the expectation. We present formulations for both continuous-time and discrete-time systems. Moreover, for systems for which the drift dynamics are affine-in-control, we propose a method for synthesizing polynomial state feedback controllers that achieve a specified probability of safety. Several case studies are presented which benchmark and illustrate the performance of our verification and control method in the continuous-time and discrete-time domains.

Robotics0 citations2019-08-14arXiv ->

Control of Mobile Robots Using Barrier Functions Under Temporal Logic Specifications

M. Srinivasan, S. Coogan

In this article, we propose a framework for the control of mobile robots subject to temporal logic specifications using barrier functions. Complex task specifications can be conveniently encoded using linear temporal logic. In particular, we consider a fragment of linear temporal logic, which encompasses a large class of motion planning specifications for a robotic system. Control barrier functions have recently emerged as a convenient tool to guarantee reachability and safety for a system. In addition, they can be encoded as affine constraints in a quadratic program. In this article, a fully automatic framework that translates a user defined specification in temporal logic to a sequence of barrier function based quadratic programs is presented. In addition, with the aim of alleviating infeasibility scenarios, we propose methods for composition of barrier functions as well as a prioritization-based control method to guarantee feasibility of the controller. We prove that the resulting system trajectory synthesized by the proposed controller satisfies the given specification. Robotic simulation and experimental results are provided in addition to the theoretical framework.

Robotics0 citations2019-07-17arXiv ->

A Sequential Composition Framework for Coordinating Multirobot Behaviors

Pietro Pierpaoli, Anqi Li, M. Srinivasan, Xiaoyi Cai, S. Coogan et al.

A number of coordinated behaviors are proposed for achieving specific tasks for multirobot systems. However, since most applications require more than one such behavior, one needs to be able to compose together sequences of behaviors while respecting local information flow constraints. Specifically, when the interagent communication depends on interrobot distances, these constraints translate into particular configurations that must be reached in finite time in order for the system to be able to transition between the behaviors. To this end, we develop a distributed framework based on finite-time convergence control barrier functions that enables a team of robots to adjust its configuration in order to meet the communication requirements for the different tasks. In order to demonstrate the significance of the proposed framework, we implemented a full-scale scenario where a team of eight planar robots explore an urban environment in order to localize and rescue a subject.

Robotics2120 citations2019-03-27arXiv ->

Control Barrier Functions: Theory and Applications

A. Ames, S. Coogan, M. Egerstedt, Gennaro Notomista, K. Sreenath et al.

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Robotics0 citations2018-08-07arXiv ->

Control of Multi-Agent Systems with Finite Time Control Barrier Certificates and Temporal Logic

M. Srinivasan, S. Coogan, M. Egerstedt

In this paper, a method to synthesize controllers using finite time convergence control barrier functions guided by linear temporal logic specifications for continuous time multi-agent dynamical systems is proposed. Finite time convergence to a desired set in the state space is guaranteed under the existence of a suitable finite time convergence control barrier function. In addition, these barrier functions also guarantee forward invariance once the system converges to the desired set. This allows us to formulate a theoretical framework which synthesizes controllers for the multi-agent system. These properties also enable us to solve the reachability problem in continuous time by formulating a theorem on the composition of multiple finite time convergence control barrier functions. This approach is more flexible than existing methods and also allows for a greater set of feasible control laws. Linear temporal logic is used to specify complex task specifications that need to be satisfied by the multi-agent system. With this solution methodology, a control law is synthesized that satisfies the given temporal logic task specification. Robotic experiments are provided which were performed on the Robotarium multi-robot testbed at Georgia Tech.

Non-CBF Papers
MPC/Planning0 citations2023-07-27arXiv ->

Efficient Interaction-Aware Interval Analysis of Neural Network Feedback Loops

Saber Jafarpour, Akash Harapanahalli, S. Coogan

In this article, we propose a computationally efficient framework for interval reachability of systems with neural network controllers. Our approach leverages inclusion functions for the open-loop system and the neural network controller to embed the closed-loop system into a larger dimensional embedding system, where a single trajectory overapproximates the original system's behavior under uncertainty. We propose two methods for constructing closed-loop embedding systems, which account for the interactions between the system and the controller in different ways. The interconnection-based approach considers the worst-case evolution of each coordinate separately by substituting the neural network inclusion function into the open-loop inclusion function. The interaction-based approach uses novel Jacobian-based inclusion functions to capture the first-order interactions between the open-loop system and the controller by leveraging state-of-the-art neural network verifiers. Finally, we implement our approach in a Python framework called ReachMM to demonstrate its efficiency and scalability on benchmarks and examples ranging to 200 state dimensions.

Learning0 citations2023-06-27arXiv ->

A Toolbox for Fast Interval Arithmetic in numpy with an Application to Formal Verification of Neural Network Controlled Systems

Akash Harapanahalli, Saber Jafarpour, S. Coogan

In this paper, we present a toolbox for interval analysis in numpy, with an application to formal verification of neural network controlled systems. Using the notion of natural inclusion functions, we systematically construct interval bounds for a general class of mappings. The toolbox offers efficient computation of natural inclusion functions using compiled C code, as well as a familiar interface in numpy with its canonical features, such as n-dimensional arrays, matrix/vector operations, and vectorization. We then use this toolbox in formal verification of dynamical systems with neural network controllers, through the composition of their inclusion functions.

MPC/Planning4 citations2023-05-31Paper ->

Runtime Assurance from Signal Temporal Logic Safety Specifications

Luke Baird, S. Coogan

In this paper, we propose a runtime assurance mechanism for online verification of a control system given a signal temporal logic (STL) specification that, at each time step, must hold for the remaining state trajectory. Given a nominal control input, we propose a mechanism that minimally adjusts the input at each time step in order to ensure existence of future inputs that maintain satisfaction of the STL specification. Because STL constraints generally impose requirements on future states, the runtime assurance mechanism also enforces continued satisfaction of the STL constraint evaluated at all past time steps. Lastly, to ensure a feasible input is always available, we provide a novel characterization of a persistently feasible set and require that the system state is always able to reach this set. We formulate this approach as a mixed integer convex program and demonstrate it on examples.

Robotics3 citations2023-05-31Paper ->

Safe Learning-based Predictive Control from Efficient Reachability

M. Cao, S. Coogan

We consider a dynamical system subject to a disturbance input that is an unknown function of the state. Given a target goal region, we propose a control scheme that encourages exploration of the state space in order to sample the dynamics and obtain an estimate of the unknown component while avoiding unsafe regions of the state space until the goal is able to be reached with high probability. By estimating the unknown component as a Gaussian process, we efficiently obtain hyperrectangular overapproximations of the reachable set for the system using the theory of mixed monotone systems, and these sets are improved over time as measurements of the dynamics are collected. Using these reachability estimates, we propose a model predictive scheme that avoids the unsafe region and ensures the system is always within reach of a conservative, guaranteed safe region that is given a priori, thus always ensuring feasibility until the goal is reachable. We demonstrate the approach on a model of an autonomous vehicle operating on an icy road and on a planar multirotor moving in an unknown wind field.

Other0 citations2023-05-22arXiv ->

GreenEVT: Greensboro Electric Vehicle Testbed

Gustav Nilsson, A. Aquino, S. Coogan, D. Molzahn

The ongoing electrification of the transportation fleet will increase the load on the electric power grid. Since both the transportation network and the power grid already experience periods of significant stress, joint analyses of both infrastructures will most likely be necessary to ensure acceptable operation in the future. To enable such analyses, this article presents an open-source testbed that jointly simulates high-fidelity models of both the electric distribution system and the transportation network. The testbed utilizes two open-source simulators, OpenDSS to simulate the electric distribution system and the microscopic traffic simulator SUMO to simulate the traffic dynamics. Electric vehicle charging links the electric distribution system and the transportation network models at vehicle locations determined using publicly available parcel data. Leveraging high-fidelity synthetic electric distribution system data from the SMART-DS project and transportation system data from OpenStreetMap, this testbed models the city of Greensboro, NC down to the household level. Moreover, the methodology and the supporting scripts released with the testbed allow adaption to other areas where high-fidelity geolocated OpenDSS datasets are available. After describing the components and usage of the testbed, we exemplify applications enabled by the testbed via two scenarios modeling the extreme stresses encountered during evacuations.

Learning0 citations2023-04-07arXiv ->

Contraction-Guided Adaptive Partitioning for Reachability Analysis of Neural Network Controlled Systems

Akash Harapanahalli, Saber Jafarpour, S. Coogan

In this paper, we present a contraction-guided adaptive partitioning algorithm for improving interval-valued robust reachable set estimates in a nonlinear feedback loop with a neural network controller and disturbances. Based on an estimate of the contraction rate of over-approximated intervals, the algorithm chooses when and where to partition. Then, by leveraging a decoupling of the neural network verification step and reachability partitioning layers, the algorithm can provide accuracy improvements for little computational cost. This approach is applicable with any sufficiently accurate open-loop interval-valued reachability estimation technique and any method for bounding the input-output behavior of a neural network. Using contraction-based robustness analysis, we provide guarantees of the algorithm's performance with mixed monotone reachability. Finally, we demonstrate the algorithm's performance through several numerical simulations and compare it with existing methods in the literature. In particular, we report a sizable improvement in the accuracy of reachable set estimation in a fraction of the runtime as compared to state-of-the-art methods.

Robotics12 citations2023Paper ->

Abstraction-Based Planning for Uncertainty-Aware Legged Navigation

Jesse Jiang, S. Coogan, Ye Zhao

This article addresses the problem of temporal-logic-based planning for bipedal robots in uncertain environments. We first propose an Interval Markov Decision Process abstraction of bipedal locomotion (IMDP-BL). Motion perturbations from multiple sources of uncertainty are incorporated into our model using stacked Gaussian process learning in order to achieve formal guarantees on the behavior of the system. We consider tasks which can be specified using Linear Temporal Logic (LTL). Through a product IMDP construction combining the IMDP-BL of the bipedal robot and a Deterministic Rabin Automaton (DRA) of the specifications, we synthesize control policies which allow the robot to safely traverse the environment, iteratively learning the unknown dynamics until the specifications can be satisfied with satisfactory probability. We demonstrate our methods with simulation case studies.

Theory0 citations2022-10-20arXiv ->

Monotonicity and Contraction on Polyhedral Cones

Saber Jafarpour, S. Coogan

In this note, we study monotone dynamical systems with respect to polyhedral cones. Using the half-space representation and the vertex representation, we propose three equivalent conditions to certify monotonicity of a dynamical system with respect to a polyhedral cone. We then introduce the notion of gauge norm associated with a cone and provide closed-from formulas for computing gauge norms associated with polyhedral cones. A key feature of gauge norms is that contractivity of monotone systems with respect to them can be efficiently characterized using simple inequalities. This result generalizes the well-known criteria for Hurwitzness of Metzler matrices and provides a scalable approach to search for Lyapunov functions of monotone systems with respect to polyhedral cones. Finally, we study the applications of our results in transient stability of dynamic flow networks and in scalable control design with safety guarantees.

MPC/Planning5 citations2022-09-01Paper ->

Robustly Forward Invariant Sets for Mixed-Monotone Systems

Matthew Abate, S. Coogan

Safety for dynamical systems is often posed as an invariance constraint, requiring the system trajectory to remain in some safe subset of the state-space for all time. This note presents new tools for studying reachability and set invariance for nondeterministic systems subject to a disturbance input using the theory of mixed-monotone dynamical systems. The vector field of a mixed-monotone system is characterized as being decomposable into increasing and decreasing components, which allows the dynamics to be embedded in a higher dimensional embedding system. Even though the original system is nondeterministic due to the unknown disturbance input, the embedding system has no disturbance and a single simulation of the embedding system provides bounds for reachable sets of the original dynamics. In this article, we present an efficient method for identifying robustly forward invariant and attractive sets for mixed-monotone systems by studying equilibria and their stability properties of the corresponding embedding system. We show how this approach can be applied to either the backward-time dynamics or a set of linearly transformed dynamics to establish different robustly forward invariant sets for the original dynamics, and we show also how periodic solutions to the embedding system establish invariant regions for the original dynamics as well. The findings of this work are demonstrated through two numerical examples and two case studies, including a five-dimensional planar quadrotor system.

MPC/Planning1 citations2022-08-23Paper ->

A Compartmental Dynamical Network Flow Model for Evacuation Planning of Cities

Gustav Nilsson, S. Coogan

An evacuation due to, e.g., hurricanes, floods, or forest fires often puts severe stress on the transportation network and can create congestion or grid locks. In this paper, we present an evacuation planning solution where we model the city traffic as a compartmental model. Each compartment corresponds to one Traffic Analysis Zone (TAZ). Under normal (i.e., non-evacuation) operations, there is often a heterogeneity in the transportation network, which enables the traffic dynam-ics to be modelled through Macroscopic Fundamental Diagrams (MFDs). In the evacuation case, where all the traffic travels in the same direction, the typical shape of the MFD is not present. Because of this, we propose a dynamic system with a differently shaped relationship between the traffic flow and the amount of traffic present. We then utilize the model to propose two different evacuation planning strategies, a staggered release approach and an approximate model predictive control (MPC) approach. Micro-simulator studies performed for the city of Greensboro, NC, show that by using this evacuation planning methodology the total travel time needed to evacuate the city is reduced to around half without delaying the overall time it takes to evacuate.

Other0 citations2022-06-27arXiv ->

Safe Schedule Verification for Urban Air Mobility Networks With Node Closures

Qinshuang Wei, Gustav Nilsson, S. Coogan

In urban air mobility (UAM) networks, takeoff and landing sites, called vertiports, are likely to experience intermittent closures due to, e.g., adverse weather. To ensure safety, all in-flight urban air vehicles (UAVs) in a UAM network must therefore have alternative landing sites with sufficient landing capacity in the event of a vertiport closure. In this article, we study the problem of safety verification of UAM schedules in the face of vertiport closures. We first provide necessary and sufficient conditions for a given UAM schedule to be safe in the sense that if a vertiport closure occurs, then all UAVs will be able to safely land at a backup landing site. We then extend these results to the scenario of multiple vertiport closures. Next, we convert these conditions into an efficient algorithm for verifying the safety of a UAM schedule via a linear program by using the properties of totally unimodular matrices. Our algorithm allows for uncertain travel time between UAM vertiports and scales quadratically with the number of scheduled UAVs. We demonstrate our algorithm on a UAM network with up to 1000 UAVs.

Robotics0 citations2022-06-03arXiv ->

Leveraging Heterogeneous Capabilities in Multi-Agent Systems for Environmental Conflict Resolution

M. Cao, J. Warnke, Yunhai Han, Xinpei Ni, Ye Zhao et al.

In this paper, we introduce a high-level controller synthesis framework that enables teams of heterogeneous agents to assist each other in resolving environmental conflicts that appear at runtime. This conflict resolution method is built upon temporal-logic-based reactive synthesis to guarantee safety and task completion under specific environment assumptions. In heterogeneous multi-agent systems, every agent is expected to complete its own tasks in service of a global team objective. However, at runtime, an agent may encounter un-modeled obstacles (e.g., doors or walls) that prevent it from achieving its own task. To address this problem, we employ the capabilities of other heterogeneous agents to resolve the obstacle. A controller framework is proposed to redirect agents with the capability of resolving the appropriate obstacles to the required target when such a situation is detected. Three case studies involving a bipedal robot Digit and a quadcopter are used to evaluate the controller performance in action. Additionally, we implement the proposed framework on a physical multi-agent robotic system to demonstrate its viability for real world applications.

Robotics0 citations2022-02-03arXiv ->

Safe Learning for Uncertainty-Aware Planning via Interval MDP Abstraction

Jesse Jiang, Ye Zhao, S. Coogan

We study the problem of refining satisfiability bounds for partially-known stochastic systems against planning specifications defined using syntactically co-safe Linear Temporal Logic (scLTL). We propose an abstraction-based approach that iteratively generates high-confidence Interval Markov Decision Process (IMDP) abstractions of the system from high-confidence bounds on the unknown component of the dynamics obtained via Gaussian process regression. In particular, we develop a synthesis strategy to sample the unknown dynamics by finding paths which avoid specification-violating states using a product IMDP. We further provide a heuristic to choose among various candidate paths to maximize the information gain. Finally, we propose an iterative algorithm to synthesize a satisfying control policy for the product IMDP system. We demonstrate our work with a case study on mobile robot navigation.

Other1 citations2022-01-03Paper ->

A Three-Dimensional, Quick-Running Analysis Method for Large Amplitude Liquid Slosh and Bulk Fluid Motion in Flight Vehicles

N. Andrews, S. Coogan, E. Smith, O. Ouyang, Stephen E. Reiman et al.

Learning6 citations2022Paper ->

Efficient Learning of Hyperrectangular Invariant Sets Using Gaussian Processes

M. Cao, M. Bloch, S. Coogan

We present a method for efficiently computing reachable sets and forward invariant sets for continuous-time systems with dynamics that include unknown components. Our main assumption is that, given any hyperrectangle of states, lower and upper bounds for the unknown components are available. With this assumption, the theory of mixed monotone systems allows us to formulate an efficient method for computing a hyperrectangular set that over-approximates the reachable set of the system. We then show a related approach that leads to sufficient conditions for identifying hyperrectangular sets that are forward invariant for the dynamics. We additionally show that set estimates tighten as the bounds on the unknown behavior tighten. Finally, we derive a method for satisfying our main assumption by modeling the unknown components as state-dependent Gaussian processes, providing bounds that are correct with high probability. A key benefit of our approach is to enable tractable computations for systems up to moderately high dimension that are subject to low dimensional uncertainty modeled as Gaussian processes, a class of systems that often appears in practice. We demonstrate our results on several examples, including a case study of a planar multirotor aerial vehicle.

Other3 citations2022Paper ->

Decomposition Functions for Interconnected Mixed Monotone Systems

Matthew Abate, S. Coogan

A dynamical system is mixed monotone when there exists a related decomposition function that separates the system dynamics into cooperative and competitive state interactions. Such a decomposition enables, e.g., efficient computation of robust reachable sets and forward invariant sets, but obtaining a decomposition function can be challenging. In this letter, we present a method for obtaining a decomposition function for a system that can be represented as an interconnection of subsystems with known decomposition functions. We further extend this approach using tools from interval reachability analysis to accommodate systems with outputs and we provide also conditions for when the system’s unique tight decomposition function is obtained via this approach. We demonstrate this methodology for computing decomposition functions with an example of a 3-dimensional unicycle model and with a case study of a 7-dimensional nonlinear spacecraft system defined as an interconnection of subsystems and feedback controllers. Reachable sets for the systems are then computed using their decomposition functions and the standard tools from mixed monotone systems theory.

Other2 citations2022Paper ->

Safety Verification for Urban Air Mobility Scheduling

Qinshuang Wei, Gustav Nilsson, S. Coogan

: In Urban Air Mobility (UAM) networks, takeoff and landing sites, called vertiports, are likely to experience intermittent closures due to, e.g., adverse weather. For safety, it will be required that all in-transit Urban Air Vehicles (UAVs) in a UAM network have alternative landing sites in the event of a vertiport closure. In this paper, we propose analytical conditions for developing an efficient algorithm that, given a proposed UAM schedule, verifies whether all UAVs are able to safely reach a back-up landing site in the event of a vertiport closure without violating the limited landing capacity of each vertiport in the network. If safety verification is not possible, the algorithm returns a counterexample demonstrating the violation. Our solution allows for uncertain travel time between UAM vertiports and scales quadratically with the number of scheduled UAVs. We demonstrate our algorithm on a UAM network with up to 1,000 UAVs.

Other5 citations2021-12-14Paper ->

Estimating High Probability Reachable Sets using Gaussian Processes

M. Cao, M. Bloch, S. Coogan

We present a method for computing reachable sets and forward invariant sets for systems with dynamics that include unknown components. Our main assumption is that, given any hyperrectangle of states, lower and upper bounds for the unknown components that hold with high probability are available. We then show that this assumption is well-suited when the unknown terms are modeled as state-dependent Gaussian processes. Under this assumption, we leverage the theory of mixed monotone systems and propose an efficient method for computing a hyperrectangular set that over-approximates the reachable set of the system with high probability. We then show a related approach that leads to sufficient conditions for identifying sets that are forward invariant for the dynamics with high probability. These theoretical results lead to practical algorithms for efficient computation of high probability reachable sets and invariant sets. A major advantage of our approach is that it leads to tractable computations for systems up to moderately high dimension that are subject to low dimensional uncertainty modeled as Gaussian Processes, a class of systems that appears often in practice. We demonstrate our results on an example of a six-dimensional model of a multirotor aerial vehicle.

Other3 citations2021-12-14Paper ->

Sensitivity of Electric Vehicle Charging Facility Occupancy to Users’ Impatience

Cesar Santoyo, Gustav Nilsson, S. Coogan

In this paper, we consider an electric vehicle charging facility that offers various levels of service, i.e., charging rates, for varying prices such that rational users choose a level of service based on their value of time, also called impatience. In particular, we characterize the sensitivity of the expected number of users, i.e., occupancy, at the facility to the probability distribution of users’ impatience. We first provide an upper bound for the difference between the expected occupancy under any two different distributions on users’ impatience. Next, we consider the case when the users’ impatience are discrete random variables, and we study the sensitivity of the expected occupancy to the probability masses and attained values of the random variables. We show that the expected occupancy varies linearly with respect to the probability masses and is piecewise constant with respect to the attained values. These results suggest how the facility operator might design prices such that the expected occupancy does not vary much under small changes in the distribution of users’ impatience, which is generally difficult to characterize accurately from data. We demonstrate this idea via examples.

MPC/Planning0 citations2021-11-18arXiv ->

The Strong Integral Input-to-State Stability Property in Dynamical Flow Networks

Gustav Nilsson, S. Coogan

Dynamical flow networks serve as macroscopic models for, e.g., transportation networks, queuing networks, and distribution networks. While the flow dynamics in such networks follow the conservation of mass on the links, the outflow from each link is often nonlinear due to, e.g., flow capacity constraints and simultaneous service rate constraints. Such nonlinear constraints imply a limit on the magnitude of exogenous inflow that is able to be accommodated by the network before it becomes overloaded and its state trajectory diverges. This article shows how the strong integral input-to-state stability (Strong iISS) property allows for quantifying the effects of the exogenous inflow on the flow dynamics. The Strong iISS property enables a unified stability analysis of classes of dynamical flow networks that were only partly analyzable before, such as networks with cycles, multicommodity flow networks, and networks with nonmonotone flow dynamics. We present sufficient conditions on the maximum magnitude of exogenous inflow to guarantee input-to-state stability for a dynamical flow network, and we also present cases when this sufficient condition is necessary. The conditions are exemplified on a few existing dynamical flow network models, specifically, fluid queuing models with time-varying exogenous inflows and multicommodity flow models.

  • Systems and Control42
  • Robotics33
  • Optimization and Control15
  • Machine Learning5
  • Artificial Intelligence1
  • Dynamical Systems1
  • physics.space-ph1
Systems and Control | 42 papers | 55.3% coverage
Learning0 citations2026-03-25arXiv ->

Integral Control Barrier Functions with Input Delay: Prediction, Feasibility, and Robustness

Adam K. Kiss, Ersin Das, Tamas G. Molnar, Aaron D. Ames

Time delays in feedback control loops can cause controllers to respond too late, and with excessively large corrective actions, leading to unsafe behavior (violation of state constraints) and controller infeasibility (violation of input constraints). To address this problem, we develop a safety-critical control framework for nonlinear systems with input delay using dynamically defined (integral) controllers. Building on the concept of Integral Control Barrier Functions (ICBFs), we concurrently address two fundamental challenges: compensating the effect of delays, while ensuring feasibility when state and input constraints are imposed jointly. To this end, we embed predictor feedback into a dynamically defined control law to compensate for delays, with the predicted state evolving according to delay-free dynamics. Then, utilizing ICBFs, we formulate a quadratic program for safe control design. For systems subject to simultaneous state and input constraints, we derive a closed-form feasibility condition for the resulting controller, yielding a compatible ICBF pair that guarantees forward invariance under delay. We also address robustness to prediction errors (e.g., caused by delay uncertainty) using tunable robust ICBFs. Our approach is validated on an adaptive cruise control example with actuation delay.

MPC/Planning0 citations2026-03-24arXiv ->

Universal Formula Families for Safe Stabilization of Single-Input Nonlinear Systems

Bo Wang, Miroslav Krstic

We develop an optimization-free framework for safe stabilization of single-input control-affine nonlinear systems with a given control Lyapunov function (CLF) and a given control barrier function (CBF), where the desired equilibrium lies in the interior of the safe set. An explicit compatibility condition is derived that is necessary and sufficient for the pointwise simultaneous satisfaction of the CLF and CBF inequalities. When this condition holds, two closed-form continuous state-feedback laws are constructed from the Lie-derivative data of the CLF and CBF via standard universal stabilizer formulas, yielding asymptotic stabilization of the origin and forward invariance of the interior of the safe set, without online quadratic programming. The two laws belong to broader families parametrized by a free nondecreasing function, providing additional design flexibility. When the compatibility condition fails, a safety-prioritizing modification preserves forward invariance and drives the state toward the safe-set boundary until a compatible region is reached, whereupon continuity at the origin and asymptotic stabilization are recovered. The framework produces families of explicit constructive alternatives to CLF-CBF quadratic programming for scalar-input nonlinear systems.

MPC/Planning0 citations2026-03-23arXiv ->

Finite-time Convergent Control Barrier Functions with Feasibility Guarantees

Anni Li, Yingqing Chen, Christos G. Cassandras, Wei Xiao

This paper studies the problem of finite-time convergence to a prescribed safe set for nonlinear systems whose initial states violate the safety constraints. Existing Control Lyapunov-Barrier Functions (CLBFs) can enforce recovery to the safe set but may suffer from the issue of chattering and they do not explicitly consider control bounds. To address these limitations, we propose a new Control Barrier Function (CBF) formulation that guarantees finite-time convergence to the safe set while ensuring feasibility under control constraints. Specifically, we strengthen the initially violated safety constraint by introducing a parameter which enables the exploitation of the asymptotic property of a CBF to converge to the safe set in finite time. Furthermore, the conditions for the existence of such a CBF under control bounds to achieve finite-time convergence are derived via reachability analysis and constraint comparison, providing a systematic approach for parameter design. A case study on 2D obstacle avoidance is presented to demonstrate the effectiveness and advantages of the proposed method.

Robotics0 citations2026-03-23arXiv ->

Interaction-Aware Predictive Environmental Control Barrier Function for Emergency Lane Change

Ying Shuai Quan, Paolo Falcone, Jonas Sjöberg

Safety-critical motion planning in mixed traffic remains challenging for autonomous vehicles, especially when it involves interactions between the ego vehicle (EV) and surrounding vehicles (SVs). In dense traffic, the feasibility of a lane change depends strongly on how SVs respond to the EV motion. This paper presents an interaction-aware safety framework that incorporates such interactions into a control barrier function (CBF)-based safety assessment. The proposed method predicts near-future vehicle positions over a finite horizon, thereby capturing reactive SV behavior and embedding it into the CBF-based safety constraint. To address uncertainty in the SV response model, a robust extension is developed by treating the model mismatch as a bounded disturbance and incorporating an online uncertainty estimate into the barrier condition. Compared with classical environmental CBF methods that neglect SV reactions, the proposed approach provides a less conservative and more informative safety representation for interactive traffic scenarios, while improving robustness to uncertainty in the modeled SV behavior.

Robotics0 citations2026-03-22arXiv ->

Koopman Meets Discrete-Time Control Barrier Functions: A Linear Model Predictive Control Framework

Shuo Liu, Liang Wu, Dawei Zhang, Jan Drgona, Calin. A. Belta

This paper proposes a Koopman-based linear model predictive control (LMPC) framework for safety-critical control of nonlinear discrete-time systems. Existing MPC formulations based on discrete-time control barrier functions (DCBFs) enforce safety through barrier constraints but typically result in computationally demanding nonlinear programming. To address this challenge, we construct a DCBF-augmented dynamical system and employ Koopman operator theory to lift the nonlinear dynamics into a higher-dimensional space where both the system dynamics and the barrier function admit a linear predictor representation. This enables the transformation of the nonlinear safety-constrained MPC problem into a quadratic program (QP). To improve feasibility while preserving safety, a relaxation mechanism with slack variables is introduced for the barrier constraints. The resulting approach combines the modeling capability of Koopman operators with the computational efficiency of QP. Numerical simulations on a navigation task for a robot with nonlinear dynamics demonstrate that the proposed framework achieves safe trajectory generation and efficient real-time control.

Other0 citations2026-03-20arXiv ->

A Spectral Perspective on Stochastic Control Barrier Functions

Inkyu Jang, Chams E. Mballo, Claire J. Tomlin, H. Jin Kim

Stochastic control barrier functions (SCBFs) provide a safety-critical control framework for systems subject to stochastic disturbances by bounding the probability of remaining within a safe set. However, synthesizing a valid SCBF that explicitly reflects the true safety probability of the system, which is the most natural measure of safety, remains a challenge. This paper addresses this issue by adopting a spectral perspective, utilizing the linear operator that governs the evolution of the closed-loop system's safety probability. We find that the dominant eigenpair of this Koopman-like operator encodes fundamental safety information of the stochastic system. The dominant eigenfunction is a natural and valid SCBF, with values that explicitly quantify the relative long-term safety of the state, while the dominant eigenvalue indicates the global rate at which the safety probability decays. A practical synthesis algorithm is proposed, termed power-policy iteration, which jointly computes the dominant eigenpair and an optimized backup policy. The method is validated using simulation experiments on safety-critical dynamics models.

Robotics0 citations2026-03-19arXiv ->

Exact-Time Safety Recovery using Time-Varying Control Barrier Functions with Optimal Barrier Tracking

Yingqing Chen, Christos G. Cassandras, Wei Xiao, Anni Li

This paper is motivated by controllers developed for autonomous vehicles which occasionally result into conditions where safety is no longer guaranteed. We develop an exact-time safety recovery framework for any control-affine nonlinear system when its state is outside a safe region using time-varying Control Barrier Functions (CBFs) with optimal barrier tracking. Unlike conventional formulations that provide only conservative upper bounds on recovery time convergence, the proposed approach guarantees recovery to the safe set at a prescribed time. The key mechanism is an active barrier tracking condition that forces the barrier function to follow exactly a designer-specified recovery trajectory. This transforms safety recovery into a trajectory design problem. The recovery trajectory is parameterized and optimized to achieve optimal performance while preserving feasibility under input constraints, avoiding the aggressive corrective actions typically induced by conventional finite-time formulations. The safety recovery framework is applied to the roundabout traffic coordination problem for Connected and Automated Vehicles (CAVs), where any initially violated safe merging constraint is replaced by an exact-time recovery barrier constraint to ensure safety guarantee restoration before CAV conflict points are reached. Simulation results demonstrate improved feasibility and performance.

MPC/Planning0 citations2026-03-19arXiv ->

Safety-Guaranteed Imitation Learning from Nonlinear Model Predictive Control for Spacecraft Close Proximity Operations

Alexander Meinert, Niklas Baldauf, Peter Stadler, Alen Turnwald

This paper presents a safety-guaranteed, runtime-efficient imitation learning framework for spacecraft close proximity control. We leverage Control Barrier Functions (CBFs) for safety certificates and Control Lyapunov Functions (CLFs) for stability as unified design principles across data generation, training, and deployment. First, a nonlinear Model Predictive Control (NMPC) expert enforces CBF constraints to provide safe reference trajectories. Second, we train a neural policy with a novel CBF-CLF-informed loss and DAgger-like rollouts with curriculum weighting, promoting data-efficiency and reducing future safety filter interventions. Third, at deployment a lightweight one-step CBF-CLF quadratic program minimally adjusts the learned control input to satisfy hard safety constraints while encouraging stability. We validate the approach for ESA-compliant close proximity operations, including fly-around with a spherical keep-out zone and final approach inside a conical approach corridor, using the Basilisk high-fidelity simulator with nonlinear dynamics and perturbations. Numerical experiments indicate stable convergence to decision points and strict adherence to safety under the filter, with task performance comparable to the NMPC expert while significantly reducing online computation. A runtime analysis demonstrates real-time feasibility on a commercial off-the-shelf processor, supporting onboard deployment for safety-critical on-orbit servicing.

Theory0 citations2026-03-19arXiv ->

Mean-field control barrier functions for stochastic multi-agent systems

Cinzia Tomaselli, Gian Carlo Maffettone, Samy Wu Fung, Levon Nurbekyan, Mario di Bernardo

Many applications involving multi-agent systems require fulfilling safety constraints. Control barrier functions offer a systematic framework to enforce forward invariance of safety sets. Recent work extended this paradigm to mean-field scenarios, where the number of agents is large enough to make density-space descriptions a reasonable workaround for the curse of dimensionality. However, an open gap in the recent literature concerns the development of mean-field control barrier functions for Fokker-Planck (advection-diffusion) equations. In this work, we address this gap, enabling safe mean-field control of agents with stochastic microscopic dynamics. We provide bounded stability guarantees under safety corrections and corroborate our results through numerical simulations in two representative scenarios, coverage and shepherding control of multi-agent systems.

Theory0 citations2026-03-19arXiv ->

Generalizations of Backup Control Barrier Functions: Expansion and Adaptation for Input-Bounded Safety-Critical Control

David E. J. van Wijk, Dohyun Lee, Ersin Das, Tamas G. Molnar, Aaron D. Ames et al.

Guaranteeing the safety of nonlinear systems with bounded inputs remains a key challenge in safe autonomy. Backup control barrier functions (bCBFs) provide a powerful mechanism for constructing controlled invariant sets by propagating trajectories under a pre-verified backup controller to a forward invariant backup set. While effective, the standard bCBF method utilizes the same backup controller for both set expansion and safety certification, which can restrict the expanded safe set and lead to conservative dynamic behavior. In this study, we generalize the bCBF framework by separating the set-expanding controller from the verified backup controller, thereby enabling a broader class of expansion strategies while preserving formal safety guarantees. We establish sufficient conditions for forward invariance of the resulting implicit safe set and show how the generalized construction recovers existing bCBF methods as special cases. Moreover, we extend the proposed framework to parameterized controller families, enabling online adaptation of the expansion controller while maintaining safety guarantees in the presence of input bounds.

Other0 citations2026-03-19arXiv ->

Topological Obstructions to the Existence of Control Barrier Functions

Massimiliano de Sa, Aaron D. Ames

In 1983, Brockett developed a topological necessary condition for the existence of continuous, asymptotically stabilizing control laws. Building upon recent work on necessary conditions for set stabilization, we develop Brockett-like necessary conditions for the existence of control barrier functions (CBFs). By leveraging the unique geometry of CBF safe sets, we provide simple and self-contained derivations of necessary conditions for the existence of CBFs and their safe, continuous controllers. We demonstrate the application of these conditions to instructive examples and kinematic nonholonomic systems, and discuss their relationship to Brockett's necessary condition.

MPC/Planning0 citations2026-03-18arXiv ->

Robust Dynamic Pricing and Admission Control with Fairness Guarantees

Yingqing Chen, Anni Li, Christos G. Cassandras, Homayoun Hamedmoghadam, Fabian Wirth et al.

Dynamic pricing is commonly used to regulate congestion in shared service systems. This paper is motivated by the fact that in the presence of users with varying price sensitivity (responsiveness), conventional monotonic pricing can lead to unfair outcomes by disproportionately excluding price-elastic users, particularly under high or uncertain demand. We therefore develop a fairness-oriented mechanism under demand uncertainty. The paper's contributions are twofold. First, we show that when fairness is imposed as a hard state constraint, the optimal (revenue maximizing) pricing policy is generally non-monotonic in demand. This structural result departs fundamentally from standard surge pricing rules and reveals that price reduction under heavy load may be necessary to maintain equitable access. Second, we address the problem that price elasticity among heterogeneous users is unobservable. To solve it, we develop a robust dynamic pricing and admission control framework that enforces capacity and fairness constraints for all user type distributions consistent with aggregate measurements. By integrating integral High Order Control Barrier Functions (iHOCBFs) with a robust optimization framework under uncertain user-type distribution, we obtain a controller that guarantees forward invariance of safety and fairness constraints while optimizing revenue. Numerical experiments demonstrate improved fairness and revenue performance relative to monotonic surge pricing policies.

Other0 citations2026-03-17arXiv ->

Enforcing Mixed State-Input Constraints with Multiple Backup Control Barrier Functions: A Projection-based Approach

Laszlo Gacsi, Adam K. Kiss, Ersin Das, Tamas G. Molnar

Ensuring the safety of control systems often requires the satisfaction of constraints on states (such as position or velocity), control inputs (such as force), and a mixture of states and inputs (such as power that depends on both velocity and force). This paper presents a safety-critical control framework for enforcing mixed state-input constraints through a generalization of backup control barrier functions (backup CBFs). First, we extend the backup CBF approach to maintain multiple decoupled state and input constraints using a single backup set-backup controller pair. Second, we address mixed state-input constraints by converting them into state constraints using a projection from the state-input space to the state space along the backup controller. In the special case of decoupled state and input constraints, the proposed method simplifies the synthesis of backup CBFs by eliminating the need for saturating backup control laws. Finally, we demonstrate the efficacy of the proposed method on an inverted pendulum example, where constraints on the angle (state), torque (input), and power (mixture of state and input) are satisfied simultaneously.

Other0 citations2026-03-17arXiv ->

Constricting Tubes for Prescribed-Time Safe Control

Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti

We propose a constricting Control Barrier Function (CBF) framework for prescribed-time control of control-affine systems with input constraints. Given a system starting outside a target safe set, we construct a time-varying safety tube that shrinks from a relaxed set containing the initial condition to the target set at a user-specified deadline. Any controller rendering this tube forward invariant guarantees prescribed-time recovery by construction. The constriction schedule is bounded and tunable by design, in contrast to prescribed-time methods where control effort diverges near the deadline. Feasibility under input constraints reduces to a single verifiable condition on the constriction rate, yielding a closed-form minimum recovery time as a function of control authority and initial violation. The framework imposes a single affine constraint per timestep regardless of state dimension, scaling to settings where grid-based reachability methods are intractable. We validate on a 16-dimensional multi-agent system and a unicycle reach-avoid problem, demonstrating prescribed-time recovery with bounded control effort.

Theory0 citations2026-03-17arXiv ->

Near-Optimal Constrained Feedback Control of Nonlinear Systems via Approximate HJB and Control Barrier Functions

Milad Alipour Shahraki, Laurent Lessard

This paper presents a two-stage framework for constrained near-optimal feedback control of input-affine nonlinear systems. An approximate value function for the unconstrained control problem is computed offline by solving the Hamilton--Jacobi--Bellman equation. Online, a quadratic program is solved that minimizes the associated approximate Hamiltonian subject to safety constraints imposed via control barrier functions. Our proposed architecture decouples performance from constraint enforcement, allowing constraints to be modified online without recomputing the value function. Validation on a linear 2-state 1D hovercraft and a nonlinear 9-state spacecraft attitude control problem demonstrates near-optimal performance relative to open-loop optimal control benchmarks and superior performance compared to control Lyapunov function-based controllers.

MPC/Planning0 citations2026-03-17arXiv ->

Eliminating Persistent Boundary Residence via Matrosov-Type Auxiliary Functions

Tianyu Han, Guangwei Wang, Bo Wang

Control barrier functions enforce safety by guaranteeing forward invariance of an admissible set. Under standard (non-strict) barrier conditions, however, forward invariance alone does not prevent trajectories from remaining on the boundary of the safe set for arbitrarily long time intervals, potentially leading to boundary sticking or deadlock phenomena. This paper studies the elimination of persistent boundary residence under forward-invariant barrier conditions. Inspired by Matrosov-type arguments, we introduce an auxiliary function framework that preserves forward invariance while excluding infinite-time residence within boundary layers. Sufficient conditions are established under which any trajectory can only remain in a prescribed neighborhood of the boundary for finite time, thereby restoring boundary-level liveness without altering forward invariance. The proposed construction does not rely on singular barrier formulations or controller-specific modifications, and can be incorporated into standard safety-critical control architectures. Numerical examples illustrate the removal of boundary sticking behaviors while maintaining safety across representative systems.

Learning0 citations2026-03-16arXiv ->

Multi-Scale Control of Large Agent Populations: From Density Dynamics to Individual Actuation

Mario di Bernardo

We review a body of recent work by the author and collaborators on controlling the spatial organisation of large agent populations across multiple scales. A central theme is the systematic bridging of microscopic agent-level dynamics and macroscopic density descriptions, enabling control design at the most natural level of abstraction and subsequent translation across scales. We show how this multi-scale perspective provides a unified approach to both \emph{direct control}, where every agent is actuated, and \emph{indirect control}, where few leaders or herders steer a larger uncontrolled population. The review covers continuification-based control with robustness under limited sensing and decentralised implementation via distributed density estimation; leader--follower density regulation with dual-feedback stability guarantees and bio-inspired plasticity; optimal-transport methods for coverage control and macro-to-micro discretisation; nonreciprocal field theory for collective decision-making; mean-field control barrier functions for population-level safety; and hierarchical reinforcement learning for settings where closed-form solutions are intractable. Together, these results demonstrate the breadth and versatility of a multi-scale control framework that integrates analytical methods, learning, and physics-inspired approaches for large agent populations.

Learning0 citations2026-03-15arXiv ->

Robust Safety Filters for Lipschitz-Bounded Adaptive Closed-Loop Systems with Structured Uncertainties

Johannes Autenrieb, Peter A. Fisher, Anuradha Annaswamy

Adaptive control provides closed-loop stability and reference tracking for uncertain dynamical systems through online parameter adaptation. These properties alone, however, do not ensure safety in the sense of forward invariance of state constraints, particularly during transient phases of adaptation. Control barrier function (CBF)-based safety filters have been proposed to address this limitation, but existing approaches often rely on conservative constraint tightening or static safety margins within quadratic program formulations. This paper proposes a reference-based adaptive safety framework for systems with structured parametric uncertainty that explicitly accounts for transient plant-reference mismatch. Safety is enforced at the reference level using a barrier-function-based filter, while adaptive control drives the plant to track the safety-certified reference. By exploiting Lipschitz bounds on the closed-loop error dynamics, a robust CBF condition is derived and reformulated as a convex second-order cone program (SOCP). The resulting approach reduces conservatism while preserving formal guarantees of forward invariance, stability, and tracking.

Robotics0 citations2026-03-13arXiv ->

Verification and Forward Invariance of Control Barrier Functions for Differential-Algebraic Systems

Hongchao Zhang, Mohamad H. Kazma, Meiyi Ma, Taylor T. Johnson, Ahmad F. Taha

Differential-algebraic equations (DAEs) arise in power networks, chemical processes, and multibody systems, where algebraic constraints encode physical conservation laws. The safety of such systems is critical, yet safe control is challenging because algebraic constraints restrict allowable state trajectories. Control barrier functions (CBFs) provide computationally efficient safety filters for ordinary differential equation (ODE) systems. However, existing CBF methods are not directly applicable to DAEs due to potential conflicts between the CBF condition and the constraint manifold. This paper introduces DAE-aware CBFs that incorporate the differential-algebraic structure through projected vector fields. We derive conditions that ensure forward invariance of safe sets while preserving algebraic constraints and extend the framework to higher-index DAEs. A systematic verification framework is developed, establishing necessary and sufficient conditions for geometric correctness and feasibility of DAE-aware CBFs. For polynomial systems, sum-of-squares certificates are provided, while for nonpolynomial and neural network candidates, satisfiability modulo theories are used for falsification. The approach is validated on wind turbine and flexible-link manipulator systems.

Learning0 citations2026-03-11arXiv ->

Distributed Safety Critical Control among Uncontrollable Agents using Reconstructed Control Barrier Functions

Yuzhang Peng, Wei Wang, Jiaqi Yan, Mengze Yu

This paper investigates the distributed safety critical control for multi-agent systems (MASs) in the presence of uncontrollable agents with uncertain behaviors. To ensure system safety, the control barrier function (CBF) is employed in this paper. However, a key challenge is that the CBF constraints are coupled when MASs perform collaborative tasks, which depend on information from multiple agents and impede the design of a fully distributed safe control scheme. To overcome this, a novel reconstructed CBF approach is proposed. In this method, the coupled CBF is reconstructed by leveraging state estimates of other agents obtained from a distributed adaptive observer. Furthermore, a prescribed performance adaptive parameter is designed to modify this reconstruction, ensuring that satisfying the reconstructed CBF constraint is sufficient to meet the original coupled one. Based on the reconstructed CBF, we design a safety-critical quadratic programming (QP) controller and prove that the proposed distributed control scheme rigorously guarantees the safety of the MAS, even in the uncertain dynamic environments involving uncontrollable agents. The effectiveness of the proposed method is illustrated through a simulation.

MPC/Planning0 citations2026-03-09arXiv ->

SEP-NMPC: Safety Enhanced Passivity-Based Nonlinear Model Predictive Control for a UAV Slung Payload System

Seyedreza Rezaei, Junjie Kang, Amaldev Haridevan, Jinjun Shan

Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a Safety Enhanced Passivity-Based Nonlinear MPC (SEP-NMPC) that provides formal guarantees of stability and safety for a quadrotor transporting a slung payload through cluttered environments. Stability is enforced by embedding a strict passivity inequality, which is derived from a shaped energy storage function with adaptive damping, directly into the NMPC. This formulation dissipates excess energy and ensures asymptotic convergence despite payload swings. Safety is guaranteed through high-order control barrier functions (HOCBFs) that render user-defined clearance sets forward-invariant, obliging both the quadrotor and the swinging payload to maintain separation while interacting with static and dynamic obstacles. The optimization remains quadratic-program compatible and is solved online at each sampling time without gain scheduling or heuristic switching. Extensive simulations and real-world experiments confirm stable payload transport, collision-free trajectories, and real-time feasibility across all tested scenarios. The SEP-NMPC framework therefore unifies passivity-based closed-loop stability with HOCBF-based safety guarantees for UAV slung-payload transportation.

Robotics0 citations2026-03-07arXiv ->

Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions

Taekyung Kim

This tutorial provides a critical review of the practical application of Control Barrier Functions (CBFs) in robotic safety. While the theoretical foundations of CBFs are well-established, I identify a recurring gap between the mathematical assumption of a safe controller's existence and its constructive realization in systems with input constraints. I highlight the distinction between candidate and valid CBFs by analyzing the interplay of system dynamics, actuation limits, and class-K functions. I further show that some purported demonstrations of safe robot policies or controllers are limited to passively safe systems, such as single integrators or kinematic manipulators, where safety is already inherited from the underlying physics and even naive geometric hard constraints suffice to prevent collisions. By revisiting simple low-dimensional examples, I show when CBF formulations provide valid safety guarantees and when they fail due to common misuses. I then provide practical guidelines for constructing realizable safety arguments for systems without such passive safety. The goal of this tutorial is to bridge the gap between theoretical guarantees and actual implementation, supported by an open-source interactive web demonstration that visualizes these concepts intuitively.

Robotics0 citations2026-03-06arXiv ->

CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments

Bojan Derajić, Sebastian Bernhard, Wolfgang Hönig

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are easy to deploy but difficult to design. Motivated by the shortcomings of existing learning- and model-based methods, we propose a simple yet effective neural CBF design method for safe robot navigation in dynamic environments. We employ the idea of a composite CBF, where multiple neural CBFs are combined into a single CBF. The individual CBFs are trained via the Hamilton-Jacobi reachability framework to approximate the optimal safe set for single moving obstacles. Additionally, we use the residual neural architecture, which guarantees that the estimated safe set does not intersect with the corresponding failure set. The method is extensively evaluated in simulation experiments for a ground robot and a quadrotor, comparing it against several baseline methods. The results show improved success rates of up to 18\% compared to the best baseline, without increasing the conservativeness of the motion. Also, the method is demonstrated in hardware experiments for both types of robots.

Robotics0 citations2026-03-06arXiv ->

Control Barrier Corridors: From Safety Functions to Safe Sets

Ömür Arslan, Nikolay Atanasov

Safe autonomy is a critical requirement and a key enabler for robots to operate safely in unstructured complex environments. Control barrier functions and safe motion corridors are two widely used but technically distinct safety methods, functional and geometric, respectively, for safe motion planning and control. Control barrier functions are applied to the safety filtering of control inputs to limit the decay rate of system safety, whereas safe motion corridors are geometrically constructed to define a local safe zone around the system state for use in motion optimization and reference-governor design. This paper introduces a new notion of control barrier corridors, which unifies these two approaches by converting control barrier functions into local safe goal regions for reference goal selection in feedback control systems. We show, with examples on fully actuated systems, kinematic unicycles, and linear output regulation systems, that individual state safety can be extended locally over control barrier corridors for convex barrier functions, provided the control convergence rate matches the barrier decay rate, highlighting a trade-off between safety and reactiveness. Such safe control barrier corridors enable safely reachable persistent goal selection over continuously changing barrier corridors during system motion, which we demonstrate for verifiably safe and persistent path following in autonomous exploration of unknown environments.

Other0 citations2026-03-05arXiv ->

Combinatorial Safety-Critical Coordination of Multi-Agent Systems via Mixed-Integer Responsibility Allocation and Control Barrier Functions

Johannes Autenrieb, Mark Spiller, Hyo-Sang Shin, Namhoon Cho

This paper presents a hybrid safety-critical coordination architecture for multi-agent systems operating in dense environments. While control barrier functions (CBFs) provide formal safety guarantees, decentralized implementations typically rely on ego-centric safety filtering and may lead to redundant constraint enforcement and conservative collective behavior. To address this limitation, we introduce a combinatorial coordination layer formulated as a mixed-integer linear program (MILP) that assigns collision-avoidance responsibilities among agents. By explicitly distributing enforcement tasks, redundant reactions are eliminated and computational complexity is reduced. Each agent subsequently solves a reduced local quadratic program enforcing only its assigned constraints.

Theory0 citations2026-03-04arXiv ->

Local Safety Filters for Networked Systems via Two-Time-Scale Design

Emiliano Dall'Anese

Safety filters based on Control Barrier Functions (CBFs) provide formal guarantees of forward invariance, but are often difficult to implement in networked dynamical systems. This is due to global coupling and communication requirements. This paper develops locally implementable approximations of networked CBF safety filters that require no coordination across subsystems. The proposed approach is based on a two-time-scale dynamic implementation inspired by singular perturbation theory, where a small parameter $ε$ separates fast filter dynamics from the plant dynamics; then, a local implementation is enabled via derivative estimation. Explicit bounds are derived to quantify the mismatch between trajectories of the systems with dynamic filter and with the ideal centralized safety filter. These results characterize how safety degradation depends on the time-scale parameter $ε$, estimation errors, and filter activation time, thereby quantifying trade-offs between safety guarantees and local implementability.

Theory0 citations2026-03-03arXiv ->

Designing Barrier Functions for Graceful Safety Control

Yejin Moon, Gabor Orosz, Hosam K. Fathy

This paper examines the problem of achieving "grace" when controlling dynamical systems for safety, which is defined in terms of providing multi-layered safety assurances. Namely, two safety layers are created: a primary layer that represents a desirable degree of safety, and a secondary failsafe layer. Graceful control then involves ensuring that even if the primary layer is breached, the failsafe layer remains forward invariant. The paper pursues this goal by constructing a safety constraint that combines the concepts of zeroing and reciprocal control barrier functions with regard to the primary and secondary safe sets, respectively. This constraint is analogous to a stiffening spring, making it possible to construct energy-based analytical proofs of the resulting graceful safety guarantees. The proposed approach is developed for systems with a relative degree of either 1 or 2, the latter case being particularly useful for mechanical systems. We demonstrate the applicability of the method using a wall collision avoidance example. This demonstration highlights the benefits of the proposed approach compared to traditional benchmarks from the literature.

Learning0 citations2026-03-03arXiv ->

Grid-Forming Control with Assignable Voltage Regulation Guarantees and Safety-Critical Current Limiting

Bhathiya Rathnayake, Sijia Geng

This paper develops a nonlinear grid-forming (GFM) controller with provable voltage-formation guarantees, with over-current limiting enforced via a control-barrier-function (CBF)-based safety filter. The nominal controller follows a droop-based inner-outer architecture, in which voltage references and frequency are generated by droop laws, an outer-loop voltage controller produces current references using backstepping (BS), and an inner-loop current controller synthesizes the terminal voltage. The grid voltage is treated as an unknown bounded disturbance, without requiring knowledge of its bound, and the controller design does not rely on any network parameters beyond the point of common coupling (PCC). To robustify voltage formation against the grid voltage, a deadzone-adapted disturbance suppression (DADS) framework is incorporated, yielding practical voltage regulation characterized by asymptotic convergence of the PCC voltage errors to an assignably small and known residual set. Furthermore, the closed-loop system is proven to be globally well posed, with all physical and adaptive states bounded and voltage error transients (due to initial conditions) decaying exponentially at an assignable rate. On top of the nominal controller, hard over-current protection is achieved through a minimally invasive CBF-based safety filter that enforces strict current limits via a single-constraint quadratic program. The safety filter is compatible with any locally Lipschitz nominal controller. Rigorous analysis establishes forward invariance of the safe-current set and boundedness of all states under current limiting. Numerical results demonstrate improved transient performance and faster recovery during current-limiting events when the proposed DADS-BS controller is used as the nominal control law, compared with conventional PI-based GFM control.

Learning0 citations2026-03-03arXiv ->

Event-Driven Safe and Resilient Control of Automated and Human-Driven Vehicles under EU-FDI Attacks

Yi Zhang, Yichao Wang, Wei Xiao, Mohamadamin Rajabinezhad, Shan Zuo

This paper studies the safe and resilient control of Connected and Automated Vehicles (CAVs) operating in mixed traffic environments where they must interact with Human-Driven Vehicles (HDVs) under uncertain dynamics and exponentially unbounded false data injection (EU-FDI) attacks. These attacks pose serious threats to safety-critical applications. While resilient control strategies can mitigate adversarial effects, they often overlook collision avoidance requirements. Conversely, safety-critical approaches tend to assume nominal operating conditions and lack resilience to adversarial inputs. To address these challenges, we propose an event-driven safe and resilient (EDSR) control framework that integrates event-driven Control Barrier Functions (CBFs) and Control Lyapunov Functions (CLFs) with adaptive attack-resilient control. The framework further incorporates data-driven estimation of HDV behaviors to ensure safety and resilience against EU-FDI attacks. Specifically, we focus on the lane-changing maneuver of CAVs in the presence of unpredictable HDVs and EU-FDI attacks on acceleration inputs. The event-driven approach reduces computational load while maintaining real-time safety guarantees. Simulation results, including comparisons with conventional safety-critical control methods that lack resilience, validate the effectiveness and robustness of the proposed EDSR framework in achieving collision-free maneuvers, stable velocity regulation, and resilient operation under adversarial conditions.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

Theory0 citations2021-03-14arXiv ->

Safe Controller Synthesis With Tunable Input-to-State Safe Control Barrier Functions

Anil Alan, Andrew J. Taylor, C. He, G. Orosz, A. Ames

To bring complex systems into real world environments in a safe manner, they will have to be robust to uncertainties—both in the environment and the system. This letter investigates the safety of control systems under input disturbances, wherein the disturbances can capture uncertainties in the system. Safety, framed as forward invariance of sets in the state space, is ensured with the framework of control barrier functions (CBFs). Concretely, the definition of input-to-state safety (ISSf) is generalized to allow the synthesis of non-conservative, tunable controllers that are provably safe under varying disturbances. This is achieved by formulating the concept of tunable input-to-state safe control barrier functions (TISSf-CBFs), which guarantee safety for disturbances that vary with state and, therefore, provide less conservative means of accommodating uncertainty. The theoretical results are demonstrated with a simple control system with input disturbance and also applied to design a safe connected cruise controller for a heavy duty truck.

Robotics0 citations2020-10-19arXiv ->

Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance

Andrew W. Singletary, Karl Klingebiel, Joseph R. Bourne, Andrew W. Browning, P. Tokumaru et al.

Artificial potential fields (APFs) and their variants have been a staple for collision avoidance of mobile robots and manipulators for almost 40 years. Its model-independent nature, ease of implementation, and real-time performance have played a large role in its continued success over the years. Control barrier functions (CBFs), on the other hand, are a more recent development, commonly used to guarantee safety for nonlinear systems in real-time in the form of a filter on a nominal controller. In this paper, we address the connections between APFs and CBFs. At a theoretic level, we show that given a broad class of APFs, one can construct a CBF that guarantees safety. Additionally, we prove that CBFs obtained from these APFs have additional beneficial properties and can be applied to nonlinear systems. Practically, we compare the performance of APFs and CBFs in the context of obstacle avoidance on simple illustrative examples and for a quadrotor with unknown dynamics, both in simulation and on hardware using onboard sensing.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Robotics0 citations2020-03-10arXiv ->

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach

M. Srinivasan, A. Dabholkar, S. Coogan, P. Vela

Control barrier functions are mathematical constructs used to guarantee safety for robotic systems. When integrated as constraints in a quadratic programming optimization problem, instantaneous control synthesis with real-time performance demands can be achieved for robotics applications. Prevailing use has assumed full knowledge of the safety barrier functions, however there are cases where the safe regions must be estimated online from sensor measurements. In these cases, the corresponding barrier function must be synthesized online. This paper describes a learning framework for estimating control barrier functions from sensor data. Doing so affords system operation in unknown state space regions without compromising safety. Here, a support vector machine classifier provides the barrier function specification as determined by sets of safe and unsafe states obtained from sensor measurements. Theoretical safety guarantees are provided. Experimental ROS-based simulation results for an omnidirectional robot equipped with LiDAR demonstrate safe operation.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Learning0 citations2019-10-01arXiv ->

Adaptive Safety with Control Barrier Functions

Andrew J. Taylor, A. Ames

Adaptive Control Lyapunov Functions (aCLFs) were introduced 20 years ago, and provided a Lyapunov-based methodology for stabilizing systems with parameter uncertainty. The goal of this paper is to revisit this classic formulation in the context of safety-critical control. This will motivate a variant of aCLFs in the context of safety: adaptive Control Barrier Functions (aCBFs). Our proposed approach adaptively achieves safety by keeping the system’s state within a safe set even in the presence of parametric model uncertainty. We unify aCLFs and aCBFs into a single control methodology for systems with uncertain parameters in the context of a Quadratic Program (QP) based framework. We validate the ability of this unified framework to achieve stability and safety in an Adaptive Cruise Control (ACC) simulation.

Robotics2120 citations2019-03-27arXiv ->

Control Barrier Functions: Theory and Applications

A. Ames, S. Coogan, M. Egerstedt, Gennaro Notomista, K. Sreenath et al.

This paper provides an introduction and overview of recent work on control barrier functions and their use to verify and enforce safety properties in the context of (optimization based) safety-critical controllers. We survey the main technical results and discuss applications to several domains including robotic systems.

Learning0 citations2019-03-12arXiv ->

Control Barrier Functions for Systems with High Relative Degree

Wei Xiao, C. Belta

This paper extends control barrier functions (CBFs) to high order control barrier functions (HOCBFs) that can be used for high relative degree constraints. The proposed HOCBFs are more general than recently proposed (exponential) HOCBFs. We introduce high order barrier functions (HOBFs), and show that their satisfaction of Lyapunov-like conditions implies the forward invariance of the intersection of a series of sets. We then introduce HOCBF, and show that any control input that satisfies the HOCBF constraint renders the intersection of a series of sets forward invariant. We formulate optimal control problems with constraints given by HOCBF and control Lyapunov functions (CLF), and provide a promising method to address the conflict between HOCBF constraints and control limitations by penalizing the class $\mathcal{K}$ functions. We illustrate the proposed method on an adaptive cruise control problem.

MPC/Planning649 citations2016-12-05arXiv ->

Robustness of Control Barrier Functions for Safety Critical Control

Xiangru Xu, P. Tabuada, J. Grizzle, A. Ames

Abstract Barrier functions (also called certificates) have been an important tool for the verification of hybrid systems, and have also played important roles in optimization and multi-objective control. The extension of a barrier function to a controlled system results in a control barrier function. This can be thought of as being analogous to how Sontag extended Lyapunov functions to control Lypaunov functions in order to enable controller synthesis for stabilization tasks. A control barrier function enables controller synthesis for safety requirements specified by forward invariance of a set using a Lyapunov-like condition. This paper develops several important extensions to the notion of a control barrier function. The first involves robustness under perturbations to the vector field defining the system. Input-to-State stability conditions are given that provide for forward invariance, when disturbances are present, of a “relaxation” of set rendered invariant without disturbances. A control barrier function can be combined with a control Lyapunov function in a quadratic program to achieve a control objective subject to safety guarantees. The second result of the paper gives conditions for the control law obtained by solving the quadratic program to be Lipschitz continuous and therefore to gives rise to well-defined solutions of the resulting closed-loop system.

Robotics | 33 papers | 43.4% coverage
Robotics0 citations2026-03-25arXiv ->

MIRROR: Visual Motion Imitation via Real-time Retargeting and Teleoperation with Parallel Differential Inverse Kinematics

Junheng Li, Lizhi Yang, Aaron D. Ames

Real-time humanoid teleoperation requires inverse kinematics (IK) solvers that are both responsive and constraint-safe under kinematic redundancy and self-collision constraints. While differential IK enables efficient online retargeting, its locally linearized updates are inherently basin-dependent and often become trapped near joint limits, singularities, or active collision boundaries, leading to unsafe or stagnant behavior. We propose a GPU-parallelized, continuation-based differential IK that improves escape from such constraint-induced local minima while preserving real-time performance, promoting safety and stability. Multiple constrained IK quadratic programs are evaluated in parallel, together with a self-collision avoidance control barrier function (CBF), and a Lyapunov-based progression criterion selects updates that reduce the final global task-space error. The method is paired with a visual skeletal pose estimation pipeline that enables robust, real-time upper-body teleoperation on the THEMIS humanoid robot hardware in real-world tasks.

Robotics0 citations2026-03-24arXiv ->

Task-Space Singularity Avoidance for Control Affine Systems Using Control Barrier Functions

Kimia Forghani, Suraj Raval, Lamar Mair, Axel Krieger, Yancy Diaz-Mercado

Singularities in robotic and dynamical systems arise when the mapping from control inputs to task-space motion loses rank, leading to an inability to determine inputs. This limits the system's ability to generate forces and torques in desired directions and prevents accurate trajectory tracking. This paper presents a control barrier function (CBF) framework for avoiding such singularities in control-affine systems. Singular configurations are identified through the eigenvalues of a state-dependent input-output mapping matrix, and barrier functions are constructed to maintain a safety margin from rank-deficient regions. Conditions for theoretical guarantees on safety are provided as a function of actuator dynamics. Simulations on a planar 2-link manipulator and a magnetically actuated needle demonstrate smooth trajectory tracking while avoiding singular configurations and reducing control input spikes by up to 100x compared to the nominal controller.

Robotics0 citations2026-03-22arXiv ->

Dynamic Control Barrier Function Regulation with Vision-Language Models for Safe, Adaptive, and Realtime Visual Navigation

Jeffrey Chen, Rohan Chandra

Robots operating in dynamic, unstructured environments must balance safety and efficiency under potentially limited sensing. While control barrier functions (CBFs) provide principled collision avoidance via safety filtering, their behavior is often governed by fixed parameters that can be overly conservative in benign scenes or overly permissive near hazards. We present AlphaAdj, a vision-to-control navigation framework that uses egocentric RGB input to adapt the conservativeness of a CBF safety filter in real time. A vision-language model(VLM) produces a bounded scalar risk estimate from the current camera view, which we map to dynamically update a CBF parameter that modulates how strongly safety constraints are enforced. To address asynchronous inference and non-trivial VLM latency in practice, we combine a geometric, speed-aware dynamic cap and a staleness-gated fusion policy with lightweight implementation choices that reduce end-to-end inference overhead. We evaluate AlphaAdj across multiple static and dynamic obstacle scenarios in a variety of environments, comparing against fixed-parameter and uncapped ablations. Results show that AlphaAdj maintains collision-free navigation while improving efficiency (in terms of path length and time to goal) by up to 18.5% relative to fixed settings and improving robustness and success rate relative to an uncapped baseline.

Robotics0 citations2026-03-21arXiv ->

Current state of the multi-agent multi-view experimental and digital twin rendezvous (MMEDR-Autonomous) framework

Logan Banker, Michael Wozniak, Mohanad Alameer, Smriti Nandan Paul, David Meisinger et al.

As near-Earth resident space objects proliferate, there is an increasing demand for reliable technologies in applications of on-orbit servicing, debris removal, and orbit modification. Rendezvous and docking are critical mission phases for such applications and can benefit from greater autonomy to reduce operational complexity and human workload. Machine learning-based methods can be integrated within the guidance, navigation, and control (GNC) architecture to design a robust rendezvous and docking framework. In this work, the Multi-Agent Multi-View Experimental and Digital Twin Rendezvous (MMEDR-Autonomous) is introduced as a unified framework comprising a learning-based optical navigation network, a reinforcement learning-based guidance approach under ongoing development, and a hardware-in-the-loop testbed. Navigation employs a lightweight monocular pose estimation network with multi-scale feature fusion, trained on realistic image augmentations to mitigate domain shift. The guidance component is examined with emphasis on learning stability, reward design, and systematic hyperparameter tuning under mission-relevant constraints. Prior Control Barrier Function results for Clohessy-Wiltshire dynamics are reviewed as a basis for enforcing safety and operational constraints and for guiding future nonlinear controller design within the MMEDR-Autonomous framework. The MMEDR-Autonomous framework is currently progressing toward integrated experimental validation in multi-agent rendezvous scenarios.

MPC/Planning0 citations2026-03-20arXiv ->

Multi-Agent Motion Planning on Industrial Magnetic Levitation Platforms: A Hybrid ADMM-HOCBF approach

Bavo Tistaert, Stan Servaes, Alejandro Gonzalez-Garcia, Ibrahim Ibrahim, Louis Callens et al.

This paper presents a novel hybrid motion planning method for holonomic multi-agent systems. The proposed decentralised model predictive control (MPC) framework tackles the intractability of classical centralised MPC for a growing number of agents while providing safety guarantees. This is achieved by combining a decentralised version of the alternating direction method of multipliers (ADMM) with a centralised high-order control barrier function (HOCBF) architecture. Simulation results show significant improvement in scalability over classical centralised MPC. We validate the efficacy and real-time capability of the proposed method by developing a highly efficient C++ implementation and deploying the resulting trajectories on a real industrial magnetic levitation platform.

Robotics0 citations2026-03-19arXiv ->

A Closed-Form CLF-CBF Controller for Whole-Body Continuum Soft Robot Collision Avoidance

Kiwan Wong, Maximillian Stölzle, Wei Xiao, Daniela Rus

Safe operation is essential for deploying robots in human-centered 3D environments. Soft continuum manipulators provide passive safety through mechanical compliance, but still require active control to achieve reliable collision avoidance. Existing approaches, such as sampling-based planning, are often computationally expensive and lack formal safety guarantees, which limits their use for real-time whole-body avoidance. This paper presents a closed-form Control Lyapunov Function--Control Barrier Function (CLF--CBF) controller for real-time 3D obstacle avoidance in soft continuum manipulators without online optimization. By analytically embedding safety constraints into the control input, the proposed method ensures stability and safety under the stated modeling assumptions, while avoiding feasibility issues commonly encountered in online optimization-based methods. The resulting controller is up to $10\times$ faster than standard CLF--CBF quadratic-programming approaches and up to $100\times$ faster than traditional sampling-based planners. Simulation and hardware experiments on a tendon-driven soft manipulator demonstrate accurate 3D trajectory tracking and robust obstacle avoidance in cluttered environments. These results show that the proposed framework provides a scalable and provably safe control strategy for soft robots operating in dynamic, safety-critical settings.

Robotics0 citations2026-03-19arXiv ->

ADMM-Based Distributed MPC with Control Barrier Functions for Safe Multi-Robot Quadrupedal Locomotion

Yicheng Zeng, Ruturaj S. Sambhus, Basit Muhammad Imran, Jeeseop Kim, Vittorio Pastore et al.

This paper proposes a fully decentralized model predictive control (MPC) framework with control barrier function (CBF) constraints for safety-critical trajectory planning in multi-robot legged systems. The incorporation of CBF constraints introduces explicit inter-agent coupling, which prevents direct decomposition of the resulting optimal control problems. To address this challenge, we reformulate the centralized safety-critical MPC problem using a structured distributed optimization framework based on the alternating direction method of multipliers (ADMM). By introducing a novel node-edge splitting formulation with consensus constraints, the proposed approach decomposes the global problem into independent node-local and edge-local quadratic programs that can be solved in parallel using only neighbor-to-neighbor communication. This enables fully decentralized trajectory optimization with symmetric computational load across agents while preserving safety and dynamic feasibility. The proposed framework is integrated into a hierarchical locomotion control architecture for quadrupedal robots, combining high-level distributed trajectory planning, mid-level nonlinear MPC enforcing single rigid body dynamics, and low-level whole-body control enforcing full-order robot dynamics. The effectiveness of the proposed approach is demonstrated through hardware experiments on two Unitree Go2 quadrupedal robots and numerical simulations involving up to four robots navigating uncertain environments with rough terrain and external disturbances. The results show that the proposed distributed formulation achieves performance comparable to centralized MPC while reducing the average per-cycle planning time by up to 51% in the four-agent case, enabling efficient real-time decentralized implementation.

MPC/Planning0 citations2026-03-19arXiv ->

Safety-Guaranteed Imitation Learning from Nonlinear Model Predictive Control for Spacecraft Close Proximity Operations

Alexander Meinert, Niklas Baldauf, Peter Stadler, Alen Turnwald

This paper presents a safety-guaranteed, runtime-efficient imitation learning framework for spacecraft close proximity control. We leverage Control Barrier Functions (CBFs) for safety certificates and Control Lyapunov Functions (CLFs) for stability as unified design principles across data generation, training, and deployment. First, a nonlinear Model Predictive Control (NMPC) expert enforces CBF constraints to provide safe reference trajectories. Second, we train a neural policy with a novel CBF-CLF-informed loss and DAgger-like rollouts with curriculum weighting, promoting data-efficiency and reducing future safety filter interventions. Third, at deployment a lightweight one-step CBF-CLF quadratic program minimally adjusts the learned control input to satisfy hard safety constraints while encouraging stability. We validate the approach for ESA-compliant close proximity operations, including fly-around with a spherical keep-out zone and final approach inside a conical approach corridor, using the Basilisk high-fidelity simulator with nonlinear dynamics and perturbations. Numerical experiments indicate stable convergence to decision points and strict adherence to safety under the filter, with task performance comparable to the NMPC expert while significantly reducing online computation. A runtime analysis demonstrates real-time feasibility on a commercial off-the-shelf processor, supporting onboard deployment for safety-critical on-orbit servicing.

Robotics0 citations2026-03-17arXiv ->

Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints

Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray

Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.

Robotics0 citations2026-03-13arXiv ->

Verification and Forward Invariance of Control Barrier Functions for Differential-Algebraic Systems

Hongchao Zhang, Mohamad H. Kazma, Meiyi Ma, Taylor T. Johnson, Ahmad F. Taha

Differential-algebraic equations (DAEs) arise in power networks, chemical processes, and multibody systems, where algebraic constraints encode physical conservation laws. The safety of such systems is critical, yet safe control is challenging because algebraic constraints restrict allowable state trajectories. Control barrier functions (CBFs) provide computationally efficient safety filters for ordinary differential equation (ODE) systems. However, existing CBF methods are not directly applicable to DAEs due to potential conflicts between the CBF condition and the constraint manifold. This paper introduces DAE-aware CBFs that incorporate the differential-algebraic structure through projected vector fields. We derive conditions that ensure forward invariance of safe sets while preserving algebraic constraints and extend the framework to higher-index DAEs. A systematic verification framework is developed, establishing necessary and sufficient conditions for geometric correctness and feasibility of DAE-aware CBFs. For polynomial systems, sum-of-squares certificates are provided, while for nonpolynomial and neural network candidates, satisfiability modulo theories are used for falsification. The approach is validated on wind turbine and flexible-link manipulator systems.

Theory0 citations2026-03-13arXiv ->

A Feasibility-Enhanced Control Barrier Function Method for Multi-UAV Collision Avoidance

Qishen Zhong, Junlong Wu, Jian Yang, Guanwei Xiao, Junqi Wu et al.

This paper presents a feasibility-enhanced control barrier function (FECBF) framework for multi-UAV collision avoidance. In dense multi-UAV scenarios, the feasibility of the CBF quadratic program (CBF-QP) can be compromised due to internal incompatibility among multiple CBF constraints. To address this issue, we analyze the internal compatibility of CBF constraints and derive a sufficient condition for internal compatibility. Based on this condition, a sign-consistency constraint is introduced to mitigate internal incompatibility. The proposed constraint is incorporated into a decentralized CBF-QP formulation using worst-case estimates and slack variables. Simulation results demonstrate that the proposed method significantly reduces infeasibility and improves collision avoidance performance compared with existing baselines in dense scenarios. Additional simulations under varying time delays demonstrate the robustness of the proposed method. Real-world experiments validate the practical applicability of the proposed method.

Robotics0 citations2026-03-11arXiv ->

Safety-critical Control Under Partial Observability: Reach-Avoid POMDP meets Belief Space Control

Matti Vahs, Joris Verhagen, Jana Tumova

Partially Observable Markov Decision Processes (POMDPs) provide a principled framework for robot decision-making under uncertainty. Solving reach-avoid POMDPs, however, requires coordinating three distinct behaviors: goal reaching, safety, and active information gathering to reduce uncertainty. Existing online POMDP solvers attempt to address all three within a single belief tree search, but this unified approach struggles with the conflicting time scales inherent to these objectives. We propose a layered, certificate-based control architecture that operates directly in belief space, decoupling goal reaching, information gathering, and safety into modular components. We introduce Belief Control Lyapunov Functions (BCLFs) that formalize information gathering as a Lyapunov convergence problem in belief space, and show how they can be learned via reinforcement learning. For safety, we develop Belief Control Barrier Functions (BCBFs) that leverage conformal prediction to provide probabilistic safety guarantees over finite horizons. The resulting control synthesis reduces to lightweight quadratic programs solvable in real time, even for non-Gaussian belief representations with dimension $>10^4$. Experiments in simulation and on a space-robotics platform demonstrate real-time performance and improved safety and task success compared to state-of-the-art constrained POMDP solvers.

Robotics0 citations2026-03-11arXiv ->

Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control

Jake Gonzales, Kazuki Mizuta, Karen Leung, Lillian J. Ratliff

In this paper, we present a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control to provide formal safety guarantees while considering complex human behavior. The approach uses conformal risk control to quantify and control the prediction errors in CBF safety values and establishes formal guarantees on the probability of constraint satisfaction during interaction. We introduce an algorithm that dynamically adjusts the safety margins produced by conformal risk control based on the current interaction context. Through experiments on human-robot navigation scenarios, we demonstrate that our approach significantly reduces collision rates and safety violations as compared to baseline methods while maintaining high success rates in goal-reaching tasks and efficient control. The code, simulations, and other supplementary material can be found on the project website: https://jakeagonzales.github.io/crc-cbf-website/.

Robotics0 citations2026-03-10arXiv ->

Towards Terrain-Aware Safe Locomotion for Quadrupedal Robots Using Proprioceptive Sensing

Peiyu Yang, Jiatao Ding, Wei Pan, Claudio Semini, Cosimo Della Santina

Achieving safe quadrupedal locomotion in real-world environments has attracted much attention in recent years. When walking over uneven terrain, achieving reliable estimation and realising safety-critical control based on the obtained information is still an open question. To address this challenge, especially for low-cost robots equipped solely with proprioceptive sensors (e.g., IMUs, joint encoders, and contact force sensors), this work first presents an estimation framework that generates a 2.5-D terrain map and extracts support plane parameters, which are then integrated into contact and state estimation. Then, we integrate this estimation framework into a safety-critical control pipeline by formulating control barrier functions that provide rigorous safety guarantees. Experiments demonstrate that the proposed terrain estimation method provides smooth terrain representations. Moreover, the coupled estimation framework of terrain, state, and contact reduces the mean absolute error of base position estimation by 64.8%, decreases the estimation variance by 47.2%, and improves the robustness of contact estimation compared to a decoupled framework. The terrain-informed CBFs integrate historical terrain information and current proprioceptive measurements to ensure global safety by keeping the robot out of hazardous areas and local safety by preventing body-terrain collision, relying solely on proprioceptive sensing.

Robotics1 citations2026-03-10arXiv ->

SEA-Nav: Efficient Policy Learning for Safe and Agile Quadruped Navigation in Cluttered Environments

Shiyi Chen, Mingye Yang, Haiyan Mao, Jiaqi Zhang, Haiyi Liu et al.

Efficiently training quadruped robot navigation in densely cluttered environments remains a significant challenge. Existing methods are either limited by a lack of safety and agility in simple obstacle distributions or suffer from slow locomotion in complex environments, often requiring excessively long training phases. To this end, we propose SEA-Nav (Safe, Efficient, and Agile Navigation), a reinforcement learning framework for quadruped navigation. Within diverse and dense obstacle environments, a differentiable control barrier function (CBF)-based shield constraints the navigation policy to output safe velocity commands. An adaptive collision replay mechanism and hazardous exploration rewards are introduced to increase the probability of learning from critical experiences, guiding efficient exploration and exploitation. Finally, kinematic action constraints are incorporated to ensure safe velocity commands, facilitating successful physical deployment. To the best of our knowledge, this is the first approach that achieves highly challenging quadruped navigation in the real world with minute-level training time.

MPC/Planning0 citations2026-03-09arXiv ->

SEP-NMPC: Safety Enhanced Passivity-Based Nonlinear Model Predictive Control for a UAV Slung Payload System

Seyedreza Rezaei, Junjie Kang, Amaldev Haridevan, Jinjun Shan

Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a Safety Enhanced Passivity-Based Nonlinear MPC (SEP-NMPC) that provides formal guarantees of stability and safety for a quadrotor transporting a slung payload through cluttered environments. Stability is enforced by embedding a strict passivity inequality, which is derived from a shaped energy storage function with adaptive damping, directly into the NMPC. This formulation dissipates excess energy and ensures asymptotic convergence despite payload swings. Safety is guaranteed through high-order control barrier functions (HOCBFs) that render user-defined clearance sets forward-invariant, obliging both the quadrotor and the swinging payload to maintain separation while interacting with static and dynamic obstacles. The optimization remains quadratic-program compatible and is solved online at each sampling time without gain scheduling or heuristic switching. Extensive simulations and real-world experiments confirm stable payload transport, collision-free trajectories, and real-time feasibility across all tested scenarios. The SEP-NMPC framework therefore unifies passivity-based closed-loop stability with HOCBF-based safety guarantees for UAV slung-payload transportation.

Robotics0 citations2026-03-07arXiv ->

SSP: Safety-guaranteed Surgical Policy via Joint Optimization of Behavioral and Spatial Constraints

Jianshu Hu, ZhiYuan Guan, Lei Song, Kantaphat Leelakunwet, Hesheng Wang et al.

The paradigm of robot-assisted surgery is shifting toward data-driven autonomy, where policies learned via Reinforcement Learning (RL) or Imitation Learning (IL) enable the execution of complex tasks. However, these ``black-box" policies often lack formal safety guarantees, a critical requirement for clinical deployment. In this paper, we propose the Safety-guaranteed Surgical Policy (SSP) framework to bridge the gap between data-driven generality and formal safety. We utilize Neural Ordinary Differential Equations (Neural ODEs) to learn an uncertainty-aware dynamics model from demonstration data. This learned model underpins a robust Control Barrier Function (CBF) safety controller, which minimally alters the actions of a surgical policy to ensure strict safety under uncertainty. Our controller enforces two constraint categories: behavioral constraints (restricting the task space of the agent) and spatial constraints (defining surgical no-go zones). We instantiate the SSP framework with surgical policies derived from RL, IL and Control Lyapunov Functions (CLF). Validation on in both the SurRoL simulation and da Vinci Research Kit (dVRK) demonstrates that our method achieves a near-zero constraint violation rate while maintaining high task success rates compared to unconstrained baselines.

Robotics0 citations2026-03-07arXiv ->

Is Your Safe Controller Actually Safe? A Critical Review of CBF Tautologies and Hidden Assumptions

Taekyung Kim

This tutorial provides a critical review of the practical application of Control Barrier Functions (CBFs) in robotic safety. While the theoretical foundations of CBFs are well-established, I identify a recurring gap between the mathematical assumption of a safe controller's existence and its constructive realization in systems with input constraints. I highlight the distinction between candidate and valid CBFs by analyzing the interplay of system dynamics, actuation limits, and class-K functions. I further show that some purported demonstrations of safe robot policies or controllers are limited to passively safe systems, such as single integrators or kinematic manipulators, where safety is already inherited from the underlying physics and even naive geometric hard constraints suffice to prevent collisions. By revisiting simple low-dimensional examples, I show when CBF formulations provide valid safety guarantees and when they fail due to common misuses. I then provide practical guidelines for constructing realizable safety arguments for systems without such passive safety. The goal of this tutorial is to bridge the gap between theoretical guarantees and actual implementation, supported by an open-source interactive web demonstration that visualizes these concepts intuitively.

Robotics0 citations2026-03-06arXiv ->

CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments

Bojan Derajić, Sebastian Bernhard, Wolfgang Hönig

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are easy to deploy but difficult to design. Motivated by the shortcomings of existing learning- and model-based methods, we propose a simple yet effective neural CBF design method for safe robot navigation in dynamic environments. We employ the idea of a composite CBF, where multiple neural CBFs are combined into a single CBF. The individual CBFs are trained via the Hamilton-Jacobi reachability framework to approximate the optimal safe set for single moving obstacles. Additionally, we use the residual neural architecture, which guarantees that the estimated safe set does not intersect with the corresponding failure set. The method is extensively evaluated in simulation experiments for a ground robot and a quadrotor, comparing it against several baseline methods. The results show improved success rates of up to 18\% compared to the best baseline, without increasing the conservativeness of the motion. Also, the method is demonstrated in hardware experiments for both types of robots.

Robotics0 citations2026-03-06arXiv ->

Control Barrier Corridors: From Safety Functions to Safe Sets

Ömür Arslan, Nikolay Atanasov

Safe autonomy is a critical requirement and a key enabler for robots to operate safely in unstructured complex environments. Control barrier functions and safe motion corridors are two widely used but technically distinct safety methods, functional and geometric, respectively, for safe motion planning and control. Control barrier functions are applied to the safety filtering of control inputs to limit the decay rate of system safety, whereas safe motion corridors are geometrically constructed to define a local safe zone around the system state for use in motion optimization and reference-governor design. This paper introduces a new notion of control barrier corridors, which unifies these two approaches by converting control barrier functions into local safe goal regions for reference goal selection in feedback control systems. We show, with examples on fully actuated systems, kinematic unicycles, and linear output regulation systems, that individual state safety can be extended locally over control barrier corridors for convex barrier functions, provided the control convergence rate matches the barrier decay rate, highlighting a trade-off between safety and reactiveness. Such safe control barrier corridors enable safely reachable persistent goal selection over continuously changing barrier corridors during system motion, which we demonstrate for verifiably safe and persistent path following in autonomous exploration of unknown environments.

Robotics0 citations2026-03-06arXiv ->

Safe Consensus of Cooperative Manipulation with Hierarchical Event-Triggered Control Barrier Functions

Simiao Zhuang, Bingkun Huang, Zewen Yang

Cooperative transport and manipulation of heavy or bulky payloads by multiple manipulators requires coordinated formation tracking, while simultaneously enforcing strict safety constraints in varying environments with limited communication and real-time computation budgets. This paper presents a distributed control framework that achieves consensus coordination with safety guarantees via hierarchical event-triggered control barrier functions (CBFs). We first develop a consensus-based protocol that relies solely on local neighbor information to enforce both translational and rotational consistency in task space. Building on this coordination layer, we propose a three-level hierarchical event-triggered safety architecture with CBFs, which is integrated with a risk-aware leader selection and smooth switching strategy to reduce online computation. The proposed approach is validated through real-world hardware experiments using two Franka manipulators operating with static obstacles, as well as comprehensive simulations demonstrating scalable multi-arm cooperation with dynamic obstacles. Results demonstrate higher precision cooperation under strict safety constraints, achieving substantially reduced computational cost and communication frequency compared to baseline methods.

Robotics0 citations2026-03-06arXiv ->

Iterative Convex Optimization with Control Barrier Functions for Obstacle Avoidance among Polytopes

Shuo Liu, Zhe Huang, Calin A. Belta

Obstacle avoidance of polytopic obstacles by polytopic robots is a challenging problem in optimization-based control and trajectory planning. Many existing methods rely on smooth geometric approximations, such as hyperspheres or ellipsoids, which allow differentiable distance expressions but distort the true geometry and restrict the feasible set. Other approaches integrate exact polytope distances into nonlinear model predictive control (MPC), resulting in nonconvex programs that limit real-time performance. In this paper, we construct linear discrete-time control barrier function (DCBF) constraints by deriving supporting hyperplanes from exact closest-point computations between convex polytopes. We then propose a novel iterative convex MPC-DCBF framework, where local linearization of system dynamics and robot geometry ensures convexity of the finite-horizon optimization at each iteration. The resulting formulation reduces computational complexity and enables fast online implementation for safety-critical control and trajectory planning of general nonlinear dynamics. The framework extends to multi-robot and three-dimensional environments. Numerical experiments demonstrate collision-free navigation in cluttered maze scenarios with millisecond-level solve times.

Robotics0 citations2026-03-06arXiv ->

Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints

Bo Leng, Weiqi Zhang, Zhuoren Li, Lu Xiong, Guizhe Jin et al.

Reinforcement learning has demonstrated significant potential in the field of autonomous driving. However, it suffers from defects such as training instability and unsafe action outputs when faced with autonomous racing environments characterized by high dynamics and strong nonlinearities. To this end, this paper proposes a trajectory guidance and dynamics constraints Reinforcement Learning (TraD-RL) method for autonomous racing. The key features of this method are as follows: 1) leveraging the prior expert racing line to construct an augmented state representation and facilitate reward shaping, thereby integrating domain knowledge to stabilize early-stage policy learning; 2) embedding explicit vehicle dynamic priors into a safe operating envelope formulated via control barrier functions to enable safety-constrained learning; and 3) adopting a multi-stage curriculum learning strategy that shifts from expert-guided learning to autonomous exploration, allowing the learned policy to surpass expert-level performance. The proposed method is evaluated in a high-fidelity simulation environment modeled after the Tempelhof Airport Street Circuit. Experimental results demonstrate that TraD-RL effectively improves both lap speed and driving stability of the autonomous racing vehicle, achieving a synergistic optimization of racing performance and safety.

Robotics0 citations2026-03-05arXiv ->

Safe-Night VLA: Seeing the Unseen via Thermal-Perceptive Vision-Language-Action Models for Safety-Critical Manipulation

Dian Yu, Qingchuan Zhou, Bingkun Huang, Majid Khadiv, Zewen Yang

Current Vision-Language-Action (VLA) models rely primarily on RGB perception, preventing them from capturing modalities such as thermal signals that are imperceptible to conventional visual sensors. Moreover, end-to-end generative policies lack explicit safety constraints, making them fragile when encountering obstacles and novel scenarios outside the training distribution. To address these limitations, we propose Safe-Night VLA, a multimodal manipulation framework that enables robots to see the unseen while enforcing rigorous safety constraints for thermal-aware manipulation in unstructured environments. Specifically, Safe-Night VLA integrates long-wave infrared thermal perception into a pre-trained vision-language backbone, enabling semantic reasoning grounded in thermodynamic properties. To ensure safe execution under out-of-distribution conditions, we incorporate a safety filter via control barrier functions, which provide deterministic workspace constraint enforcement during policy execution. We validate our framework through real-world experiments on a Franka manipulator, introducing a novel evaluation paradigm featuring temperature-conditioned manipulation, subsurface target localization, and reflection disambiguation, while maintaining constrained execution at inference time. Results demonstrate that Safe-Night VLA outperforms RGB-only baselines and provide empirical evidence that foundation models can effectively leverage non-visible physical modalities for robust manipulation.

Robotics0 citations2026-03-05arXiv ->

Safe-SAGE: Social-Semantic Adaptive Guidance for Safe Engagement through Laplace-Modulated Poisson Safety Functions

Lizhi Yang, Ryan M. Bena, Meg Wilkinson, Gilbert Bahati, Andy Navarro Brenes et al.

Traditional safety-critical control methods, such as control barrier functions, suffer from semantic blindness, exhibiting the same behavior around obstacles regardless of contextual significance. This limitation leads to the uniform treatment of all obstacles, despite their differing semantic meanings. We present Safe-SAGE (Social-Semantic Adaptive Guidance for Safe Engagement), a unified framework that bridges the gap between high-level semantic understanding and low-level safety-critical control through a Poisson safety function (PSF) modulated using a Laplace guidance field. Our approach perceives the environment by fusing multi-sensor point clouds with vision-based instance segmentation and persistent object tracking to maintain up-to-date semantics beyond the camera's field of view. A multi-layer safety filter is then used to modulate system inputs to achieve safe navigation using this semantic understanding of the environment. This safety filter consists of both a model predictive control layer and a control barrier function layer. Both layers utilize the PSF and flux modulation of the guidance field to introduce varying levels of conservatism and multi-agent passing norms for different obstacles in the environment. Our framework enables legged robots to safely navigate semantically rich, dynamic environments with context-dependent safety margins.

Other128 citations2022-06-07arXiv ->

Control Barrier Functions and Input-to-State Safety With Application to Automated Vehicles

Anil Alan, Andrew J. Taylor, C. He, A. Ames, G. Orosz

Balancing safety and performance is one of the predominant challenges in modern control system design. Moreover, it is crucial to robustly ensure safety without inducing unnecessary conservativeness that degrades performance. In this work, we present a constructive approach for safety-critical control synthesis via control barrier functions (CBFs). By filtering a hand-designed controller via a CBF, we are able to attain performant behavior while providing rigorous guarantees of safety. In the face of disturbances, robust safety and performance are simultaneously achieved through the notion of input-to-state safety (ISSf). We take a tutorial approach by developing the CBF-design methodology in parallel with an inverted pendulum example, making the challenges and sensitivities in the design process concrete. To establish the capability of the proposed approach, we consider the practical setting of safety-critical design via CBFs for a connected automated vehicle (CAV) in the form of a class-8 truck without a trailer. Through experimentation, we see the impact of unmodeled disturbances in the truck’s actuation system on the safety guarantees provided by CBFs. We characterize these disturbances and using ISSf, produce a robust controller that achieves safety without conceding performance. We evaluate our design both in simulation, and for the first time on an automotive system, experimentally.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

Robotics0 citations2020-10-30arXiv ->

Multi-Layered Safety for Legged Robots via Control Barrier Functions and Model Predictive Control

R. Grandia, Andrew J. Taylor, A. Ames, Marco Hutter

The problem of dynamic locomotion over rough terrain requires both accurate foot placement together with an emphasis on dynamic stability. Existing approaches to this problem prioritize immediate safe foot placement over longer term dynamic stability considerations, or relegate the coordination of foot placement and dynamic stability to heuristic methods. We propose a multi-layered locomotion framework that unifies Control Barrier Functions (CBFs) with Model Predictive Control (MPC) to simultaneously achieve safe foot placement and dynamic stability. Our approach incorporates CBF based safety constraints both in a low frequency kinodynamic MPC formulation and a high frequency inverse dynamics tracking controller. This ensures that safety-critical execution is considered when optimizing locomotion over a longer horizon. We validate the proposed method in a 3D stepping-stone scenario in simulation and experimentally on the ANYmal quadruped platform.

Robotics0 citations2020-10-19arXiv ->

Comparative Analysis of Control Barrier Functions and Artificial Potential Fields for Obstacle Avoidance

Andrew W. Singletary, Karl Klingebiel, Joseph R. Bourne, Andrew W. Browning, P. Tokumaru et al.

Artificial potential fields (APFs) and their variants have been a staple for collision avoidance of mobile robots and manipulators for almost 40 years. Its model-independent nature, ease of implementation, and real-time performance have played a large role in its continued success over the years. Control barrier functions (CBFs), on the other hand, are a more recent development, commonly used to guarantee safety for nonlinear systems in real-time in the form of a filter on a nominal controller. In this paper, we address the connections between APFs and CBFs. At a theoretic level, we show that given a broad class of APFs, one can construct a CBF that guarantees safety. Additionally, we prove that CBFs obtained from these APFs have additional beneficial properties and can be applied to nonlinear systems. Practically, we compare the performance of APFs and CBFs in the context of obstacle avoidance on simple illustrative examples and for a quadrotor with unknown dynamics, both in simulation and on hardware using onboard sensing.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

Robotics0 citations2020-03-10arXiv ->

Synthesis of Control Barrier Functions Using a Supervised Machine Learning Approach

M. Srinivasan, A. Dabholkar, S. Coogan, P. Vela

Control barrier functions are mathematical constructs used to guarantee safety for robotic systems. When integrated as constraints in a quadratic programming optimization problem, instantaneous control synthesis with real-time performance demands can be achieved for robotics applications. Prevailing use has assumed full knowledge of the safety barrier functions, however there are cases where the safe regions must be estimated online from sensor measurements. In these cases, the corresponding barrier function must be synthesized online. This paper describes a learning framework for estimating control barrier functions from sensor data. Doing so affords system operation in unknown state space regions without compromising safety. Here, a support vector machine classifier provides the barrier function specification as determined by sets of safe and unsafe states obtained from sensor measurements. Theoretical safety guarantees are provided. Experimental ROS-based simulation results for an omnidirectional robot equipped with LiDAR demonstrate safe operation.

Learning0 citations2019-03-12arXiv ->

Control Barrier Functions for Systems with High Relative Degree

Wei Xiao, C. Belta

This paper extends control barrier functions (CBFs) to high order control barrier functions (HOCBFs) that can be used for high relative degree constraints. The proposed HOCBFs are more general than recently proposed (exponential) HOCBFs. We introduce high order barrier functions (HOBFs), and show that their satisfaction of Lyapunov-like conditions implies the forward invariance of the intersection of a series of sets. We then introduce HOCBF, and show that any control input that satisfies the HOCBF constraint renders the intersection of a series of sets forward invariant. We formulate optimal control problems with constraints given by HOCBF and control Lyapunov functions (CLF), and provide a promising method to address the conflict between HOCBF constraints and control limitations by penalizing the class $\mathcal{K}$ functions. We illustrate the proposed method on an adaptive cruise control problem.

Optimization and Control | 15 papers | 19.7% coverage
MPC/Planning0 citations2026-03-24arXiv ->

Universal Formula Families for Safe Stabilization of Single-Input Nonlinear Systems

Bo Wang, Miroslav Krstic

We develop an optimization-free framework for safe stabilization of single-input control-affine nonlinear systems with a given control Lyapunov function (CLF) and a given control barrier function (CBF), where the desired equilibrium lies in the interior of the safe set. An explicit compatibility condition is derived that is necessary and sufficient for the pointwise simultaneous satisfaction of the CLF and CBF inequalities. When this condition holds, two closed-form continuous state-feedback laws are constructed from the Lie-derivative data of the CLF and CBF via standard universal stabilizer formulas, yielding asymptotic stabilization of the origin and forward invariance of the interior of the safe set, without online quadratic programming. The two laws belong to broader families parametrized by a free nondecreasing function, providing additional design flexibility. When the compatibility condition fails, a safety-prioritizing modification preserves forward invariance and drives the state toward the safe-set boundary until a compatible region is reached, whereupon continuity at the origin and asymptotic stabilization are recovered. The framework produces families of explicit constructive alternatives to CLF-CBF quadratic programming for scalar-input nonlinear systems.

Other0 citations2026-03-20arXiv ->

A Spectral Perspective on Stochastic Control Barrier Functions

Inkyu Jang, Chams E. Mballo, Claire J. Tomlin, H. Jin Kim

Stochastic control barrier functions (SCBFs) provide a safety-critical control framework for systems subject to stochastic disturbances by bounding the probability of remaining within a safe set. However, synthesizing a valid SCBF that explicitly reflects the true safety probability of the system, which is the most natural measure of safety, remains a challenge. This paper addresses this issue by adopting a spectral perspective, utilizing the linear operator that governs the evolution of the closed-loop system's safety probability. We find that the dominant eigenpair of this Koopman-like operator encodes fundamental safety information of the stochastic system. The dominant eigenfunction is a natural and valid SCBF, with values that explicitly quantify the relative long-term safety of the state, while the dominant eigenvalue indicates the global rate at which the safety probability decays. A practical synthesis algorithm is proposed, termed power-policy iteration, which jointly computes the dominant eigenpair and an optimized backup policy. The method is validated using simulation experiments on safety-critical dynamics models.

Robotics0 citations2026-03-19arXiv ->

ADMM-Based Distributed MPC with Control Barrier Functions for Safe Multi-Robot Quadrupedal Locomotion

Yicheng Zeng, Ruturaj S. Sambhus, Basit Muhammad Imran, Jeeseop Kim, Vittorio Pastore et al.

This paper proposes a fully decentralized model predictive control (MPC) framework with control barrier function (CBF) constraints for safety-critical trajectory planning in multi-robot legged systems. The incorporation of CBF constraints introduces explicit inter-agent coupling, which prevents direct decomposition of the resulting optimal control problems. To address this challenge, we reformulate the centralized safety-critical MPC problem using a structured distributed optimization framework based on the alternating direction method of multipliers (ADMM). By introducing a novel node-edge splitting formulation with consensus constraints, the proposed approach decomposes the global problem into independent node-local and edge-local quadratic programs that can be solved in parallel using only neighbor-to-neighbor communication. This enables fully decentralized trajectory optimization with symmetric computational load across agents while preserving safety and dynamic feasibility. The proposed framework is integrated into a hierarchical locomotion control architecture for quadrupedal robots, combining high-level distributed trajectory planning, mid-level nonlinear MPC enforcing single rigid body dynamics, and low-level whole-body control enforcing full-order robot dynamics. The effectiveness of the proposed approach is demonstrated through hardware experiments on two Unitree Go2 quadrupedal robots and numerical simulations involving up to four robots navigating uncertain environments with rough terrain and external disturbances. The results show that the proposed distributed formulation achieves performance comparable to centralized MPC while reducing the average per-cycle planning time by up to 51% in the four-agent case, enabling efficient real-time decentralized implementation.

Other0 citations2026-03-19arXiv ->

Topological Obstructions to the Existence of Control Barrier Functions

Massimiliano de Sa, Aaron D. Ames

In 1983, Brockett developed a topological necessary condition for the existence of continuous, asymptotically stabilizing control laws. Building upon recent work on necessary conditions for set stabilization, we develop Brockett-like necessary conditions for the existence of control barrier functions (CBFs). By leveraging the unique geometry of CBF safe sets, we provide simple and self-contained derivations of necessary conditions for the existence of CBFs and their safe, continuous controllers. We demonstrate the application of these conditions to instructive examples and kinematic nonholonomic systems, and discuss their relationship to Brockett's necessary condition.

Theory0 citations2026-03-18arXiv ->

Adversarial Robustness for Matrix Control Barrier Functions in Sampled-Data Systems

James Usevitch

This paper presents novel theoretical results to guarantee multi-agent set invariance using Matrix Control Barrier Functions in sampled-data systems. More specifically, the paper presents conditions under which heterogeneous control-affine agents applying zero-order-hold control inputs can compute control inputs to render safe sets defined by matrix inequalities forward invariant. It then introduces methods to guarantee set invariance while accounting for the presence of adversarial agents seeking to drive the system state to unsafe sets. Finally, the paper presents theoretical extensions of these set invariance results to systems having high relative degree with respect to the matrix-valued safe set function.

Theory0 citations2026-03-18arXiv ->

Dynamical Properties of Safety Filters for Linear Systems and Affine Control Barrier Functions

Pol Mestres, Shima Sadat Mousavi, Aaron D. Ames

This letter studies the dynamical properties of safety filters designed based on Control Barrier Functions (CBF). This mechanism, which is popular in safety-critical applications, takes a nominal controller and minimally modifies it to render it safe. Although CBF-based safety filters make the closed-loop system safe, characterizing their additional dynamical properties, such as stability, boundedness, or existence of spurious equilibria, remains a challenging problem. Here, we address this problem for the case of linear systems and an affine CBF constraint. We provide conditions under which the closed-loop system presents undesired equilibria, unbounded trajectories, or the origin is globally exponentially stable.

Other0 citations2026-03-17arXiv ->

Constricting Tubes for Prescribed-Time Safe Control

Darshan Gadginmath, Ahmed Allibhoy, Fabio Pasqualetti

We propose a constricting Control Barrier Function (CBF) framework for prescribed-time control of control-affine systems with input constraints. Given a system starting outside a target safe set, we construct a time-varying safety tube that shrinks from a relaxed set containing the initial condition to the target set at a user-specified deadline. Any controller rendering this tube forward invariant guarantees prescribed-time recovery by construction. The constriction schedule is bounded and tunable by design, in contrast to prescribed-time methods where control effort diverges near the deadline. Feasibility under input constraints reduces to a single verifiable condition on the constriction rate, yielding a closed-form minimum recovery time as a function of control authority and initial violation. The framework imposes a single affine constraint per timestep regardless of state dimension, scaling to settings where grid-based reachability methods are intractable. We validate on a 16-dimensional multi-agent system and a unicycle reach-avoid problem, demonstrating prescribed-time recovery with bounded control effort.

MPC/Planning0 citations2026-03-17arXiv ->

Eliminating Persistent Boundary Residence via Matrosov-Type Auxiliary Functions

Tianyu Han, Guangwei Wang, Bo Wang

Control barrier functions enforce safety by guaranteeing forward invariance of an admissible set. Under standard (non-strict) barrier conditions, however, forward invariance alone does not prevent trajectories from remaining on the boundary of the safe set for arbitrarily long time intervals, potentially leading to boundary sticking or deadlock phenomena. This paper studies the elimination of persistent boundary residence under forward-invariant barrier conditions. Inspired by Matrosov-type arguments, we introduce an auxiliary function framework that preserves forward invariance while excluding infinite-time residence within boundary layers. Sufficient conditions are established under which any trajectory can only remain in a prescribed neighborhood of the boundary for finite time, thereby restoring boundary-level liveness without altering forward invariance. The proposed construction does not rely on singular barrier formulations or controller-specific modifications, and can be incorporated into standard safety-critical control architectures. Numerical examples illustrate the removal of boundary sticking behaviors while maintaining safety across representative systems.

Theory0 citations2026-03-04arXiv ->

Local Safety Filters for Networked Systems via Two-Time-Scale Design

Emiliano Dall'Anese

Safety filters based on Control Barrier Functions (CBFs) provide formal guarantees of forward invariance, but are often difficult to implement in networked dynamical systems. This is due to global coupling and communication requirements. This paper develops locally implementable approximations of networked CBF safety filters that require no coordination across subsystems. The proposed approach is based on a two-time-scale dynamic implementation inspired by singular perturbation theory, where a small parameter $ε$ separates fast filter dynamics from the plant dynamics; then, a local implementation is enabled via derivative estimation. Explicit bounds are derived to quantify the mismatch between trajectories of the systems with dynamic filter and with the ideal centralized safety filter. These results characterize how safety degradation depends on the time-scale parameter $ε$, estimation errors, and filter activation time, thereby quantifying trade-offs between safety guarantees and local implementability.

Robotics0 citations2021-09-25arXiv ->

Safety-Critical Control and Planning for Obstacle Avoidance between Polytopes with Control Barrier Functions

A. Thirugnanam, Jun Zeng, K. Sreenath

Obstacle avoidance between polytopes is a chal-lenging topic for optimal control and optimization-based tra-jectory planning problems. Existing work either solves this problem through mixed-integer optimization, relying on simpli-fication of system dynamics, or through model predictive control with dual variables using distance constraints, requiring long horizons for obstacle avoidance. In either case, the solution can only be applied as an offline planning algorithm. In this paper, we exploit the property that a smaller horizon is sufficient for obstacle avoidance by using discrete-time control barrier function (DCBF) constraints and we propose a novel optimization formulation with dual variables based on DCBFs to generate a collision-free dynamically-feasible trajectory. The proposed optimization formulation has lower computational complexity compared to existing work and can be used as a fast online algorithm for control and planning for general nonlinear dynamical systems. We validate our algorithm on different robot shapes using numerical simulations with a kinematic bicycle model, resulting in successful navigation through maze environments with polytopic obstacles.

Robotics0 citations2021-05-21arXiv ->

Enhancing Feasibility and Safety of Nonlinear Model Predictive Control with Discrete-Time Control Barrier Functions

Jun Zeng, Zhongyu Li, K. Sreenath

Safety is one of the fundamental problems in robotics. Recently, one-step or multi-step optimal control problems for discrete-time nonlinear dynamical system were formulated to offer tracking stability using control Lyapunov functions (CLFs) while subject to input constraints as well as safety-critical constraints using control barrier functions (CBFs). The limitations of these existing approaches are mainly about feasibility and safety. In the existing approaches, the feasibility of the optimization and the system safety cannot be enhanced at the same time theoretically. In this paper, we propose two formulations that unifies CLFs and CBFs under the framework of nonlinear model predictive control (NMPC). In the proposed formulations, safety criteria is commonly formulated as CBF constraints and stability performance is ensured with either a terminal cost function or CLF constraints. Slack variables with relaxing technique are introduced on the CBF constraints to resolve the tradeoff between feasibility and safety so that they can be enhanced at the same. The advantages about feasibility and safety of proposed formulations compared with existing methods are analyzed theoretically and validated with numerical results.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Learning0 citations2020-03-07arXiv ->

Control barrier functions for stochastic systems

Andrew Clark

Control Barrier Functions (CBFs) aim to ensure safety by constraining the control input at each time step so that the system state remains within a desired safe region. This paper presents a framework for CBFs in stochastic systems in the presence of Gaussian process and measurement noise. We first consider the case where the system state is known at each time step, and present reciprocal and zero CBF constructions that guarantee safety with probability 1. We extend our results to high relative degree systems with linear dynamics and affine safety constraints. We then develop CBFs for incomplete state information environments, in which the state must be estimated using sensors that are corrupted by Gaussian noise. We prove that our proposed CBF ensures safety with probability 1 when the state estimate is within a given bound of the true state, which can be achieved using an Extended Kalman Filter when the system is linear or the process and measurement noise are sufficiently small. We propose control policies that combine these CBFs with Control Lyapunov Functions in order to jointly ensure safety and stochastic stability. Our results are validated via numerical study on an adaptive cruise control example.

Theory296 citations2018-03-08arXiv ->

Input-to-State Safety With Control Barrier Functions

Shishir N Y Kolathaya, A. Ames

This letter presents a new notion of input-to-state safe control barrier functions (ISSf-CBFs), which ensure safety of nonlinear dynamical systems under input disturbances. Similar to how safety conditions are specified in terms of forward invariance of a set, input-to-state safety conditions are specified in terms of forward invariance of a slightly larger set. In this context, invariance of the larger set implies that the states stay either inside or very close to the smaller safe set; and this closeness is bounded by the magnitude of the disturbances. The main contribution of the letter is the methodology used for obtaining a valid ISSf-CBF, given a control barrier function. The associated universal control law will also be provided. Towards the end, we will study unified quadratic programs that combine control Lyapunov functions and ISSf-CBFs in order to obtain a single control law that ensures both safety and stability in systems with input disturbances.

MPC/Planning649 citations2016-12-05arXiv ->

Robustness of Control Barrier Functions for Safety Critical Control

Xiangru Xu, P. Tabuada, J. Grizzle, A. Ames

Abstract Barrier functions (also called certificates) have been an important tool for the verification of hybrid systems, and have also played important roles in optimization and multi-objective control. The extension of a barrier function to a controlled system results in a control barrier function. This can be thought of as being analogous to how Sontag extended Lyapunov functions to control Lypaunov functions in order to enable controller synthesis for stabilization tasks. A control barrier function enables controller synthesis for safety requirements specified by forward invariance of a set using a Lyapunov-like condition. This paper develops several important extensions to the notion of a control barrier function. The first involves robustness under perturbations to the vector field defining the system. Input-to-State stability conditions are given that provide for forward invariance, when disturbances are present, of a “relaxation” of set rendered invariant without disturbances. A control barrier function can be combined with a control Lyapunov function in a quadratic program to achieve a control objective subject to safety guarantees. The second result of the paper gives conditions for the control law obtained by solving the quadratic program to be Lipschitz continuous and therefore to gives rise to well-defined solutions of the resulting closed-loop system.

Machine Learning | 5 papers | 6.6% coverage
Robotics0 citations2026-03-17arXiv ->

Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints

Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray

Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.

Robotics0 citations2026-03-06arXiv ->

CN-CBF: Composite Neural Control Barrier Function for Safe Robot Navigation in Dynamic Environments

Bojan Derajić, Sebastian Bernhard, Wolfgang Hönig

Safe navigation of autonomous robots remains one of the core challenges in the field, especially in dynamic and uncertain environments. One of the prevalent approaches is safety filtering based on control barrier functions (CBFs), which are easy to deploy but difficult to design. Motivated by the shortcomings of existing learning- and model-based methods, we propose a simple yet effective neural CBF design method for safe robot navigation in dynamic environments. We employ the idea of a composite CBF, where multiple neural CBFs are combined into a single CBF. The individual CBFs are trained via the Hamilton-Jacobi reachability framework to approximate the optimal safe set for single moving obstacles. Additionally, we use the residual neural architecture, which guarantees that the estimated safe set does not intersect with the corresponding failure set. The method is extensively evaluated in simulation experiments for a ground robot and a quadrotor, comparing it against several baseline methods. The results show improved success rates of up to 18\% compared to the best baseline, without increasing the conservativeness of the motion. Also, the method is demonstrated in hardware experiments for both types of robots.

Robotics0 citations2020-04-16arXiv ->

Reinforcement Learning for Safety-Critical Control under Model Uncertainty, using Control Lyapunov Functions and Control Barrier Functions

Jason J. Choi, F. Castañeda, C. Tomlin, K. Sreenath

In this paper, the issue of model uncertainty in safety-critical control is addressed with a data-driven approach. For this purpose, we utilize the structure of an input-ouput linearization controller based on a nominal model along with a Control Barrier Function and Control Lyapunov Function based Quadratic Program (CBF-CLF-QP). Specifically, we propose a novel reinforcement learning framework which learns the model uncertainty present in the CBF and CLF constraints, as well as other control-affine dynamic constraints in the quadratic program. The trained policy is combined with the nominal model-based CBF-CLF-QP, resulting in the Reinforcement Learning-based CBF-CLF-QP (RL-CBF-CLF-QP), which addresses the problem of model uncertainty in the safety constraints. The performance of the proposed method is validated by testing it on an underactuated nonlinear bipedal robot walking on randomly spaced stepping stones with one step preview, obtaining stable and safe walking under model uncertainty.

MPC/Planning0 citations2020-04-07arXiv ->

Learning Control Barrier Functions from Expert Demonstrations

Alexander Robey, Haimin Hu, Lars Lindemann, Hanwen Zhang, Dimos V. Dimarogonas et al.

Inspired by the success of imitation and inverse reinforcement learning in replicating expert behavior through optimal control, we propose a learning based approach to safe controller synthesis based on control barrier functions (CBFs). We consider the setting of a known nonlinear control affine dynamical system and assume that we have access to safe trajectories generated by an expert — a practical example of such a setting would be a kinematic model of a self-driving vehicle with safe trajectories (e.g., trajectories that avoid collisions with obstacles in the environment) generated by a human driver. We then propose and analyze an optimization based approach to learning a CBF that enjoys provable safety guarantees under suitable Lipschitz smoothness assumptions on the underlying dynamical system. A strength of our approach is that it is agnostic to the parameterization used to represent the CBF, assuming only that the Lipschitz constant of such functions can be efficiently bounded. Furthermore, if the CBF parameterization is convex, then under mild assumptions, so is our learning process. We end with extensive numerical evaluations of our results on both planar and realistic examples, using both random feature and deep neural network parameterizations of the CBF. To the best of our knowledge, these are the first results that learn provably safe control barrier functions from data.

Learning275 citations2019-12-20arXiv ->

Learning for Safety-Critical Control with Control Barrier Functions

Andrew J. Taylor, Andrew W. Singletary, Yisong Yue, A. Ames

Modern nonlinear control theory seeks to endow systems with properties of stability and safety, and have been deployed successfully in multiple domains. Despite this success, model uncertainty remains a significant challenge in synthesizing safe controllers, leading to degradation in the properties provided by the controllers. This paper develops a machine learning framework utilizing Control Barrier Functions (CBFs) to reduce model uncertainty as it impact the safe behavior of a system. This approach iteratively collects data and updates a controller, ultimately achieving safe behavior. We validate this method in simulation and experimentally on a Segway platform.

Artificial Intelligence | 1 papers | 1.3% coverage
Robotics0 citations2026-03-11arXiv ->

Safe Probabilistic Planning for Human-Robot Interaction using Conformal Risk Control

Jake Gonzales, Kazuki Mizuta, Karen Leung, Lillian J. Ratliff

In this paper, we present a novel probabilistic safe control framework for human-robot interaction that combines control barrier functions (CBFs) with conformal risk control to provide formal safety guarantees while considering complex human behavior. The approach uses conformal risk control to quantify and control the prediction errors in CBF safety values and establishes formal guarantees on the probability of constraint satisfaction during interaction. We introduce an algorithm that dynamically adjusts the safety margins produced by conformal risk control based on the current interaction context. Through experiments on human-robot navigation scenarios, we demonstrate that our approach significantly reduces collision rates and safety violations as compared to baseline methods while maintaining high success rates in goal-reaching tasks and efficient control. The code, simulations, and other supplementary material can be found on the project website: https://jakeagonzales.github.io/crc-cbf-website/.

Dynamical Systems | 1 papers | 1.3% coverage
Learning0 citations2026-03-16arXiv ->

Multi-Scale Control of Large Agent Populations: From Density Dynamics to Individual Actuation

Mario di Bernardo

We review a body of recent work by the author and collaborators on controlling the spatial organisation of large agent populations across multiple scales. A central theme is the systematic bridging of microscopic agent-level dynamics and macroscopic density descriptions, enabling control design at the most natural level of abstraction and subsequent translation across scales. We show how this multi-scale perspective provides a unified approach to both \emph{direct control}, where every agent is actuated, and \emph{indirect control}, where few leaders or herders steer a larger uncontrolled population. The review covers continuification-based control with robustness under limited sensing and decentralised implementation via distributed density estimation; leader--follower density regulation with dual-feedback stability guarantees and bio-inspired plasticity; optimal-transport methods for coverage control and macro-to-micro discretisation; nonreciprocal field theory for collective decision-making; mean-field control barrier functions for population-level safety; and hierarchical reinforcement learning for settings where closed-form solutions are intractable. Together, these results demonstrate the breadth and versatility of a multi-scale control framework that integrates analytical methods, learning, and physics-inspired approaches for large agent populations.

physics.space-ph | 1 papers | 1.3% coverage
Robotics0 citations2026-03-21arXiv ->

Current state of the multi-agent multi-view experimental and digital twin rendezvous (MMEDR-Autonomous) framework

Logan Banker, Michael Wozniak, Mohanad Alameer, Smriti Nandan Paul, David Meisinger et al.

As near-Earth resident space objects proliferate, there is an increasing demand for reliable technologies in applications of on-orbit servicing, debris removal, and orbit modification. Rendezvous and docking are critical mission phases for such applications and can benefit from greater autonomy to reduce operational complexity and human workload. Machine learning-based methods can be integrated within the guidance, navigation, and control (GNC) architecture to design a robust rendezvous and docking framework. In this work, the Multi-Agent Multi-View Experimental and Digital Twin Rendezvous (MMEDR-Autonomous) is introduced as a unified framework comprising a learning-based optical navigation network, a reinforcement learning-based guidance approach under ongoing development, and a hardware-in-the-loop testbed. Navigation employs a lightweight monocular pose estimation network with multi-scale feature fusion, trained on realistic image augmentations to mitigate domain shift. The guidance component is examined with emphasis on learning stability, reward design, and systematic hyperparameter tuning under mission-relevant constraints. Prior Control Barrier Function results for Clohessy-Wiltshire dynamics are reviewed as a basis for enforcing safety and operational constraints and for guiding future nonlinear controller design within the MMEDR-Autonomous framework. The MMEDR-Autonomous framework is currently progressing toward integrated experimental validation in multi-agent rendezvous scenarios.

  • IROS 202545
  • ICRA 202648
  • ICRA 202538
  • RSS 202534
  • CDC 202520
  • ACC 202622
  • ACC 202510
  • ACC 202410
  • RAL 20262
  • RAL 202512
  • TRO 20253
  • TAC 20253
IROS 2025 | 45 papers
CBF Related Papers
Robotics0 citations2025-10-01arXiv ->

Safe Motion Planning and Control Using Predictive and Adaptive Barrier Methods for Autonomous Surface Vessels

Alejandro Gonzalez-Garcia, Wei Xiao, Wei Wang, Alejandro Astudillo, Wilm Decré et al.

Safe motion planning is essential for autonomous vessel operations, especially in challenging spaces such as narrow inland waterways. However, conventional motion planning approaches are often computationally intensive or overly conservative. This paper proposes a safe motion planning strategy combining Model Predictive Control (MPC) and Control Barrier Functions (CBFs). We introduce a time-varying inflated ellipse obstacle representation, where the inflation radius is adjusted depending on the relative position and attitude between the vessel and the obstacle. The proposed adaptive inflation reduces the conservativeness of the controller compared to traditional fixed-ellipsoid obstacle formulations. The MPC solution provides an approximate motion plan, and high-order CBFs ensure the vessel's safety using the varying inflation radius. Simulation and real-world experiments demonstrate that the proposed strategy enables the fully-actuated autonomous robot vessel to navigate through narrow spaces in real time and resolve potential deadlocks, all while ensuring safety.

Robotics0 citations2025-08-13arXiv ->

Reactive Model Predictive Contouring Control for Robot Manipulators

Junheon Yoon, Woo-Jeong Baek, Jaeheung Park

This contribution presents a robot path-following framework via Reactive Model Predictive Contouring Control (RMPCC) that successfully avoids obstacles, singularities and self-collisions in dynamic environments at 100 Hz. Many path-following methods rely on the time parametrization, but struggle to handle collision and singularity avoidance while adhering kinematic limits or other constraints. Specifically, the error between the desired path and the actual position can become large when executing evasive maneuvers. Thus, this paper derives a method that parametrizes the reference path by a path parameter and performs the optimization via RMPCC. In particular, Control Barrier Functions (CBFs) are introduced to avoid collisions and singularities in dynamic environments. A Jacobian-based linearization and Gauss-Newton Hessian approximation enable solving the nonlinear RMPCC problem at 100 Hz, outperforming state-of-the-art methods by a factor of 10. Experiments confirm that the framework handles dynamic obstacles in real-world settings with low contouring error and low robot acceleration.

Robotics0 citations2025-06-07arXiv ->

Towards Data-Driven Model-Free Safety-Critical Control

Zhe Shen, Yitaek Kim, Christoffer Sloth

This paper presents a framework for enabling safe velocity control of general robotic systems using data-driven model-free Control Barrier Functions (CBFs). Model-free CBFs rely on an exponentially stable velocity controller and a design parameter (e.g. alpha in CBFs); this design parameter depends on the exponential decay rate of the controller. However, in practice, the decay rate is often unavailable, making it non-trivial to use model-free CBFs, as it requires manual tuning for alpha. To address this, a Neural Network is used to learn the Lyapunov function from data, and the maximum decay rate of the systems built-in velocity controller is subsequently estimated. Furthermore, to integrate the estimated decay rate with model-free CBFs, we derive a probabilistic safety condition that incorporates a confidence bound on the violation rate of the exponential stability condition, using Chernoff bound. This enhances robustness against uncertainties in stability violations. The proposed framework has been tested on a UR5e robot in multiple experimental settings, and its effectiveness in ensuring safe velocity control with model-free CBFs has been demonstrated.

Robotics3 citations2025-05-16arXiv ->

SHIELD: Safety on Humanoids via CBFs In Expectation on Learned Dynamics

Lizhi Yang, Blake Werner, Ryan K. Cosner, David Fridovich-Keil, Preston Culbertson et al.

Robot learning has produced remarkably effective ``black-box'' controllers for complex tasks such as dynamic locomotion on humanoids. Yet ensuring dynamic safety, i.e., constraint satisfaction, remains challenging for such policies. Reinforcement learning (RL) embeds constraints heuristically through reward engineering, and adding or modifying constraints requires retraining. Model-based approaches, like control barrier functions (CBFs), enable runtime constraint specification with formal guarantees but require accurate dynamics models. This paper presents SHIELD, a layered safety framework that bridges this gap by: (1) training a generative, stochastic dynamics residual model using real-world data from hardware rollouts of the nominal controller, capturing system behavior and uncertainties; and (2) adding a safety layer on top of the nominal (learned locomotion) controller that leverages this model via a stochastic discrete-time CBF formulation enforcing safety constraints in probability. The result is a minimally-invasive safety layer that can be added to the existing autonomy stack to give probabilistic guarantees of safety that balance risk and performance. In hardware experiments on an Unitree G1 humanoid, SHIELD enables safe navigation (obstacle avoidance) through varied indoor and outdoor environments using a nominal (unknown) RL controller and onboard perception.

Robotics0 citations2025-05-11arXiv ->

Secure Safety Filter: Towards Safe Flight Control under Sensor Attacks

Xiao Tan, Junior Sundar, Renzo Bruzzone, Pio Ong, Willian T. Lunardi et al.

Modern autopilot systems are prone to sensor attacks that can jeopardize flight safety. To mitigate this risk, we proposed a modular solution: the secure safety filter, which extends the well-established control barrier function (CBF)-based safety filter to account for, and mitigate, sensor attacks. This module consists of a secure state reconstructor (which generates plausible states) and a safety filter (which computes the safe control input that is closest to the nominal one). Differing from existing work focusing on linear, noise-free systems, the proposed secure safety filter handles bounded measurement noise and, by leveraging reduced-order model techniques, is applicable to the nonlinear dynamics of drones. Software-in-the-loop simulations and drone hardware experiments demonstrate the effectiveness of the secure safety filter in rendering the system safe in the presence of sensor attacks.

Other Papers
Robotics0 citations2026-03-04arXiv ->

GIANT - Global Path Integration and Attentive Graph Networks for Multi-Agent Trajectory Planning

Jonas le Fevre Sejersen, Toyotaro Suzumura, Erdal Kayacan

This paper presents a novel approach to multi-robot collision avoidance that integrates global path planning with local navigation strategies, utilizing attentive graph neural networks to manage dynamic interactions among agents. We introduce a local navigation model that leverages pre-planned global paths, allowing robots to adhere to optimal routes while dynamically adjusting to environmental changes. The models robustness is enhanced through the introduction of noise during training, resulting in superior performance in complex, dynamic environments. Our approach is evaluated against established baselines, including NH-ORCA, DRL-NAV, and GA3C-CADRL, across various structurally diverse simulated scenarios. The results demonstrate that our model achieves consistently higher success rates, lower collision rates, and more efficient navigation, particularly in challenging scenarios where baseline models struggle. This work offers an advancement in multi-robot navigation, with implications for robust performance in complex, dynamic environments with varying degrees of complexity, such as those encountered in logistics, where adaptability is essential for accommodating unforeseen obstacles and unpredictable changes.

Robotics0 citations2026-01-29arXiv ->

Thinker: A vision-language foundation model for embodied intelligence

Baiyu Pan, Daqin Luo, Junpeng Yang, Jiyuan Wang, Yixuan Zhang et al.

When large vision-language models are applied to the field of robotics, they encounter problems that are simple for humans yet error-prone for models. Such issues include confusion between third-person and first-person perspectives and a tendency to overlook information in video endings during temporal reasoning. To address these challenges, we propose Thinker, a large vision-language foundation model designed for embodied intelligence. We tackle the aforementioned issues from two perspectives. Firstly, we construct a large-scale dataset tailored for robotic perception and reasoning, encompassing ego-view videos, visual grounding, spatial understanding, and chain-of-thought data. Secondly, we introduce a simple yet effective approach that substantially enhances the model's capacity for video comprehension by jointly incorporating key frames and full video sequences as inputs. Our model achieves state-of-the-art results on two of the most commonly used benchmark datasets in the field of task planning.

Robotics0 citations2026-01-08arXiv ->

The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms

Lingdong Kong, Shaoyuan Xie, Zeying Gong, Ye Li, Meng Chu et al.

Autonomous systems are increasingly deployed in open and dynamic environments -- from city streets to aerial and indoor spaces -- where perception models must remain reliable under sensor noise, environmental variation, and platform shifts. However, even state-of-the-art methods often degrade under unseen conditions, highlighting the need for robust and generalizable robot sensing. The RoboSense 2025 Challenge is designed to advance robustness and adaptability in robot perception across diverse sensing scenarios. It unifies five complementary research tracks spanning language-grounded decision making, socially compliant navigation, sensor configuration generalization, cross-view and cross-modal correspondence, and cross-platform 3D perception. Together, these tasks form a comprehensive benchmark for evaluating real-world sensing reliability under domain shifts, sensor failures, and platform discrepancies. RoboSense 2025 provides standardized datasets, baseline models, and unified evaluation protocols, enabling large-scale and reproducible comparison of robust perception methods. The challenge attracted 143 teams from 85 institutions across 16 countries, reflecting broad community engagement. By consolidating insights from 23 winning solutions, this report highlights emerging methodological trends, shared design principles, and open challenges across all tracks, marking a step toward building robots that can sense reliably, act robustly, and adapt across platforms in real-world environments.

Robotics0 citations2026-01-01arXiv ->

Efficient Prediction of Dense Visual Embeddings via Distillation and RGB-D Transformers

Söhnke Benedikt Fischedick, Daniel Seichter, Benedict Stephan, Robin Schmidt, Horst-Michael Gross

In domestic environments, robots require a comprehensive understanding of their surroundings to interact effectively and intuitively with untrained humans. In this paper, we propose DVEFormer - an efficient RGB-D Transformer-based approach that predicts dense text-aligned visual embeddings (DVE) via knowledge distillation. Instead of directly performing classical semantic segmentation with fixed predefined classes, our method uses teacher embeddings from Alpha-CLIP to guide our efficient student model DVEFormer in learning fine-grained pixel-wise embeddings. While this approach still enables classical semantic segmentation, e.g., via linear probing, it further enables flexible text-based querying and other applications, such as creating comprehensive 3D maps. Evaluations on common indoor datasets demonstrate that our approach achieves competitive performance while meeting real-time requirements, operating at 26.3 FPS for the full model and 77.0 FPS for a smaller variant on an NVIDIA Jetson AGX Orin. Additionally, we show qualitative results that highlight the effectiveness and possible use cases in real-world applications. Overall, our method serves as a drop-in replacement for traditional segmentation approaches while enabling flexible natural-language querying and seamless integration into 3D mapping pipelines for mobile robotics.

Robotics0 citations2025-12-30arXiv ->

Local Path Optimization in The Latent Space Using Learned Distance Gradient

Jiawei Zhang, Chengchao Bai, Wei Pan, Tianhang Liu, Jifeng Guo

Constrained motion planning is a common but challenging problem in robotic manipulation. In recent years, data-driven constrained motion planning algorithms have shown impressive planning speed and success rate. Among them, the latent motion method based on manifold approximation is the most efficient planning algorithm. Due to errors in manifold approximation and the difficulty in accurately identifying collision conflicts within the latent space, time-consuming path validity checks and path replanning are required. In this paper, we propose a method that trains a neural network to predict the minimum distance between the robot and obstacles using latent vectors as inputs. The learned distance gradient is then used to calculate the direction of movement in the latent space to move the robot away from obstacles. Based on this, a local path optimization algorithm in the latent space is proposed, and it is integrated with the path validity checking process to reduce the time of replanning. The proposed method is compared with state-of-the-art algorithms in multiple planning scenarios, demonstrating the fastest planning speed

MPC/Planning0 citations2025-12-30arXiv ->

Heteroscedastic Bayesian Optimization-Based Dynamic PID Tuning for Accurate and Robust UAV Trajectory Tracking

Fuqiang Gu, Jiangshan Ai, Xu Lu, Xianlei Long, Yan Li et al.

Unmanned Aerial Vehicles (UAVs) play an important role in various applications, where precise trajectory tracking is crucial. However, conventional control algorithms for trajectory tracking often exhibit limited performance due to the underactuated, nonlinear, and highly coupled dynamics of quadrotor systems. To address these challenges, we propose HBO-PID, a novel control algorithm that integrates the Heteroscedastic Bayesian Optimization (HBO) framework with the classical PID controller to achieve accurate and robust trajectory tracking. By explicitly modeling input-dependent noise variance, the proposed method can better adapt to dynamic and complex environments, and therefore improve the accuracy and robustness of trajectory tracking. To accelerate the convergence of optimization, we adopt a two-stage optimization strategy that allow us to more efficiently find the optimal controller parameters. Through experiments in both simulation and real-world scenarios, we demonstrate that the proposed method significantly outperforms state-of-the-art (SOTA) methods. Compared to SOTA methods, it improves the position accuracy by 24.7% to 42.9%, and the angular accuracy by 40.9% to 78.4%.

Robotics0 citations2025-12-24arXiv ->

Stretchable and High-Precision Optical Tactile Sensor for Trajectory Tracking of Parallel Mechanisms

Yiding Nie, Dongliang Fan, Jiatai Huang, Chunyu Liu, Jian S. Dai

Stretchable sensors indicate promising prospects for soft robotics, medical devices, and human-machine interactions due to the high compliance of soft materials. Discrete sensing strategies, including sensor arrays and distributed sensors, are broadly involved in tactile sensors across versatile applications. However, it remains a challenge to achieve high spatial resolution with self-decoupled capacity and insensitivity to other off-axis stimuli for stretchable tactile sensors. Herein, we develop a stretchable tactile sensor based on the proposed continuous spectral-filtering principle, allowing superhigh resolution for applied stimuli. This proposed sensor enables a high-linear spatial response (0.996) even during stretching and bending, and high continuous spatial (7 μm) and force (5 mN) resolutions with design scalability and interaction robustness to survive piercing and cutting. We further demonstrate the sensors' performance by integrating them into a planar parallel mechanism for precise trajectory tracking (rotational resolution: 0.02°) in real time.

Robotics0 citations2025-12-23arXiv ->

Energy-Efficient Omnidirectional Locomotion for Wheeled Quadrupeds via Predictive Energy-Aware Nominal Gait Selection

Xu Yang, Wei Yang, Kaibo He, Bo Yang, Yanan Sui et al.

Wheeled-legged robots combine the efficiency of wheels with the versatility of legs, but face significant energy optimization challenges when navigating diverse environments. In this work, we present a hierarchical control framework that integrates predictive power modeling with residual reinforcement learning to optimize omnidirectional locomotion efficiency for wheeled quadrupedal robots. Our approach employs a novel power prediction network that forecasts energy consumption across different gait patterns over a 1-second horizon, enabling intelligent selection of the most energy-efficient nominal gait. A reinforcement learning policy then generates residual adjustments to this nominal gait, fine-tuning the robot's actions to balance energy efficiency with performance objectives. Comparative analysis shows our method reduces energy consumption by up to 35\% compared to fixed-gait approaches while maintaining comparable velocity tracking performance. We validate our framework through extensive simulations and real-world experiments on a modified Unitree Go1 platform, demonstrating robust performance even under external disturbances. Videos and implementation details are available at \href{https://sites.google.com/view/switching-wpg}{https://sites.google.com/view/switching-wpg}.

Robotics0 citations2025-12-19arXiv ->

SurgiPose: Estimating Surgical Tool Kinematics from Monocular Video for Surgical Robot Learning

Juo-Tung Chen, XinHao Chen, Ji Woong Kim, Paul Maria Scheikl, Richard Jaepyeong Cha et al.

Imitation learning (IL) has shown immense promise in enabling autonomous dexterous manipulation, including learning surgical tasks. To fully unlock the potential of IL for surgery, access to clinical datasets is needed, which unfortunately lack the kinematic data required for current IL approaches. A promising source of large-scale surgical demonstrations is monocular surgical videos available online, making monocular pose estimation a crucial step toward enabling large-scale robot learning. Toward this end, we propose SurgiPose, a differentiable rendering based approach to estimate kinematic information from monocular surgical videos, eliminating the need for direct access to ground truth kinematics. Our method infers tool trajectories and joint angles by optimizing tool pose parameters to minimize the discrepancy between rendered and real images. To evaluate the effectiveness of our approach, we conduct experiments on two robotic surgical tasks: tissue lifting and needle pickup, using the da Vinci Research Kit Si (dVRK Si). We train imitation learning policies with both ground truth measured kinematics and estimated kinematics from video and compare their performance. Our results show that policies trained on estimated kinematics achieve comparable success rates to those trained on ground truth data, demonstrating the feasibility of using monocular video based kinematic estimation for surgical robot learning. By enabling kinematic estimation from monocular surgical videos, our work lays the foundation for large scale learning of autonomous surgical policies from online surgical data.

Learning0 citations2025-12-16arXiv ->

CLAIM: Camera-LiDAR Alignment with Intensity and Monodepth

Zhuo Zhang, Yonghui Liu, Meijie Zhang, Feiyang Tan, Yikang Ding

In this paper, we unleash the potential of the powerful monodepth model in camera-LiDAR calibration and propose CLAIM, a novel method of aligning data from the camera and LiDAR. Given the initial guess and pairs of images and LiDAR point clouds, CLAIM utilizes a coarse-to-fine searching method to find the optimal transformation minimizing a patched Pearson correlation-based structure loss and a mutual information-based texture loss. These two losses serve as good metrics for camera-LiDAR alignment results and require no complicated steps of data processing, feature extraction, or feature matching like most methods, rendering our method simple and adaptive to most scenes. We validate CLAIM on public KITTI, Waymo, and MIAS-LCEC datasets, and the experimental results demonstrate its superior performance compared with the state-of-the-art methods. The code is available at https://github.com/Tompson11/claim.

Robotics0 citations2025-12-11arXiv ->

Mr. Virgil: Learning Multi-robot Visual-range Relative Localization

Si Wang, Zhehan Li, Jiadong Lu, Rong Xiong, Yanjun Cao et al.

Ultra-wideband (UWB)-vision fusion localization has achieved extensive applications in the domain of multi-agent relative localization. The challenging matching problem between robots and visual detection renders existing methods highly dependent on identity-encoded hardware or delicate tuning algorithms. Overconfident yet erroneous matches may bring about irreversible damage to the localization system. To address this issue, we introduce Mr. Virgil, an end-to-end learning multi-robot visual-range relative localization framework, consisting of a graph neural network for data association between UWB rangings and visual detections, and a differentiable pose graph optimization (PGO) back-end. The graph-based front-end supplies robust matching results, accurate initial position predictions, and credible uncertainty estimates, which are subsequently integrated into the PGO back-end to elevate the accuracy of the final pose estimation. Additionally, a decentralized system is implemented for real-world applications. Experiments spanning varying robot numbers, simulation and real-world, occlusion and non-occlusion conditions showcase the stability and exactitude under various scenes compared to conventional methods. Our code is available at: https://github.com/HiOnes/Mr-Virgil.

Robotics0 citations2025-11-19arXiv ->

Decentralized Gaussian Process Classification and an Application in Subsea Robotics

Yifei Gao, Hans J. He, Daniel J. Stilwell, James McMahon

Teams of cooperating autonomous underwater vehicles (AUVs) rely on acoustic communication for coordination, yet this communication medium is constrained by limited range, multi-path effects, and low bandwidth. One way to address the uncertainty associated with acoustic communication is to learn the communication environment in real-time. We address the challenge of a team of robots building a map of the probability of communication success from one location to another in real-time. This is a decentralized classification problem -- communication events are either successful or unsuccessful -- where AUVs share a subset of their communication measurements to build the map. The main contribution of this work is a rigorously derived data sharing policy that selects measurements to be shared among AUVs. We experimentally validate our proposed sharing policy using real acoustic communication data collected from teams of Virginia Tech 690 AUVs, demonstrating its effectiveness in underwater environments.

Robotics0 citations2025-11-19arXiv ->

RRT*former: Environment-Aware Sampling-Based Motion Planning using Transformer

Mingyang Feng, Shaoyuan Li, Xiang Yin

We investigate the sampling-based optimal path planning problem for robotics in complex and dynamic environments. Most existing sampling-based algorithms neglect environmental information or the information from previous samples. Yet, these pieces of information are highly informative, as leveraging them can provide better heuristics when sampling the next state. In this paper, we propose a novel sampling-based planning algorithm, called \emph{RRT*former}, which integrates the standard RRT* algorithm with a Transformer network in a novel way. Specifically, the Transformer is used to extract features from the environment and leverage information from previous samples to better guide the sampling process. Our extensive experiments demonstrate that, compared to existing sampling-based approaches such as RRT*, Neural RRT*, and their variants, our algorithm achieves considerable improvements in both the optimality of the path and sampling efficiency. The code for our implementation is available on https://github.com/fengmingyang666/RRTformer.

Robotics0 citations2025-11-18arXiv ->

iGaussian: Real-Time Camera Pose Estimation via Feed-Forward 3D Gaussian Splatting Inversion

Hao Wang, Linqing Zhao, Xiuwei Xu, Jiwen Lu, Haibin Yan

Recent trends in SLAM and visual navigation have embraced 3D Gaussians as the preferred scene representation, highlighting the importance of estimating camera poses from a single image using a pre-built Gaussian model. However, existing approaches typically rely on an iterative \textit{render-compare-refine} loop, where candidate views are first rendered using NeRF or Gaussian Splatting, then compared against the target image, and finally, discrepancies are used to update the pose. This multi-round process incurs significant computational overhead, hindering real-time performance in robotics. In this paper, we propose iGaussian, a two-stage feed-forward framework that achieves real-time camera pose estimation through direct 3D Gaussian inversion. Our method first regresses a coarse 6DoF pose using a Gaussian Scene Prior-based Pose Regression Network with spatial uniform sampling and guided attention mechanisms, then refines it through feature matching and multi-model fusion. The key contribution lies in our cross-correlation module that aligns image embeddings with 3D Gaussian attributes without differentiable rendering, coupled with a Weighted Multiview Predictor that fuses features from Multiple strategically sampled viewpoints. Experimental results on the NeRF Synthetic, Mip-NeRF 360, and T\&T+DB datasets demonstrate a significant performance improvement over previous methods, reducing median rotation errors to 0.2° while achieving 2.87 FPS tracking on mobile robots, which is an impressive 10 times speedup compared to optimization-based approaches. Code: https://github.com/pythongod-exe/iGaussian

Robotics0 citations2025-11-17arXiv ->

OpenRoboCare: A Multimodal Multi-Task Expert Demonstration Dataset for Robot Caregiving

Xiaoyu Liang, Ziang Liu, Kelvin Lin, Edward Gu, Ruolin Ye et al.

We present OpenRoboCare, a multimodal dataset for robot caregiving, capturing expert occupational therapist demonstrations of Activities of Daily Living (ADLs). Caregiving tasks involve complex physical human-robot interactions, requiring precise perception under occlusions, safe physical contact, and long-horizon planning. While recent advances in robot learning from demonstrations have shown promise, there is a lack of a large-scale, diverse, and expert-driven dataset that captures real-world caregiving routines. To address this gap, we collect data from 21 occupational therapists performing 15 ADL tasks on two manikins. The dataset spans five modalities: RGB-D video, pose tracking, eye-gaze tracking, task and action annotations, and tactile sensing, providing rich multimodal insights into caregiver movement, attention, force application, and task execution strategies. We further analyze expert caregiving principles and strategies, offering insights to improve robot efficiency and task feasibility. Additionally, our evaluations demonstrate that OpenRoboCare presents challenges for state-of-the-art robot perception and human activity recognition methods, both critical for developing safe and adaptive assistive robots, highlighting the value of our contribution. See our website for additional visualizations: https://emprise.cs.cornell.edu/robo-care/.

Robotics0 citations2025-11-17arXiv ->

TOPP-DWR: Time-Optimal Path Parameterization of Differential-Driven Wheeled Robots Considering Piecewise-Constant Angular Velocity Constraints

Yong Li, Yujun Huang, Yi Chen, Hui Cheng

Differential-driven wheeled robots (DWR) represent the quintessential type of mobile robots and find extensive appli- cations across the robotic field. Most high-performance control approaches for DWR explicitly utilize the linear and angular velocities of the trajectory as control references. However, existing research on time-optimal path parameterization (TOPP) for mobile robots usually neglects the angular velocity and joint vel- ocity constraints, which can result in degraded control perfor- mance in practical applications. In this article, a systematic and practical TOPP algorithm named TOPP-DWR is proposed for DWR and other mobile robots. First, the non-uniform B-spline is adopted to represent the initial trajectory in the task space. Second, the piecewise-constant angular velocity, as well as joint velocity, linear velocity, and linear acceleration constraints, are incorporated into the TOPP problem. During the construction of the optimization problem, the aforementioned constraints are uniformly represented as linear velocity constraints. To boost the numerical computational efficiency, we introduce a slack variable to reformulate the problem into second-order-cone programming (SOCP). Subsequently, comparative experiments are conducted to validate the superiority of the proposed method. Quantitative performance indexes show that TOPP-DWR achieves TOPP while adhering to all constraints. Finally, field autonomous navigation experiments are carried out to validate the practicability of TOPP-DWR in real-world applications.

MPC/Planning0 citations2025-11-12arXiv ->

Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning

Yunchang Ma, Tenglong Liu, Yixing Lan, Xin Yin, Changxin Zhang et al.

In offline reinforcement learning, value overestimation caused by out-of-distribution (OOD) actions significantly limits policy performance. Recently, diffusion models have been leveraged for their strong distribution-matching capabilities, enforcing conservatism through behavior policy constraints. However, existing methods often apply indiscriminate regularization to redundant actions in low-quality datasets, resulting in excessive conservatism and an imbalance between the expressiveness and efficiency of diffusion modeling. To address these issues, we propose DIffusion policies with Value-conditional Optimization (DIVO), a novel approach that leverages diffusion models to generate high-quality, broadly covered in-distribution state-action samples while facilitating efficient policy improvement. Specifically, DIVO introduces a binary-weighted mechanism that utilizes the advantage values of actions in the offline dataset to guide diffusion model training. This enables a more precise alignment with the dataset's distribution while selectively expanding the boundaries of high-advantage actions. During policy improvement, DIVO dynamically filters high-return-potential actions from the diffusion model, effectively guiding the learned policy toward better performance. This approach achieves a critical balance between conservatism and explorability in offline RL. We evaluate DIVO on the D4RL benchmark and compare it against state-of-the-art baselines. Empirical results demonstrate that DIVO achieves superior performance, delivering significant improvements in average returns across locomotion tasks and outperforming existing methods in the challenging AntMaze domain, where sparse rewards pose a major difficulty.

Robotics0 citations2025-11-10arXiv ->

Leveraging Text-Driven Semantic Variation for Robust OOD Segmentation

Seungheon Song, Jaekoo Lee

In autonomous driving and robotics, ensuring road safety and reliable decision-making critically depends on out-of-distribution (OOD) segmentation. While numerous methods have been proposed to detect anomalous objects on the road, leveraging the vision-language space-which provides rich linguistic knowledge-remains an underexplored field. We hypothesize that incorporating these linguistic cues can be especially beneficial in the complex contexts found in real-world autonomous driving scenarios. To this end, we present a novel approach that trains a Text-Driven OOD Segmentation model to learn a semantically diverse set of objects in the vision-language space. Concretely, our approach combines a vision-language model's encoder with a transformer decoder, employs Distance-Based OOD prompts located at varying semantic distances from in-distribution (ID) classes, and utilizes OOD Semantic Augmentation for OOD representations. By aligning visual and textual information, our approach effectively generalizes to unseen objects and provides robust OOD segmentation in diverse driving environments. We conduct extensive experiments on publicly available OOD segmentation datasets such as Fishyscapes, Segment-Me-If-You-Can, and Road Anomaly datasets, demonstrating that our approach achieves state-of-the-art performance across both pixel-level and object-level evaluations. This result underscores the potential of vision-language-based OOD segmentation to bolster the safety and reliability of future autonomous driving systems.

Robotics0 citations2025-11-10arXiv ->

Semi-distributed Cross-modal Air-Ground Relative Localization

Weining Lu, Deer Bin, Lian Ma, Ming Ma, Zhihao Ma et al.

Efficient, accurate, and flexible relative localization is crucial in air-ground collaborative tasks. However, current approaches for robot relative localization are primarily realized in the form of distributed multi-robot SLAM systems with the same sensor configuration, which are tightly coupled with the state estimation of all robots, limiting both flexibility and accuracy. To this end, we fully leverage the high capacity of Unmanned Ground Vehicle (UGV) to integrate multiple sensors, enabling a semi-distributed cross-modal air-ground relative localization framework. In this work, both the UGV and the Unmanned Aerial Vehicle (UAV) independently perform SLAM while extracting deep learning-based keypoints and global descriptors, which decouples the relative localization from the state estimation of all agents. The UGV employs a local Bundle Adjustment (BA) with LiDAR, camera, and an IMU to rapidly obtain accurate relative pose estimates. The BA process adopts sparse keypoint optimization and is divided into two stages: First, optimizing camera poses interpolated from LiDAR-Inertial Odometry (LIO), followed by estimating the relative camera poses between the UGV and UAV. Additionally, we implement an incremental loop closure detection algorithm using deep learning-based descriptors to maintain and retrieve keyframes efficiently. Experimental results demonstrate that our method achieves outstanding performance in both accuracy and efficiency. Unlike traditional multi-robot SLAM approaches that transmit images or point clouds, our method only transmits keypoint pixels and their descriptors, effectively constraining the communication bandwidth under 0.3 Mbps. Codes and data will be publicly available on https://github.com/Ascbpiac/cross-model-relative-localization.git.

Robotics0 citations2025-11-07arXiv ->

Let Me Show You: Learning by Retrieving from Egocentric Video for Robotic Manipulation

Yichen Zhu, Feifei Feng

Robots operating in complex and uncertain environments face considerable challenges. Advanced robotic systems often rely on extensive datasets to learn manipulation tasks. In contrast, when humans are faced with unfamiliar tasks, such as assembling a chair, a common approach is to learn by watching video demonstrations. In this paper, we propose a novel method for learning robot policies by Retrieving-from-Video (RfV), using analogies from human demonstrations to address manipulation tasks. Our system constructs a video bank comprising recordings of humans performing diverse daily tasks. To enrich the knowledge from these videos, we extract mid-level information, such as object affordance masks and hand motion trajectories, which serve as additional inputs to enhance the robot model's learning and generalization capabilities. We further feature a dual-component system: a video retriever that taps into an external video bank to fetch task-relevant video based on task specification, and a policy generator that integrates this retrieved knowledge into the learning cycle. This approach enables robots to craft adaptive responses to various scenarios and generalize to tasks beyond those in the training data. Through rigorous testing in multiple simulated and real-world settings, our system demonstrates a marked improvement in performance over conventional robotic systems, showcasing a significant breakthrough in the field of robotics.

Learning0 citations2025-11-06arXiv ->

BoRe-Depth: Self-supervised Monocular Depth Estimation with Boundary Refinement for Embedded Systems

Chang Liu, Juan Li, Sheng Zhang, Chang Liu, Jie Li et al.

Depth estimation is one of the key technologies for realizing 3D perception in unmanned systems. Monocular depth estimation has been widely researched because of its low-cost advantage, but the existing methods face the challenges of poor depth estimation performance and blurred object boundaries on embedded systems. In this paper, we propose a novel monocular depth estimation model, BoRe-Depth, which contains only 8.7M parameters. It can accurately estimate depth maps on embedded systems and significantly improves boundary quality. Firstly, we design an Enhanced Feature Adaptive Fusion Module (EFAF) which adaptively fuses depth features to enhance boundary detail representation. Secondly, we integrate semantic knowledge into the encoder to improve the object recognition and boundary perception capabilities. Finally, BoRe-Depth is deployed on NVIDIA Jetson Orin, and runs efficiently at 50.7 FPS. We demonstrate that the proposed model significantly outperforms previous lightweight models on multiple challenging datasets, and we provide detailed ablation studies for the proposed methods. The code is available at https://github.com/liangxiansheng093/BoRe-Depth.

Robotics0 citations2025-11-06arXiv ->

Integrating Ergonomics and Manipulability for Upper Limb Postural Optimization in Bimanual Human-Robot Collaboration

Chenzui Li, Yiming Chen, Xi Wu, Giacinto Barresi, Fei Chen

This paper introduces an upper limb postural optimization method for enhancing physical ergonomics and force manipulability during bimanual human-robot co-carrying tasks. Existing research typically emphasizes human safety or manipulative efficiency, whereas our proposed method uniquely integrates both aspects to strengthen collaboration across diverse conditions (e.g., different grasping postures of humans, and different shapes of objects). Specifically, the joint angles of a simplified human skeleton model are optimized by minimizing the cost function to prioritize safety and manipulative capability. To guide humans towards the optimized posture, the reference end-effector poses of the robot are generated through a transformation module. A bimanual model predictive impedance controller (MPIC) is proposed for our human-like robot, CURI, to recalibrate the end effector poses through planned trajectories. The proposed method has been validated through various subjects and objects during human-human collaboration (HHC) and human-robot collaboration (HRC). The experimental results demonstrate significant improvement in muscle conditions by comparing the activation of target muscles before and after optimization.

Robotics0 citations2025-11-04arXiv ->

Synthetic Crop-Weed Image Generation and its Impact on Model Generalization

Garen Boyadjian, Cyrille Pierre, Johann Laconte, Riccardo Bertoglio

Precise semantic segmentation of crops and weeds is necessary for agricultural weeding robots. However, training deep learning models requires large annotated datasets, which are costly to obtain in real fields. Synthetic data can reduce this burden, but the gap between simulated and real images remains a challenge. In this paper, we present a pipeline for procedural generation of synthetic crop-weed images using Blender, producing annotated datasets under diverse conditions of plant growth, weed density, lighting, and camera angle. We benchmark several state-of-the-art segmentation models on synthetic and real datasets and analyze their cross-domain generalization. Our results show that training on synthetic images leads to a sim-to-real gap of 10%, surpassing previous state-of-the-art methods. Moreover, synthetic data demonstrates good generalization properties, outperforming real datasets in cross-domain scenarios. These findings highlight the potential of synthetic agricultural datasets and support hybrid strategies for more efficient model training.

Robotics0 citations2025-11-03arXiv ->

FoldPath: End-to-End Object-Centric Motion Generation via Modulated Implicit Paths

Paolo Rabino, Gabriele Tiboni, Tatiana Tommasi

Object-Centric Motion Generation (OCMG) is instrumental in advancing automated manufacturing processes, particularly in domains requiring high-precision expert robotic motions, such as spray painting and welding. To realize effective automation, robust algorithms are essential for generating extended, object-aware trajectories across intricate 3D geometries. However, contemporary OCMG techniques are either based on ad-hoc heuristics or employ learning-based pipelines that are still reliant on sensitive post-processing steps to generate executable paths. We introduce FoldPath, a novel, end-to-end, neural field based method for OCMG. Unlike prior deep learning approaches that predict discrete sequences of end-effector waypoints, FoldPath learns the robot motion as a continuous function, thus implicitly encoding smooth output paths. This paradigm shift eliminates the need for brittle post-processing steps that concatenate and order the predicted discrete waypoints. Particularly, our approach demonstrates superior predictive performance compared to recently proposed learning-based methods, and attains generalization capabilities even in real industrial settings, where only a limited amount of 70 expert samples are provided. We validate FoldPath through comprehensive experiments in a realistic simulation environment and introduce new, rigorous metrics designed to comprehensively evaluate long-horizon robotic paths, thus advancing the OCMG task towards practical maturity.

Robotics0 citations2025-11-03arXiv ->

CM-LIUW-Odometry: Robust and High-Precision LiDAR-Inertial-UWB-Wheel Odometry for Extreme Degradation Coal Mine Tunnels

Kun Hu, Menggang Li, Zhiwen Jin, Chaoquan Tang, Eryi Hu et al.

Simultaneous Localization and Mapping (SLAM) in large-scale, complex, and GPS-denied underground coal mine environments presents significant challenges. Sensors must contend with abnormal operating conditions: GPS unavailability impedes scene reconstruction and absolute geographic referencing, uneven or slippery terrain degrades wheel odometer accuracy, and long, feature-poor tunnels reduce LiDAR effectiveness. To address these issues, we propose CoalMine-LiDAR-IMU-UWB-Wheel-Odometry (CM-LIUW-Odometry), a multimodal SLAM framework based on the Iterated Error-State Kalman Filter (IESKF). First, LiDAR-inertial odometry is tightly fused with UWB absolute positioning constraints to align the SLAM system with a global coordinate. Next, wheel odometer is integrated through tight coupling, enhanced by nonholonomic constraints (NHC) and vehicle lever arm compensation, to address performance degradation in areas beyond UWB measurement range. Finally, an adaptive motion mode switching mechanism dynamically adjusts the robot's motion mode based on UWB measurement range and environmental degradation levels. Experimental results validate that our method achieves superior accuracy and robustness in real-world underground coal mine scenarios, outperforming state-of-the-art approaches. We open source our code of this work on Github to benefit the robotics community.

Robotics0 citations2025-10-30arXiv ->

REALMS2 -- Resilient Exploration And Lunar Mapping System 2 -- A Comprehensive Approach

Dave van der Meer, Loïck P. Chovet, Gabriel M. Garcia, Abhishek Bera, Miguel A. Olivares-Mendez

The European Space Agency (ESA) and the European Space Resources Innovation Centre (ESRIC) created the Space Resources Challenge to invite researchers and companies to propose innovative solutions for Multi-Robot Systems (MRS) space prospection. This paper proposes the Resilient Exploration And Lunar Mapping System 2 (REALMS2), a MRS framework for planetary prospection and mapping. Based on Robot Operating System version 2 (ROS 2) and enhanced with Visual Simultaneous Localisation And Mapping (vSLAM) for map generation, REALMS2 uses a mesh network for a robust ad hoc network. A single graphical user interface (GUI) controls all the rovers, providing a simple overview of the robotic mission. This system is designed for heterogeneous multi-robot exploratory missions, tackling the challenges presented by extraterrestrial environments. REALMS2 was used during the second field test of the ESA-ESRIC Challenge and allowed to map around 60% of the area, using three homogeneous rovers while handling communication delays and blackouts.

Robotics0 citations2025-10-29arXiv ->

Efficient Online Learning with Predictive Coding Networks: Exploiting Temporal Correlations

Darius Masoum Zadeh-Jousdani, Elvin Hajizada, Eyke Hüllermeier

Robotic systems operating at the edge require efficient online learning algorithms that can continuously adapt to changing environments while processing streaming sensory data. Traditional backpropagation, while effective, conflicts with biological plausibility principles and may be suboptimal for continuous adaptation scenarios. The Predictive Coding (PC) framework offers a biologically plausible alternative with local, Hebbian-like update rules, making it suitable for neuromorphic hardware implementation. However, PC's main limitation is its computational overhead due to multiple inference iterations during training. We present Predictive Coding Network with Temporal Amortization (PCN-TA), which preserves latent states across temporal frames. By leveraging temporal correlations, PCN-TA significantly reduces computational demands while maintaining learning performance. Our experiments on the COIL-20 robotic perception dataset demonstrate that PCN-TA achieves 10% fewer weight updates compared to backpropagation and requires 50% fewer inference steps than baseline PC networks. These efficiency gains directly translate to reduced computational overhead for moving another step toward edge deployment and real-time adaptation support in resource-constrained robotic systems. The biologically-inspired nature of our approach also makes it a promising candidate for future neuromorphic hardware implementations, enabling efficient online learning at the edge.

Robotics0 citations2025-10-28arXiv ->

Enhancing Vision-Language Models for Autonomous Driving through Task-Specific Prompting and Spatial Reasoning

Aodi Wu, Xubo Luo

This technical report presents our solution for the RoboSense Challenge at IROS 2025, which evaluates Vision-Language Models (VLMs) on autonomous driving scene understanding across perception, prediction, planning, and corruption detection tasks. We propose a systematic framework built on four core components. First, a Mixture-of-Prompts router classifies questions and dispatches them to task-specific expert prompts, eliminating interference across diverse question types. Second, task-specific prompts embed explicit coordinate systems, spatial reasoning rules, role-playing, Chain-of-Thought/Tree-of-Thought reasoning, and few-shot examples tailored to each task. Third, a visual assembly module composes multi-view images with object crops, magenta markers, and adaptive historical frames based on question requirements. Fourth, we configure model inference parameters (temperature, top-p, message roles) per task to optimize output quality. Implemented on Qwen2.5-VL-72B, our approach achieves 70.87% average accuracy on Phase-1 (clean data) and 72.85% on Phase-2 (corrupted data), demonstrating that structured prompting and spatial grounding substantially enhance VLM performance on safety-critical autonomous driving tasks. Code and prompt are available at https://github.com/wuaodi/UCAS-CSU-phase2.

Robotics0 citations2025-10-27arXiv ->

Stand, Walk, Navigate: Recovery-Aware Visual Navigation on a Low-Cost Wheeled Quadruped

Jans Solano, Diego Quiroz

Wheeled-legged robots combine the efficiency of wheels with the obstacle negotiation of legs, yet many state-of-the-art systems rely on costly actuators and sensors, and fall-recovery is seldom integrated, especially for wheeled-legged morphologies. This work presents a recovery-aware visual-inertial navigation system on a low-cost wheeled quadruped. The proposed system leverages vision-based perception from a depth camera and deep reinforcement learning policies for robust locomotion and autonomous recovery from falls across diverse terrains. Simulation experiments show agile mobility with low-torque actuators over irregular terrain and reliably recover from external perturbations and self-induced failures. We further show goal directed navigation in structured indoor spaces with low-cost perception. Overall, this approach lowers the barrier to deploying autonomous navigation and robust locomotion policies in budget-constrained robotic platforms.

Robotics0 citations2025-10-27arXiv ->

DPGLA: Bridging the Gap between Synthetic and Real Data for Unsupervised Domain Adaptation in 3D LiDAR Semantic Segmentation

Wanmeng Li, Simone Mosco, Daniel Fusaro, Alberto Pretto

Annotating real-world LiDAR point clouds for use in intelligent autonomous systems is costly. To overcome this limitation, self-training-based Unsupervised Domain Adaptation (UDA) has been widely used to improve point cloud semantic segmentation by leveraging synthetic point cloud data. However, we argue that existing methods do not effectively utilize unlabeled data, as they either rely on predefined or fixed confidence thresholds, resulting in suboptimal performance. In this paper, we propose a Dynamic Pseudo-Label Filtering (DPLF) scheme to enhance real data utilization in point cloud UDA semantic segmentation. Additionally, we design a simple and efficient Prior-Guided Data Augmentation Pipeline (PG-DAP) to mitigate domain shift between synthetic and real-world point clouds. Finally, we utilize data mixing consistency loss to push the model to learn context-free representations. We implement and thoroughly evaluate our approach through extensive comparisons with state-of-the-art methods. Experiments on two challenging synthetic-to-real point cloud semantic segmentation tasks demonstrate that our approach achieves superior performance. Ablation studies confirm the effectiveness of the DPLF and PG-DAP modules. We release the code of our method in this paper.

Robotics0 citations2025-10-27arXiv ->

Awakening Facial Emotional Expressions in Human-Robot

Yongtong Zhu, Lei Li, Iggy Qian, WenBin Zhou, Ye Yuan et al.

The facial expression generation capability of humanoid social robots is critical for achieving natural and human-like interactions, playing a vital role in enhancing the fluidity of human-robot interactions and the accuracy of emotional expression. Currently, facial expression generation in humanoid social robots still relies on pre-programmed behavioral patterns, which are manually coded at high human and time costs. To enable humanoid robots to autonomously acquire generalized expressive capabilities, they need to develop the ability to learn human-like expressions through self-training. To address this challenge, we have designed a highly biomimetic robotic face with physical-electronic animated facial units and developed an end-to-end learning framework based on KAN (Kolmogorov-Arnold Network) and attention mechanisms. Unlike previous humanoid social robots, we have also meticulously designed an automated data collection system based on expert strategies of facial motion primitives to construct the dataset. Notably, to the best of our knowledge, this is the first open-source facial dataset for humanoid social robots. Comprehensive evaluations indicate that our approach achieves accurate and diverse facial mimicry across different test subjects.

Robotics0 citations2025-10-27arXiv ->

ManiDP: Manipulability-Aware Diffusion Policy for Posture-Dependent Bimanual Manipulation

Zhuo Li, Junjia Liu, Dianxi Li, Tao Teng, Miao Li et al.

Recent work has demonstrated the potential of diffusion models in robot bimanual skill learning. However, existing methods ignore the learning of posture-dependent task features, which are crucial for adapting dual-arm configurations to meet specific force and velocity requirements in dexterous bimanual manipulation. To address this limitation, we propose Manipulability-Aware Diffusion Policy (ManiDP), a novel imitation learning method that not only generates plausible bimanual trajectories, but also optimizes dual-arm configurations to better satisfy posture-dependent task requirements. ManiDP achieves this by extracting bimanual manipulability from expert demonstrations and encoding the encapsulated posture features using Riemannian-based probabilistic models. These encoded posture features are then incorporated into a conditional diffusion process to guide the generation of task-compatible bimanual motion sequences. We evaluate ManiDP on six real-world bimanual tasks, where the experimental results demonstrate a 39.33$\%$ increase in average manipulation success rate and a 0.45 improvement in task compatibility compared to baseline methods. This work highlights the importance of integrating posture-relevant robotic priors into bimanual skill diffusion to enable human-like adaptability and dexterity.

MPC/Planning0 citations2025-10-26arXiv ->

TWC-SLAM: Multi-Agent Cooperative SLAM with Text Semantics and WiFi Features Integration for Similar Indoor Environments

Chunyu Li, Shoubin Chen, Dong Li, Weixing Xue, Qingquan Li

Multi-agent cooperative SLAM often encounters challenges in similar indoor environments characterized by repetitive structures, such as corridors and rooms. These challenges can lead to significant inaccuracies in shared location identification when employing point cloud-based techniques. To mitigate these issues, we introduce TWC-SLAM, a multi-agent cooperative SLAM framework that integrates text semantics and WiFi signal features to enhance location identification and loop closure detection. TWC-SLAM comprises a single-agent front-end odometry module based on FAST-LIO2, a location identification and loop closure detection module that leverages text semantics and WiFi features, and a global mapping module. The agents are equipped with sensors capable of capturing textual information and detecting WiFi signals. By correlating these data sources, TWC-SLAM establishes a common location, facilitating point cloud alignment across different agents' maps. Furthermore, the system employs loop closure detection and optimization modules to achieve global optimization and cohesive mapping. We evaluated our approach using an indoor dataset featuring similar corridors, rooms, and text signs. The results demonstrate that TWC-SLAM significantly improves the performance of cooperative SLAM systems in complex environments with repetitive architectural features.

Learning0 citations2025-10-26arXiv ->

SCAL for Pinch-Lifting: Complementary Rotational and Linear Prototypes for Environment-Adaptive Grasping

Wentao Guo, Wenzeng Zhang

This paper presents environment-adaptive pinch-lifting built on a slot-constrained adaptive linkage (SCAL) and instantiated in two complementary fingers: SCAL-R, a rotational-drive design with an active fingertip that folds inward after contact to form an envelope, and SCAL-L, a linear-drive design that passively opens on contact to span wide or weak-feature objects. Both fingers convert surface following into an upward lifting branch while maintaining fingertip orientation, enabling thin or low-profile targets to be raised from supports with minimal sensing and control. Two-finger grippers are fabricated via PLA-based 3D printing. Experiments evaluate (i) contact-preserving sliding and pinch-lifting on tabletops, (ii) ramp negotiation followed by lift, and (iii) handling of bulky objects via active enveloping (SCAL-R) or contact-triggered passive opening (SCAL-L). Across dozens of trials on small parts, boxes, jars, and tape rolls, both designs achieve consistent grasps with limited tuning. A quasi-static analysis provides closed-form fingertip-force models for linear parallel pinching and two-point enveloping, offering geometry-aware guidance for design and operation. Overall, the results indicate complementary operating regimes and a practical path to robust, environment-adaptive grasping with simple actuation.

Learning0 citations2025-10-26arXiv ->

Bag-of-Word-Groups (BoWG): A Robust and Efficient Loop Closure Detection Method Under Perceptual Aliasing

Xiang Fei, Tina Tian, Howie Choset, Lu Li

Loop closure is critical in Simultaneous Localization and Mapping (SLAM) systems to reduce accumulative drift and ensure global mapping consistency. However, conventional methods struggle in perceptually aliased environments, such as narrow pipes, due to vector quantization, feature sparsity, and repetitive textures, while existing solutions often incur high computational costs. This paper presents Bag-of-Word-Groups (BoWG), a novel loop closure detection method that achieves superior precision-recall, robustness, and computational efficiency. The core innovation lies in the introduction of word groups, which captures the spatial co-occurrence and proximity of visual words to construct an online dictionary. Additionally, drawing inspiration from probabilistic transition models, we incorporate temporal consistency directly into similarity computation with an adaptive scheme, substantially improving precision-recall performance. The method is further strengthened by a feature distribution analysis module and dedicated post-verification mechanisms. To evaluate the effectiveness of our method, we conduct experiments on both public datasets and a confined-pipe dataset we constructed. Results demonstrate that BoWG surpasses state-of-the-art methods, including both traditional and learning-based approaches, in terms of precision-recall and computational efficiency. Our approach also exhibits excellent scalability, achieving an average processing time of 16 ms per image across 17,565 images in the Bicocca25b dataset.

Robotics0 citations2025-10-25arXiv ->

Estimating Continuum Robot Shape under External Loading using Spatiotemporal Neural Networks

Enyi Wang, Zhen Deng, Chuanchuan Pan, Bingwei He, Jianwei Zhang

This paper presents a learning-based approach for accurately estimating the 3D shape of flexible continuum robots subjected to external loads. The proposed method introduces a spatiotemporal neural network architecture that fuses multi-modal inputs, including current and historical tendon displacement data and RGB images, to generate point clouds representing the robot's deformed configuration. The network integrates a recurrent neural module for temporal feature extraction, an encoding module for spatial feature extraction, and a multi-modal fusion module to combine spatial features extracted from visual data with temporal dependencies from historical actuator inputs. Continuous 3D shape reconstruction is achieved by fitting Bézier curves to the predicted point clouds. Experimental validation demonstrates that our approach achieves high precision, with mean shape estimation errors of 0.08 mm (unloaded) and 0.22 mm (loaded), outperforming state-of-the-art methods in shape sensing for TDCRs. The results validate the efficacy of deep learning-based spatiotemporal data fusion for precise shape estimation under loading conditions.

Robotics0 citations2025-10-25arXiv ->

STG-Avatar: Animatable Human Avatars via Spacetime Gaussian

Guangan Jiang, Tianzi Zhang, Dong Li, Zhenjun Zhao, Haoang Li et al.

Realistic animatable human avatars from monocular videos are crucial for advancing human-robot interaction and enhancing immersive virtual experiences. While recent research on 3DGS-based human avatars has made progress, it still struggles with accurately representing detailed features of non-rigid objects (e.g., clothing deformations) and dynamic regions (e.g., rapidly moving limbs). To address these challenges, we present STG-Avatar, a 3DGS-based framework for high-fidelity animatable human avatar reconstruction. Specifically, our framework introduces a rigid-nonrigid coupled deformation framework that synergistically integrates Spacetime Gaussians (STG) with linear blend skinning (LBS). In this hybrid design, LBS enables real-time skeletal control by driving global pose transformations, while STG complements it through spacetime adaptive optimization of 3D Gaussians. Furthermore, we employ optical flow to identify high-dynamic regions and guide the adaptive densification of 3D Gaussians in these regions. Experimental results demonstrate that our method consistently outperforms state-of-the-art baselines in both reconstruction quality and operational efficiency, achieving superior quantitative metrics while retaining real-time rendering capabilities. Our code is available at https://github.com/jiangguangan/STG-Avatar

Robotics0 citations2025-10-23arXiv ->

A Parameter-Efficient Mixture-of-Experts Framework for Cross-Modal Geo-Localization

LinFeng Li, Jian Zhao, Zepeng Yang, Yuhang Song, Bojun Lin et al.

We present a winning solution to RoboSense 2025 Track 4: Cross-Modal Drone Navigation. The task retrieves the most relevant geo-referenced image from a large multi-platform corpus (satellite/drone/ground) given a natural-language query. Two obstacles are severe inter-platform heterogeneity and a domain gap between generic training descriptions and platform-specific test queries. We mitigate these with a domain-aligned preprocessing pipeline and a Mixture-of-Experts (MoE) framework: (i) platform-wise partitioning, satellite augmentation, and removal of orientation words; (ii) an LLM-based caption refinement pipeline to align textual semantics with the distinct visual characteristics of each platform. Using BGE-M3 (text) and EVA-CLIP (image), we train three platform experts using a progressive two-stage, hard-negative mining strategy to enhance discriminative power, and fuse their scores at inference. The system tops the official leaderboard, demonstrating robust cross-modal geo-localization under heterogeneous viewpoints.

Robotics0 citations2025-10-22arXiv ->

GRASPLAT: Enabling dexterous grasping through novel view synthesis

Matteo Bortolon, Nuno Ferreira Duarte, Plinio Moreno, Fabio Poiesi, José Santos-Victor et al.

Achieving dexterous robotic grasping with multi-fingered hands remains a significant challenge. While existing methods rely on complete 3D scans to predict grasp poses, these approaches face limitations due to the difficulty of acquiring high-quality 3D data in real-world scenarios. In this paper, we introduce GRASPLAT, a novel grasping framework that leverages consistent 3D information while being trained solely on RGB images. Our key insight is that by synthesizing physically plausible images of a hand grasping an object, we can regress the corresponding hand joints for a successful grasp. To achieve this, we utilize 3D Gaussian Splatting to generate high-fidelity novel views of real hand-object interactions, enabling end-to-end training with RGB data. Unlike prior methods, our approach incorporates a photometric loss that refines grasp predictions by minimizing discrepancies between rendered and real images. We conduct extensive experiments on both synthetic and real-world grasping datasets, demonstrating that GRASPLAT improves grasp success rates up to 36.9% over existing image-based methods. Project page: https://mbortolon97.github.io/grasplat/

Robotics0 citations2025-10-20arXiv ->

Botany-Bot: Digital Twin Monitoring of Occluded and Underleaf Plant Structures with Gaussian Splats

Simeon Adebola, Chung Min Kim, Justin Kerr, Shuangyu Xie, Prithvi Akella et al.

Commercial plant phenotyping systems using fixed cameras cannot perceive many plant details due to leaf occlusion. In this paper, we present Botany-Bot, a system for building detailed "annotated digital twins" of living plants using two stereo cameras, a digital turntable inside a lightbox, an industrial robot arm, and 3D segmentated Gaussian Splat models. We also present robot algorithms for manipulating leaves to take high-resolution indexable images of occluded details such as stem buds and the underside/topside of leaves. Results from experiments suggest that Botany-Bot can segment leaves with 90.8% accuracy, detect leaves with 86.2% accuracy, lift/push leaves with 77.9% accuracy, and take detailed overside/underside images with 77.3% accuracy. Code, videos, and datasets are available at https://berkeleyautomation.github.io/Botany-Bot/.

ICRA 2026 | 48 papers
CBF Related Papers
MPC/Planning0 citations2026-03-09arXiv ->

SEP-NMPC: Safety Enhanced Passivity-Based Nonlinear Model Predictive Control for a UAV Slung Payload System

Seyedreza Rezaei, Junjie Kang, Amaldev Haridevan, Jinjun Shan

Model Predictive Control (MPC) is widely adopted for agile multirotor vehicles, yet achieving both stability and obstacle-free flight is particularly challenging when a payload is suspended beneath the airframe. This paper introduces a Safety Enhanced Passivity-Based Nonlinear MPC (SEP-NMPC) that provides formal guarantees of stability and safety for a quadrotor transporting a slung payload through cluttered environments. Stability is enforced by embedding a strict passivity inequality, which is derived from a shaped energy storage function with adaptive damping, directly into the NMPC. This formulation dissipates excess energy and ensures asymptotic convergence despite payload swings. Safety is guaranteed through high-order control barrier functions (HOCBFs) that render user-defined clearance sets forward-invariant, obliging both the quadrotor and the swinging payload to maintain separation while interacting with static and dynamic obstacles. The optimization remains quadratic-program compatible and is solved online at each sampling time without gain scheduling or heuristic switching. Extensive simulations and real-world experiments confirm stable payload transport, collision-free trajectories, and real-time feasibility across all tested scenarios. The SEP-NMPC framework therefore unifies passivity-based closed-loop stability with HOCBF-based safety guarantees for UAV slung-payload transportation.

Robotics0 citations2026-03-02arXiv ->

A Safety-Aware Shared Autonomy Framework with BarrierIK Using Control Barrier Functions

Berk Guler, Kay Pompetzki, Yuanzheng Sun, Simon Manschitz, Jan Peters

Shared autonomy blends operator intent with autonomous assistance. In cluttered environments, linear blending can produce unsafe commands even when each source is individually collision-free. Many existing approaches model obstacle avoidance through potentials or cost terms, which only enforce safety as a soft constraint. In contrast, safety-critical control requires hard guarantees. We investigate the use of control barrier functions (CBFs) at the inverse kinematics (IK) layer of shared autonomy, targeting post-blend safety while preserving task performance. Our approach is evaluated in simulation on representative cluttered environments and in a VR teleoperation study comparing pure teleoperation with shared autonomy. Across conditions, employing CBFs at the IK layer reduces violation time and increases minimum clearance while maintaining task performance. In the user study, participants reported higher perceived safety and trust, lower interference, and an overall preference for shared autonomy with our safety filter. Additional materials available at https://berkguler.github.io/barrierik.

Robotics0 citations2025-11-09arXiv ->

From Demonstrations to Safe Deployment: Path-Consistent Safety Filtering for Diffusion Policies

Ralf Römer, Julian Balletshofer, Jakob Thumm, Marco Pavone, Angela P. Schoellig et al.

Diffusion policies (DPs) achieve state-of-the-art performance on complex manipulation tasks by learning from large-scale demonstration datasets, often spanning multiple embodiments and environments. However, they cannot guarantee safe behavior, requiring external safety mechanisms. These, however, alter actions in ways unseen during training, causing unpredictable behavior and performance degradation. To address these problems, we propose path-consistent safety filtering (PACS) for DPs. Our approach performs path-consistent braking on a trajectory computed from the sequence of generated actions. In this way, we keep the execution consistent with the training distribution of the policy, maintaining the learned, task-completing behavior. To enable real-time deployment and handle uncertainties, we verify safety using set-based reachability analysis. Our experimental evaluation in simulation and on three challenging real-world human-robot interaction tasks shows that PACS (a) provides formal safety guarantees in dynamic environments, (b) preserves task success rates, and (c) outperforms reactive safety approaches, such as control barrier functions, by up to 68 % in terms of task success. Videos are available at our project website: https://tum-lsy.github.io/pacs.

Robotics0 citations2025-10-16arXiv ->

CBF-RL: Safety Filtering Reinforcement Learning in Training with Control Barrier Functions

Lizhi Yang, Blake Werner, Massimiliano de Sa, Aaron D. Ames

Reinforcement learning (RL), while powerful and expressive, can often prioritize performance at the expense of safety. Yet safety violations can lead to catastrophic outcomes in real-world deployments. Control Barrier Functions (CBFs) offer a principled method to enforce dynamic safety -- traditionally deployed online via safety filters. While the result is safe behavior, the fact that the RL policy does not have knowledge of the CBF can lead to conservative behaviors. This paper proposes CBF-RL, a framework for generating safe behaviors with RL by enforcing CBFs in training. CBF-RL has two key attributes: (1) minimally modifying a nominal RL policy to encode safety constraints via a CBF term, (2) and safety filtering of the policy rollouts in training. Theoretically, we prove that continuous-time safety filters can be deployed via closed-form expressions on discrete-time roll-outs. Practically, we demonstrate that CBF-RL internalizes the safety constraints in the learned policy -- both enforcing safer actions and biasing towards safer rewards -- enabling safe deployment without the need for an online safety filter. We validate our framework through ablation studies on navigation tasks and on the Unitree G1 humanoid robot, where CBF-RL enables safer exploration, faster convergence, and robust performance under uncertainty, enabling the humanoid robot to avoid obstacles and climb stairs safely in real-world settings without a runtime safety filter.

Robotics0 citations2025-10-01arXiv ->

Beyond Collision Cones: Dynamic Obstacle Avoidance for Nonholonomic Robots via Dynamic Parabolic Control Barrier Functions

Hun Kuk Park, Taekyung Kim, Dimitra Panagou

Control Barrier Functions (CBFs) are a powerful tool for ensuring the safety of autonomous systems, yet applying them to nonholonomic robots in cluttered, dynamic environments remains an open challenge. State-of-the-art methods often rely on collision-cone or velocity-obstacle constraints which, by only considering the angle of the relative velocity, are inherently conservative and can render the CBF-based quadratic program infeasible, particularly in dense scenarios. To address this issue, we propose a Dynamic Parabolic Control Barrier Function (DPCBF) that defines the safe set using a parabolic boundary. The parabola's vertex and curvature dynamically adapt based on both the distance to an obstacle and the magnitude of the relative velocity, creating a less restrictive safety constraint. We prove that the proposed DPCBF is valid for a kinematic bicycle model subject to input constraints. Extensive comparative simulations demonstrate that our DPCBF-based controller significantly enhances navigation success rates and QP feasibility compared to baseline methods. Our approach successfully navigates through dense environments with up to 100 dynamic obstacles, scenarios where collision cone-based methods fail due to infeasibility.

Robotics0 citations2025-07-03arXiv ->

Minimal Intervention Shared Control with Guaranteed Safety under Non-Convex Constraints

Shivam Chaubey, Francesco Verdoja, Shankar Deka, Ville Kyrki

Shared control combines human intention with autonomous decision-making. At the low level, the primary goal is to maintain safety regardless of the user's input to the system. However, existing shared control methods-based on, e.g., Model Predictive Control, Control Barrier Functions, or learning-based control-often face challenges with feasibility, scalability, and mixed constraints. To address these challenges, we propose a Constraint-Aware Assistive Controller that computes control actions online while ensuring recursive feasibility, strict constraint satisfaction, and minimal deviation from the user's intent. It also accommodates a structured class of non-convex constraints common in real-world settings. We leverage Robust Controlled Invariant Sets for recursive feasibility and a Mixed-Integer Quadratic Programming formulation to handle non-convex constraints. We validate the approach through a large-scale user study with 66 participants-one of the most extensive in shared control research-using a simulated environment to assess task load, trust, and perceived control, in addition to performance. The results show consistent improvements across all these aspects without compromising safety and user intent. Additionally, a real-world experiment on a robotic manipulator demonstrates the framework's applicability under bounded disturbances, ensuring safety and collision-free operation.

Other Papers
Robotics0 citations2026-03-25arXiv ->

Knowledge-Guided Manipulation Using Multi-Task Reinforcement Learning

Aditya Narendra, Mukhammadrizo Maribjonov, Dmitry Makarov, Dmitry Yudin, Aleksandr Panov

This paper introduces Knowledge Graph based Massively Multi-task Model-based Policy Optimization (KG-M3PO), a framework for multi-task robotic manipulation in partially observable settings that unifies Perception, Knowledge, and Policy. The method augments egocentric vision with an online 3D scene graph that grounds open-vocabulary detections into a metric, relational representation. A dynamic-relation mechanism updates spatial, containment, and affordance edges at every step, and a graph neural encoder is trained end-to-end through the RL objective so that relational features are shaped directly by control performance. Multiple observation modalities (visual, proprioceptive, linguistic, and graph-based) are encoded into a shared latent space, upon which the RL agent operates to drive the control loop. The policy conditions on lightweight graph queries alongside visual and proprioceptive inputs, yielding a compact, semantically informed state for decision making. Experiments on a suite of manipulation tasks with occlusions, distractors, and layout shifts demonstrate consistent gains over strong baselines: the knowledge-conditioned agent achieves higher success rates, improved sample efficiency, and stronger generalization to novel objects and unseen scene configurations. These results support the premise that structured, continuously maintained world knowledge is a powerful inductive bias for scalable, generalizable manipulation: when the knowledge module participates in the RL computation graph, relational representations align with control, enabling robust long-horizon behavior under partial observability.

Theory0 citations2026-03-25arXiv ->

Uncertainty-Aware Vision-based Risk Object Identification via Conformal Risk Tube Prediction

Kai-Yu Fu, Yi-Ting Chen

We study object importance-based vision risk object identification (Vision-ROI), a key capability for hazard detection in intelligent driving systems. Existing approaches make deterministic decisions and ignore uncertainty, which could lead to safety-critical failures. Specifically, in ambiguous scenarios, fixed decision thresholds may cause premature or delayed risk detection and temporally unstable predictions, especially in complex scenes with multiple interacting risks. Despite these challenges, current methods lack a principled framework to model risk uncertainty jointly across space and time. We propose Conformal Risk Tube Prediction, a unified formulation that captures spatiotemporal risk uncertainty, provides coverage guarantees for true risks, and produces calibrated risk scores with uncertainty estimates. To conduct a systematic evaluation, we present a new dataset and metrics probing diverse scenario configurations with multi-risk coupling effects, which are not supported by existing datasets. We systematically analyze factors affecting uncertainty estimation, including scenario variations, per-risk category behavior, and perception error propagation. Our method delivers substantial improvements over prior approaches, enhancing vision-ROI robustness and downstream performance, such as reducing nuisance braking alerts. For more qualitative results, please visit our project webpage: https://hcis-lab.github.io/CRTP/

Robotics0 citations2026-03-24arXiv ->

Quadrature Oscillation System for Coordinated Motion in Crawling Origami Robot

Sean Liu, Ankur Mehta, Wenzhong Yan

Origami-inspired robots offer rapid, accessible design and manufacture with diverse functionalities. In particular, origami robots without conventional electronics have the unique advantage of functioning in extreme environments such as ones with high radiation or large magnetic fields. However, the absence of sophisticated control systems limits these robots to simple autonomous behaviors. In our previous studies, we developed a printable, electronics-free, and self-sustained oscillator that generates simple complementary square-wave signals. Our study presents a quadrature oscillation system capable of generating four square-wave signals a quarter-cycle out of phase, enabling four distinct states. Such control signals are important in various engineering and robotics applications, such as orchestrating limb movements in bio-inspired robots. We demonstrate the practicality and value of this oscillation system by designing and constructing an origami crawling robot that utilizes the quadrature oscillator to achieve coordinated locomotion. Together, the oscillator and robot illustrate the potential for more complex control and functions in origami robotics, paving the way for more electronics-free, rapid-design origami robots with advanced autonomous behaviors.

Robotics0 citations2026-03-24arXiv ->

PhotoAgent: A Robotic Photographer with Spatial and Aesthetic Understanding

Lirong Che, Zhenfeng Gan, Yanbo Chen, Junbo Tan, Xueqian Wang

Embodied agents for creative tasks like photography must bridge the semantic gap between high-level language commands and geometric control. We introduce PhotoAgent, an agent that achieves this by integrating Large Multimodal Models (LMMs) reasoning with a novel control paradigm. PhotoAgent first translates subjective aesthetic goals into solvable geometric constraints via LMM-driven, chain-of-thought (CoT) reasoning, allowing an analytical solver to compute a high-quality initial viewpoint. This initial pose is then iteratively refined through visual reflection within a photorealistic internal world model built with 3D Gaussian Splatting (3DGS). This ``mental simulation'' replaces costly and slow physical trial-and-error, enabling rapid convergence to aesthetically superior results. Evaluations confirm that PhotoAgent excels in spatial reasoning and achieves superior final image quality.

Robotics0 citations2026-03-23arXiv ->

Conformal Koopman for Embedded Nonlinear Control with Statistical Robustness: Theory and Real-World Validation

Koki Hirano, Hiroyasu Tsukamoto

We propose a fully data-driven, Koopman-based framework for statistically robust control of discrete-time nonlinear systems with linear embeddings. Establishing a connection between the Koopman operator and contraction theory, it offers distribution-free probabilistic bounds on the state tracking error under Koopman modeling uncertainty. Conformal prediction is employed here to rigorously derive a bound on the state-dependent modeling uncertainty throughout the trajectory, ensuring safety and robustness without assuming a specific error prediction structure or distribution. Unlike prior approaches that merely combine conformal prediction with Koopman-based control in an open-loop setting, our method establishes a closed-loop control architecture with formal guarantees that explicitly account for both forward and inverse modeling errors. Also, by expressing the tracking error bound in terms of the control parameters and the modeling errors, our framework offers a quantitative means to formally enhance the performance of arbitrary Koopman-based control. We validate our method both in numerical simulations with the Dubins car and in real-world experiments with a highly nonlinear flapping-wing drone. The results demonstrate that our method indeed provides formal safety guarantees while maintaining accurate tracking performance under Koopman modeling uncertainty.

Robotics0 citations2026-03-22arXiv ->

GAPG: Geometry Aware Push-Grasping Synergy for Goal-Oriented Manipulation in Clutter

Lijingze Xiao, Jinhong Du, Yang Cong, Supeng Diao, Yu Ren

Grasping target objects is a fundamental skill for robotic manipulation, but in cluttered environments with stacked or occluded objects, a single-step grasp is often insufficient. To address this, previous work has introduced pushing as an auxiliary action to create graspable space. However, these methods often struggle with both stability and efficiency because they neglect the scene's geometric information, which is essential for evaluating grasp robustness and ensuring that pushing actions are safe and effective. To this end, we propose a geometry-aware push-grasp synergy framework that leverages point cloud data to integrate grasp and push evaluation. Specifically, the grasp evaluation module analyzes the geometric relationship between the gripper's point cloud and the points enclosed within its closing region to determine grasp feasibility and stability. Guided by this, the push evaluation module predicts how pushing actions influence future graspable space, enabling the robot to select actions that reliably transform non-graspable states into graspable ones. By jointly reasoning about geometry in both grasping and pushing, our framework achieves safer, more efficient, and more reliable manipulation in cluttered settings. Our method is extensively tested in simulation and real-world environments in various scenarios. Experimental results demonstrate that our model generalizes well to real-world scenes and unseen objects.

Robotics0 citations2026-03-22arXiv ->

Anatomical Prior-Driven Framework for Autonomous Robotic Cardiac Ultrasound Standard View Acquisition

Zhiyan Cao, Zhengxi Wu, Yiwei Wang, Pei-Hsuan Lin, Li Zhang et al.

Cardiac ultrasound diagnosis is critical for cardiovascular disease assessment, but acquiring standard views remains highly operator-dependent. Existing medical segmentation models often yield anatomically inconsistent results in images with poor textural differentiation between distinct feature classes, while autonomous probe adjustment methods either rely on simplistic heuristic rules or black-box learning. To address these issues, our study proposed an anatomical prior (AP)-driven framework integrating cardiac structure segmentation and autonomous probe adjustment for standard view acquisition. A YOLO-based multi-class segmentation model augmented by a spatial-relation graph (SRG) module is designed to embed AP into the feature pyramid. Quantifiable anatomical features of standard views are extracted. Their priors are fitted to Gaussian distributions to construct probabilistic APs. The probe adjustment process of robotic ultrasound scanning is formalized as a reinforcement learning (RL) problem, with the RL state built from real-time anatomical features and the reward reflecting the AP matching. Experiments validate the efficacy of the framework. The SRG-YOLOv11s improves mAP50 by 11.3% and mIoU by 6.8% on the Special Case dataset, while the RL agent achieves a 92.5% success rate in simulation and 86.7% in phantom experiments.

Robotics0 citations2026-03-21arXiv ->

Implementing Robust M-Estimators with Certifiable Factor Graph Optimization

Zhexin Xu, Hanna Jiamei Zhang, Helena Calatrava, Pau Closas, David M. Rosen

Parameter estimation in robotics and computer vision faces formidable challenges from both outlier contamination and nonconvex optimization landscapes. While M-estimation addresses the problem of outliers through robust loss functions, it creates severely nonconvex problems that are difficult to solve globally. Adaptive reweighting schemes provide one particularly appealing strategy for implementing M-estimation in practice: these methods solve a sequence of simpler weighted least squares (WLS) subproblems, enabling both the use of standard least squares solvers and the recovery of higher-quality estimates than simple local search. However, adaptive reweighting still crucially relies upon solving the inner WLS problems effectively, a task that remains challenging in many robotics applications due to the intrinsic nonconvexity of many common parameter spaces (e.g. rotations and poses). In this paper, we show how one can easily implement adaptively reweighted M-estimators with certifiably correct solvers for the inner WLS subproblems using only fast local optimization over smooth manifolds. Our approach exploits recent work on certifiable factor graph optimization to provide global optimality certificates for the inner WLS subproblems while seamlessly integrating into existing factor graph-based software libraries and workflows. Experimental evaluation on pose-graph optimization and landmark SLAM tasks demonstrates that our adaptively reweighted certifiable estimation approach provides higher-quality estimates than alternative local search-based methods, while scaling tractably to realistic problem sizes.

Robotics0 citations2026-03-21arXiv ->

LASER: Level-Based Asynchronous Scheduling and Execution Regime for Spatiotemporally Constrained Multi-Robot Timber Manufacturing

Zhenxiang Huang, Lior Skoury, Tim Stark, Aaron Wagner, Hans Jakob Wagner et al.

Automating large-scale manufacturing in domains like timber construction requires multi-robot systems to manage tightly coupled spatiotemporal constraints, such as collision avoidance and process-driven deadlines. This paper introduces LASER (Level-based Asynchronous Scheduling and Execution Regime), a complete framework for scheduling and executing complex assembly tasks, demonstrated on a screw-press gluing application for timber slab manufacturing. Our central contribution is to integrate a barrier-based mechanism into a constraint programming (CP) scheduling formulation that partitions tasks into spatiotemporally disjoint sets, which we define as levels. This structure enables robots to execute tasks in parallel and asynchronously within a level, synchronizing only at level barriers, which guarantees collision-free operation by construction and provides robustness to timing uncertainties. To solve this formulation for large problems, we propose two specialized algorithms: an iterative temporal-relaxation approach for heterogeneous task sequences and a bi-level decomposition for homogeneous tasks that balances workload. We validate the LASER framework by fabricating a full-scale 2.4m x 6m timber slab with a two-robot system mounted on parallel linear tracks, successfully coordinating 108 subroutines and 352 screws under tight adhesive time windows. Computational studies show our method scales steadily with size compared to a monolithic approach.

Robotics0 citations2026-03-20arXiv ->

Multi-Robot Learning-Informed Task Planning Under Uncertainty

Abhish Khanal, Abhishek Paudel, Hung Pham, Gregory J. Stein

We want a multi-robot team to complete complex tasks in minimum time where the locations of task-relevant objects are not known. Effective task completion requires reasoning over long horizons about the likely locations of task-relevant objects, how individual actions contribute to overall progress, and how to coordinate team efforts. Planning in this setting is extremely challenging: even when task-relevant information is partially known, coordinating which robot performs which action and when is difficult, and uncertainty introduces a multiplicity of possible outcomes for each action, which further complicates long-horizon decision-making and coordination. To address this, we propose a multi-robot planning abstraction that integrates learning to estimate uncertain aspects of the environment with model-based planning for long-horizon coordination. We demonstrate the efficient multi-stage task planning of our approach for 1, 2, and 3 robot teams over competitive baselines in large ProcTHOR household environments. Additionally, we demonstrate the effectiveness of our approach with a team of two LoCoBot mobile robots in real household settings.

Robotics0 citations2026-03-20arXiv ->

The Robot's Inner Critic: Self-Refinement of Social Behaviors through VLM-based Replanning

Jiyu Lim, Youngwoo Yoon, Kwanghyun Park

Conventional robot social behavior generation has been limited in flexibility and autonomy, relying on predefined motions or human feedback. This study proposes CRISP (Critique-and-Replan for Interactive Social Presence), an autonomous framework where a robot critiques and replans its own actions by leveraging a Vision-Language Model (VLM) as a `human-like social critic.' CRISP integrates (1) extraction of movable joints and constraints by analyzing the robot's description file (e.g., MJCF), (2) generation of step-by-step behavior plans based on situational context, (3) generation of low-level joint control code by referencing visual information (joint range-of-motion visualizations), (4) VLM-based evaluation of social appropriateness and naturalness, including pinpointing erroneous steps, and (5) iterative refinement of behaviors through reward-based search. This approach is not tied to a specific robot API; it can generate subtly different, human-like motions on various platforms using only the robot's structure file. In a user study involving five different robot types and 20 scenarios, including mobile manipulators and humanoids, our proposed method achieved significantly higher preference and situational appropriateness ratings compared to previous methods. This research presents a general framework that minimizes human intervention while expanding the robot's autonomous interaction capabilities and cross-platform applicability. Detailed result videos and supplementary information regarding this work are available at: https://limjiyu99.github.io/inner-critic/

Robotics0 citations2026-03-19arXiv ->

A Passive Elastic-Folding Mechanism for Stackable Airdrop Sensors

Damyon Kim, Yuichi Honjo, Tatsuya Iizuka, Naomi Okubo, Naoto Endo et al.

Air-dispersed sensor networks deployed from aerial robotic systems (e.g., UAVs) provide a low-cost approach to wide-area environmental monitoring. However, existing methods often rely on active actuators for mid-air shape or trajectory control, increasing both power consumption and system cost. Here, we introduce a passive elastic-folding hinge mechanism that transforms sensors from a flat, stackable form into a three-dimensional structure upon release. Hinges are fabricated by laminating commercial sheet materials with rigid printed circuit boards (PCBs) and programming fold angles through a single oven-heating step, enabling scalable production without specialized equipment. Our geometric model links laminate geometry, hinge mechanics, and resulting fold angle, providing a predictive design methodology for target configurations. Laboratory tests confirmed fold angles between 10 degrees and 100 degrees, with a standard deviation of 4 degrees and high repeatability. Field trials further demonstrated reliable data collection and LoRa transmission during dispersion, while the Horizontal Wind Model (HWM)-based trajectory simulations indicated strong potential for wide-area sensing exceeding 10 km.

MPC/Planning0 citations2026-03-19arXiv ->

Graph-of-Constraints Model Predictive Control for Reactive Multi-agent Task and Motion Planning

Anastasios Manganaris, Jeremy Lu, Ahmed H. Qureshi, Suresh Jagannathan

Sequences of interdependent geometric constraints are central to many multi-agent Task and Motion Planning (TAMP) problems. However, existing methods for handling such constraint sequences struggle with partially ordered tasks and dynamic agent assignments. They typically assume static assignments and cannot adapt when disturbances alter task allocations. To overcome these limitations, we introduce Graph-of-Constraints Model Predictive Control (GoC-MPC), a generalized sequence-of-constraints framework integrated with MPC. GoC-MPC naturally supports partially ordered tasks, dynamic agent coordination, and disturbance recovery. By defining constraints over tracked 3D keypoints, our method robustly solves diverse multi-agent manipulation tasks-coordinating agents and adapting online from visual observations alone, without relying on training data or environment models. Experiments demonstrate that GoC-MPC achieves higher success rates, significantly faster TAMP computation, and shorter overall paths compared to recent baselines, establishing it as an efficient and robust solution for multi-agent manipulation under real-world disturbances. Our supplementary video and code can be found at https://sites.google.com/view/goc-mpc/home .

Robotics0 citations2026-03-18arXiv ->

Rapid Adaptation of Particle Dynamics for Generalized Deformable Object Mobile Manipulation

Bohan Wu, Roberto Martín-Martín, Li Fei-Fei

We address the challenge of learning to manipulate deformable objects with unknown dynamics. In non-rigid objects, the dynamics parameters define how they react to interactions -- how they stretch, bend, compress, and move -- and they are critical to determining the optimal actions to perform a manipulation task successfully. In other robotic domains, such as legged locomotion and in-hand rigid object manipulation, state-of-the-art approaches can handle unknown dynamics using Rapid Motor Adaptation (RMA). Through a supervised procedure in simulation that encodes each rigid object's dynamics, such as mass and position, these approaches learn a policy that conditions actions on a vector of latent dynamic parameters inferred from sequences of state-actions. However, in deformable object manipulation, the object's dynamics not only includes its mass and position, but also how the shape of the object changes. Our key insight is that the recent ground-truth particle positions of a deformable object in simulation capture changes in the object's shape, making it possible to extend RMA to deformable object manipulation. This key insight allows us to develop RAPiD, a two-phase method that learns to perform real-robot deformable object mobile manipulation by: 1) learning a visuomotor policy conditioned on the object's dynamics embedding, which is encoded from the object's privileged information in simulation, such as its mass and ground-truth particle positions, and 2) learning to infer this embedding using non-privileged information instead, such as robot visual observations and actions, so that the learned policy can transfer to the real world. On a mobile manipulator with 22 degrees of freedom, RAPiD enables over 80%+ success rates across two vision-based deformable object mobile manipulation tasks in the real world, under various object dynamics, categories, and instances.

Robotics0 citations2026-03-18arXiv ->

An HMDP-MPC Decision-making Framework with Adaptive Safety Margins and Hysteresis for Autonomous Driving

Siyuan Li, Chengyuan Liu, Wen-Hua Chen

This paper presents a unified decision-making framework that integrates Hybrid Markov Decision Processes (HMDPs) with Model Predictive Control (MPC), augmented by velocity-dependent safety margins and a prediction-aware hysteresis mechanism. Both the ego and surrounding vehicles are modeled as HMDPs, allowing discrete maneuver transition and kinematic evolution to be jointly considered within the MPC optimization. Safety margins derived from the Intelligent Driver Model (IDM) adapt to traffic context but vary with speed, which can cause oscillatory decisions and velocity fluctuations. To mitigate this, we propose a frozen-release hysteresis mechanism with distinct trigger and release thresholds, effectively enlarging the reaction buffer and suppressing oscillations. Decision continuity is further safeguarded by a two-layer recovery scheme: a global bounded relaxation tied to IDM margins and a deterministic fallback policy. The framework is evaluated through a case study, an ablation against a no-hysteresis baseline, and largescale randomized experiments across 18 traffic settings. Across 8,050 trials, it achieves a collision rate of only 0.05%, with 98.77% of decisions resolved by nominal MPC and minimal reliance on relaxation or fallback. These results demonstrate the robustness and adaptability of the proposed decision-making framework in heterogeneous traffic conditions.

Robotics0 citations2026-03-18arXiv ->

DarkDriving: A Real-World Day and Night Aligned Dataset for Autonomous Driving in the Dark Environment

Wuqi Wang, Haochen Yang, Baolu Li, Jiaqi Sun, Xiangmo Zhao et al.

The low-light conditions are challenging to the vision-centric perception systems for autonomous driving in the dark environment. In this paper, we propose a new benchmark dataset (named DarkDriving) to investigate the low-light enhancement for autonomous driving. The existing real-world low-light enhancement benchmark datasets can be collected by controlling various exposures only in small-ranges and static scenes. The dark images of the current nighttime driving datasets do not have the precisely aligned daytime counterparts. The extreme difficulty to collect a real-world day and night aligned dataset in the dynamic driving scenes significantly limited the research in this area. With a proposed automatic day-night Trajectory Tracking based Pose Matching (TTPM) method in a large real-world closed driving test field (area: 69 acres), we collected the first real-world day and night aligned dataset for autonomous driving in the dark environment. The DarkDriving dataset has 9,538 day and night image pairs precisely aligned in location and spatial contents, whose alignment error is in just several centimeters. For each pair, we also manually label the object 2D bounding boxes. DarkDriving introduces four perception related tasks, including low-light enhancement, generalized low-light enhancement, and low-light enhancement for 2D detection and 3D detection of autonomous driving in the dark environment. The experimental results show that our DarkDriving dataset provides a comprehensive benchmark for evaluating low-light enhancement for autonomous driving and it can also be generalized to enhance dark images and promote detection in some other low-light driving environment, such as nuScenes.The code and dataset will be publicly available at https://github.com/DriveMindLab/DarkDriving-ICRA-2026.

Robotics0 citations2026-03-17arXiv ->

Real-Time Decoding of Movement Onset and Offset for Brain-Controlled Rehabilitation Exoskeleton

Kanishka Mitra, Satyam Kumar, Frigyes Samuel Racz, Deland Liu, Ashish D. Deshpande et al.

Robot-assisted therapy can deliver high-dose, task-specific training after neurologic injury, but most systems act primarily at the limb level-engaging the impaired neural circuits only indirectly-which remains a key barrier to truly contingent, neuroplasticity-targeted rehabilitation. We address this gap by implementing online, dual-state motor imagery control of an upper-limb exoskeleton, enabling goal-directed reaches to be both initiated and terminated directly from non-invasive EEG. Eight participants used EEG to initiate assistance and then volitionally halt the robot mid-trajectory. Across two online sessions, group-mean hit rates were 61.5% for onset and 64.5% for offset, demonstrating reliable start-stop command delivery despite instrumental noise and passive arm motion. Methodologically, we reveal a systematic, class-driven bias induced by common task-based recentering using an asymmetric margin diagnostic, and we introduce a class-agnostic fixation-based recentering method that tracks drift without sampling command classes while preserving class geometry. This substantially improves threshold-free separability (AUC gains: onset +56%, p = 0.0117; offset +34%, p = 0.0251) and reduces bias within and across days. Together, these results help bridge offline decoding and practical, intention-driven start-stop control of a rehabilitation exoskeleton, enabling precisely timed, contingent assistance aligned with neuroplasticity goals while supporting future clinical translation.

MPC/Planning0 citations2026-03-17arXiv ->

ASCENT: Transformer-Based Aircraft Trajectory Prediction in Non-Towered Terminal Airspace

Alexander Prutsch, David Schinagl, Horst Possegger

Accurate trajectory prediction can improve General Aviation safety in non-towered terminal airspace, where high traffic density increases accident risk. We present ASCENT, a lightweight transformer-based model for multi-modal 3D aircraft trajectory forecasting, which integrates domain-aware 3D coordinate normalization and parameterized predictions. ASCENT employs a transformer-based motion encoder and a query-based decoder, enabling the generation of diverse maneuver hypotheses with low latency. Experiments on the TrajAir and TartanAviation datasets demonstrate that our model outperforms prior baselines, as the encoder effectively captures motion dynamics and the decoder aligns with structured aircraft traffic patterns. Furthermore, ablation studies confirm the contributions of the decoder design, coordinate-frame modeling, and parameterized outputs. These results establish ASCENT as an effective approach for real-time aircraft trajectory prediction in non-towered terminal airspace.

Robotics0 citations2026-03-17arXiv ->

A Pin-Array Structured Climbing Robot for Stable Locomotion on Steep Rocky Terrain

Keita Nagaoka, Kentaro Uno, Kazuya Yoshida

Climbing robots face significant challenges when navigating unstructured environments, where reliable attachment to irregular surfaces is critical. We present a novel mobile climbing robot equipped with compliant pin-array structured grippers that passively conform to surface irregularities, ensuring stable ground gripping without the need for complicated sensing or control. Each pin features a vertically split design, combining an elastic element with a metal spine to enable mechanical interlocking with microscale surface features. Statistical modeling and experimental validation indicate that variability in individual pin forces and contact numbers are the primary sources of grasping uncertainty. The robot demonstrated robust and stable locomotion in indoor tests on inclined walls (10-30 degrees) and in outdoor tests on natural rocky terrain. This work highlights that a design emphasizing passive compliance and mechanical redundancy provides a practical and robust solution for real-world climbing robots while minimizing control complexity.

Robotics0 citations2026-03-17arXiv ->

LIMBERO: A Limbed Climbing Exploration Robot Toward Traveling on Rocky Cliffs

Kentaro Uno, Masazumi Imai, Kazuki Takada, Teruhiro Kataonami, Yudai Matsuura et al.

In lunar and planetary exploration, legged robots have attracted significant attention as an alternative to conventional wheeled robots, which struggle to traverse rough and uneven terrain. To enable locomotion over highly irregular and steeply inclined surfaces, limbed climbing robots equipped with grippers on their feet have emerged as a promising solution. In this paper, we present LIMBERO, a 10 kg-class quadrupedal climbing robot that employs spine-type grippers for stable locomotion and climbing on rugged and steep terrain. We first introduce a novel gripper design featuring coupled finger-closing and spine-hooking motions, tightly actuated by a single motor, which achieves exceptional grasping performance (>150 N) despite its lightweight design (525 g). Furthermore, we develop an efficient algorithm to visualize a geometry-based graspability index on continuous rough terrain. Finally, we integrate these components into LIMBERO and demonstrate its ability to ascend steep rocky surfaces under a 1 G gravity condition, a performance not previously achieved yet for limbed climbing robots of this scale.

Robotics0 citations2026-03-17arXiv ->

When Rolling Gets Weird: A Curved-Link Tensegrity Robot for Non-Intuitive Behavior

Lauren Ervin, Harish Bezawada, Vishesh Vikas

Conventional mobile tensegrity robots constructed with straight links offer mobility at the cost of locomotion speed. While spherical robots provide highly effective rolling behavior, they often lack the stability required for navigating unstructured terrain common in many space exploration environments. This research presents a solution with a semi-circular, curved-link tensegrity robot that strikes a balance between efficient rolling locomotion and controlled stability, enabled by discontinuities present at the arc endpoints. Building upon an existing geometric static modeling framework [1], this work presents the system design of an improved Tensegrity eXploratory Robot 2 (TeXploR2). Internal shifting masses instantaneously roll along each curved-link, dynamically altering the two points of contact with the ground plane. Simulations of quasistatic, piecewise continuous locomotion sequences reveal new insights into the positional displacement between inertial and body frames. Non-intuitive rolling behaviors are identified and experimentally validated using a tetherless prototype, demonstrating successful dynamic locomotion. A preliminary impact test highlights the tensegrity structure's inherent shock absorption capabilities and conformability. Future work will focus on finalizing a dynamic model that is experimentally validated with extended testing in real-world environments as well as further refinement of the prototype to incorporate additional curved-links and subsequent ground contact points for increased controllability.

Robotics0 citations2026-03-17arXiv ->

CD-FKD: Cross-Domain Feature Knowledge Distillation for Robust Single-Domain Generalization in Object Detection

Junseok Lee, Sungho Shin, Seongju Lee, Kyoobin Lee

Single-domain generalization is essential for object detection, particularly when training models on a single source domain and evaluating them on unseen target domains. Domain shifts, such as changes in weather, lighting, or scene conditions, pose significant challenges to the generalization ability of existing models. To address this, we propose Cross-Domain Feature Knowledge Distillation (CD-FKD), which enhances the generalization capability of the student network by leveraging both global and instance-wise feature distillation. The proposed method uses diversified data through downscaling and corruption to train the student network, whereas the teacher network receives the original source domain data. The student network mimics the features of the teacher through both global and instance-wise distillation, enabling it to extract object-centric features effectively, even for objects that are difficult to detect owing to corruption. Extensive experiments on challenging scenes demonstrate that CD-FKD outperforms state-of-the-art methods in both target domain generalization and source domain performance, validating its effectiveness in improving object detection robustness to domain shifts. This approach is valuable in real-world applications, like autonomous driving and surveillance, where robust object detection in diverse environments is crucial.

Robotics0 citations2026-03-16arXiv ->

Coupled Particle Filters for Robust Affordance Estimation

Patrick Lowin, Vito Mengers, Oliver Brock

Robotic affordance estimation is challenging due to visual, geometric, and semantic ambiguities in sensory input. We propose a method that disambiguates these signals using two coupled recursive estimators for sub-aspects of affordances: graspable and movable regions. Each estimator encodes property-specific regularities to reduce uncertainty, while their coupling enables bidirectional information exchange that focuses attention on regions where both agree, i.e., affordances. Evaluated on a real-world dataset, our method outperforms three recent affordance estimators (Where2Act, Hands-as-Probes, and HRP) by 308%, 245%, and 257% in precision, and remains robust under challenging conditions such as low light or cluttered environments. Furthermore, our method achieves a 70% success rate in our real-world evaluation. These results demonstrate that coupling complementary estimators yields precise, robust, and embodiment-appropriate affordance predictions.

Robotics0 citations2026-03-16arXiv ->

KiRAS: Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning in Quadruped Robots

Xiaoyi Wei, Peng Zhai, Jiaxin Tu, Yueqi Zhang, Yuqi Li et al.

With advances in reinforcement learning and imitation learning, quadruped robots can acquire diverse skills within a single policy by imitating multiple skill-specific datasets. However, the lack of datasets on complex terrains limits the ability of such multi-skill policies to generalize effectively in unstructured environments. Inspired by animation, we adopt keyframes as minimal and universal skill representations, relaxing dataset constraints and enabling the integration of terrain adaptability with skill diversity. We propose Keyframe Guided Self-Imitation for Robust and Adaptive Skill Learning (KiRAS), an end-to-end framework for acquiring and transitioning between diverse skill primitives on complex terrains. KiRAS first learns diverse skills on flat terrain through keyframe-guided self-imitation, eliminating the need for expert datasets; then continues training the same policy network on rough terrains to enhance robustness. To eliminate catastrophic forgetting, a proficiency-based Skill Initialization Technique is introduced. Experiments on Solo-8 and Unitree Go1 robots show that KiRAS enables robust skill acquisition and smooth transitions across challenging terrains. This framework demonstrates its potential as a lightweight platform for multi-skill generation and dataset collection. It further enables flexible skill transitions that enhance locomotion on challenging terrains.

Robotics0 citations2026-03-16arXiv ->

BodyGuards: Escorting by Multiple Robots in Unknown Environment under Limited Communication

Zhuoli Tian, Yanze Bao, Meng Guo

Multi-robot systems are increasingly deployed in high-risk missions such as reconnaissance, disaster response, and subterranean operations. Protecting a human operator while navigating unknown and adversarial environments remains a critical challenge, especially when the communication among the operator and robots is restricted. Unlike existing collaborative exploration methods that aim for complete coverage, this work focuses on task-oriented exploration to minimize the navigation time of the operator to reach its goal while ensuring safety under adversarial threats. A novel escorting framework BodyGuards, is proposed to explicitly integrate seamlessly collaborative exploration, inter-robot-operator communication and escorting. The framework consists of three core components: (I) a dynamic movement strategy for the operator that maintains a local map with risk zones for proactive path planning; (II) a dual-mode robotic strategy combining frontier based exploration with optimized return events to balance exploration, threat detection, and intermittent communication; and (III) multi-robot coordination protocols that jointly plan exploration and information sharing for efficient escorting. Extensive human-in-the-loop simulations and hardware experiments demonstrate that the method significantly reduces operator risk and mission time, outperforming baselines in adversarial and constrained environments.

Robotics0 citations2026-03-16arXiv ->

TrajMamba: An Ego-Motion-Guided Mamba Model for Pedestrian Trajectory Prediction from an Egocentric Perspective

Yusheng Peng, Gaofeng Zhang, Liping Zheng

Future trajectory prediction of a tracked pedestrian from an egocentric perspective is a key task in areas such as autonomous driving and robot navigation. The challenge of this task lies in the complex dynamic relative motion between the ego-camera and the tracked pedestrian. To address this challenge, we propose an ego-motion-guided trajectory prediction network based on the Mamba model. Firstly, two Mamba models are used as encoders to extract pedestrian motion and ego-motion features from pedestrian movement and ego-vehicle movement, respectively. Then, an ego-motion guided Mamba decoder that explicitly models the relative motion between the pedestrian and the vehicle by integrating pedestrian motion features as historical context with ego-motion features as guiding cues to capture decoded features. Finally, the future trajectory is generated from the decoded features corresponding to the future timestamps. Extensive experiments demonstrate the effectiveness of the proposed model, which achieves state-of-the-art performance on the PIE and JAAD datasets.

Robotics0 citations2026-03-16arXiv ->

Efficient Event Camera Volume System

Juan Camilo Soto, Ian Noronha, Saru Bharti, Upinder Kaur

Event cameras promise low latency and high dynamic range, yet their sparse output challenges integration into standard robotic pipelines. We introduce \nameframew (Efficient Event Camera Volume System), a novel framework that models event streams as continuous-time Dirac impulse trains, enabling artifact-free compression through direct transform evaluation at event timestamps. Our key innovation combines density-driven adaptive selection among DCT, DTFT, and DWT transforms with transform-specific coefficient pruning strategies tailored to each domain's sparsity characteristics. The framework eliminates temporal binning artifacts while automatically adapting compression strategies based on real-time event density analysis. On EHPT-XC and MVSEC datasets, our framework achieves superior reconstruction fidelity with DTFT delivering the lowest earth mover distance. In downstream segmentation tasks, EECVS demonstrates robust generalization. Notably, our approach demonstrates exceptional cross-dataset generalization: when evaluated with EventSAM segmentation, EECVS achieves mean IoU 0.87 on MVSEC versus 0.44 for voxel grids at 24 channels, while remaining competitive on EHPT-XC. Our ROS2 implementation provides real-time deployment with DCT processing achieving 1.5 ms latency and 2.7X higher throughput than alternative transforms, establishing the first adaptive event compression framework that maintains both computational efficiency and superior generalization across diverse robotic scenarios.

Robotics0 citations2026-03-15arXiv ->

One-Policy-Fits-All: Geometry-Aware Action Latents for Cross-Embodiment Manipulation

Juncheng Mu, Sizhe Yang, Hojin Bae, Feiyu Jia, Qingwei Ben et al.

Cross-embodiment manipulation is crucial for enhancing the scalability of robot manipulation and reducing the high cost of data collection. However, the significant differences between embodiments, such as variations in action spaces and structural disparities, pose challenges for joint training across multiple sources of data. To address this, we propose One-Policy-Fits-All (OPFA), a framework that enables learning a single, versatile policy across multiple embodiments. We first learn a Geometry-Aware Latent Representation (GaLR), which leverages 3D convolution networks and transformers to build a shared latent action space across different embodiments. Then we design a unified latent retargeting decoder that extracts embodiment-specific actions from the latent representations, without any embodiment-specific decoder tuning. OPFA enables end-to-end co-training of data from diverse embodiments, including various grippers and dexterous hands with arbitrary degrees of freedom, significantly improving data efficiency and reducing the cost of skill transfer. We conduct extensive experiments across 11 different end-effectors. The results demonstrate that OPFA significantly improves policy performance in diverse settings by leveraging heterogeneous embodiment data. For instance, cross-embodiment co-training can improve success rates by more than 50% compared to single-source training. Moreover, by adding only a few demonstrations from a new embodiment (e.g., eight), OPFA can achieve performance comparable to that of a well-trained model with 72 demonstrations.

Robotics0 citations2026-03-15arXiv ->

Towards Versatile Opti-Acoustic Sensor Fusion and Volumetric Mapping

Ivana Collado-Gonzalez, John McConnell, Brendan Englot

Accurate 3D volumetric mapping is critical for autonomous underwater vehicles operating in obstacle-rich environments. Vision-based perception provides high-resolution data but fails in turbid conditions, while sonar is robust to lighting and turbidity but suffers from low resolution and elevation ambiguity. This paper presents a volumetric mapping framework that fuses a stereo sonar pair with a monocular camera to enable safe navigation under varying visibility conditions. Overlapping sonar fields of view resolve elevation ambiguity, producing fully defined 3D point clouds at each time step. The framework identifies regions of interest in camera images, associates them with corresponding sonar returns, and combines sonar range with camera-derived elevation cues to generate additional 3D points. Each 3D point is assigned a confidence value reflecting its reliability. These confidence-weighted points are fused using a Gaussian Process Volumetric Mapping framework that prioritizes the most reliable measurements. Experimental comparisons with other opti-acoustic and sonar-based approaches, along with field tests in a marina environment, demonstrate the method's effectiveness in capturing complex geometries and preserving critical information for robot navigation in both clear and turbid conditions. Our code is open-source to support community adoption.

MPC/Planning0 citations2026-03-14arXiv ->

Implicit Maximum Likelihood Estimation for Real-time Generative Model Predictive Control

Grayson Lee, Minh Bui, Shuzi Zhou, Yankai Li, Mo Chen et al.

Diffusion-based models have recently shown strong performance in trajectory planning, as they are capable of capturing diverse, multimodal distributions of complex behaviors. A key limitation of these models is their slow inference speed, which results from the iterative denoising process. This makes them less suitable for real-time applications such as closed-loop model predictive control (MPC), where plans must be generated quickly and adapted continuously to a changing environment. In this paper, we investigate Implicit Maximum Likelihood Estimation (IMLE) as an alternative generative modeling approach for planning. IMLE offers strong mode coverage while enabling inference that is two orders of magnitude faster, making it particularly well suited for real-time MPC tasks. Our results demonstrate that IMLE achieves competitive performance on standard offline reinforcement learning benchmarks compared to the standard diffusion-based planner, while substantially improving planning speed in both open-loop and closed-loop settings. We further validate IMLE in a closed-loop human navigation scenario, operating in real-time, demonstrating how it enables rapid and adaptive plan generation in dynamic environments. Real-world videos and code are available at https://gmpc-imle.github.io/.

Robotics0 citations2026-03-14arXiv ->

D-Compress: Detail-Preserving LiDAR Range Image Compression for Real-Time Streaming on Resource-Constrained Robots

Shengqian Wang, Chang Tu, He Chen

Efficient 3D LiDAR point cloud compression (LPCC) and streaming are critical for edge server-assisted robotic systems, enabling real-time communication with compact data representations. A widely adopted approach represents LiDAR point clouds as range images, enabling the direct use of mature image and video compression codecs. However, because these codecs are designed with human visual perception in mind, they often compromise geometric details, which downgrades the performance of downstream robotic tasks such as mapping and object detection. Furthermore, rate-distortion optimization (RDO)-based rate control remains largely underexplored for range image compression (RIC) under dynamic bandwidth conditions. To address these limitations, we propose D-Compress, a new detail-preserving and fast RIC framework tailored for real-time streaming. D-Compress integrates both intra- and inter-frame prediction with an adaptive discrete wavelet transform approach for precise residual compression. Additionally, we introduce a new RDO-based rate control algorithm for RIC through new rate-distortion modeling. Extensive evaluations on various datasets demonstrate the superiority of D-Compress, which outperforms state-of-the-art (SOTA) compression methods in both geometric accuracy and downstream task performance, particularly at compression ratios exceeding 100x, while maintaining real-time execution on resource-constrained hardware. Moreover, evaluations under dynamic bandwidth conditions validate the robustness of its rate control mechanism.

Theory0 citations2026-03-13arXiv ->

Sonar-MASt3R: Real-Time Opti-Acoustic Fusion in Turbid, Unstructured Environments

Amy Phung, Richard Camilli

Underwater intervention is an important capability in several marine domains, with numerous industrial, scientific, and defense applications. However, existing perception systems used during intervention operations rely on data from optical cameras, which limits capabilities in poor visibility or lighting conditions. Prior work has examined opti-acoustic fusion methods, which use sonar data to resolve the depth ambiguity of the camera data while using camera data to resolve the elevation angle ambiguity of the sonar data. However, existing methods cannot achieve dense 3D reconstructions in real-time, and few studies have reported results from applying these methods in a turbid environment. In this work, we propose the opti-acoustic fusion method Sonar-MASt3R, which uses MASt3R to extract dense correspondences from optical camera data in real-time and pairs it with geometric cues from an acoustic 3D reconstruction to ensure robustness in turbid conditions. Experimental results using data recorded from an opti-acoustic eye-in-hand configuration across turbidity values ranging from <0.5 to >12 NTU highlight this method's improved robustness to turbidity relative to baseline methods.

Robotics0 citations2026-03-13arXiv ->

Perceive What Matters: Relevance-Driven Scheduling for Multimodal Streaming Perception

Dingcheng Huang, Xiaotong Zhang, Kamal Youcef-Toumi

In modern human-robot collaboration (HRC) applications, multiple perception modules jointly extract visual, auditory, and contextual cues to achieve comprehensive scene understanding, enabling the robot to provide appropriate assistance to human agents intelligently. While executing multiple perception modules on a frame-by-frame basis enhances perception quality in offline settings, it inevitably accumulates latency, leading to a substantial decline in system performance in streaming perception scenarios. Recent work in scene understanding, termed Relevance, has established a solid foundation for developing efficient methodologies in HRC. However, modern perception pipelines still face challenges related to information redundancy and suboptimal allocation of computational resources. Drawing inspiration from the Relevance concept and the information sparsity in HRC events, we propose a novel lightweight perception scheduling framework that efficiently leverages output from previous frames to estimate and schedule necessary perception modules in real-time based on scene context. The experimental results demonstrate that the proposed perception scheduling framework effectively reduces computational latency by up to 27.52% compared to conventional parallel perception pipelines, while also achieving a 72.73% improvement in MMPose activation recall. Additionally, the framework demonstrates high keyframe accuracy, achieving rates of up to 98%. The results validate the framework's capability to enhance real-time perception efficiency without significantly compromising accuracy. The framework shows potential as a scalable and systematic solution for multimodal streaming perception systems in HRC.

Learning0 citations2026-03-13arXiv ->

SldprtNet: A Large-Scale Multimodal Dataset for CAD Generation in Language-Driven 3D Design

Ruogu Li, Sikai Li, Yao Mu, Mingyu Ding

We introduce SldprtNet, a large-scale dataset comprising over 242,000 industrial parts, designed for semantic-driven CAD modeling, geometric deep learning, and the training and fine-tuning of multimodal models for 3D design. The dataset provides 3D models in both .step and .sldprt formats to support diverse training and testing. To enable parametric modeling and facilitate dataset scalability, we developed supporting tools, an encoder and a decoder, which support 13 types of CAD commands and enable lossless transformation between 3D models and a structured text representation. Additionally, each sample is paired with a composite image created by merging seven rendered views from different viewpoints of the 3D model, effectively reducing input token length and accelerating inference. By combining this image with the parameterized text output from the encoder, we employ the lightweight multimodal language model Qwen2.5-VL-7B to generate a natural language description of each part's appearance and functionality. To ensure accuracy, we manually verified and aligned the generated descriptions, rendered images, and 3D models. These descriptions, along with the parameterized modeling scripts, rendered images, and 3D model files, are fully aligned to construct SldprtNet. To assess its effectiveness, we fine-tuned baseline models on a dataset subset, comparing image-plus-text inputs with text-only inputs. Results confirm the necessity and value of multimodal datasets for CAD generation. It features carefully selected real-world industrial parts, supporting tools for scalable dataset expansion, diverse modalities, and ensured diversity in model complexity and geometric features, making it a comprehensive multimodal dataset built for semantic-driven CAD modeling and cross-modal learning.

MPC/Planning0 citations2026-03-13arXiv ->

Motion-Specific Battery Health Assessment for Quadrotors Using High-Fidelity Battery Models

Joonhee Kim, Sanghyun Park, Donghyeong Kim, Eunseon Choi, Soohee Han

Quadrotor endurance is ultimately limited by battery behavior, yet most energy aware planning treats the battery as a simple energy reservoir and overlooks how flight motions induce dynamic current loads that accelerate battery degradation. This work presents an end to end framework for motion aware battery health assessment in quadrotors. We first design a wide range current sensing module to capture motion specific current profiles during real flights, preserving transient features. In parallel, a high fidelity battery model is calibrated using reference performance tests and a metaheuristic based on a degradation coupled electrochemical model.By simulating measured flight loads in the calibrated model, we systematically resolve how different flight motions translate into degradation modes loss of lithium inventory and loss of active material as well as internal side reactions. The results demonstrate that even when two flight profiles consume the same average energy, their transient load structures can drive different degradation pathways, emphasizing the need for motion-aware battery management that balances efficiency with battery degradation.

Robotics0 citations2026-03-13arXiv ->

Conflict Mitigation in Shared Environments using Flow-Aware Multi-Agent Path Finding

Lukas Heuer, Yufei Zhu, Luigi Palmieri, Andrey Rudenko, Anna Mannucci et al.

Deploying multi-robot systems in environments shared with dynamic and uncontrollable agents presents significant challenges, especially for large robot fleets. In such environments, individual robot operations can be delayed due to unforeseen conflicts with uncontrollable agents. While existing research primarily focuses on preserving the completeness of Multi-Agent Path Finding (MAPF) solutions considering delays, there is limited emphasis on utilizing additional environmental information to enhance solution quality in the presence of other dynamic agents. To this end, we propose Flow-Aware Multi-Agent Path Finding (FA-MAPF), a novel framework that integrates learned motion patterns of uncontrollable agents into centralized MAPF algorithms. Our evaluation, conducted on a diverse set of benchmark maps with simulated uncontrollable agents and on a real-world map with recorded human trajectories, demonstrates the effectiveness of FA-MAPF compared to state-of-the-art baselines. The experimental results show that FA-MAPF can consistently reduce conflicts with uncontrollable agents, up to 55%, without compromising task efficiency.

Robotics0 citations2026-03-11arXiv ->

GRACE: A Unified 2D Multi-Robot Path Planning Simulator & Benchmark for Grid, Roadmap, And Continuous Environments

Chuanlong Zang, Anna Mannucci, Isabelle Barz, Philipp Schillinger, Florian Lier et al.

Advancing Multi-Agent Pathfinding (MAPF) and Multi-Robot Motion Planning (MRMP) requires platforms that enable transparent, reproducible comparisons across modeling choices. Existing tools either scale under simplifying assumptions (grids, homogeneous agents) or offer higher fidelity with less comparable instrumentation. We present GRACE, a unified 2D simulator+benchmark that instantiates the same task at multiple abstraction levels (grid, roadmap, continuous) via explicit, reproducible operators and a common evaluation protocol. Our empirical results on public maps and representative planners enable commensurate comparisons on a shared instance set. Furthermore, we quantify the expected representation-fidelity trade-offs (MRMP solves instances at higher fidelity but lower speed, while grid/roadmap planners scale farther). By consolidating representation, execution, and evaluation, GRACE thereby aims to make cross-representation studies more comparable and provides a means to advance multi-robot planning research and its translation to practice.

Robotics0 citations2026-03-11arXiv ->

SUBTA: A Framework for Supported User-Guided Bimanual Teleoperation in Structured Assembly

Xiao Liu, Prakash Baskaran, Songpo Li, Simon Manschitz, Wei Ma et al.

In human-robot collaboration, shared autonomy enhances human performance through precise, intuitive support. Effective robotic assistance requires accurately inferring human intentions and understanding task structures to determine optimal support timing and methods. In this paper, we present SUBTA, a supported teleoperation system for bimanual assembly that couples learned intention estimation, scene-graph task planning, and context-dependent motion assists. We validate our approach through a user study (N=12) comparing standard teleoperation, motion-support only, and SUBTA. Linear mixed-effects analysis revealed that SUBTA significantly outperformed standard teleoperation in position accuracy (p<0.001, d=1.18) and orientation accuracy (p<0.001, d=1.75), while reducing mental demand (p=0.002, d=1.34). Post-experiment ratings indicate clearer, more trustworthy visual feedback and predictable interventions in SUBTA. The results demonstrate that SUBTA greatly improves both effectiveness and user experience in teleoperation.

Robotics0 citations2026-03-11arXiv ->

FAR-Dex: Few-shot Data Augmentation and Adaptive Residual Policy Refinement for Dexterous Manipulation

Yushan Bai, Fulin Chen, Hongzheng Sun, Yuchuang Tong, En Li et al.

Achieving human-like dexterous manipulation through the collaboration of multi-fingered hands with robotic arms remains a longstanding challenge in robotics, primarily due to the scarcity of high-quality demonstrations and the complexity of high-dimensional action spaces. To address these challenges, we propose FAR-Dex, a hierarchical framework that integrates few-shot data augmentation with adaptive residual refinement to enable robust and precise arm-hand coordination in dexterous tasks. First, FAR-DexGen leverages the IsaacLab simulator to generate diverse and physically constrained trajectories from a few demonstrations, providing a data foundation for policy training. Second, FAR-DexRes introduces an adaptive residual module that refines policies by combining multi-step trajectory segments with observation features, thereby enhancing accuracy and robustness in manipulation scenarios. Experiments in both simulation and real-world demonstrate that FAR-Dex improves data quality by 13.4% and task success rates by 7% over state-of-the-art methods. It further achieves over 80% success in real-world tasks, enabling fine-grained dexterous manipulation with strong positional generalization.

Robotics0 citations2026-03-10arXiv ->

Autonomous Search for Sparsely Distributed Visual Phenomena through Environmental Context Modeling

Eric Chen, Travis Manderson, Nare Karapetyan, Peter Edmunds, Nicholas Roy et al.

Autonomous underwater vehicles (AUVs) are increasingly used to survey coral reefs, yet efficiently locating specific coral species of interest remains difficult: target species are often sparsely distributed across the reef, and an AUV with limited battery life cannot afford to search everywhere. When detections of the target itself are too sparse to provide directional guidance, the robot benefits from an additional signal to decide where to look next. We propose using the visual environmental context -- the habitat features that tend to co-occur with a target species -- as that signal. Because context features are spatially denser and often vary more smoothly than target detections, we hypothesize that a reward function targeted at broader environmental context will enable adaptive planners to make better decisions on where to go next, even in regions where no target has yet been observed. Starting from a single labeled image, our method uses patch-level DINOv2 embeddings to perform one-shot detections of both the target species and its surrounding context online. We validate our approach using real imagery collected by an AUV at two reef sites in St. John, U.S. Virgin Islands, simulating the robot's motion offline. Our results demonstrate that one-shot detection combined with adaptive context modeling enables efficient autonomous surveying, sampling up to 75$\%$ of the target in roughly half the time required by exhaustive coverage when the target is sparsely distributed, and outperforming search strategies that only use target detections.

Robotics0 citations2026-03-10arXiv ->

STONE Dataset: A Scalable Multi-Modal Surround-View 3D Traversability Dataset for Off-Road Robot Navigation

Konyul Park, Daehun Kim, Jiyong Oh, Seunghoon Yu, Junseo Park et al.

Reliable off-road navigation requires accurate estimation of traversable regions and robust perception under diverse terrain and sensing conditions. However, existing datasets lack both scalability and multi-modality, which limits progress in 3D traversability prediction. In this work, we introduce STONE, a large-scale multi-modal dataset for off-road navigation. STONE provides (1) trajectory-guided 3D traversability maps generated by a fully automated, annotation-free pipeline, and (2) comprehensive surround-view sensing with synchronized 128-channel LiDAR, six RGB cameras, and three 4D imaging radars. The dataset covers a wide range of environments and conditions, including day and night, grasslands, farmlands, construction sites, and lakes. Our auto-labeling pipeline reconstructs dense terrain surfaces from LiDAR scans, extracts geometric attributes such as slope, elevation, and roughness, and assigns traversability labels beyond the robot's trajectory using a Mahalanobis-distance-based criterion. This design enables scalable, geometry-aware ground-truth construction without manual annotation. Finally, we establish a benchmark for voxel-level 3D traversability prediction and provide strong baselines under both single-modal and multi-modal settings. STONE is available at: https://konyul.github.io/STONE-dataset/

Robotics0 citations2026-03-10arXiv ->

Quality over Quantity: Demonstration Curation via Influence Functions for Data-Centric Robot Learning

Haeone Lee, Taywon Min, Junsu Kim, Sinjae Kang, Fangchen Liu et al.

Learning from demonstrations has emerged as a promising paradigm for end-to-end robot control, particularly when scaled to diverse and large datasets. However, the quality of demonstration data, often collected through human teleoperation, remains a critical bottleneck for effective data-driven robot learning. Human errors, operational constraints, and teleoperator variability introduce noise and suboptimal behaviors, making data curation essential yet largely manual and heuristic-driven. In this work, we propose Quality over Quantity (QoQ), a grounded and systematic approach to identifying high-quality data by defining data quality as the contribution of each training sample to reducing loss on validation demonstrations. To efficiently estimate this contribution, we leverage influence functions, which quantify the impact of individual training samples on model performance. We further introduce two key techniques to adapt influence functions for robot demonstrations: (i) using maximum influence across validation samples to capture the most relevant state-action pairs, and (ii) aggregating influence scores of state-action pairs within the same trajectory to reduce noise and improve data coverage. Experiments in both simulated and real-world settings show that QoQ consistently improves policy performances over prior data selection methods.

ICRA 2025 | 38 papers
CBF Related Papers
Robotics0 citations2025-03-22arXiv ->

Computationally and Sample Efficient Safe Reinforcement Learning Using Adaptive Conformal Prediction

Hao Zhou, Yanze Zhang, Wenhao Luo

Safety is a critical concern in learning-enabled autonomous systems especially when deploying these systems in real-world scenarios. An important challenge is accurately quantifying the uncertainty of unknown models to generate provably safe control policies that facilitate the gathering of informative data, thereby achieving both safe and optimal policies. Additionally, the selection of the data-driven model can significantly impact both the real-time implementation and the uncertainty quantification process. In this paper, we propose a provably sample efficient episodic safe learning framework that remains robust across various model choices with quantified uncertainty for online control tasks. Specifically, we first employ Quadrature Fourier Features (QFF) for kernel function approximation of Gaussian Processes (GPs) to enable efficient approximation of unknown dynamics. Then the Adaptive Conformal Prediction (ACP) is used to quantify the uncertainty from online observations and combined with the Control Barrier Functions (CBF) to characterize the uncertainty-aware safe control constraints under learned dynamics. Finally, an optimism-based exploration strategy is integrated with ACP-based CBFs for safe exploration and near-optimal safe nonlinear control. Theoretical proofs and simulation results are provided to demonstrate the effectiveness and efficiency of the proposed framework.

Other Papers
Robotics0 citations2026-02-28arXiv ->

TMR-VLA:Vision-Language-Action Model for Magnetic Motion Control of Tri-leg Silicone-based Soft Robot

Ruijie Tang, Chi Kit Ng, Kaixuan Wu, Long Bai, Guankun Wang et al.

In-vivo environments, magnetically actuated soft robots offer advantages such as wireless operation and precise control, showing promising potential for painless detection and therapeutic procedures. We developed a trileg magnetically driven soft robot (TMR) whose multi-legged design enables more flexible gaits and diverse motion patterns. For the silicone made of reconfigurable soft robots, its navigation ability can be separated into sequential motions, namely squatting, rotation, lifting a leg, walking and so on. Its motion and behavior depend on its bending shapes. To bridge motion type description and specific low-level voltage control, we introduced TMR-VLA, an end-to-end multi-modal system for a trileg magnetic soft robot capable of performing hybrid motion types, which is promising for developing a navigation ability by adapting its shape to language-constrained motion types. The TMR-VLA deploys embodied endoluminal localization ability from EndoVLA, and fuses sequential frames and natural language commands as input. Low-level voltage output is generated based on the current observation state and specific motion type description. The result shows the TMR-VLA can predict how the voltage applied to TMR will change the dynamics of a silicon-made soft robot. The TMR-VLA reached a 74% average success rate.

Robotics0 citations2026-02-24arXiv ->

Robot Local Planner: A Periodic Sampling-Based Motion Planner with Minimal Waypoints for Home Environments

Keisuke Takeshita, Takahiro Yamazaki, Tomohiro Ono, Takashi Yamamoto

The objective of this study is to enable fast and safe manipulation tasks in home environments. Specifically, we aim to develop a system that can recognize its surroundings and identify target objects while in motion, enabling it to plan and execute actions accordingly. We propose a periodic sampling-based whole-body trajectory planning method, called the "Robot Local Planner (RLP)." This method leverages unique features of home environments to enhance computational efficiency, motion optimality, and robustness against recognition and control errors, all while ensuring safety. The RLP minimizes computation time by planning with minimal waypoints and generating safe trajectories. Furthermore, overall motion optimality is improved by periodically executing trajectory planning to select more optimal motions. This approach incorporates inverse kinematics that are robust to base position errors, further enhancing robustness. Evaluation experiments demonstrated that the RLP outperformed existing methods in terms of motion planning time, motion duration, and robustness, confirming its effectiveness in home environments. Moreover, application experiments using a tidy-up task achieved high success rates and short operation times, thereby underscoring its practical feasibility.

Robotics0 citations2026-02-04arXiv ->

GeoLanG: Geometry-Aware Language-Guided Grasping with Unified RGB-D Multimodal Learning

Rui Tang, Guankun Wang, Long Bai, Huxin Gao, Jiewen Lai et al.

Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing methods often rely on multi-stage pipelines that separate object perception and grasping, which leads to limited cross-modal fusion, redundant computation, and poor generalization in cluttered, occluded, or low-texture scenes. To address these limitations, we propose GeoLanG, an end-to-end multi-task framework built upon the CLIP architecture that unifies visual and linguistic inputs into a shared representation space for robust semantic alignment and improved generalization. To enhance target discrimination under occlusion and low-texture conditions, we explore a more effective use of depth information through the Depth-guided Geometric Module (DGGM), which converts depth into explicit geometric priors and injects them into the attention mechanism without additional computational overhead. In addition, we propose Adaptive Dense Channel Integration, which adaptively balances the contributions of multi-layer features to produce more discriminative and generalizable visual representations. Extensive experiments on the OCID-VLG dataset, as well as in both simulation and real-world hardware, demonstrate that GeoLanG enables precise and robust language-guided grasping in complex, cluttered environments, paving the way toward more reliable multimodal robotic manipulation in real-world human-centric settings.

Robotics0 citations2026-02-03arXiv ->

Enhancing Navigation Efficiency of Quadruped Robots via Leveraging Personal Transportation Platforms

Minsung Yoon, Sung-Eui Yoon

Quadruped robots face limitations in long-range navigation efficiency due to their reliance on legs. To ameliorate the limitations, we introduce a Reinforcement Learning-based Active Transporter Riding method (\textit{RL-ATR}), inspired by humans' utilization of personal transporters, including Segways. The \textit{RL-ATR} features a transporter riding policy and two state estimators. The policy devises adequate maneuvering strategies according to transporter-specific control dynamics, while the estimators resolve sensor ambiguities in non-inertial frames by inferring unobservable robot and transporter states. Comprehensive evaluations in simulation validate proficient command tracking abilities across various transporter-robot models and reduced energy consumption compared to legged locomotion. Moreover, we conduct ablation studies to quantify individual component contributions within the \textit{RL-ATR}. This riding ability could broaden the locomotion modalities of quadruped robots, potentially expanding the operational range and efficiency.

Robotics0 citations2026-01-01arXiv ->

Breaking Task Impasses Quickly: Adaptive Neuro-Symbolic Learning for Open-World Robotics

Pierrick Lorang

Adapting to unforeseen novelties in open-world environments remains a major challenge for autonomous systems. While hybrid planning and reinforcement learning (RL) approaches show promise, they often suffer from sample inefficiency, slow adaptation, and catastrophic forgetting. We present a neuro-symbolic framework integrating hierarchical abstractions, task and motion planning (TAMP), and reinforcement learning to enable rapid adaptation in robotics. Our architecture combines symbolic goal-oriented learning and world model-based exploration to facilitate rapid adaptation to environmental changes. Validated in robotic manipulation and autonomous driving, our approach achieves faster convergence, improved sample efficiency, and superior robustness over state-of-the-art hybrid methods, demonstrating its potential for real-world deployment.

Learning0 citations2025-12-11arXiv ->

Neural Ranging Inertial Odometry

Si Wang, Bingqi Shen, Fei Wang, Yanjun Cao, Rong Xiong et al.

Ultra-wideband (UWB) has shown promising potential in GPS-denied localization thanks to its lightweight and drift-free characteristics, while the accuracy is limited in real scenarios due to its sensitivity to sensor arrangement and non-Gaussian pattern induced by multi-path or multi-signal interference, which commonly occurs in many typical applications like long tunnels. We introduce a novel neural fusion framework for ranging inertial odometry which involves a graph attention UWB network and a recurrent neural inertial network. Our graph net learns scene-relevant ranging patterns and adapts to any number of anchors or tags, realizing accurate positioning without calibration. Additionally, the integration of least squares and the incorporation of nominal frame enhance overall performance and scalability. The effectiveness and robustness of our methods are validated through extensive experiments on both public and self-collected datasets, spanning indoor, outdoor, and tunnel environments. The results demonstrate the superiority of our proposed IR-ULSG in handling challenging conditions, including scenarios outside the convex envelope and cases where only a single anchor is available.

Robotics0 citations2025-12-09arXiv ->

Zero-Splat TeleAssist: A Zero-Shot Pose Estimation Framework for Semantic Teleoperation

Srijan Dokania, Dharini Raghavan

We introduce Zero-Splat TeleAssist, a zero-shot sensor-fusion pipeline that transforms commodity CCTV streams into a shared, 6-DoF world model for multilateral teleoperation. By integrating vision-language segmentation, monocular depth, weighted-PCA pose extraction, and 3D Gaussian Splatting (3DGS), TeleAssist provides every operator with real-time global positions and orientations of multiple robots without fiducials or depth sensors in an interaction-centric teleoperation setup.

Learning0 citations2025-11-28arXiv ->

MrGS: Multi-modal Radiance Fields with 3D Gaussian Splatting for RGB-Thermal Novel View Synthesis

Minseong Kweon, Janghyun Kim, Ukcheol Shin, Jinsun Park

Recent advances in Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS) have achieved considerable performance in RGB scene reconstruction. However, multi-modal rendering that incorporates thermal infrared imagery remains largely underexplored. Existing approaches tend to neglect distinctive thermal characteristics, such as heat conduction and the Lambertian property. In this study, we introduce MrGS, a multi-modal radiance field based on 3DGS that simultaneously reconstructs both RGB and thermal 3D scenes. Specifically, MrGS derives RGB- and thermal-related information from a single appearance feature through orthogonal feature extraction and employs view-dependent or view-independent embedding strategies depending on the degree of Lambertian reflectance exhibited by each modality. Furthermore, we leverage two physics-based principles to effectively model thermal-domain phenomena. First, we integrate Fourier's law of heat conduction prior to alpha blending to model intensity interpolation caused by thermal conduction between neighboring Gaussians. Second, we apply the Stefan-Boltzmann law and the inverse-square law to formulate a depth-aware thermal radiation map that imposes additional geometric constraints on thermal rendering. Experimental results demonstrate that the proposed MrGS achieves high-fidelity RGB-T scene reconstruction while reducing the number of Gaussians.

MPC/Planning0 citations2025-11-25arXiv ->

Conformal Safety Monitoring for Flight Testing: A Case Study in Data-Driven Safety Learning

Aaron O. Feldman, D. Isaiah Harp, Joseph Duncan, Mac Schwager

We develop a data-driven approach for runtime safety monitoring in flight testing, where pilots perform maneuvers on aircraft with uncertain parameters. Because safety violations can arise unexpectedly as a result of these uncertainties, pilots need clear, preemptive criteria to abort the maneuver in advance of safety violation. To solve this problem, we use offline stochastic trajectory simulation to learn a calibrated statistical model of the short-term safety risk facing pilots. We use flight testing as a motivating example for data-driven learning/monitoring of safety due to its inherent safety risk, uncertainty, and human-interaction. However, our approach consists of three broadly-applicable components: a model to predict future state from recent observations, a nearest neighbor model to classify the safety of the predicted state, and classifier calibration via conformal prediction. We evaluate our method on a flight dynamics model with uncertain parameters, demonstrating its ability to reliably identify unsafe scenarios, match theoretical guarantees, and outperform baseline approaches in preemptive classification of risk.

Robotics0 citations2025-11-24arXiv ->

Efficient Optimization of a Permanent Magnet Array for a Stable 2D Trap

Ann-Sophia Müller, Moonkwang Jeong, Jiyuan Tian, Meng Zhang, Tian Qiu

Untethered magnetic manipulation of biomedical millirobots has a high potential for minimally invasive surgical applications. However, it is still challenging to exert high actuation forces on the small robots over a large distance. Permanent magnets offer stronger magnetic torques and forces than electromagnetic coils, however, feedback control is more difficult. As proven by Earnshaw's theorem, it is not possible to achieve a stable magnetic trap in 3D by static permanent magnets. Here, we report a stable 2D magnetic force trap by an array of permanent magnets to control a millirobot. The trap is located in an open space with a tunable distance to the magnet array in the range of 20 - 120mm, which is relevant to human anatomical scales. The design is achieved by a novel GPU-accelerated optimization algorithm that uses mean squared error (MSE) and Adam optimizer to efficiently compute the optimal angles for any number of magnets in the array. The algorithm is verified using numerical simulation and physical experiments with an array of two magnets. A millirobot is successfully trapped and controlled to follow a complex trajectory. The algorithm demonstrates high scalability by optimizing the angles for 100 magnets in under three seconds. Moreover, the optimization workflow can be adapted to optimize a permanent magnet array to achieve the desired force vector fields.

Robotics0 citations2025-11-19arXiv ->

Painted Heart Beats

Angshu Adhya, Cindy Yang, Emily Wu, Rishad Hasan, Abhishek Narula et al.

In this work we present AURA, a framework for synergistic human-artist painting. We developed a robot arm that collaboratively paints with a human artist. The robot has an awareness of the artist's heartbeat through the EmotiBit sensor, which provides the arousal levels of the painter. Given the heartbeat detected, the robot decides to increase proximity to the artist's workspace or retract. If a higher heartbeat is detected, which is associated with increased arousal in human artists, the robot will move away from that area of the canvas. If the artist's heart rate is detected as neutral, indicating the human artist's baseline state, the robot will continue its painting actions across the entire canvas. We also demonstrate and propose alternative robot-artist interactions using natural language and physical touch. This work combines the biometrics of a human artist to inform fluent artistic interactions.

Robotics0 citations2025-11-05arXiv ->

SENT Map -- Semantically Enhanced Topological Maps with Foundation Models

Raj Surya Rajendran Kathirvel, Zach A Chavis, Stephen J. Guy, Karthik Desingh

We introduce SENT-Map, a semantically enhanced topological map for representing indoor environments, designed to support autonomous navigation and manipulation by leveraging advancements in foundational models (FMs). Through representing the environment in a JSON text format, we enable semantic information to be added and edited in a format that both humans and FMs understand, while grounding the robot to existing nodes during planning to avoid infeasible states during deployment. Our proposed framework employs a two stage approach, first mapping the environment alongside an operator with a Vision-FM, then using the SENT-Map representation alongside a natural-language query within an FM for planning. Our experimental results show that semantic-enhancement enables even small locally-deployable FMs to successfully plan over indoor environments.

Robotics0 citations2025-11-03arXiv ->

EREBUS: End-to-end Robust Event Based Underwater Simulation

Hitesh Kyatham, Arjun Suresh, Aadi Palnitkar, Yiannis Aloimonos

The underwater domain presents a vast array of challenges for roboticists and computer vision researchers alike, such as poor lighting conditions and high dynamic range scenes. In these adverse conditions, traditional vision techniques struggle to adapt and lead to suboptimal performance. Event-based cameras present an attractive solution to this problem, mitigating the issues of traditional cameras by tracking changes in the footage on a frame-by-frame basis. In this paper, we introduce a pipeline which can be used to generate realistic synthetic data of an event-based camera mounted to an AUV (Autonomous Underwater Vehicle) in an underwater environment for training vision models. We demonstrate the effectiveness of our pipeline using the task of rock detection with poor visibility and suspended particulate matter, but the approach can be generalized to other underwater tasks.

Robotics0 citations2025-11-02arXiv ->

Real-Time Learning of Predictive Dynamic Obstacle Models for Robotic Motion Planning

Stella Kombo, Masih Haseli, Skylar X. Wei, Joel W. Burdick

Autonomous systems often must predict the motions of nearby agents from partial and noisy data. This paper asks and answers the question: "can we learn, in real-time, a nonlinear predictive model of another agent's motions?" Our online framework denoises and forecasts such dynamics using a modified sliding-window Hankel Dynamic Mode Decomposition (Hankel-DMD). Partial noisy measurements are embedded into a Hankel matrix, while an associated Page matrix enables singular-value hard thresholding (SVHT) to estimate the effective rank. A Cadzow projection enforces structured low-rank consistency, yielding a denoised trajectory and local noise variance estimates. From this representation, a time-varying Hankel-DMD lifted linear predictor is constructed for multi-step forecasts. The residual analysis provides variance-tracking signals that can support downstream estimators and risk-aware planning. We validate the approach in simulation under Gaussian and heavy-tailed noise, and experimentally on a dynamic crane testbed. Results show that the method achieves stable variance-aware denoising and short-horizon prediction suitable for integration into real-time control frameworks.

Robotics0 citations2025-10-09arXiv ->

Point and Go: Intuitive Reference Frame Reallocation in Mode Switching for Assistive Robotics

A. Wang, C. Jiang, M. Przystupa, J. Valentine, M. Jagersand

Operating high degree of freedom robots can be difficult for users of wheelchair mounted robotic manipulators. Mode switching in Cartesian space has several drawbacks such as unintuitive control reference frames, separate translation and orientation control, and limited movement capabilities that hinder performance. We propose Point and Go mode switching, which reallocates the Cartesian mode switching reference frames into a more intuitive action space comprised of new translation and rotation modes. We use a novel sweeping motion to point the gripper, which defines the new translation axis along the robot base frame's horizontal plane. This creates an intuitive `point and go' translation mode that allows the user to easily perform complex, human-like movements without switching control modes. The system's rotation mode combines position control with a refined end-effector oriented frame that provides precise and consistent robot actions in various end-effector poses. We verified its effectiveness through initial experiments, followed by a three-task user study that compared our method to Cartesian mode switching and a state of the art learning method. Results show that Point and Go mode switching reduced completion times by 31\%, pauses by 41\%, and mode switches by 33\%, while receiving significantly favorable responses in user surveys.

Robotics0 citations2025-10-07arXiv ->

A Preview of HoloOcean 2.0

Blake Romrell, Abigail Austin, Braden Meyers, Ryan Anderson, Carter Noh et al.

Marine robotics simulators play a fundamental role in the development of marine robotic systems. With increased focus on the marine robotics field in recent years, there has been significant interest in developing higher fidelitysimulation of marine sensors, physics, and visual rendering capabilities to support autonomous marine robot development and validation. HoloOcean 2.0, the next major release of HoloOcean, brings state-of-the-art features under a general marine simulator capable of supporting a variety of tasks. New features in HoloOcean 2.0 include migration to Unreal Engine (UE) 5.3, advanced vehicle dynamics using models from Fossen, and support for ROS2 using a custom bridge. Additional features are currently in development, including significantly more efficient ray tracing-based sidescan, forward-looking, and bathymetric sonar implementations; semantic sensors; environment generation tools; volumetric environmental effects; and realistic waves.

Robotics0 citations2025-09-10arXiv ->

TANGO: Traversability-Aware Navigation with Local Metric Control for Topological Goals

Stefan Podgorski, Sourav Garg, Mehdi Hosseinzadeh, Lachlan Mares, Feras Dayoub et al.

Visual navigation in robotics traditionally relies on globally-consistent 3D maps or learned controllers, which can be computationally expensive and difficult to generalize across diverse environments. In this work, we present a novel RGB-only, object-level topometric navigation pipeline that enables zero-shot, long-horizon robot navigation without requiring 3D maps or pre-trained controllers. Our approach integrates global topological path planning with local metric trajectory control, allowing the robot to navigate towards object-level sub-goals while avoiding obstacles. We address key limitations of previous methods by continuously predicting local trajectory using monocular depth and traversability estimation, and incorporating an auto-switching mechanism that falls back to a baseline controller when necessary. The system operates using foundational models, ensuring open-set applicability without the need for domain-specific fine-tuning. We demonstrate the effectiveness of our method in both simulated environments and real-world tests, highlighting its robustness and deployability. Our approach outperforms existing state-of-the-art methods, offering a more adaptable and effective solution for visual navigation in open-set environments. The source code is made publicly available: https://github.com/podgorki/TANGO.

Robotics0 citations2025-09-07arXiv ->

DVLO4D: Deep Visual-Lidar Odometry with Sparse Spatial-temporal Fusion

Mengmeng Liu, Michael Ying Yang, Jiuming Liu, Yunpeng Zhang, Jiangtao Li et al.

Visual-LiDAR odometry is a critical component for autonomous system localization, yet achieving high accuracy and strong robustness remains a challenge. Traditional approaches commonly struggle with sensor misalignment, fail to fully leverage temporal information, and require extensive manual tuning to handle diverse sensor configurations. To address these problems, we introduce DVLO4D, a novel visual-LiDAR odometry framework that leverages sparse spatial-temporal fusion to enhance accuracy and robustness. Our approach proposes three key innovations: (1) Sparse Query Fusion, which utilizes sparse LiDAR queries for effective multi-modal data fusion; (2) a Temporal Interaction and Update module that integrates temporally-predicted positions with current frame data, providing better initialization values for pose estimation and enhancing model's robustness against accumulative errors; and (3) a Temporal Clip Training strategy combined with a Collective Average Loss mechanism that aggregates losses across multiple frames, enabling global optimization and reducing the scale drift over long sequences. Extensive experiments on the KITTI and Argoverse Odometry dataset demonstrate the superiority of our proposed DVLO4D, which achieves state-of-the-art performance in terms of both pose accuracy and robustness. Additionally, our method has high efficiency, with an inference time of 82 ms, possessing the potential for the real-time deployment.

MPC/Planning0 citations2025-09-01arXiv ->

FGO-SLAM: Enhancing Gaussian SLAM with Globally Consistent Opacity Radiance Field

Fan Zhu, Yifan Zhao, Ziyu Chen, Biao Yu, Hui Zhu

Visual SLAM has regained attention due to its ability to provide perceptual capabilities and simulation test data for Embodied AI. However, traditional SLAM methods struggle to meet the demands of high-quality scene reconstruction, and Gaussian SLAM systems, despite their rapid rendering and high-quality mapping capabilities, lack effective pose optimization methods and face challenges in geometric reconstruction. To address these issues, we introduce FGO-SLAM, a Gaussian SLAM system that employs an opacity radiance field as the scene representation to enhance geometric mapping performance. After initial pose estimation, we apply global adjustment to optimize camera poses and sparse point cloud, ensuring robust tracking of our approach. Additionally, we maintain a globally consistent opacity radiance field based on 3D Gaussians and introduce depth distortion and normal consistency terms to refine the scene representation. Furthermore, after constructing tetrahedral grids, we identify level sets to directly extract surfaces from 3D Gaussians. Results across various real-world and large-scale synthetic datasets demonstrate that our method achieves state-of-the-art tracking accuracy and mapping performance.

Robotics0 citations2025-08-30arXiv ->

Domain Adaptation-Based Crossmodal Knowledge Distillation for 3D Semantic Segmentation

Jialiang Kang, Jiawen Wang, Dingsheng Luo

Semantic segmentation of 3D LiDAR data plays a pivotal role in autonomous driving. Traditional approaches rely on extensive annotated data for point cloud analysis, incurring high costs and time investments. In contrast, realworld image datasets offer abundant availability and substantial scale. To mitigate the burden of annotating 3D LiDAR point clouds, we propose two crossmodal knowledge distillation methods: Unsupervised Domain Adaptation Knowledge Distillation (UDAKD) and Feature and Semantic-based Knowledge Distillation (FSKD). Leveraging readily available spatio-temporally synchronized data from cameras and LiDARs in autonomous driving scenarios, we directly apply a pretrained 2D image model to unlabeled 2D data. Through crossmodal knowledge distillation with known 2D-3D correspondence, we actively align the output of the 3D network with the corresponding points of the 2D network, thereby obviating the necessity for 3D annotations. Our focus is on preserving modality-general information while filtering out modality-specific details during crossmodal distillation. To achieve this, we deploy self-calibrated convolution on 3D point clouds as the foundation of our domain adaptation module. Rigorous experimentation validates the effectiveness of our proposed methods, consistently surpassing the performance of state-of-the-art approaches in the field.

Robotics0 citations2025-08-27arXiv ->

Impedance Primitive-augmented Hierarchical Reinforcement Learning for Sequential Tasks

Amin Berjaoui Tahmaz, Ravi Prakash, Jens Kober

This paper presents an Impedance Primitive-augmented hierarchical reinforcement learning framework for efficient robotic manipulation in sequential contact tasks. We leverage this hierarchical structure to sequentially execute behavior primitives with variable stiffness control capabilities for contact tasks. Our proposed approach relies on three key components: an action space enabling variable stiffness control, an adaptive stiffness controller for dynamic stiffness adjustments during primitive execution, and affordance coupling for efficient exploration while encouraging compliance. Through comprehensive training and evaluation, our framework learns efficient stiffness control capabilities and demonstrates improvements in learning efficiency, compositionality in primitive selection, and success rates compared to the state-of-the-art. The training environments include block lifting, door opening, object pushing, and surface cleaning. Real world evaluations further confirm the framework's sim2real capability. This work lays the foundation for more adaptive and versatile robotic manipulation systems, with potential applications in more complex contact-based tasks.

MPC/Planning0 citations2025-08-26arXiv ->

Direction Informed Trees (DIT*): Optimal Path Planning via Direction Filter and Direction Cost Heuristic

Liding Zhang, Kejia Chen, Kuanqi Cai, Yu Zhang, Yixuan Dang et al.

Optimal path planning requires finding a series of feasible states from the starting point to the goal to optimize objectives. Popular path planning algorithms, such as Effort Informed Trees (EIT*), employ effort heuristics to guide the search. Effective heuristics are accurate and computationally efficient, but achieving both can be challenging due to their conflicting nature. This paper proposes Direction Informed Trees (DIT*), a sampling-based planner that focuses on optimizing the search direction for each edge, resulting in goal bias during exploration. We define edges as generalized vectors and integrate similarity indexes to establish a directional filter that selects the nearest neighbors and estimates direction costs. The estimated direction cost heuristics are utilized in edge evaluation. This strategy allows the exploration to share directional information efficiently. DIT* convergence faster than existing single-query, sampling-based planners on tested problems in R^4 to R^16 and has been demonstrated in real-world environments with various planning tasks. A video showcasing our experimental results is available at: https://youtu.be/2SX6QT2NOek

Learning0 citations2025-08-20arXiv ->

Taming VR Teleoperation and Learning from Demonstration for Multi-Task Bimanual Table Service Manipulation

Weize Li, Zhengxiao Han, Lixin Xu, Xiangyu Chen, Harrison Bounds et al.

This technical report presents the champion solution of the Table Service Track in the ICRA 2025 What Bimanuals Can Do (WBCD) competition. We tackled a series of demanding tasks under strict requirements for speed, precision, and reliability: unfolding a tablecloth (deformable-object manipulation), placing a pizza into the container (pick-and-place), and opening and closing a food container with the lid. Our solution combines VR-based teleoperation and Learning from Demonstrations (LfD) to balance robustness and autonomy. Most subtasks were executed through high-fidelity remote teleoperation, while the pizza placement was handled by an ACT-based policy trained from 100 in-person teleoperated demonstrations with randomized initial configurations. By carefully integrating scoring rules, task characteristics, and current technical capabilities, our approach achieved both high efficiency and reliability, ultimately securing the first place in the competition.

Robotics0 citations2025-08-07arXiv ->

Evaluation of an Autonomous Surface Robot Equipped with a Transformable Mobility Mechanism for Efficient Mobility Control

Yasuyuki Fujii, Dinh Tuan Tran, Joo-Ho Lee

Efficient mobility and power consumption are critical for autonomous water surface robots in long-term water environmental monitoring. This study develops and evaluates a transformable mobility mechanism for a water surface robot with two control modes: station-keeping and traveling to improve energy efficiency and maneuverability. Field experiments show that, in a round-trip task between two points, the traveling mode reduces power consumption by 10\% and decreases the total time required for travel by 5\% compared to the station-keeping mode. These results confirm the effectiveness of the transformable mobility mechanism for enhancing operational efficiency in patrolling on water surface.

Learning0 citations2025-08-05arXiv ->

OmniShape: Zero-Shot Multi-Hypothesis Shape and Pose Estimation in the Real World

Katherine Liu, Sergey Zakharov, Dian Chen, Takuya Ikeda, Greg Shakhnarovich et al.

We would like to estimate the pose and full shape of an object from a single observation, without assuming known 3D model or category. In this work, we propose OmniShape, the first method of its kind to enable probabilistic pose and shape estimation. OmniShape is based on the key insight that shape completion can be decoupled into two multi-modal distributions: one capturing how measurements project into a normalized object reference frame defined by the dataset and the other modelling a prior over object geometries represented as triplanar neural fields. By training separate conditional diffusion models for these two distributions, we enable sampling multiple hypotheses from the joint pose and shape distribution. OmniShape demonstrates compelling performance on challenging real world datasets. Project website: https://tri-ml.github.io/omnishape

Robotics0 citations2025-08-04arXiv ->

AeroSafe: Mobile Indoor Air Purification using Aerosol Residence Time Analysis and Robotic Cough Emulator Testbed

M Tanjid Hasan Tonmoy, Rahath Malladi, Kaustubh Singh, Forsad Al Hossain, Rajesh Gupta et al.

Indoor air quality plays an essential role in the safety and well-being of occupants, especially in the context of airborne diseases. This paper introduces AeroSafe, a novel approach aimed at enhancing the efficacy of indoor air purification systems through a robotic cough emulator testbed and a digital-twins-based aerosol residence time analysis. Current portable air filters often overlook the concentrations of respiratory aerosols generated by coughs, posing a risk, particularly in high-exposure environments like healthcare facilities and public spaces. To address this gap, we present a robotic dual-agent physical emulator comprising a maneuverable mannequin simulating cough events and a portable air purifier autonomously responding to aerosols. The generated data from this emulator trains a digital twins model, combining a physics-based compartment model with a machine learning approach, using Long Short-Term Memory (LSTM) networks and graph convolution layers. Experimental results demonstrate the model's ability to predict aerosol concentration dynamics with a mean residence time prediction error within 35 seconds. The proposed system's real-time intervention strategies outperform static air filter placement, showcasing its potential in mitigating airborne pathogen risks.

Robotics0 citations2025-08-04arXiv ->

Tethered Multi-Robot Systems in Marine Environments

Markus Buchholz, Ignacio Carlucho, Michele Grimaldi, Yvan R. Petillot

This paper introduces a novel simulation framework for evaluating motion control in tethered multi-robot systems within dynamic marine environments. Specifically, it focuses on the coordinated operation of an Autonomous Underwater Vehicle (AUV) and an Autonomous Surface Vehicle(ASV). The framework leverages GazeboSim, enhanced with realistic marine environment plugins and ArduPilots SoftwareIn-The-Loop (SITL) mode, to provide a high-fidelity simulation platform. A detailed tether model, combining catenary equations and physical simulation, is integrated to accurately represent the dynamic interactions between the vehicles and the environment. This setup facilitates the development and testing of advanced control strategies under realistic conditions, demonstrating the frameworks capability to analyze complex tether interactions and their impact on system performance.

Robotics0 citations2025-08-03arXiv ->

Beyond Simulation: Benchmarking World Models for Planning and Causality in Autonomous Driving

Hunter Schofield, Mohammed Elmahgiubi, Kasra Rezaee, Jinjun Shan

World models have become increasingly popular in acting as learned traffic simulators. Recent work has explored replacing traditional traffic simulators with world models for policy training. In this work, we explore the robustness of existing metrics to evaluate world models as traffic simulators to see if the same metrics are suitable for evaluating a world model as a pseudo-environment for policy training. Specifically, we analyze the metametric employed by the Waymo Open Sim-Agents Challenge (WOSAC) and compare world model predictions on standard scenarios where the agents are fully or partially controlled by the world model (partial replay). Furthermore, since we are interested in evaluating the ego action-conditioned world model, we extend the standard WOSAC evaluation domain to include agents that are causal to the ego vehicle. Our evaluations reveal a significant number of scenarios where top-ranking models perform well under no perturbation but fail when the ego agent is forced to replay the original trajectory. To address these cases, we propose new metrics to highlight the sensitivity of world models to uncontrollable objects and evaluate the performance of world models as pseudo-environments for policy training and analyze some state-of-the-art world models under these new metrics.

Robotics0 citations2025-08-01arXiv ->

A control scheme for collaborative object transportation between a human and a quadruped robot using the MIGHTY suction cup

Konstantinos Plotas, Emmanouil Papadakis, Drosakis Drosakis, Panos Trahanias, Dimitrios Papageorgiou

In this work, a control scheme for human-robot collaborative object transportation is proposed, considering a quadruped robot equipped with the MIGHTY suction cup that serves both as a gripper for holding the object and a force/torque sensor. The proposed control scheme is based on the notion of admittance control, and incorporates a variable damping term aiming towards increasing the controllability of the human and, at the same time, decreasing her/his effort. Furthermore, to ensure that the object is not detached from the suction cup during the collaboration, an additional control signal is proposed, which is based on a barrier artificial potential. The proposed control scheme is proven to be passive and its performance is demonstrated through experimental evaluations conducted using the Unitree Go1 robot equipped with the MIGHTY suction cup.

Robotics0 citations2025-07-30arXiv ->

TIR-Diffusion: Diffusion-based Thermal Infrared Image Denoising via Latent and Wavelet Domain Optimization

Tai Hyoung Rhee, Dong-guw Lee, Ayoung Kim

Thermal infrared imaging exhibits considerable potentials for robotic perception tasks, especially in environments with poor visibility or challenging lighting conditions. However, TIR images typically suffer from heavy non-uniform fixed-pattern noise, complicating tasks such as object detection, localization, and mapping. To address this, we propose a diffusion-based TIR image denoising framework leveraging latent-space representations and wavelet-domain optimization. Utilizing a pretrained stable diffusion model, our method fine-tunes the model via a novel loss function combining latent-space and discrete wavelet transform (DWT) / dual-tree complex wavelet transform (DTCWT) losses. Additionally, we implement a cascaded refinement stage to enhance fine details, ensuring high-fidelity denoising results. Experiments on benchmark datasets demonstrate superior performance of our approach compared to state-of-the-art denoising methods. Furthermore, our method exhibits robust zero-shot generalization to diverse and challenging real-world TIR datasets, underscoring its effectiveness for practical robotic deployment.

Learning0 citations2025-07-21arXiv ->

Toward a Real-Time Framework for Accurate Monocular 3D Human Pose Estimation with Geometric Priors

Mohamed Adjel

Monocular 3D human pose estimation remains a challenging and ill-posed problem, particularly in real-time settings and unconstrained environments. While direct imageto-3D approaches require large annotated datasets and heavy models, 2D-to-3D lifting offers a more lightweight and flexible alternative-especially when enhanced with prior knowledge. In this work, we propose a framework that combines real-time 2D keypoint detection with geometry-aware 2D-to-3D lifting, explicitly leveraging known camera intrinsics and subject-specific anatomical priors. Our approach builds on recent advances in self-calibration and biomechanically-constrained inverse kinematics to generate large-scale, plausible 2D-3D training pairs from MoCap and synthetic datasets. We discuss how these ingredients can enable fast, personalized, and accurate 3D pose estimation from monocular images without requiring specialized hardware. This proposal aims to foster discussion on bridging data-driven learning and model-based priors to improve accuracy, interpretability, and deployability of 3D human motion capture on edge devices in the wild.

Robotics0 citations2025-07-15arXiv ->

Uncertainty Aware Mapping for Vision-Based Underwater Robots

Abhimanyu Bhowmik, Mohit Singh, Madhushree Sannigrahi, Martin Ludvigsen, Kostas Alexis

Vision-based underwater robots can be useful in inspecting and exploring confined spaces where traditional sensors and preplanned paths cannot be followed. Sensor noise and situational change can cause significant uncertainty in environmental representation. Thus, this paper explores how to represent mapping inconsistency in vision-based sensing and incorporate depth estimation confidence into the mapping framework. The scene depth and the confidence are estimated using the RAFT-Stereo model and are integrated into a voxel-based mapping framework, Voxblox. Improvements in the existing Voxblox weight calculation and update mechanism are also proposed. Finally, a qualitative analysis of the proposed method is performed in a confined pool and in a pier in the Trondheim fjord. Experiments using an underwater robot demonstrated the change in uncertainty in the visualization.

Robotics0 citations2025-07-14arXiv ->

Ariel Explores: Vision-based underwater exploration and inspection via generalist drone-level autonomy

Mohit Singh, Mihir Dharmadhikari, Kostas Alexis

This work presents a vision-based underwater exploration and inspection autonomy solution integrated into Ariel, a custom vision-driven underwater robot. Ariel carries a $5$ camera and IMU based sensing suite, enabling a refraction-aware multi-camera visual-inertial state estimation method aided by a learning-based proprioceptive robot velocity prediction method that enhances robustness against visual degradation. Furthermore, our previously developed and extensively field-verified autonomous exploration and general visual inspection solution is integrated on Ariel, providing aerial drone-level autonomy underwater. The proposed system is field-tested in a submarine dry dock in Trondheim under challenging visual conditions. The field demonstration shows the robustness of the state estimation solution and the generalizability of the path planning techniques across robot embodiments.

MPC/Planning0 citations2025-07-08arXiv ->

Mapping the Catacombs: An Underwater Cave Segment of the Devil's Eye System

Michalis Chatzispyrou, Luke Horgan, Hyunkil Hwang, Harish Sathishchandra, Monika Roznere et al.

This paper presents a framework for mapping underwater caves. Underwater caves are crucial for fresh water resource management, underwater archaeology, and hydrogeology. Mapping the cave's outline and dimensions, as well as creating photorealistic 3D maps, is critical for enabling a better understanding of this underwater domain. In this paper, we present the mapping of an underwater cave segment (the catacombs) of the Devil's Eye cave system at Ginnie Springs, FL. We utilized a set of inexpensive action cameras in conjunction with a dive computer to estimate the trajectories of the cameras together with a sparse point cloud. The resulting reconstructions are utilized to produce a one-dimensional retract of the cave passages in the form of the average trajectory together with the boundaries (top, bottom, left, and right). The use of the dive computer enables the observability of the z-dimension in addition to the roll and pitch in a visual/inertial framework (SVIn2). In addition, the keyframes generated by SVIn2 together with the estimated camera poses for select areas are used as input to a global optimization (bundle adjustment) framework -- COLMAP -- in order to produce a dense reconstruction of those areas. The same cave segment is manually surveyed using the MNemo V2 instrument, providing an additional set of measurements validating the proposed approach. It is worth noting that with the use of action cameras, the primary components of a cave map can be constructed. Furthermore, with the utilization of a global optimization framework guided by the results of VI-SLAM package SVIn2, photorealistic dense 3D representations of selected areas can be reconstructed.

Robotics0 citations2025-07-07arXiv ->

Feature Geometry for Stereo Sidescan and Forward-looking Sonar

Kalin Norman, Joshua G. Mangelson

In this paper, we address stereo acoustic data fusion for marine robotics and propose a geometry-based method for projecting observed features from one sonar to another for a cross-modal stereo sonar setup that consists of both a forward-looking and a sidescan sonar. Our acoustic geometry for sidescan and forward-looking sonar is inspired by the epipolar geometry for stereo cameras, and we leverage relative pose information to project where an observed feature in one sonar image will be found in the image of another sonar. Additionally, we analyze how both the feature location relative to the sonar and the relative pose between the two sonars impact the projection. From simulated results, we identify desirable stereo configurations for applications in field robotics like feature correspondence and recovery of the 3D information of the feature.

Robotics0 citations2025-07-07arXiv ->

Cat Royale: An Artistic Inquiry into Trust in Robots

Matt Adams, Nick Tandavanitj, Steve Benford, Ayse Kucukyilmaz, Victor Ngo et al.

Cat Royale is an artwork created by the artists Blast Theory to explore the question of whether we should trust robots to care for our loved ones. The artists endeavoured to create a `Cat Utopia', a luxurious environment that was inhabited by a family of three cats for six hours a day for twelve days, at the centre of which a robot arm played with them by wielding toys. Behind the scenes, the decision engine recommended games based on ongoing assessment of their happiness. A video installation featuring an eight-hour movie of the cats' exploits is currently touring worldwide, provoking audiences to engage with the question of trust in autonomous systems.

Robotics0 citations2025-07-01arXiv ->

Stable Tracking of Eye Gaze Direction During Ophthalmic Surgery

Tinghe Hong, Shenlin Cai, Boyang Li, Kai Huang

Ophthalmic surgical robots offer superior stability and precision by reducing the natural hand tremors of human surgeons, enabling delicate operations in confined surgical spaces. Despite the advancements in developing vision- and force-based control methods for surgical robots, preoperative navigation remains heavily reliant on manual operation, limiting the consistency and increasing the uncertainty. Existing eye gaze estimation techniques in the surgery, whether traditional or deep learning-based, face challenges including dependence on additional sensors, occlusion issues in surgical environments, and the requirement for facial detection. To address these limitations, this study proposes an innovative eye localization and tracking method that combines machine learning with traditional algorithms, eliminating the requirements of landmarks and maintaining stable iris detection and gaze estimation under varying lighting and shadow conditions. Extensive real-world experiment results show that our proposed method has an average estimation error of 0.58 degrees for eye orientation estimation and 2.08-degree average control error for the robotic arm's movement based on the calculated orientation.

RSS 2025 | 34 papers
CBF Related Papers
Robotics0 citations2025-05-06arXiv ->

Demonstrating ViSafe: Vision-enabled Safety for High-speed Detect and Avoid

Parv Kapoor, Ian Higgins, Nikhil Keetha, Jay Patrikar, Brady Moon et al.

Assured safe-separation is essential for achieving seamless high-density operation of airborne vehicles in a shared airspace. To equip resource-constrained aerial systems with this safety-critical capability, we present ViSafe, a high-speed vision-only airborne collision avoidance system. ViSafe offers a full-stack solution to the Detect and Avoid (DAA) problem by tightly integrating a learning-based edge-AI framework with a custom multi-camera hardware prototype designed under SWaP-C constraints. By leveraging perceptual input-focused control barrier functions (CBF) to design, encode, and enforce safety thresholds, ViSafe can provide provably safe runtime guarantees for self-separation in high-speed aerial operations. We evaluate ViSafe's performance through an extensive test campaign involving both simulated digital twins and real-world flight scenarios. By independently varying agent types, closure rates, interaction geometries, and environmental conditions (e.g., weather and lighting), we demonstrate that ViSafe consistently ensures self-separation across diverse scenarios. In first-of-its-kind real-world high-speed collision avoidance tests with closure rates reaching 144 km/h, ViSafe sets a new benchmark for vision-only autonomous collision avoidance, establishing a new standard for safety in high-speed aerial navigation.

Robotics0 citations2025-05-04arXiv ->

Resolving Conflicting Constraints in Multi-Agent Reinforcement Learning with Layered Safety

Jason J. Choi, Jasmine Jerry Aloor, Jingqi Li, Maria G. Mendoza, Hamsa Balakrishnan et al.

Preventing collisions in multi-robot navigation is crucial for deployment. This requirement hinders the use of learning-based approaches, such as multi-agent reinforcement learning (MARL), on their own due to their lack of safety guarantees. Traditional control methods, such as reachability and control barrier functions, can provide rigorous safety guarantees when interactions are limited only to a small number of robots. However, conflicts between the constraints faced by different agents pose a challenge to safe multi-agent coordination. To overcome this challenge, we propose a method that integrates multiple layers of safety by combining MARL with safety filters. First, MARL is used to learn strategies that minimize multiple agent interactions, where multiple indicates more than two. Particularly, we focus on interactions likely to result in conflicting constraints within the engagement distance. Next, for agents that enter the engagement distance, we prioritize pairs requiring the most urgent corrective actions. Finally, a dedicated safety filter provides tactical corrective actions to resolve these conflicts. Crucially, the design decisions for all layers of this framework are grounded in reachability analysis and a control barrier-value function-based filtering mechanism. We validate our Layered Safe MARL framework in 1) hardware experiments using Crazyflie drones and 2) high-density advanced aerial mobility (AAM) operation scenarios, where agents navigate to designated waypoints while avoiding collisions. The results show that our method significantly reduces conflict while maintaining safety without sacrificing much efficiency (i.e., shorter travel time and distance) compared to baselines that do not incorporate layered safety. The project website is available at https://dinamo-mit.github.io/Layered-Safe-MARL/

MPC/Planning0 citations2025-04-16arXiv ->

Safety with Agency: Human-Centered Safety Filter with Application to AI-Assisted Motorsports

Donggeon David Oh, Justin Lidard, Haimin Hu, Himani Sinhmar, Elle Lazarski et al.

We propose a human-centered safety filter (HCSF) for shared autonomy that significantly enhances system safety without compromising human agency. Our HCSF is built on a neural safety value function, which we first learn scalably through black-box interactions and then use at deployment to enforce a novel state-action control barrier function (Q-CBF) safety constraint. Since this Q-CBF safety filter does not require any knowledge of the system dynamics for both synthesis and runtime safety monitoring and intervention, our method applies readily to complex, black-box shared autonomy systems. Notably, our HCSF's CBF-based interventions modify the human's actions minimally and smoothly, avoiding the abrupt, last-moment corrections delivered by many conventional safety filters. We validate our approach in a comprehensive in-person user study using Assetto Corsa-a high-fidelity car racing simulator with black-box dynamics-to assess robustness in "driving on the edge" scenarios. We compare both trajectory data and drivers' perceptions of our HCSF assistance against unassisted driving and a conventional safety filter. Experimental results show that 1) compared to having no assistance, our HCSF improves both safety and user satisfaction without compromising human agency or comfort, and 2) relative to a conventional safety filter, our proposed HCSF boosts human agency, comfort, and satisfaction while maintaining robustness.

Other Papers
Robotics0 citations2026-02-24arXiv ->

Efficient Hierarchical Any-Angle Path Planning on Multi-Resolution 3D Grids

Victor Reijgwart, Cesar Cadena, Roland Siegwart, Lionel Ott

Hierarchical, multi-resolution volumetric mapping approaches are widely used to represent large and complex environments as they can efficiently capture their occupancy and connectivity information. Yet widely used path planning methods such as sampling and trajectory optimization do not exploit this explicit connectivity information, and search-based methods such as A* suffer from scalability issues in large-scale high-resolution maps. In many applications, Euclidean shortest paths form the underpinning of the navigation system. For such applications, any-angle planning methods, which find optimal paths by connecting corners of obstacles with straight-line segments, provide a simple and efficient solution. In this paper, we present a method that has the optimality and completeness properties of any-angle planners while overcoming computational tractability issues common to search-based methods by exploiting multi-resolution representations. Extensive experiments on real and synthetic environments demonstrate the proposed approach's solution quality and speed, outperforming even sampling-based methods. The framework is open-sourced to allow the robotics and planning community to build on our research.

Robotics0 citations2026-01-08arXiv ->

Intent at a Glance: Gaze-Guided Robotic Manipulation via Foundation Models

Tracey Yee Hsin Tay, Xu Yan, Jonathan Ouyang, Daniel Wu, William Jiang et al.

Designing intuitive interfaces for robotic control remains a central challenge in enabling effective human-robot interaction, particularly in assistive care settings. Eye gaze offers a fast, non-intrusive, and intent-rich input modality, making it an attractive channel for conveying user goals. In this work, we present GAMMA (Gaze Assisted Manipulation for Modular Autonomy), a system that leverages ego-centric gaze tracking and a vision-language model to infer user intent and autonomously execute robotic manipulation tasks. By contextualizing gaze fixations within the scene, the system maps visual attention to high-level semantic understanding, enabling skill selection and parameterization without task-specific training. We evaluate GAMMA on a range of table-top manipulation tasks and compare it against baseline gaze-based control without reasoning. Results demonstrate that GAMMA provides robust, intuitive, and generalizable control, highlighting the potential of combining foundation models and gaze for natural and scalable robot autonomy. Project website: https://gamma0.vercel.app/

Robotics0 citations2025-11-03arXiv ->

Learning from Watching: Scalable Extraction of Manipulation Trajectories from Human Videos

X. Hu, G. Ye

Collecting high-quality data for training large-scale robotic models typically relies on real robot platforms, which is labor-intensive and costly, whether via teleoperation or scripted demonstrations. To scale data collection, many researchers have turned to leveraging human manipulation videos available online. However, current methods predominantly focus on hand detection or object pose estimation, failing to fully exploit the rich interaction cues embedded in these videos. In this work, we propose a novel approach that combines large foundation models for video understanding with point tracking techniques to extract dense trajectories of all task-relevant keypoints during manipulation. This enables more comprehensive utilization of Internet-scale human demonstration videos. Experimental results demonstrate that our method can accurately track keypoints throughout the entire manipulation process, paving the way for more scalable and data-efficient robot learning.

Robotics0 citations2025-10-27arXiv ->

Finding 3D Scene Analogies with Multimodal Foundation Models

Junho Kim, Young Min Kim

Connecting current observations with prior experiences helps robots adapt and plan in new, unseen 3D environments. Recently, 3D scene analogies have been proposed to connect two 3D scenes, which are smooth maps that align scene regions with common spatial relationships. These maps enable detailed transfer of trajectories or waypoints, potentially supporting demonstration transfer for imitation learning or task plan transfer across scenes. However, existing methods for the task require additional training and fixed object vocabularies. In this work, we propose to use multimodal foundation models for finding 3D scene analogies in a zero-shot, open-vocabulary setting. Central to our approach is a hybrid neural representation of scenes that consists of a sparse graph based on vision-language model features and a feature field derived from 3D shape foundation models. 3D scene analogies are then found in a coarse-to-fine manner, by first aligning the graph and refining the correspondence with feature fields. Our method can establish accurate correspondences between complex scenes, and we showcase applications in trajectory and waypoint transfer.

Robotics0 citations2025-10-12arXiv ->

Gain Tuning Is Not What You Need: Reward Gain Adaptation for Constrained Locomotion Learning

Arthicha Srisuchinnawong, Poramate Manoonpong

Existing robot locomotion learning techniques rely heavily on the offline selection of proper reward weighting gains and cannot guarantee constraint satisfaction (i.e., constraint violation) during training. Thus, this work aims to address both issues by proposing Reward-Oriented Gains via Embodied Regulation (ROGER), which adapts reward-weighting gains online based on penalties received throughout the embodied interaction process. The ratio between the positive reward (primary reward) and negative reward (penalty) gains is automatically reduced as the learning approaches the constraint thresholds to avoid violation. Conversely, the ratio is increased when learning is in safe states to prioritize performance. With a 60-kg quadruped robot, ROGER achieved near-zero constraint violation throughout multiple learning trials. It also achieved up to 50% more primary reward than the equivalent state-of-the-art techniques. In MuJoCo continuous locomotion benchmarks, including a single-leg hopper, ROGER exhibited comparable or up to 100% higher performance and 60% less torque usage and orientation deviation compared to those trained with the default reward function. Finally, real-world locomotion learning of a physical quadruped robot was achieved from scratch within one hour without any falls. Therefore, this work contributes to constraint-satisfying real-world continual robot locomotion learning and simplifies reward weighting gain tuning, potentially facilitating the development of physical robots and those that learn in the real world.

Robotics0 citations2025-09-30arXiv ->

Kinodynamic Motion Planning for Mobile Robot Navigation across Inconsistent World Models

Eric R. Damm, Thomas M. Howard

Mobile ground robots lacking prior knowledge of an environment must rely on sensor data to develop a model of their surroundings. In these scenarios, consistent identification of obstacles and terrain features can be difficult due to noise and algorithmic shortcomings, which can make it difficult for motion planning systems to generate safe motions. One particular difficulty to overcome is when regions of the cost map switch between being marked as obstacles and free space through successive planning cycles. One potential solution to this, which we refer to as Valid in Every Hypothesis (VEH), is for the planning system to plan motions that are guaranteed to be safe through a history of world models. Another approach is to track a history of world models, and adjust node costs according to the potential penalty of needing to reroute around previously hazardous areas. This work discusses three major iterations on this idea. The first iteration, called PEH, invokes a sub-search for every node expansion that crosses through a divergence point in the world models. The second and third iterations, called GEH and GEGRH respectively, defer the sub-search until after an edge expands into the goal region. GEGRH uses an additional step to revise the graph based on divergent nodes in each world. Initial results showed that, although PEH and GEH find more optimistic solutions than VEH, they are unable to generate solutions in less than one-second, which exceeds our requirements for field deployment. Analysis of results from a field experiment in an unstructured, off-road environment on a Clearpath Robotics Warthog UGV indicate that GEGRH finds lower cost trajectories and has faster average planning times than VEH. Compared to single-hypothesis (SH) search, where only the latest world model is considered, GEGRH generates more conservative plans with a small increase in average planning time.

Robotics0 citations2025-07-29arXiv ->

emg2tendon: From sEMG Signals to Tendon Control in Musculoskeletal Hands

Sagar Verma

Tendon-driven robotic hands offer unparalleled dexterity for manipulation tasks, but learning control policies for such systems presents unique challenges. Unlike joint-actuated robotic hands, tendon-driven systems lack a direct one-to-one mapping between motion capture (mocap) data and tendon controls, making the learning process complex and expensive. Additionally, visual tracking methods for real-world applications are prone to occlusions and inaccuracies, further complicating joint tracking. Wrist-wearable surface electromyography (sEMG) sensors present an inexpensive, robust alternative to capture hand motion. However, mapping sEMG signals to tendon control remains a significant challenge despite the availability of EMG-to-pose data sets and regression-based models in the existing literature. We introduce the first large-scale EMG-to-Tendon Control dataset for robotic hands, extending the emg2pose dataset, which includes recordings from 193 subjects, spanning 370 hours and 29 stages with diverse gestures. This dataset incorporates tendon control signals derived using the MyoSuite MyoHand model, addressing limitations such as invalid poses in prior methods. We provide three baseline regression models to demonstrate emg2tendon utility and propose a novel diffusion-based regression model for predicting tendon control from sEMG recordings. This dataset and modeling framework marks a significant step forward for tendon-driven dexterous robotic manipulation, laying the groundwork for scalable and accurate tendon control in robotic hands. https://emg2tendon.github.io/

Learning0 citations2025-07-22arXiv ->

Morpheus: A Neural-driven Animatronic Face with Hybrid Actuation and Diverse Emotion Control

Zongzheng Zhang, Jiawen Yang, Ziqiao Peng, Meng Yang, Jianzhu Ma et al.

Previous animatronic faces struggle to express emotions effectively due to hardware and software limitations. On the hardware side, earlier approaches either use rigid-driven mechanisms, which provide precise control but are difficult to design within constrained spaces, or tendon-driven mechanisms, which are more space-efficient but challenging to control. In contrast, we propose a hybrid actuation approach that combines the best of both worlds. The eyes and mouth-key areas for emotional expression-are controlled using rigid mechanisms for precise movement, while the nose and cheek, which convey subtle facial microexpressions, are driven by strings. This design allows us to build a compact yet versatile hardware platform capable of expressing a wide range of emotions. On the algorithmic side, our method introduces a self-modeling network that maps motor actions to facial landmarks, allowing us to automatically establish the relationship between blendshape coefficients for different facial expressions and the corresponding motor control signals through gradient backpropagation. We then train a neural network to map speech input to corresponding blendshape controls. With our method, we can generate distinct emotional expressions such as happiness, fear, disgust, and anger, from any given sentence, each with nuanced, emotion-specific control signals-a feature that has not been demonstrated in earlier systems. We release the hardware design and code at https://github.com/ZZongzheng0918/Morpheus-Hardware and https://github.com/ZZongzheng0918/Morpheus-Software.

Robotics0 citations2025-07-17arXiv ->

Learning to Predict Mobile Robot Stability in Off-Road Environments

Nathaniel Rose, Arif Ahmed, Emanuel Gutierrez-Cornejo, Parikshit Maini

Navigating in off-road environments for wheeled mobile robots is challenging due to dynamic and rugged terrain. Traditional physics-based stability metrics, such as Static Stability Margin (SSM) or Zero Moment Point (ZMP) require knowledge of contact forces, terrain geometry, and the robot's precise center-of-mass that are difficult to measure accurately in real-world field conditions. In this work, we propose a learning-based approach to estimate robot platform stability directly from proprioceptive data using a lightweight neural network, IMUnet. Our method enables data-driven inference of robot stability without requiring an explicit terrain model or force sensing. We also develop a novel vision-based ArUco tracking method to compute a scalar score to quantify robot platform stability called C3 score. The score captures image-space perturbations over time as a proxy for physical instability and is used as a training signal for the neural network based model. As a pilot study, we evaluate our approach on data collected across multiple terrain types and speeds and demonstrate generalization to previously unseen conditions. These initial results highlight the potential of using IMU and robot velocity as inputs to estimate platform stability. The proposed method finds application in gating robot tasks such as precision actuation and sensing, especially for mobile manipulation tasks in agricultural and space applications. Our learning method also provides a supervision mechanism for perception based traversability estimation and planning.

Robotics0 citations2025-07-13arXiv ->

Influence of Static and Dynamic Downwash Interactions on Multi-Quadrotor Systems

Anoop Kiran, Nora Ayanian, Kenneth Breuer

Flying multiple quadrotors in close proximity presents a significant challenge due to complex aerodynamic interactions, particularly downwash effects that are known to destabilize vehicles and degrade performance. Traditionally, multi-quadrotor systems rely on conservative strategies, such as collision avoidance zones around the robot volume, to circumvent this effect. This restricts their capabilities by requiring a large volume for the operation of a multi-quadrotor system, limiting their applicability in dense environments. This work provides a comprehensive, data-driven analysis of the downwash effect, with a focus on characterizing, analyzing, and understanding forces, moments, and velocities in both single and multi-quadrotor configurations. We use measurements of forces and torques to characterize vehicle interactions, and particle image velocimetry (PIV) to quantify the spatial features of the downwash wake for a single quadrotor and an interacting pair of quadrotors. This data can be used to inform physics-based strategies for coordination, leverage downwash for optimized formations, expand the envelope of operation, and improve the robustness of multi-quadrotor control.

Robotics0 citations2025-07-12arXiv ->

Domain Adaptation and Multi-view Attention for Learnable Landmark Tracking with Sparse Data

Timothy Chase, Karthik Dantu

The detection and tracking of celestial surface terrain features are crucial for autonomous spaceflight applications, including Terrain Relative Navigation (TRN), Entry, Descent, and Landing (EDL), hazard analysis, and scientific data collection. Traditional photoclinometry-based pipelines often rely on extensive a priori imaging and offline processing, constrained by the computational limitations of radiation-hardened systems. While historically effective, these approaches typically increase mission costs and duration, operate at low processing rates, and have limited generalization. Recently, learning-based computer vision has gained popularity to enhance spacecraft autonomy and overcome these limitations. While promising, emerging techniques frequently impose computational demands exceeding the capabilities of typical spacecraft hardware for real-time operation and are further challenged by the scarcity of labeled training data for diverse extraterrestrial environments. In this work, we present novel formulations for in-situ landmark tracking via detection and description. We utilize lightweight, computationally efficient neural network architectures designed for real-time execution on current-generation spacecraft flight processors. For landmark detection, we propose improved domain adaptation methods that enable the identification of celestial terrain features with distinct, cheaply acquired training data. Concurrently, for landmark description, we introduce a novel attention alignment formulation that learns robust feature representations that maintain correspondence despite significant landmark viewpoint variations. Together, these contributions form a unified system for landmark tracking that demonstrates superior performance compared to existing state-of-the-art techniques.

Robotics0 citations2025-06-29arXiv ->

Safe and Performant Deployment of Autonomous Systems via Model Predictive Control and Hamilton-Jacobi Reachability Analysis

Hao Wang, Armand Jordana, Ludovic Righetti, Somil Bansal

While we have made significant algorithmic developments to enable autonomous systems to perform sophisticated tasks, it remains difficult for them to perform tasks effective and safely. Most existing approaches either fail to provide any safety assurances or substantially compromise task performance for safety. In this work, we develop a framework, based on model predictive control (MPC) and Hamilton-Jacobi (HJ) reachability, to optimize task performance for autonomous systems while respecting the safety constraints. Our framework guarantees recursive feasibility for the MPC controller, and it is scalable to high-dimensional systems. We demonstrate the effectiveness of our framework with two simulation studies using a 4D Dubins Car and a 6 Dof Kuka iiwa manipulator, and the experiments show that our framework significantly improves the safety constraints satisfaction of the systems over the baselines.

Robotics0 citations2025-06-28arXiv ->

Hierarchical Vision-Language Planning for Multi-Step Humanoid Manipulation

André Schakkal, Ben Zandonati, Zhutian Yang, Navid Azizan

Enabling humanoid robots to reliably execute complex multi-step manipulation tasks is crucial for their effective deployment in industrial and household environments. This paper presents a hierarchical planning and control framework designed to achieve reliable multi-step humanoid manipulation. The proposed system comprises three layers: (1) a low-level RL-based controller responsible for tracking whole-body motion targets; (2) a mid-level set of skill policies trained via imitation learning that produce motion targets for different steps of a task; and (3) a high-level vision-language planning module that determines which skills should be executed and also monitors their completion in real-time using pretrained vision-language models (VLMs). Experimental validation is performed on a Unitree G1 humanoid robot executing a non-prehensile pick-and-place task. Over 40 real-world trials, the hierarchical system achieved a 73% success rate in completing the full manipulation sequence. These experiments confirm the feasibility of the proposed hierarchical system, highlighting the benefits of VLM-based skill planning and monitoring for multi-step manipulation scenarios. See https://vlp-humanoid.github.io/ for video demonstrations of the policy rollout.

Robotics0 citations2025-06-28arXiv ->

Robust Peg-in-Hole Assembly under Uncertainties via Compliant and Interactive Contact-Rich Manipulation

Yiting Chen, Kenneth Kimble, Howard H. Qian, Podshara Chanrungmaneekul, Robert Seney et al.

Robust and adaptive robotic peg-in-hole assembly under tight tolerances is critical to various industrial applications. However, it remains an open challenge due to perceptual and physical uncertainties from contact-rich interactions that easily exceed the allowed clearance. In this paper, we study how to leverage contact between the peg and its matching hole to eliminate uncertainties in the assembly process under unstructured settings. By examining the role of compliance under contact constraints, we present a manipulation system that plans collision-inclusive interactions for the peg to 1) iteratively identify its task environment to localize the target hole and 2) exploit environmental contact constraints to refine insertion motions into the target hole without relying on precise perception, enabling a robust solution to peg-in-hole assembly. By conceptualizing the above process as the composition of funneling in different state spaces, we present a formal approach to constructing manipulation funnels as an uncertainty-absorbing paradigm for peg-in-hole assembly. The proposed system effectively generalizes across diverse peg-in-hole scenarios across varying scales, shapes, and materials in a learning-free manner. Extensive experiments on a NIST Assembly Task Board (ATB) and additional challenging scenarios validate its robustness in real-world applications.

Robotics0 citations2025-06-23arXiv ->

Learning Physical Systems: Symplectification via Gauge Fixing in Dirac Structures

Aristotelis Papatheodorou, Pranav Vaidhyanathan, Natalia Ares, Ioannis Havoutis

Physics-informed deep learning has achieved remarkable progress by embedding geometric priors, such as Hamiltonian symmetries and variational principles, into neural networks, enabling structure-preserving models that extrapolate with high accuracy. However, in systems with dissipation and holonomic constraints, ubiquitous in legged locomotion and multibody robotics, the canonical symplectic form becomes degenerate, undermining the very invariants that guarantee stability and long-term prediction. In this work, we tackle this foundational limitation by introducing Presymplectification Networks (PSNs), the first framework to learn the symplectification lift via Dirac structures, restoring a non-degenerate symplectic geometry by embedding constrained systems into a higher-dimensional manifold. Our architecture combines a recurrent encoder with a flow-matching objective to learn the augmented phase-space dynamics end-to-end. We then attach a lightweight Symplectic Network (SympNet) to forecast constrained trajectories while preserving energy, momentum, and constraint satisfaction. We demonstrate our method on the dynamics of the ANYmal quadruped robot, a challenging contact-rich, multibody system. To the best of our knowledge, this is the first framework that effectively bridges the gap between constrained, dissipative mechanical systems and symplectic learning, unlocking a whole new class of geometric machine learning models, grounded in first principles yet adaptable from data.

Robotics0 citations2025-06-21arXiv ->

Leveling the Playing Field: Carefully Comparing Classical and Learned Controllers for Quadrotor Trajectory Tracking

Pratik Kunapuli, Jake Welde, Dinesh Jayaraman, Vijay Kumar

Learning-based control approaches like reinforcement learning (RL) have recently produced a slew of impressive results for tasks like quadrotor trajectory tracking and drone racing. Naturally, it is common to demonstrate the advantages of these new controllers against established methods like analytical controllers. We observe, however, that reliably comparing the performance of such very different classes of controllers is more complicated than might appear at first sight. As a case study, we take up the problem of agile tracking of an end-effector for a quadrotor with a fixed arm. We develop a set of best practices for synthesizing the best-in-class RL and geometric controllers (GC) for benchmarking. In the process, we resolve widespread RL-favoring biases in prior studies that provide asymmetric access to: (1) the task definition, in the form of an objective function, (2) representative datasets, for parameter optimization, and (3) feedforward information, describing the desired future trajectory. The resulting findings are the following: our improvements to the experimental protocol for comparing learned and classical controllers are critical, and each of the above asymmetries can yield misleading conclusions. Prior works have claimed that RL outperforms GC, but we find the gaps between the two controller classes are much smaller than previously published when accounting for symmetric comparisons. Geometric control achieves lower steady-state error than RL, while RL has better transient performance, resulting in GC performing better in relatively slow or less agile tasks, but RL performing better when greater agility is required. Finally, we open-source implementations of geometric and RL controllers for these aerial vehicles, implementing best practices for future development. Website and code is available at https://pratikkunapuli.github.io/rl-vs-gc/

Robotics0 citations2025-06-21arXiv ->

Towards Zero-Shot Coordination between Teams of Agents: The N-XPlay Framework

Ava Abderezaei, Chi-Hui Lin, Joseph Miceli, Naren Sivagnanadasan, Stéphane Aroca-Ouellette et al.

Zero-shot coordination (ZSC) -- the ability to collaborate with unfamiliar partners -- is essential to making autonomous agents effective teammates. Existing ZSC methods evaluate coordination capabilities between two agents who have not previously interacted. However, these scenarios do not reflect the complexity of real-world multi-agent systems, where coordination often involves a hierarchy of sub-groups and interactions between teams of agents, known as Multi-Team Systems (MTS). To address this gap, we first introduce N-player Overcooked, an N-agent extension of the popular two-agent ZSC benchmark, enabling evaluation of ZSC in N-agent scenarios. We then propose N-XPlay for ZSC in N-agent, multi-team settings. Comparison against Self-Play across two-, three- and five-player Overcooked scenarios, where agents are split between an ``ego-team'' and a group of unseen collaborators shows that agents trained with N-XPlay are better able to simultaneously balance ``intra-team'' and ``inter-team'' coordination than agents trained with SP.

Robotics0 citations2025-06-20arXiv ->

Kinematic Model Optimization via Differentiable Contact Manifold for In-Space Manipulation

Abhay Negi, Omey M. Manyar, Satyandra K. Gupta

Robotic manipulation in space is essential for emerging applications such as debris removal and in-space servicing, assembly, and manufacturing (ISAM). A key requirement for these tasks is the ability to perform precise, contact-rich manipulation under significant uncertainty. In particular, thermal-induced deformation of manipulator links and temperature-dependent encoder bias introduce kinematic parameter errors that significantly degrade end-effector accuracy. Traditional calibration techniques rely on external sensors or dedicated calibration procedures, which can be infeasible or risky in dynamic, space-based operational scenarios. This paper proposes a novel method for kinematic parameter estimation that only requires encoder measurements and binary contact detection. The approach focuses on estimating link thermal deformation strain and joint encoder biases by leveraging information of the contact manifold - the set of relative SE(3) poses at which contact between the manipulator and environment occurs. We present two core contributions: (1) a differentiable, learning-based model of the contact manifold, and (2) an optimization-based algorithm for estimating kinematic parameters from encoder measurements at contact instances. By enabling parameter estimation using only encoder measurements and contact detection, this method provides a robust, interpretable, and data-efficient solution for safe and accurate manipulation in the challenging conditions of space.

Robotics0 citations2025-06-20arXiv ->

Dex1B: Learning with 1B Demonstrations for Dexterous Manipulation

Jianglong Ye, Keyi Wang, Chengjing Yuan, Ruihan Yang, Yiquan Li et al.

Generating large-scale demonstrations for dexterous hand manipulation remains challenging, and several approaches have been proposed in recent years to address this. Among them, generative models have emerged as a promising paradigm, enabling the efficient creation of diverse and physically plausible demonstrations. In this paper, we introduce Dex1B, a large-scale, diverse, and high-quality demonstration dataset produced with generative models. The dataset contains one billion demonstrations for two fundamental tasks: grasping and articulation. To construct it, we propose a generative model that integrates geometric constraints to improve feasibility and applies additional conditions to enhance diversity. We validate the model on both established and newly introduced simulation benchmarks, where it significantly outperforms prior state-of-the-art methods. Furthermore, we demonstrate its effectiveness and robustness through real-world robot experiments. Our project page is at https://jianglongye.com/dex1b

Robotics0 citations2025-06-20arXiv ->

Judo: A User-Friendly Open-Source Package for Sampling-Based Model Predictive Control

Albert H. Li, Brandon Hung, Aaron D. Ames, Jiuguang Wang, Simon Le Cleac'h et al.

Recent advancements in parallel simulation and successful robotic applications are spurring a resurgence in sampling-based model predictive control. To build on this progress, however, the robotics community needs common tooling for prototyping, evaluating, and deploying sampling-based controllers. We introduce Judo, a software package designed to address this need. To facilitate rapid prototyping and evaluation, Judo provides robust implementations of common sampling-based MPC algorithms and standardized benchmark tasks. It further emphasizes usability with simple but extensible interfaces for controller and task definitions, asynchronous execution for straightforward simulation-to-hardware transfer, and a highly customizable interactive GUI for tuning controllers interactively. While written in Python, the software leverages MuJoCo as its physics backend to achieve real-time performance, which we validate across both consumer and server-grade hardware. Code at https://github.com/bdaiinstitute/judo.

Robotics0 citations2025-06-19arXiv ->

CodeDiffuser: Attention-Enhanced Diffusion Policy via VLM-Generated Code for Instruction Ambiguity

Guang Yin, Yitong Li, Yixuan Wang, Dale McConachie, Paarth Shah et al.

Natural language instructions for robotic manipulation tasks often exhibit ambiguity and vagueness. For instance, the instruction "Hang a mug on the mug tree" may involve multiple valid actions if there are several mugs and branches to choose from. Existing language-conditioned policies typically rely on end-to-end models that jointly handle high-level semantic understanding and low-level action generation, which can result in suboptimal performance due to their lack of modularity and interpretability. To address these challenges, we introduce a novel robotic manipulation framework that can accomplish tasks specified by potentially ambiguous natural language. This framework employs a Vision-Language Model (VLM) to interpret abstract concepts in natural language instructions and generates task-specific code - an interpretable and executable intermediate representation. The generated code interfaces with the perception module to produce 3D attention maps that highlight task-relevant regions by integrating spatial and semantic information, effectively resolving ambiguities in instructions. Through extensive experiments, we identify key limitations of current imitation learning methods, such as poor adaptation to language and environmental variations. We show that our approach excels across challenging manipulation tasks involving language ambiguity, contact-rich manipulation, and multi-object interactions.

Robotics0 citations2025-06-17arXiv ->

FEAST: A Flexible Mealtime-Assistance System Towards In-the-Wild Personalization

Rajat Kumar Jenamani, Tom Silver, Ben Dodson, Shiqin Tong, Anthony Song et al.

Physical caregiving robots hold promise for improving the quality of life of millions worldwide who require assistance with feeding. However, in-home meal assistance remains challenging due to the diversity of activities (e.g., eating, drinking, mouth wiping), contexts (e.g., socializing, watching TV), food items, and user preferences that arise during deployment. In this work, we propose FEAST, a flexible mealtime-assistance system that can be personalized in-the-wild to meet the unique needs of individual care recipients. Developed in collaboration with two community researchers and informed by a formative study with a diverse group of care recipients, our system is guided by three key tenets for in-the-wild personalization: adaptability, transparency, and safety. FEAST embodies these principles through: (i) modular hardware that enables switching between assisted feeding, drinking, and mouth-wiping, (ii) diverse interaction methods, including a web interface, head gestures, and physical buttons, to accommodate diverse functional abilities and preferences, and (iii) parameterized behavior trees that can be safely and transparently adapted using a large language model. We evaluate our system based on the personalization requirements identified in our formative study, demonstrating that FEAST offers a wide range of transparent and safe adaptations and outperforms a state-of-the-art baseline limited to fixed customizations. To demonstrate real-world applicability, we conduct an in-home user study with two care recipients (who are community researchers), feeding them three meals each across three diverse scenarios. We further assess FEAST's ecological validity by evaluating with an Occupational Therapist previously unfamiliar with the system. In all cases, users successfully personalize FEAST to meet their individual needs and preferences. Website: https://emprise.cs.cornell.edu/feast

Robotics0 citations2025-06-17arXiv ->

Can Pretrained Vision-Language Embeddings Alone Guide Robot Navigation?

Nitesh Subedi, Adam Haroon, Shreyan Ganguly, Samuel T. K. Tetteh, Prajwal Koirala et al.

Foundation models have revolutionized robotics by providing rich semantic representations without task-specific training. While many approaches integrate pretrained vision-language models (VLMs) with specialized navigation architectures, the fundamental question remains: can these pretrained embeddings alone successfully guide navigation without additional fine-tuning or specialized modules? We present a minimalist framework that decouples this question by training a behavior cloning policy directly on frozen vision-language embeddings from demonstrations collected by a privileged expert. Our approach achieves a 74% success rate in navigation to language-specified targets, compared to 100% for the state-aware expert, though requiring 3.2 times more steps on average. This performance gap reveals that pretrained embeddings effectively support basic language grounding but struggle with long-horizon planning and spatial reasoning. By providing this empirical baseline, we highlight both the capabilities and limitations of using foundation models as drop-in representations for embodied tasks, offering critical insights for robotics researchers facing practical design tradeoffs between system complexity and performance in resource-constrained scenarios. Our code is available at https://github.com/oadamharoon/text2nav

Other0 citations2025-06-16arXiv ->

Diffusion-based Inverse Observation Model for Artificial Skin

Ante Maric, Julius Jankowski, Giammarco Caroleo, Alessandro Albini, Perla Maiolino et al.

Contact-based estimation of object pose is challenging due to discontinuities and ambiguous observations that can correspond to multiple possible system states. This multimodality makes it difficult to efficiently sample valid hypotheses while respecting contact constraints. Diffusion models can learn to generate samples from such multimodal probability distributions through denoising algorithms. We leverage these probabilistic modeling capabilities to learn an inverse observation model conditioned on tactile measurements acquired from a distributed artificial skin. We present simulated experiments demonstrating efficient sampling of contact hypotheses for object pose estimation through touch.

Robotics0 citations2025-06-16arXiv ->

Towards Efficient Occupancy Mapping via Gaussian Process Latent Field Shaping

Cedric Le Gentil, Cedric Pradalier, Timothy D. Barfoot

Occupancy mapping has been a key enabler of mobile robotics. Originally based on a discrete grid representation, occupancy mapping has evolved towards continuous representations that can predict the occupancy status at any location and account for occupancy correlations between neighbouring areas. Gaussian Process (GP) approaches treat this task as a binary classification problem using both observations of occupied and free space. Conceptually, a GP latent field is passed through a logistic function to obtain the output class without actually manipulating the GP latent field. In this work, we propose to act directly on the latent function to efficiently integrate free space information as a prior based on the shape of the sensor's field-of-view. A major difference with existing methods is the change in the classification problem, as we distinguish between free and unknown space. The `occupied' area is the infinitesimally thin location where the class transitions from free to unknown. We demonstrate in simulated environments that our approach is sound and leads to competitive reconstruction accuracy.

Robotics0 citations2025-06-14arXiv ->

Sense and Sensibility: What makes a social robot convincing to high-school students?

Pablo Gonzalez-Oliveras, Olov Engwall, Ali Reza Majlesi

This study with 40 high-school students demonstrates the high influence of a social educational robot on students' decision-making for a set of eight true-false questions on electric circuits, for which the theory had been covered in the students' courses. The robot argued for the correct answer on six questions and the wrong on two, and 75% of the students were persuaded by the robot to perform beyond their expected capacity, positively when the robot was correct and negatively when it was wrong. Students with more experience of using large language models were even more likely to be influenced by the robot's stance -- in particular for the two easiest questions on which the robot was wrong -- suggesting that familiarity with AI can increase susceptibility to misinformation by AI. We further examined how three different levels of portrayed robot certainty, displayed using semantics, prosody and facial signals, affected how the students aligned with the robot's answer on specific questions and how convincing they perceived the robot to be on these questions. The students aligned with the robot's answers in 94.4% of the cases when the robot was portrayed as Certain, 82.6% when it was Neutral and 71.4% when it was Uncertain. The alignment was thus high for all conditions, highlighting students' general susceptibility to accept the robot's stance, but alignment in the Uncertain condition was significantly lower than in the Certain. Post-test questionnaire answers further show that students found the robot most convincing when it was portrayed as Certain. These findings highlight the need for educational robots to adjust their display of certainty based on the reliability of the information they convey, to promote students' critical thinking and reduce undue influence.

Learning0 citations2025-06-13arXiv ->

ViTaSCOPE: Visuo-tactile Implicit Representation for In-hand Pose and Extrinsic Contact Estimation

Jayjun Lee, Nima Fazeli

Mastering dexterous, contact-rich object manipulation demands precise estimation of both in-hand object poses and external contact locations$\unicode{x2013}$tasks particularly challenging due to partial and noisy observations. We present ViTaSCOPE: Visuo-Tactile Simultaneous Contact and Object Pose Estimation, an object-centric neural implicit representation that fuses vision and high-resolution tactile feedback. By representing objects as signed distance fields and distributed tactile feedback as neural shear fields, ViTaSCOPE accurately localizes objects and registers extrinsic contacts onto their 3D geometry as contact fields. Our method enables seamless reasoning over complementary visuo-tactile cues by leveraging simulation for scalable training and zero-shot transfers to the real-world by bridging the sim-to-real gap. We evaluate our method through comprehensive simulated and real-world experiments, demonstrating its capabilities in dexterous manipulation scenarios.

Robotics0 citations2025-06-13arXiv ->

SPLATART: Articulated Gaussian Splatting with Estimated Object Structure

Stanley Lewis, Vishal Chandra, Tom Gao, Odest Chadwicke Jenkins

Representing articulated objects remains a difficult problem within the field of robotics. Objects such as pliers, clamps, or cabinets require representations that capture not only geometry and color information, but also part seperation, connectivity, and joint parametrization. Furthermore, learning these representations becomes even more difficult with each additional degree of freedom. Complex articulated objects such as robot arms may have seven or more degrees of freedom, and the depth of their kinematic tree may be notably greater than the tools, drawers, and cabinets that are the typical subjects of articulated object research. To address these concerns, we introduce SPLATART - a pipeline for learning Gaussian splat representations of articulated objects from posed images, of which a subset contains image space part segmentations. SPLATART disentangles the part separation task from the articulation estimation task, allowing for post-facto determination of joint estimation and representation of articulated objects with deeper kinematic trees than previously exhibited. In this work, we present data on the SPLATART pipeline as applied to the syntheic Paris dataset objects, and qualitative results on a real-world object under spare segmentation supervision. We additionally present on articulated serial chain manipulators to demonstrate usage on deeper kinematic tree structures.

Robotics0 citations2025-06-12arXiv ->

Demonstrating Multi-Suction Item Picking at Scale via Multi-Modal Learning of Pick Success

Che Wang, Jeroen van Baar, Chaitanya Mitash, Shuai Li, Dylan Randle et al.

This work demonstrates how autonomously learning aspects of robotic operation from sparsely-labeled, real-world data of deployed, engineered solutions at industrial scale can provide with solutions that achieve improved performance. Specifically, it focuses on multi-suction robot picking and performs a comprehensive study on the application of multi-modal visual encoders for predicting the success of candidate robotic picks. Picking diverse items from unstructured piles is an important and challenging task for robot manipulation in real-world settings, such as warehouses. Methods for picking from clutter must work for an open set of items while simultaneously meeting latency constraints to achieve high throughput. The demonstrated approach utilizes multiple input modalities, such as RGB, depth and semantic segmentation, to estimate the quality of candidate multi-suction picks. The strategy is trained from real-world item picking data, with a combination of multimodal pretrain and finetune. The manuscript provides comprehensive experimental evaluation performed over a large item-picking dataset, an item-picking dataset targeted to include partial occlusions, and a package-picking dataset, which focuses on containers, such as boxes and envelopes, instead of unpackaged items. The evaluation measures performance for different item configurations, pick scenes, and object types. Ablations help to understand the effects of in-domain pretraining, the impact of different modalities and the importance of finetuning. These ablations reveal both the importance of training over multiple modalities but also the ability of models to learn during pretraining the relationship between modalities so that during finetuning and inference, only a subset of them can be used as input.

Robotics0 citations2025-06-12arXiv ->

Using Language and Road Manuals to Inform Map Reconstruction for Autonomous Driving

Akshar Tumu, Henrik I. Christensen, Marcell Vazquez-Chanlatte, Chikao Tsuchiya, Dhaval Bhanderi

Lane-topology prediction is a critical component of safe and reliable autonomous navigation. An accurate understanding of the road environment aids this task. We observe that this information often follows conventions encoded in natural language, through design codes that reflect the road structure and road names that capture the road functionality. We augment this information in a lightweight manner to SMERF, a map-prior-based online lane-topology prediction model, by combining structured road metadata from OSM maps and lane-width priors from Road design manuals with the road centerline encodings. We evaluate our method on two geo-diverse complex intersection scenarios. Our method shows improvement in both lane and traffic element detection and their association. We report results using four topology-aware metrics to comprehensively assess the model performance. These results demonstrate the ability of our approach to generalize and scale to diverse topologies and conditions.

Other0 citations2025-06-10arXiv ->

EMG-Driven Stiffness-Modulating Palpation for Telerehabilitation

Thomas M. Kwok, Hilary HY Cheng, Wai Tuck Chow

In this work, we introduce HJ-Pal, a lightweight wearable haptic device that leverages EMG-driven honeycomb jamming to render muscle activation as kinesthetic feedback, enabling remote palpation for small muscle assessment in telerehabilitation.

CDC 2025 | 20 papers
CBF Related Papers
Robotics0 citations2025-12-01arXiv ->

Dynamic Log-Gaussian Process Control Barrier Function for Safe Robotic Navigation in Dynamic Environments

Xin Yin, Chenyang Liang, Yanning Guo, Jie Mei

Control Barrier Functions (CBFs) have emerged as efficient tools to address the safe navigation problem for robot applications. However, synthesizing informative and obstacle motion-aware CBFs online using real-time sensor data remains challenging, particularly in unknown and dynamic scenarios. Motived by this challenge, this paper aims to propose a novel Gaussian Process-based formulation of CBF, termed the Dynamic Log Gaussian Process Control Barrier Function (DLGP-CBF), to enable real-time construction of CBF which are both spatially informative and responsive to obstacle motion. Firstly, the DLGP-CBF leverages a logarithmic transformation of GP regression to generate smooth and informative barrier values and gradients, even in sparse-data regions. Secondly, by explicitly modeling the DLGP-CBF as a function of obstacle positions, the derived safety constraint integrates predicted obstacle velocities, allowing the controller to proactively respond to dynamic obstacles' motion. Simulation results demonstrate significant improvements in obstacle avoidance performance, including increased safety margins, smoother trajectories, and enhanced responsiveness compared to baseline methods.

Robotics0 citations2025-09-18arXiv ->

A Nonlinear Scaling-based Design of Control Lyapunov-barrier Function for Relative Degree 2 Case and its Application to Safe Feedback Linearization

Haechan Pyon, Gyunghoon Park

In this paper we address the problem of control Lyapunov-barrier function (CLBF)-based safe stabilization for a class of nonlinear control-affine systems. A difficulty may arise for the case when a constraint has the relative degree larger than 1, at which computing a proper CLBF is not straightforward. Instead of adding an (possibly non-existent) control barrier function (CBF) to a control Lyapunov function (CLF), our key idea is to simply scale the value of the CLF on the unsafe set, by utilizing a sigmoid function as a scaling factor. We provide a systematic design method for the CLBF, with a detailed condition for the parameters of the sigmoid function to satisfy. It is also seen that the proposed approach to the CLBF design can be applied to the problem of task-space control for a planar robot manipulator with guaranteed safety, for which a safe feedback linearization-based controller is presented.

MPC/Planning0 citations2025-09-04arXiv ->

Compatibility of Multiple Control Barrier Functions for Constrained Nonlinear Systems

Max H. Cohen, Eugene Lavretsky, Aaron D. Ames

Control barrier functions (CBFs) are a powerful tool for the constrained control of nonlinear systems; however, the majority of results in the literature focus on systems subject to a single CBF constraint, making it challenging to synthesize provably safe controllers that handle multiple state constraints. This paper presents a framework for constrained control of nonlinear systems subject to box constraints on the systems' vector-valued outputs using multiple CBFs. Our results illustrate that when the output has a vector relative degree, the CBF constraints encoding these box constraints are compatible, and the resulting optimization-based controller is locally Lipschitz continuous and admits a closed-form expression. Additional results are presented to characterize the degradation of nominal tracking objectives in the presence of safety constraints. Simulations of a planar quadrotor are presented to demonstrate the efficacy of the proposed framework.

MPC/Planning0 citations2025-09-04arXiv ->

Sample Efficient Certification of Discrete-Time Control Barrier Functions

Sampath Kumar Mulagaleti, Andrea Del Prete

Control Invariant (CI) sets are instrumental in certifying the safety of dynamical systems. Control Barrier Functions (CBFs) are effective tools to compute such sets, since the zero sublevel sets of CBFs are CI sets. However, computing CBFs generally involves addressing a complex robust optimization problem, which can be intractable. Scenario-based methods have been proposed to simplify this computation. Then, one needs to verify if the CBF actually satisfies the robust constraints. We present an approach to perform this verification that relies on Lipschitz arguments, and forms the basis of a certification algorithm designed for sample efficiency. Through a numerical example, we validated the efficiency of the proposed procedure.

MPC/Planning0 citations2025-08-27arXiv ->

Distributed Safety-Critical MPC for Multi-Agent Formation Control and Obstacle Avoidance

Chao Wang, Shuyuan Zhang, Lei Wang

For nonlinear multi-agent systems with high relative degrees, achieving formation control and obstacle avoidance in a distributed manner remains a significant challenge. To address this issue, we propose a novel distributed safety-critical model predictive control (DSMPC) algorithm that incorporates discrete-time high-order control barrier functions (DHCBFs) to enforce safety constraints, alongside discrete-time control Lyapunov functions (DCLFs) to establish terminal constraints. To facilitate distributed implementation, we develop estimated neighbor states for formulating DHCBFs and DCLFs, while also devising a bound constraint to limit estimation errors and ensure convergence. Additionally, we provide theoretical guarantees regarding the feasibility and stability of the proposed DSMPC algorithm based on a mild assumption. The effectiveness of the proposed method is evidenced by the simulation results, demonstrating improved performance and reduced computation time compared to existing approaches.

Robotics0 citations2025-07-19arXiv ->

Corridor-based Adaptive Control Barrier and Lyapunov Functions for Safe Mobile Robot Navigation

Nicholas Mohammad, Nicola Bezzo

Safe navigation in unknown and cluttered environments remains a challenging problem in robotics. Model Predictive Contour Control (MPCC) has shown promise for performant obstacle avoidance by enabling precise and agile trajectory tracking, however, existing methods lack formal safety assurances. To address this issue, we propose a general Control Lyapunov Function (CLF) and Control Barrier Function (CBF) enabled MPCC framework that enforces safety constraints derived from a free-space corridor around the planned trajectory. To enhance feasibility, we dynamically adapt the CBF parameters at runtime using a Soft Actor-Critic (SAC) policy. The approach is validated with extensive simulations and an experiment on mobile robot navigation in unknown cluttered environments.

MPC/Planning0 citations2025-07-17arXiv ->

On the Properties of Optimal-Decay Control Barrier Functions

Pio Ong, Max H. Cohen, Tamas G. Molnar, Aaron D. Ames

Control barrier functions provide a powerful means for synthesizing safety filters that ensure safety framed as forward set invariance. Key to CBFs' effectiveness is the simple inequality on the system dynamics: $\dot{h} \geq - α(h)$. Yet determining the class $\mathcal{K}^e$ function $α$ is a user defined choice that can have a dramatic effect on the resulting system behavior. This paper formalizes the process of choosing $α$ using optimal-decay control barrier functions (OD-CBFs). These modify the traditional CBF inequality to: $\dot{h} \geq - ωα(h)$, where $ω\geq 0$ is automatically determined by the safety filter. A comprehensive characterization of this framework is elaborated, including tractable conditions on OD-CBF validity, control invariance of the underlying sets in the state space, forward invariance conditions for safe sets, and discussion on optimization-based safe controllers in terms of their feasibility, Lipschitz continuity, and closed-form expressions. The framework also extends existing higher-order CBF techniques, addressing safety constraints with vanishing relative degrees. The proposed method is demonstrated on a satellite control problem in simulation.

Other0 citations2025-05-21arXiv ->

Constant-Sum High-Order Barrier Functions for Safety Between Parallel Boundaries

Kwang Hak Kim, Mamadou Diagne, Miroslav Krstić

This paper takes a step towards addressing the difficulty of constructing Control Barrier Functions (CBFs) for parallel safety boundaries. A single CBF for both boundaries has been reported to be difficult to validate for safety, and we identify why this challenge is inherent. To overcome this, the proposed method constructs separate CBFs for each boundary. We begin by presenting results for the relative degree one case and then extend these to higher relative degrees using the CBF backstepping technique, establishing conditions that guarantee safety. Finally, we showcase our method by applying it to a unicycle system, deriving a simple, verifiable condition to validate the target CBFs for direct implementation of our results.

MPC/Planning0 citations2025-05-20arXiv ->

Sequential QCQP for Bilevel Optimization with Line Search

Sina Sharifi, Erfan Yazdandoost Hamedani, Mahyar Fazlyab

Bilevel optimization involves a hierarchical structure where one problem is nested within another, leading to complex interdependencies between levels. We propose a single-loop, tuning-free algorithm that guarantees anytime feasibility, i.e., approximate satisfaction of the lower-level optimality condition, while ensuring descent of the upper-level objective. At each iteration, a convex quadratically-constrained quadratic program (QCQP) with a closed-form solution yields the search direction, followed by a backtracking line search inspired by control barrier functions to ensure safe, uniformly positive step sizes. The resulting method is scalable, requires no hyperparameter tuning, and converges under mild local regularity assumptions. We establish an O(1/k) ergodic convergence rate in terms of a first-order stationary metric and demonstrate the algorithm's effectiveness on representative bilevel tasks.

Other0 citations2025-05-11arXiv ->

Secure Safety Filter Design for Sampled-data Nonlinear Systems under Sensor Spoofing Attacks

Xiao Tan, Pio Ong, Paulo Tabuada, Aaron D. Ames

This paper presents a secure safety filter design for nonlinear systems under sensor spoofing attacks. Existing approaches primarily focus on linear systems which limits their applications in real-world scenarios. In this work, we extend these results to nonlinear systems in a principled way. We introduce exact observability maps that abstract specific state estimation algorithms and extend them to a secure version capable of handling sensor attacks. Our generalization also applies to the relaxed observability case, with slightly relaxed guarantees. More importantly, we propose a secure safety filter design in both exact and relaxed cases, which incorporates secure state estimation and a control barrier function-enabled safety filter. The proposed approach provides theoretical safety guarantees for nonlinear systems in the presence of sensor attacks. We numerically validate our analysis on a unicycle vehicle equipped with redundant yet partly compromised sensors.

MPC/Planning0 citations2025-04-07arXiv ->

Hybrid Control Barrier Functions for Nonholonomic Multi-Agent Systems

Aurora Haraldsen, Josef Matous, Kristin Y. Pettersen

This paper addresses the problem of guaranteeing safety of multiple coordinated agents moving in dynamic environments. It has recently been shown that this problem can be efficiently solved through the notion of Control Barrier Functions (CBFs). However, for nonholonomic vehicles that are required to keep positive speeds, existing CBFs lose their validity. To overcome this limitation, we propose a hybrid formulation based on synergistic CBFs (SCBFs), which leverages a discrete switching mechanism to avoid configurations that would render the CBF invalid. Unlike existing approaches, our method ensures safety in the presence of moving obstacles and inter-agent interactions while respecting nonzero speed restrictions. We formally analyze the feasibility of the constraints with respect to actuation limits, and the efficacy of the solution is demonstrated in simulation of a multi-agent coordination problem in the presence of moving obstacles.

Robotics0 citations2025-04-04arXiv ->

Distributed Resilience-Aware Control in Multi-Robot Networks

Haejoon Lee, Dimitra Panagou

Ensuring resilient consensus in multi-robot systems with misbehaving agents remains a challenge, as many existing network resilience properties are inherently combinatorial and globally defined. While previous works have proposed control laws to enhance or preserve resilience in multi-robot networks, they often assume a fixed topology with known resilience properties, or require global state knowledge. These assumptions may be impractical in physically-constrained environments, where safety and resilience requirements are conflicting, or when misbehaving agents share inaccurate state information. In this work, we propose a distributed control law that enables each robot to guarantee resilient consensus and safety during its navigation without fixed topologies using only locally available information. To this end, we establish a sufficient condition for resilient consensus in time-varying networks based on the degree of non-misbehaving or normal agents. Using this condition, we design a Control Barrier Function (CBF)-based controller that guarantees resilient consensus and collision avoidance without requiring estimates of global state and/or control actions of all other robots. Finally, we validate our method through simulations.

Learning0 citations2025-04-03arXiv ->

How to Adapt Control Barrier Functions? A Learning-Based Approach with Applications to a VTOL Quadplane

Taekyung Kim, Randal W. Beard, Dimitra Panagou

In this paper, we present a novel theoretical framework for online adaptation of Control Barrier Function (CBF) parameters, i.e., of the class K functions included in the CBF condition, under input constraints. We introduce the concept of locally validated CBF parameters, which are adapted online to guarantee finite-horizon safety, based on conditions derived from Nagumo's theorem and tangent cone analysis. To identify these parameters online, we integrate a learning-based approach with an uncertainty-aware verification process that account for both epistemic and aleatoric uncertainties inherent in neural network predictions. Our method is demonstrated on a VTOL quadplane model during challenging transition and landing maneuvers, showcasing enhanced performance while maintaining safety.

MPC/Planning0 citations2025-04-01arXiv ->

Feedback Optimization with State Constraints through Control Barrier Functions

Giannis Delimpaltadakis, Pol Mestres, Jorge Cortés, W. P. M. H. Heemels

Recently, there has been a surge of research on a class of methods called feedback optimization. These are methods to steer the state of a control system to an equilibrium that arises as the solution of an optimization problem. Despite the growing literature on the topic, the important problem of enforcing state constraints at all times remains unaddressed. In this work, we present the first feedback-optimization method that enforces state constraints. The method combines a class of dynamics called safe gradient flows with high-order control barrier functions. We provide a number of results on our proposed controller, including well-posedness guarantees, anytime constraint-satisfaction guarantees, equivalence between the closed-loop's equilibria and the optimization problem's critical points, and local asymptotic stability of optima.

MPC/Planning0 citations2025-04-01arXiv ->

Probabilistically safe and efficient model-based reinforcement learning

Filippo Airaldi, Bart De Schutter, Azita Dabiri

This paper proposes tackling safety-critical stochastic Reinforcement Learning (RL) tasks with a sample-based, model-based approach. At the core of the method lies a Model Predictive Control (MPC) scheme that acts as function approximation, providing a model-based predictive control policy. To ensure safety, a probabilistic Control Barrier Function (CBF) is integrated into the MPC controller. To approximate the effects of stochasticies in the optimal control formulation and to fulfil the probabilistic CBF condition, a sample-based approach with guarantees is employed. Furthermore, to counterbalance the additional computational burden due to sampling, a learnable terminal cost formulation is included in the MPC objective. An RL algorithm is deployed to learn both the terminal cost and the CBF constraint. Results from a numerical experiment on a constrained LTI problem corroborate the effectiveness of the proposed methodology in reducing computation time while preserving control performance and safety.

Other Papers
Robotics0 citations2026-01-16arXiv ->

Adaptive Monitoring of Stochastic Fire Front Processes via Information-seeking Predictive Control

Savvas Papaioannou, Panayiotis Kolios, Christos G. Panayiotou, Marios M. Polycarpou

We consider the problem of adaptively monitoring a wildfire front using a mobile agent (e.g., a drone), whose trajectory determines where sensor data is collected and thus influences the accuracy of fire propagation estimation. This is a challenging problem, as the stochastic nature of wildfire evolution requires the seamless integration of sensing, estimation, and control, often treated separately in existing methods. State-of-the-art methods either impose linear-Gaussian assumptions to establish optimality or rely on approximations and heuristics, often without providing explicit performance guarantees. To address these limitations, we formulate the fire front monitoring task as a stochastic optimal control problem that integrates sensing, estimation, and control. We derive an optimal recursive Bayesian estimator for a class of stochastic nonlinear elliptical-growth fire front models. Subsequently, we transform the resulting nonlinear stochastic control problem into a finite-horizon Markov decision process and design an information-seeking predictive control law obtained via a lower confidence bound-based adaptive search algorithm with asymptotic convergence to the optimal policy.

Robotics0 citations2025-11-25arXiv ->

Energy Efficient Nonlinear Microscopic Dynamical Model for Autonomous and Electric Vehicles

Yuneil Yeo, Jaewoong Lee, Scott Moura, Maria Laura Delle Monache

This article proposes a nonlinear microscopic dynamical model for autonomous electric vehicles (A-EVs) that considers battery energy efficiency in the car-following dynamics. The model builds upon the Optimal Velocity Model (OVM), with the control term based on the battery dynamics to enable thermally optimal and energy-efficient driving. We rigorously prove that the proposed model achieves lower energy consumption compared to the Optimal Velocity Follow-the-Leader (OVFL) model. Through numerical simulations, we validate the analytical results on the energy efficiency. We additionally investigate the stability properties of the proposed model.

Robotics0 citations2025-11-19arXiv ->

Real-Time Optimal Control via Transformer Networks and Bernstein Polynomials

Gage MacLin, Venanzio Cichella, Andrew Patterson, Irene Gregory

In this paper, we propose a Transformer-based framework for approximating solutions to infinite-dimensional optimization problems: calculus of variations problems and optimal control problems. Our approach leverages offline training on data generated by solving a sample of infinite- dimensional optimization problems using composite Bernstein collocation. Once trained, the Transformer efficiently generates near-optimal, feasible trajectories, making it well-suited for real-time applications. In motion planning for autonomous vehicles, for instance, these trajectories can serve to warm- start optimal motion planners or undergo rigorous evaluation to ensure safety. We demonstrate the effectiveness of this method through numerical results on a classical control problem and an online obstacle avoidance task. This data-driven approach offers a promising solution for real-time optimal control of nonlinear, nonconvex systems.

Robotics0 citations2025-09-16arXiv ->

Ellipsoidal partitions for improved multi-stage robust model predictive control

Moritz Heinlein, Florian Messerer, Moritz Diehl, Sergio Lucia

Ellipsoidal tube-based model predictive control methods effectively account for the propagation of the reachable set, typically employing linear feedback policies. In contrast, scenario-based approaches offer more flexibility in the feedback structure by considering different control actions for different branches of a scenario tree. However, they face challenges in ensuring rigorous guarantees. This work aims to integrate the strengths of both methodologies by enhancing ellipsoidal tube-based MPC with a scenario tree formulation. The uncertainty ellipsoids are partitioned by halfspaces such that each partitioned set can be controlled independently. The proposed ellipsoidal multi-stage approach is demonstrated in a human-robot system, highlighting its advantages in handling uncertainty while maintaining computational tractability.

Learning0 citations2025-09-03arXiv ->

Population-aware Online Mirror Descent for Mean-Field Games with Common Noise by Deep Reinforcement Learning

Zida Wu, Mathieu Lauriere, Matthieu Geist, Olivier Pietquin, Ankur Mehta

Mean Field Games (MFGs) offer a powerful framework for studying large-scale multi-agent systems. Yet, learning Nash equilibria in MFGs remains a challenging problem, particularly when the initial distribution is unknown or when the population is subject to common noise. In this paper, we introduce an efficient deep reinforcement learning (DRL) algorithm designed to achieve population-dependent Nash equilibria without relying on averaging or historical sampling, inspired by Munchausen RL and Online Mirror Descent. The resulting policy is adaptable to various initial distributions and sources of common noise. Through numerical experiments on seven canonical examples, we demonstrate that our algorithm exhibits superior convergence properties compared to state-of-the-art algorithms, particularly a DRL version of Fictitious Play for population-dependent policies. The performance in the presence of common noise underscores the robustness and adaptability of our approach.

ACC 2026 | 22 papers
CBF Related Papers
Robotics0 citations2026-03-17arXiv ->

Shielded Reinforcement Learning Under Dynamic Temporal Logic Constraints

Sadık Bera Yüksel, Ali Tevfik Buyukkocak, Derya Aksaray

Reinforcement Learning (RL) has shown promise in various robotics applications, yet its deployment on real systems is still limited due to safety and operational constraints. The safe RL field has gained considerable attention in recent years, which focuses on imposing safety constraints throughout the learning process. However, real systems often require more complex constraints than just safety, such as periodic recharging or time-bounded visits to specific regions. Imposing such spatio-temporal tasks during learning still remains a challenge. Signal Temporal Logic (STL) is a formal language for specifying temporal properties of real-valued signals and provides a way to express such complex tasks. In this paper, we propose a framework that leverages sequential control barrier functions and model-free RL to ensure that the given STL tasks are satisfied throughout the learning process. Our method extends beyond traditional safety constraints by enforcing rich STL specifications, which can involve visits to dynamic targets with unknown trajectories. We also demonstrate the effectiveness of our framework through various simulations.

Theory0 citations2026-03-16arXiv ->

ReLU Barrier Functions for Nonlinear Systems with Constrained Control: A Union of Invariant Sets Approach

Pouya Samanipour, Hasan A. Poonawala

Certifying safety for nonlinear systems with polytopic input constraints is challenging because CBF synthesis must ensure control admissibility under saturation. We propose an approximation--verification pipeline that performs convex barrier synthesis on piecewise-affine (PWA) surrogates and certifies safety for the original nonlinear system via facet-wise verification. To reduce conservatism while preserving tractability, we use a two-slope Leaky ReLU surrogate for the extended class-$\mathcal{K}$ function $α(\cdot)$ and combine multiple certificates using a Union of Invariant Sets (UIS). Counterexamples are handled through local uncertainty updates. Simulations on pendulum and cart-pole systems with input saturation show larger certified invariant sets than linear-$α$ designs with tractable computation time.

Robotics0 citations2026-02-08arXiv ->

From Ellipsoids to Midair Control of Dynamic Hitches

Jiawei Xu, Subhrajit Bhattacharya, David Saldaña

The ability to manipulate and interlace cables using aerial vehicles can greatly improve aerial transportation tasks. Such interlacing cables create hitches by winding two or more cables around each other, which can enclose payloads or can further develop into knots. Dynamic modeling and control of such hitches are key to mastering inter-cable interactions in the context of cable-suspended aerial manipulation. This paper introduces an ellipsoid-based kinematic model to connect the geometric nature of a hitch created by two cables and the dynamics of the hitch driven by four aerial vehicles, which reveals the control-affine form of the system. As the constraint for maintaining tension of a cable is also control-affine, we design a quadratic programming-based controller that combines Control Lyapunov and High-Order Control Barrier Functions (CLF-HOCBF-QP) to precisely track a desired hitch position and system shape while enforcing safety constraints like cable tautness. We convert desired geometric reference configurations into target robot positions and introduce a composite error into the Lyapunov function to ensure a relative degree of one to the input. Numerical simulations validate our approach, demonstrating stable, high-speed tracking of dynamic references.

Other0 citations2026-02-04arXiv ->

Banach Control Barrier Functions for Large-Scale Swarm Control

Xuting Gao, Guillem Pascual, Scott Brown, Sonia Martínez

This paper studies the safe control of very large multi-agent systems via a generalized framework that employs so-called Banach Control Barrier Functions (B-CBFs). Modeling a large swarm as probability distribution over a spatial domain, we show how B-CBFs can be used to appropriately capture a variety of macroscopic constraints that can integrate with large-scale swarm objectives. Leveraging this framework, we define stable and filtered gradient flows for large swarms, paying special attention to optimal transport algorithms. Further, we show how to derive agent-level, microscopical algorithms that are consistent with macroscopic counterparts in the large-scale limit. We then identify conditions for which a group of agents can compute a distributed solution that only requires local information from other agents within a communication range. Finally, we showcase the theoretical results over swarm systems in the simulations section.

Other0 citations2026-02-04arXiv ->

Peak Bounds for the Estimation Error under Sensor Attacks

Axel Stafström, Daniel Arnström, Adam Miksits, David Umsonst

This paper investigates bounds on the estimation error of a linear system affected by norm-bounded disturbances and full sensor attacks. The system is equipped with a detector that evaluates the norm of the innovation signal to detect faults, and the attacker wants to avoid detection. We utilize induced $L_\infty$ system norms, also called \emph{peak-to-peak} norms, to compare the estimation error bounds under nominal operations and under attack. This leads to a sufficient condition for when the bound on the estimation error is smaller during an attack than during nominal operation. This condition is independent of the attack strategy and depends only on the attacker's desire to remain undetected and (indirectly) the observer gain. Therefore, we investigate both an observer design method, that seeks to reduce the error bound under attack while keeping the nominal error bound low, and detector threshold tuning. As a numerical illustration, we show how a sensor attack can deactivate a robust safety filter based on control barrier functions if the attacked error bound is larger than the nominal one. We also statistically evaluate our observer design method and the effect of the detector threshold.

Other0 citations2026-02-02arXiv ->

Robust Safety-Critical Control of Networked SIR Dynamics

Saba Samadi, Brooks A. Butler, Philip E. Paré

We present a robust safety-critical control framework tailored for networked susceptible-infected-recovered (SIR) epidemic dynamics, leveraging control barrier functions (CBFs) and robust control barrier functions to address the challenges of epidemic spread and mitigation. In our networked SIR model, each node must keep its infection level below a critical threshold, despite dynamic interactions with neighboring nodes and inherent uncertainties in the epidemic parameters and measurement errors, to ensure public health safety. We first derive a CBF-based controller that guarantees infection thresholds are not exceeded in the nominal case. We enhance the framework to handle realistic epidemic scenarios under uncertainties by incorporating compensation terms that reinforce safety against uncertainties: an independent method with constant bounds for uniform uncertainty, and a novel approach that scales with the state to capture increased relative noise in early or suppressed outbreak stages. Simulation results on a networked SIR system illustrate that the nominal CBF controller maintains safety under low uncertainty, while the robust approaches provide formal safety guarantees under higher uncertainties; in particular, the novel method employs more conservative control efforts to provide larger safety margins, whereas the independent approach optimizes resource allocation by allowing infection levels to approach the boundaries in steady epidemic regimes.

Robotics0 citations2025-10-23arXiv ->

From Bundles to Backstepping: Geometric Control Barrier Functions for Safety-Critical Control on Manifolds

Massimiliano de Sa, Pio Ong, Aaron D. Ames

Control barrier functions (CBFs) have a well-established theory in Euclidean spaces, yet still lack general formulations and constructive synthesis tools for systems evolving on manifolds common in robotics and aerospace applications. In this paper, we develop a general theory of geometric CBFs on bundles and, for control-affine systems, recover the standard optimization-based CBF controllers and their smooth analogues. Then, by generalizing kinetic energy-based CBF backstepping to Riemannian manifolds, we provide a constructive CBF synthesis technique for geometric mechanical systems, as well as easily verifiable conditions under which it succeeds. Further, this technique utilizes mechanical structure to avoid computations on higher-order tangent bundles. We demonstrate its application to an underactuated satellite on SO(3).

Robotics0 citations2025-10-15arXiv ->

Belief Space Control of Safety-Critical Systems Under State-Dependent Measurement Noise

Rohan Walia, Mitchell Black, Andrew Schoer, Kevin Leahy

Safety-critical control is imperative for deploying autonomous systems in the real world. Control Barrier Functions (CBFs) offer strong safety guarantees when accurate system and sensor models are available. However, widely used additive, fixed-noise models are not representative of complex sensor modalities with state-dependent error characteristics. Although CBFs have been designed to mitigate uncertainty using fixed worst-case bounds on measurement noise, this approach can lead to overly-conservative control. To solve this problem, we extend the Belief Control Barrier Function (BCBF) framework to accommodate state-dependent measurement noise via the Generalized Extended Kalman Filter (GEKF) algorithm, which models measurement noise as a linear function of the state. Using the original BCBF framework as baseline, we demonstrate the performance of the BCBF-GEKF approach through simulation results on a 1D single integrator setpoint tracking scenario and 2D unicycle kinematics trajectory tracking scenario. Our results confirm that the BCBF-GEKF approach offers less conservative control with greater safety.

Theory0 citations2025-10-08arXiv ->

Decentralized CBF-based Safety Filters for Collision Avoidance of Cooperative Missile Systems with Input Constraints

Johannes Autenrieb, Mark Spiller

This paper presents a decentralized safety filter for collision avoidance in multi-agent aerospace interception scenarios. The approach leverages robust control barrier functions (RCBFs) to guarantee forward invariance of safety sets under bounded inputs and high-relative-degree dynamics. Each effector executes its nominal cooperative guidance command, while a local quadratic program (QP) modifies the input only when necessary. Event-triggered activation based on range and zero-effort miss (ZEM) criteria ensures scalability by restricting active constraints to relevant neighbors. To resolve feasibility issues from simultaneous constraints, a slack-variable relaxation scheme is introduced that prioritizes critical agents in a Pareto-optimal manner. Simulation results in many-on-many interception scenarios demonstrate that the proposed framework maintains collision-free operation with minimal deviation from nominal guidance, providing a computationally efficient and scalable solution for safety-critical multi-agent aerospace systems.

Robotics0 citations2025-10-07arXiv ->

Safe Landing on Small Celestial Bodies with Gravitational Uncertainty Using Disturbance Estimation and Control Barrier Functions

Felipe Arenas-Uribe, T. Michael Seigler, Jesse B. Hoagg

Soft landing on small celestial bodies (SCBs) poses unique challenges, as gravitational models poorly characterize the higher-order gravitational effects of SCBs. Existing control approaches lack guarantees for safety under gravitational uncertainty. This paper proposes a three-stage control architecture that combines disturbance estimation, trajectory tracking, and safety enforcement. An extended high-gain observer estimates gravitational disturbances online, a feedback-linearizing controller tracks a reference trajectory, and a minimum-intervention quadratic program enforces state and input constraints while remaining close to the nominal control. The proposed approach enables aggressive yet safe maneuvers despite gravitational uncertainty. Numerical simulations demonstrate the effectiveness of the controller in achieving soft-landing on irregularly shaped SCBs, highlighting its potential for autonomous SCB missions.

Other0 citations2025-10-01arXiv ->

Predictive Control Barrier Functions for Discrete-Time Linear Systems with Unmodeled Delays

Juan Augusto Paredes Salazar, James Usevitch, Ankit Goel

This paper introduces a predictive control barrier function (PCBF) framework for enforcing state constraints in discrete-time systems with unknown relative degree, which can be caused by input delays or unmodeled input dynamics. Existing discrete-time CBF formulations typically require the construction of auxiliary barrier functions when the relative degree is greater than one, which complicates implementation and may yield conservative safe sets. The proposed PCBF framework addresses this challenge by extending the prediction horizon to construct a CBF for an associated system with relative degree one. As a result, the superlevel set of the PCBF coincides with the safe set, simplifying constraint enforcement and eliminating the need for auxiliary functions. The effectiveness of the proposed method is demonstrated on a discrete-time double integrator with input delay and a bicopter system with position constraints.

Theory0 citations2025-09-15arXiv ->

A Converse Control Lyapunov Theorem for Joint Safety and Stability

Thanin Quartz, Maxwell Fitzsimmons, Jun Liu

We show that the existence of a strictly compatible pair of control Lyapunov and control barrier functions is equivalent to the existence of a single smooth Lyapunov function that certifies both asymptotic stability and safety. This characterization complements existing literature on converse Lyapunov functions by establishing a partial differential equation (PDE) characterization with prescribed boundary conditions on the safe set, ensuring that the safe set is exactly certified by this Lyapunov function. The result also implies that if a safety and stability specification cannot be certified by a single Lyapunov function, then any pair of control Lyapunov and control barrier functions necessarily leads to a conflict and cannot be satisfied simultaneously in a robust sense.

Other0 citations2025-09-12arXiv ->

Combinatorial Control Barrier Functions: Nested Boolean and p-choose-r Compositions of Safety Constraints

Pio Ong, Haejoon Lee, Tamas G. Molnar, Dimitra Panagou, Aaron D. Ames

This paper investigates the problem of composing multiple control barrier functions (CBFs) -- and matrix control barrier functions (MCBFs) -- through logical and combinatorial operations. Standard CBF formulations naturally enable conjunctive (AND) combinations, but disjunctive (OR) and more general logical structures introduce nonsmoothness and possibly a combinatorial blow-up in the number of logical combinations. We introduce the framework of combinatorial CBFs that addresses p-choose-r safety specifications and their nested composition. The proposed framework ensures safety for the exact safe set in a scalable way, using the original number of primitive constraints. We establish theoretical guarantees on safety under these compositions, and we demonstrate their use on a patrolling problem in a multi-agent system.

Other Papers
Theory0 citations2026-03-24arXiv ->

Design Guidelines for Nonlinear Kalman Filters via Covariance Compensation

Shida Jiang, Jaewoong Lee, Shengyu Tao, Scott Moura

Nonlinear extensions of the Kalman filter (KF), such as the extended Kalman filter (EKF) and the unscented Kalman filter (UKF), are indispensable for state estimation in complex dynamical systems, yet the conditions for a nonlinear KF to provide robust and accurate estimations remain poorly understood. This work proposes a theoretical framework that identifies the causes of failure and success in certain nonlinear KFs and establishes guidelines for their improvement. Central to our framework is the concept of covariance compensation: the deviation between the covariance predicted by a nonlinear KF and that of the EKF. With this definition and detailed theoretical analysis, we derive three design guidelines for nonlinear KFs: (i) invariance under orthogonal transformations, (ii) sufficient covariance compensation beyond the EKF baseline, and (iii) selection of compensation magnitude that favors underconfidence. Both theoretical analysis and empirical validation confirm that adherence to these principles significantly improves estimation accuracy, whereas fixed parameter choices commonly adopted in the literature are often suboptimal. The codes and the proofs for all the theorems in this paper are available at https://github.com/Shida-Jiang/Guidelines-for-Nonlinear-Kalman-Filters.

Robotics0 citations2026-03-23arXiv ->

Partial Attention in Deep Reinforcement Learning for Safe Multi-Agent Control

Turki Bin Mohaya, Peter Seiler

Attention mechanisms excel at learning sequential patterns by discriminating data based on relevance and importance. This provides state-of-the-art performance in advanced generative artificial intelligence models. This paper applies this concept of an attention mechanism for multi-agent safe control. We specifically consider the design of a neural network to control autonomous vehicles in a highway merging scenario. The environment is modeled as a Decentralized Partially Observable Markov Decision Process (Dec-POMDP). Within a QMIX framework, we include partial attention for each autonomous vehicle, thus allowing each ego vehicle to focus on the most relevant neighboring vehicles. Moreover, we propose a comprehensive reward signal that considers the global objectives of the environment (e.g., safety and vehicle flow) and the individual interests of each agent. Simulations are conducted in the Simulation of Urban Mobility (SUMO). The results show better performance compared to other driving algorithms in terms of safety, driving speed, and reward.

Robotics0 citations2026-03-15arXiv ->

Progress-Based Fault Detection and Health-Aware Task Allocation for Heterogeneous Multi-Robot Systems

Jack Cline, Christian Macaranas, Siavash Farzan

We present a progress-based fault detection module and its integration with dynamic task allocation for heterogeneous robot teams. The detector monitors a normalized task-completion signal with a lightweight Kalman filter (KF) and a normalized innovation squared (NIS) test, augmented with a low-rate stall gate, an uncertainty gate, and debounce logic. Health estimates influence the allocator via health-weighted costs and health-dependent masks; reallocation is event-triggered and regularized with an $\ell_1$ assignment-change penalty to limit reassignment churn while preserving feasibility through slack variables. The detector has constant per-robot update cost, and the allocation remains a convex quadratic program (QP). Experiments on a common team-task setup evaluate measurement-noise increases, velocity-slip biases, communication dropouts, and task abandonment. The results show timely detection in the noise and bias cases, maintained task completion with limited reassignment, and the expected observability delays under communication dropouts.

Robotics0 citations2026-03-10arXiv ->

A Generalized Voronoi Graph based Coverage Control Approach for Non-Convex Environment

Zuyi Guo, Ronghao Zheng, Meiqin Liu, Senlin Zhang

To address the challenge of efficient coverage by multi-robot systems in non-convex regions with multiple obstacles, this paper proposes a coverage control method based on the Generalized Voronoi Graph (GVG), which has two phases: Load-Balancing Algorithm phase and Collaborative Coverage phase. In Load-Balancing Algorithm phase, the non-convex region is partitioned into multiple sub-regions based on GVG. Besides, a weighted load-balancing algorithm is developed, which considers the quality differences among sub-regions. By iteratively optimizing the robot allocation ratio, the number of robots in each sub-region is matched with the sub-region quality to achieve load balance. In Collaborative Coverage phase, each robot is controlled by a new controller to effectively coverage the region. The convergence of the method is proved and its performance is evaluated through simulations.

Robotics0 citations2026-03-04arXiv ->

Gaussian Mixture-Based Inverse Perception Contract for Uncertainty-Aware Robot Navigation

Bingyao Du, Joonkyung Kim, Yiwei Lyu

Reliable navigation in cluttered environments requires perception outputs that are not only accurate but also equipped with uncertainty sets suitable for safe control. An inverse perception contract (IPC) provides such a connection by mapping perceptual estimates to sets that contain the ground truth with high confidence. Existing IPC formulations, however, instantiate uncertainty as a single ellipsoidal set and rely on deterministic trust scores to guide robot motion. Such a representation cannot capture the multi-modal and irregular structure of fine-grained perception errors, often resulting in over-conservative sets and degraded navigation performance. In this work, we introduce Gaussian Mixture-based Inverse Perception Contract (GM-IPC), which extends IPC to represent uncertainty with unions of ellipsoidal confidence sets derived from Gaussian mixture models. This design moves beyond deterministic single-set abstractions, enabling fine-grained, multi-modal, and non-convex error structures to be captured with formal guarantees. A learning framework is presented that trains GM-IPC to account for probabilistic inclusion, distribution matching, and empty-space penalties, ensuring both validity and compactness of the predicted sets. We further show that the resulting uncertainty characterizations can be leveraged in downstream planning frameworks for real-time safe navigation, enabling less conservative and more adaptive robot motion while preserving safety in a probabilistic manner.

Robotics0 citations2025-10-08arXiv ->

Delay Independent Safe Control with Neural Networks: Positive Lur'e Certificates for Risk Aware Autonomy

Hamidreza Montazeri Hedesh, Milad Siami

We present a risk-aware safety certification method for autonomous, learning enabled control systems. Focusing on two realistic risks, state/input delays and interval matrix uncertainty, we model the neural network (NN) controller with local sector bounds and exploit positivity structure to derive linear, delay-independent certificates that guarantee local exponential stability across admissible uncertainties. To benchmark performance, we adopt and implement a state-of-the-art IQC NN verification pipeline. On representative cases, our positivity-based tests run orders of magnitude faster than SDP-based IQC while certifying regimes the latter cannot-providing scalable safety guarantees that complement risk-aware control.

MPC/Planning0 citations2025-10-07arXiv ->

A Formal gatekeeper Framework for Safe Dual Control with Active Exploration

Kaleb Ben Naveed, Devansh R. Agrawal, Dimitra Panagou

Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations, yet ignores uncertainty reduction and leads to overly conservative behavior. Actively reducing uncertainty on-the-fly during a nominal mission defines the dual control problem. Most approaches address this by adding a weighted exploration term to the cost, tuned to trade off the nominal objective and uncertainty reduction, but without formal consideration of when exploration is beneficial. Moreover, safety is enforced in some methods but not in others. We propose a framework that integrates robust planning with active exploration under formal guarantees as follows: The key innovation and contribution is that exploration is pursued only when it provides a verifiable improvement without compromising safety. To achieve this, we utilize our earlier work on gatekeeper as an architecture for safety verification, and extend it so that it generates both safe and informative trajectories that reduce uncertainty and the cost of the mission, or keep it within a user-defined budget. The methodology is evaluated via simulation case studies on the online dual control of a quadrotor under parametric uncertainty.

Robotics0 citations2025-10-06arXiv ->

Koopman Control Factorization: Data-Driven Convex Controller Design for a Class of Nonlinear Systems

Taha Ondogan, Ran Jing, Andrew P. Sabelhaus, Roberto Tron

Although Koopman operators provide a global linearization for autonomous dynamical systems, nonautonomous systems are not globally linear in the inputs. State (or output) feedback controller design therefore remains nonconvex in typical formulations, even with approximations via bilinear control-affine terms. We address this gap by introducing the Koopman Control Factorization, a novel parameterization of control-affine dynamical systems combined with a feedback controller defined as a linear combination of nonlinear measurements. With this choice, the Koopman operator of the closed-loop system is a bilinear combination of the coefficients in two matrices: one representing the system, and the other the controller. We propose a set of sufficient conditions such that the factorization holds. Then, we present an algorithm that calculates the feedback matrix via semi-definite programming, producing a Lyapunov-stable closed-loop system with convex optimization. We evaluate the proposed controllers on two canonical examples of control-affine nonlinear systems (inverted pendulums), and show that our factorization and controller successfully stabilize both under properly-chosen basis functions. This manuscript introduces a broadly generalizable control synthesis method for stabilization of nonlinear systems that is quick-to-compute, verifiably stable, data-driven, and does not rely on approximations.

Robotics0 citations2025-10-01arXiv ->

A Robust Neural Control Design for Multi-drone Slung Payload Manipulation with Control Contraction Metrics

Xinyuan Liang, Longhao Qian, Yi Lok Lo, Hugh H. T. Liu

This paper presents a robust neural control design for a three-drone slung payload transportation system to track a reference path under external disturbances. The control contraction metric (CCM) is used to generate a neural exponentially converging baseline controller while complying with control input saturation constraints. We also incorporate the uncertainty and disturbance estimator (UDE) technique to dynamically compensate for persistent disturbances. The proposed framework yields a modularized design, allowing the controller and estimator to perform their individual tasks and achieve a zero trajectory tracking error if the disturbances meet certain assumptions. The stability and robustness of the complete system, incorporating both the CCM controller and the UDE compensator, are presented. Simulations are conducted to demonstrate the capability of the proposed control design to follow complicated trajectories under external disturbances.

ACC 2025 | 10 papers
CBF Related Papers
MPC/Planning0 citations2025-06-03arXiv ->

Nonlinear Optimal Control of DC Microgrids with Safety and Stability Guarantees

Muratkhan Abdirash, Xiaofan Cui

A DC microgrid is a promising alternative to the traditional AC power grid, since it can efficiently integrate distributed and renewable energy resources. However, as an emerging framework, it lacks the rigorous theoretical guarantees of its AC counterpart. In particular, safe stabilization of the DC microgrid has been a non-trivial task in power electronics. To address that, we take a control theoretic perspective in designing the feedback controller with provable guarantees. We present a systematic way to construct Control Lyapunov Functions (CLF) to stabilize the microgrid, and, independently, Control Barrier Functions (CBF) to enforce its safe operation at all times. The safety-critical controller (SCC) proposed in this work integrates the two control objectives, with safety prioritized, into a quadratic program (QP) as linear constraints, which allows for its online deployment using off-the-shelf convex optimization solvers. The SCC is compared against a robust version of the conventional droop control through numerical experiments whose results indicate the SCC outperforms the droop controller in guaranteeing safety and retaining stability at the same time.

Other0 citations2025-03-25arXiv ->

Control Barrier Functions for Shared Control and Vehicle Safety

James Dallas, John Talbot, Makoto Suminaka, Michael Thompson, Thomas Lew et al.

This manuscript presents a control barrier function based approach to shared control for preventing a vehicle from entering the part of the state space where it is unrecoverable. The maximal phase recoverable ellipse is presented as a safe set in the sideslip angle--yaw rate phase plane where the vehicle's state can be maintained. An exponential control barrier function is then defined on the maximal phase recoverable ellipse to promote safety. Simulations demonstrate that this approach enables safe drifting, that is, driving at the handling limit without spinning out. Results are then validated for shared control drifting with an experimental vehicle in a closed course. The results show the ability of this shared control formulation to maintain the vehicle's state within a safe domain in a computationally efficient manner, even in extreme drifting maneuvers.

Other0 citations2025-03-24arXiv ->

Feasibility of multiple robust control barrier functions for bounding box constraints

Mark Spiller, Emilia Isbono, Philipp Schitz

Enforcing multiple constraints based on the concept of control barrier functions (CBFs) is a remaining challenge because each of the CBFs requires a condition on the control inputs to be satisfied which may easily lead to infeasibility problems. The problem becomes even more challenging with input constraints and disturbances. In this paper, we consider enforcement of bounding box constraints for a second order system under limited control authority and input disturbances. To solve the constrained control problem, we apply multiple robust control barrier functions (RCBFs) which, in general, do not provide a feasible solution to the problem. However, we derive conditions on how to select the RCBF parameters to guarantee that a feasible solution always exists.

Other Papers
Learning0 citations2025-09-02arXiv ->

Robustness Enhancement for Multi-Quadrotor Centralized Transportation System via Online Tuning and Learning

Tianhua Gao, Kohji Tomita, Akiya Kamimura

This paper introduces an adaptive-neuro geometric control for a centralized multi-quadrotor cooperative transportation system, which enhances both adaptivity and disturbance rejection. Our strategy is to coactively tune the model parameters and learn the external disturbances in real-time. To realize this, we augmented the existing geometric control with multiple neural networks and adaptive laws, where the estimated model parameters and the weights of the neural networks are simultaneously tuned and adjusted online. The Lyapunov-based adaptation guarantees bounded estimation errors without requiring either pre-training or the persistent excitation (PE) condition. The proposed control system has been proven to be stable in the sense of Lyapunov under certain preconditions, and its enhanced robustness under scenarios of disturbed environment and model-unmatched plant was demonstrated by numerical simulations.

Learning0 citations2025-07-23arXiv ->

Generalized Advantage Estimation for Distributional Policy Gradients

Shahil Shaik, Jonathon M. Smereka, Yue Wang

Generalized Advantage Estimation (GAE) has been used to mitigate the computational complexity of reinforcement learning (RL) by employing an exponentially weighted estimation of the advantage function to reduce the variance in policy gradient estimates. Despite its effectiveness, GAE is not designed to handle value distributions integral to distributional RL, which can capture the inherent stochasticity in systems and is hence more robust to system noises. To address this gap, we propose a novel approach that utilizes the optimal transport theory to introduce a Wasserstein-like directional metric, which measures both the distance and the directional discrepancies between probability distributions. Using the exponentially weighted estimation, we leverage this Wasserstein-like directional metric to derive distributional GAE (DGAE). Similar to traditional GAE, our proposed DGAE provides a low-variance advantage estimate with controlled bias, making it well-suited for policy gradient algorithms that rely on advantage estimation for policy updates. We integrated DGAE into three different policy gradient methods. Algorithms were evaluated across various OpenAI Gym environments and compared with the baselines with traditional GAE to assess the performance.

Robotics0 citations2025-07-17arXiv ->

Refining Motion for Peak Performance: Identifying Optimal Gait Parameters for Energy-Efficient Quadrupedal Bounding

Yasser G. Alqaham, Jing Cheng, Zhenyu Gan

Energy efficiency is a critical factor in the performance and autonomy of quadrupedal robots. While previous research has focused on mechanical design and actuation improvements, the impact of gait parameters on energetics has been less explored. In this paper, we hypothesize that gait parameters, specifically duty factor, phase shift, and stride duration, are key determinants of energy consumption in quadrupedal locomotion. To test this hypothesis, we modeled the Unitree A1 quadrupedal robot and developed a locomotion controller capable of independently adjusting these gait parameters. Simulations of bounding gaits were conducted in Gazebo across a range of gait parameters at three different speeds: low, medium, and high. Experimental tests were also performed to validate the simulation results. The findings demonstrate that optimizing gait parameters can lead to significant reductions in energy consumption, enhancing the overall efficiency of quadrupedal locomotion. This work contributes to the advancement of energy-efficient control strategies for legged robots, offering insights directly applicable to commercially available platforms.

Robotics0 citations2025-07-16arXiv ->

Traffic-Aware Pedestrian Intention Prediction

Fahimeh Orvati Nia, Hai Lin

Accurate pedestrian intention estimation is crucial for the safe navigation of autonomous vehicles (AVs) and hence attracts a lot of research attention. However, current models often fail to adequately consider dynamic traffic signals and contextual scene information, which are critical for real-world applications. This paper presents a Traffic-Aware Spatio-Temporal Graph Convolutional Network (TA-STGCN) that integrates traffic signs and their states (Red, Yellow, Green) into pedestrian intention prediction. Our approach introduces the integration of dynamic traffic signal states and bounding box size as key features, allowing the model to capture both spatial and temporal dependencies in complex urban environments. The model surpasses existing methods in accuracy. Specifically, TA-STGCN achieves a 4.75% higher accuracy compared to the baseline model on the PIE dataset, demonstrating its effectiveness in improving pedestrian intention prediction.

Learning0 citations2025-04-21arXiv ->

Safety Embedded Adaptive Control Using Barrier States

Maitham F. AL-Sunni, Hassan Almubarak, John M. Dolan

In this work, we explore the application of barrier states (BaS) in the realm of safe nonlinear adaptive control. Our proposed framework derives barrier states for systems with parametric uncertainty, which are augmented into the uncertain dynamical model. We employ an adaptive nonlinear control strategy based on a control Lyapunov functions approach to design a stabilizing controller for the augmented system. The developed theory shows that the controller ensures safe control actions for the original system while meeting specified performance objectives. We validate the effectiveness of our approach through simulations on diverse systems, including a planar quadrotor subject to unknown drag forces and an adaptive cruise control system, for which we provide comparisons with existing methodologies.

Robotics0 citations2025-03-17arXiv ->

Layered Nonlinear Model Predictive Control for Robust Stabilization of Hybrid Systems

Zachary Olkin, Aaron D. Ames

Computing the receding horizon optimal control of nonlinear hybrid systems is typically prohibitively slow, limiting real-time implementation. To address this challenge, we propose a layered Model Predictive Control (MPC) architecture for robust stabilization of hybrid systems. A high level "hybrid" MPC is solved at a slow rate to produce a stabilizing hybrid trajectory, potentially sub-optimally, including a domain and guard sequence. This domain and guard sequence is passed to a low level "fixed mode" MPC which is a traditional, time-varying, state-constrained MPC that can be solved rapidly, e.g., using nonlinear programming (NLP) tools. A robust version of the fixed mode MPC is constructed by using tracking error tubes that are not guaranteed to have finite size for all time. Using these tubes, we demonstrate that the speed at which the fixed mode MPC is re-calculated is directly tied to the robustness of the system, thereby justifying the layered approach. Finally, simulation examples of a five link bipedal robot and a controlled nonlinear bouncing ball are used to illustrate the formal results.

Robotics0 citations2025-03-13arXiv ->

Efficient Reachability Analysis for Convolutional Neural Networks Using Hybrid Zonotopes

Yuhao Zhang, Xiangru Xu

Feedforward neural networks are widely used in autonomous systems, particularly for control and perception tasks within the system loop. However, their vulnerability to adversarial attacks necessitates formal verification before deployment in safety-critical applications. Existing set propagation-based reachability analysis methods for feedforward neural networks often struggle to achieve both scalability and accuracy. This work presents a novel set-based approach for computing the reachable sets of convolutional neural networks. The proposed method leverages a hybrid zonotope representation and an efficient neural network reduction technique, providing a flexible trade-off between computational complexity and approximation accuracy. Numerical examples are presented to demonstrate the effectiveness of the proposed approach.

ACC 2024 | 10 papers
CBF Related Papers
Other0 citations2025-04-08arXiv ->

Collision-free landing of multiple UAVs on moving ground vehicles using time-varying control barrier functions

Viswa Narayanan Sankaranarayanan, Akshit Saradagi, Sumeet Satpute, George Nikolakopoulos

In this article, we present a centralized approach for the control of multiple unmanned aerial vehicles (UAVs) for landing on moving unmanned ground vehicles (UGVs) using control barrier functions (CBFs). The proposed control framework employs two kinds of CBFs to impose safety constraints on the UAVs' motion. The first class of CBFs (LCBF) is a three-dimensional exponentially decaying function centered above the landing platform, designed to safely and precisely land UAVs on the UGVs. The second set is a spherical CBF (SCBF), defined between every pair of UAVs, which avoids collisions between them. The LCBF is time-varying and adapts to the motions of the UGVs. In the proposed CBF approach, the control input from the UAV's nominal tracking controller designed to reach the landing platform is filtered to choose a minimally-deviating control input that ensures safety (as defined by the CBFs). As the control inputs of every UAV are shared in establishing multiple CBF constraints, we prove that the control inputs are shared without conflict in rendering the safe sets forward invariant. The performance of the control framework is validated through a simulated scenario involving three UAVs landing on three moving targets.

Robotics0 citations2024-07-04arXiv ->

Safety-Critical Control with Uncertainty Quantification using Adaptive Conformal Prediction

Hao Zhou, Yanze Zhang, Wenhao Luo

Safety assurance is critical in the planning and control of robotic systems. For robots operating in the real world, the safety-critical design often needs to explicitly address uncertainties and the pre-computed guarantees often rely on the assumption of the particular distribution of the uncertainty. However, it is difficult to characterize the actual uncertainty distribution beforehand and thus the established safety guarantee may be violated due to possible distribution mismatch. In this paper, we propose a novel safe control framework that provides a high-probability safety guarantee for stochastic dynamical systems following unknown distributions of motion noise. Specifically, this framework adopts adaptive conformal prediction to dynamically quantify the prediction uncertainty from online observations and combines that with the probabilistic extension of the control barrier functions (CBFs) to characterize the uncertainty-aware control constraints. By integrating the constraints in the model predictive control scheme, it allows robots to adaptively capture the true prediction uncertainty online in a distribution-free setting and enjoys formally provable high-probability safety assurance. Simulation results on multi-robot systems with stochastic single-integrator dynamics and unicycle dynamics are provided to demonstrate the effectiveness of our framework.

Robotics0 citations2024-04-14arXiv ->

MPC Based Linear Equivalence with Control Barrier Functions for VTOL-UAVs

Ali Mohamed Ali, Hashim A. Hashim, Chao Shen

In this work, we propose a cascaded scheme of linear Model prediction Control (MPC) based on Control Barrier Functions (CBF) with Dynamic Feedback Linearization (DFL) for Vertical Take-off and Landing (VTOL) Unmanned Aerial Vehicles (UAVs). CBF is a tool that allows enforcement of forward invariance of a set using Lyapunov-like functions to ensure safety. The First control synthesis that employed CBF was based on Quadratic Program (QP) that modifies the existing controller to satisfy the safety requirements. However, the CBF-QP-based controllers leading to longer detours and undesirable transient performance. Recent contributions utilize the framework of MPC benefiting from the prediction capabilities and constraints imposed on the state and control inputs. Due to the intrinsic nonlinearities of the dynamics of robotics systems, all the existing MPC-CBF solutions rely on nonlinear MPC formulations or operate on less accurate linear models. In contrast, our novel solution unlocks the benefits of linear MPC-CBF while considering the full underactuated dynamics without any linear approximations. The cascaded scheme converts the problem of safe VTOL-UAV navigation to a Quadratic Constraint Quadratic Programming (QCQP) problem solved efficiently by off-the-shelf solvers. The closed-loop stability and recursive feasibility is proved along with numerical simulations showing the effective and robust solutions. Keywords: Unmanned Aerial Vehicles, Vertical Take-off and Landing, Model Predictive Control, MPC, Nonlinearity, Dynamic Feedback Linearization, Optimal Control.

Other Papers
Robotics0 citations2024-08-19arXiv ->

Neural Horizon Model Predictive Control -- Increasing Computational Efficiency with Neural Networks

Hendrik Alsmeier, Anton Savchenko, Rolf Findeisen

The expansion in automation of increasingly fast applications and low-power edge devices poses a particular challenge for optimization based control algorithms, like model predictive control. Our proposed machine-learning supported approach addresses this by utilizing a feed-forward neural network to reduce the computation load of the online-optimization. We propose approximating part of the problem horizon, while maintaining safety guarantees -- constraint satisfaction -- via the remaining optimization part of the controller. The approach is validated in simulation, demonstrating an improvement in computational efficiency, while maintaining guarantees and near-optimal performance. The proposed MPC scheme can be applied to a wide range of applications, including those requiring a rapid control response, such as robotics and embedded applications with limited computational resources.

Robotics0 citations2024-07-09arXiv ->

Adaptive Backstepping and Non-singular Sliding Mode Control for Quadrotor UAVs with Unknown Time-varying Uncertainties

Arezo Shevidi, Hashim A. Hashim

This paper presents a novel quaternion-based nonsingular control system for underactuated vertical-take-off and landing (VTOL) Unmanned Aerial Vehicles (UAVs). Position and attitude tracking is challenging regarding singularity and accuracy. Quaternion-based Adaptive Backstepping Control (QABC) is developed to tackle the underactuated issues of UAV control systems in a cascaded way. Leveraging the virtual control (auxiliary control) developed in the QABC, desired attitude components and required thrust are produced. Afterwards, we propose Quaternion-based Sliding Mode Control (QASMC) to enhance the stability and mitigate chattering issues. The sliding surface is modified to avoid singularity compared to conventional SMC. To improve the robustness of controllers, the control parameters are updated using adaptation laws. Furthermore, the asymptotic stability of translational and rotational dynamics is guaranteed by utilizing Lyapunov stability and Barbalet Lemma. Finally, the comprehensive comparison results are provided to verify the effectiveness of the proposed controllers in the presence of unknown time-varying parameter uncertainties and significant initial errors. Keywords: Non-singular Sliding Mode Control, Adaptive Backstepping Control, Unit-quaternion, Drones, Unmanned Aerial Vehicles, Asymptotic Stability, Position and Orientation Control

Robotics0 citations2024-04-18arXiv ->

Contingency Model Predictive Control for Bipedal Locomotion on Moving Surfaces with a Linear Inverted Pendulum Model

Kuo Chen, Xinyan Huang, Xunjie Chen, Jingang Yi

Gait control of legged robotic walkers on dynamically moving surfaces (e.g., ships and vehicles) is challenging due to the limited balance control actuation and unknown surface motion. We present a contingent model predictive control (CMPC) for bipedal walker locomotion on moving surfaces with a linear inverted pendulum (LIP) model. The CMPC is a robust design that is built on regular model predictive control (MPC) to incorporate the "worst case" predictive motion of the moving surface. Integrated with an LIP model and walking stability constraints, the CMPC framework generates a set of consistent control inputs considering to anticipated uncertainties of the surface motions. Simulation results and comparison with the regular MPC for bipedal walking are conducted and presented. The results confirm the feasibility and superior performance of the proposed CMPC design over the regular MPC under various motion profiles of moving surfaces.

Other0 citations2024-04-11arXiv ->

The Role of Confidence for Trust-based Resilient Consensus (Extended Version)

Luca Ballotta, Michal Yemini

We consider a multi-agent system where agents aim to achieve a consensus despite interactions with malicious agents that communicate misleading information. Physical channels supporting communication in cyberphysical systems offer attractive opportunities to detect malicious agents, nevertheless, trustworthiness indications coming from the channel are subject to uncertainty and need to be treated with this in mind. We propose a resilient consensus protocol that incorporates trust observations from the channel and weighs them with a parameter that accounts for how confident an agent is regarding its understanding of the legitimacy of other agents in the network, with no need for the initial observation window $T_0$ that has been utilized in previous works. Analytical and numerical results show that (i) our protocol achieves a resilient consensus in the presence of malicious agents and (ii) the steady-state deviation from nominal consensus can be minimized by a suitable choice of the confidence parameter that depends on the statistics of trust observations.

Robotics0 citations2024-04-05arXiv ->

ROMA-iQSS: An Objective Alignment Approach via State-Based Value Learning and ROund-Robin Multi-Agent Scheduling

Chi-Hui Lin, Joewie J. Koh, Alessandro Roncone, Lijun Chen

Effective multi-agent collaboration is imperative for solving complex, distributed problems. In this context, two key challenges must be addressed: first, autonomously identifying optimal objectives for collective outcomes; second, aligning these objectives among agents. Traditional frameworks, often reliant on centralized learning, struggle with scalability and efficiency in large multi-agent systems. To overcome these issues, we introduce a decentralized state-based value learning algorithm that enables agents to independently discover optimal states. Furthermore, we introduce a novel mechanism for multi-agent interaction, wherein less proficient agents follow and adopt policies from more experienced ones, thereby indirectly guiding their learning process. Our theoretical analysis shows that our approach leads decentralized agents to an optimal collective policy. Empirical experiments further demonstrate that our method outperforms existing decentralized state-based and action-based value learning strategies by effectively identifying and aligning optimal objectives.

MPC/Planning0 citations2024-03-26arXiv ->

Path Integral Control with Rollout Clustering and Dynamic Obstacles

Steven Patrick, Efstathios Bakolas

Model Predictive Path Integral (MPPI) control has proven to be a powerful tool for the control of uncertain systems (such as systems subject to disturbances and systems with unmodeled dynamics). One important limitation of the baseline MPPI algorithm is that it does not utilize simulated trajectories to their fullest extent. For one, it assumes that the average of all trajectories weighted by their performance index will be a safe trajectory. In this paper, multiple examples are shown where the previous assumption does not hold, and a trajectory clustering technique is presented that reduces the chances of the weighted average crossing in an unsafe region. Secondly, MPPI does not account for dynamic obstacles, so the authors put forward a novel cost function that accounts for dynamic obstacles without adding significant computation time to the overall algorithm. The novel contributions proposed in this paper were evaluated with extensive simulations to demonstrate improvements upon the state-of-the-art MPPI techniques.

Robotics0 citations2024-03-17arXiv ->

PyroTrack: Belief-Based Deep Reinforcement Learning Path Planning for Aerial Wildfire Monitoring in Partially Observable Environments

Sahand Khoshdel, Qi Luo, Fatemeh Afghah

Motivated by agility, 3D mobility, and low-risk operation compared to human-operated management systems of autonomous unmanned aerial vehicles (UAVs), this work studies UAV-based active wildfire monitoring where a UAV detects fire incidents in remote areas and tracks the fire frontline. A UAV path planning solution is proposed considering realistic wildfire management missions, where a single low-altitude drone with limited power and flight time is available. Noting the limited field of view of commercial low-altitude UAVs, the problem formulates as a partially observable Markov decision process (POMDP), in which wildfire progression outside the field of view causes inaccurate state representation that prevents the UAV from finding the optimal path to track the fire front in limited time. Common deep reinforcement learning (DRL)-based trajectory planning solutions require diverse drone-recorded wildfire data to generalize pre-trained models to real-time systems, which is not currently available at a diverse and standard scale. To narrow down the gap caused by partial observability in the space of possible policies, a belief-based state representation with broad, extensive simulated data is proposed where the beliefs (i.e., ignition probabilities of different grid areas) are updated using a Bayesian framework for the cells within the field of view. The performance of the proposed solution in terms of the ratio of detected fire cells and monitored ignited area (MIA) is evaluated in a complex fire scenario with multiple rapidly growing fire batches, indicating that the belief state representation outperforms the observation state representation both in fire coverage and the distance to fire frontline.

RAL 2026 | 2 papers
CBF Related Papers
Robotics0 citations2026-01-18arXiv ->

Allocating Corrective Control to Mitigate Multi-agent Safety Violations Under Private Preferences

Johnathan Corbin, Sarah H. Q. Li, Jonathan Rogers

We propose a novel framework that computes the corrective control efforts to ensure joint safety in multi-agent dynamical systems. This framework efficiently distributes the required corrective effort without revealing individual agents' private preferences. Our framework integrates high-order control barrier functions (HOCBFs), which enforce safety constraints with formal guarantees of safety for complex dynamical systems, with a privacy-preserving resource allocation mechanism based on the progressive second price (PSP) auction. When a joint safety constraint is violated, agents iteratively bid on new corrective efforts via 'avoidance credits' rather than explicitly solving for feasible corrective efforts that remove the safety violation. The resulting correction, determined via a second price payment rule, coincides with the socially optimal safe distribution of corrective actions. Critically, the bidding process achieves this optimal allocation efficiently and without revealing private preferences of individual agents. We demonstrate this method through multi-robot hardware experiments on the Robotarium platform.

Robotics0 citations2026-01-15arXiv ->

Proactive Local-Minima-Free Robot Navigation: Blending Motion Prediction with Safe Control

Yifan Xue, Ze Zhang, Knut Åkesson, Nadia Figueroa

This work addresses the challenge of safe and efficient mobile robot navigation in complex dynamic environments with concave moving obstacles. Reactive safe controllers like Control Barrier Functions (CBFs) design obstacle avoidance strategies based only on the current states of the obstacles, risking future collisions. To alleviate this problem, we use Gaussian processes to learn barrier functions online from multimodal motion predictions of obstacles generated by neural networks trained with energy-based learning. The learned barrier functions are then fed into quadratic programs using modulated CBFs (MCBFs), a local-minimum-free version of CBFs, to achieve safe and efficient navigation. The proposed framework makes two key contributions. First, it develops a prediction-to-barrier function online learning pipeline. Second, it introduces an autonomous parameter tuning algorithm that adapts MCBFs to deforming, prediction-based barrier functions. The framework is evaluated in both simulations and real-world experiments, consistently outperforming baselines and demonstrating superior safety and efficiency in crowded dynamic environments.

RAL 2025 | 12 papers
CBF Related Papers
MPC/Planning0 citations2025-11-24arXiv ->

Online Learning-Enhanced High Order Adaptive Safety Control

Lishuo Pan, Mattia Catellani, Thales C. Silva, Lorenzo Sabattini, Nora Ayanian

Control barrier functions (CBFs) are an effective model-based tool to formally certify the safety of a system. With the growing complexity of modern control problems, CBFs have received increasing attention in both optimization-based and learning-based control communities as a safety filter, owing to their provable guarantees. However, success in transferring these guarantees to real-world systems is critically tied to model accuracy. For example, payloads or wind disturbances can significantly influence the dynamics of an aerial vehicle and invalidate the safety guarantee. In this work, we propose an efficient yet flexible online learning-enhanced high-order adaptive control barrier function using Neural ODEs. Our approach improves the safety of a CBF-certified system on the fly, even under complex time-varying model perturbations. In particular, we deploy our hybrid adaptive CBF controller on a 38g nano quadrotor, keeping a safe distance from the obstacle, against 18km/h wind.

MPC/Planning0 citations2025-09-08arXiv ->

Safety Meets Speed: Accelerated Neural MPC with Safety Guarantees and No Retraining

Kaikai Wang, Tianxun Li, Liang Xu, Qinglei Hu, Keyou You

While Model Predictive Control (MPC) enforces safety via constraints, its real-time execution can exceed embedded compute budgets. We propose a Barrier-integrated Adaptive Neural Model Predictive Control (BAN-MPC) framework that synergizes neural networks' fast computation with MPC's constraint-handling capability. To ensure strict safety, we replace traditional Euclidean distance with Control Barrier Functions (CBFs) for collision avoidance. We integrate an offline-learned neural value function into the optimization objective of a Short-horizon MPC, substantially reducing online computational complexity. Additionally, we use a second neural network to learn the sensitivity of the value function to system parameters, and adaptively adjust the neural value function based on this neural sensitivity when model parameters change, eliminating the need for retraining and reducing offline computation costs. The hardware in-the-loop (HIL) experiments on Jetson Nano show that BAN-MPC solves 200 times faster than traditional MPC, enabling collision-free navigation with control error below 5\% under model parameter variations within 15\%, making it an effective embedded MPC alternative.

Robotics0 citations2025-05-05arXiv ->

Contact-Aware Safety in Soft Robots Using High-Order Control Barrier and Lyapunov Functions

Kiwan Wong, Maximilian Stölzle, Wei Xiao, Cosimo Della Santina, Daniela Rus et al.

Robots operating alongside people, particularly in sensitive scenarios such as aiding the elderly with daily tasks or collaborating with workers in manufacturing, must guarantee safety and cultivate user trust. Continuum soft manipulators promise safety through material compliance, but as designs evolve for greater precision, payload capacity, and speed, and increasingly incorporate rigid elements, their injury risk resurfaces. In this letter, we introduce a comprehensive High-Order Control Barrier Function (HOCBF) + High-Order Control Lyapunov Function (HOCLF) framework that enforces strict contact force limits across the entire soft-robot body during environmental interactions. Our approach combines a differentiable Piecewise Cosserat-Segment (PCS) dynamics model with a convex-polygon distance approximation metric, named Differentiable Conservative Separating Axis Theorem (DCSAT), based on the soft robot geometry to enable real-time, whole-body collision detection, resolution, and enforcement of the safety constraints. By embedding HOCBFs into our optimization routine, we guarantee safety, allowing, for instance, safe navigation in operational space under HOCLF-driven motion objectives. Extensive planar simulations demonstrate that our method maintains safety-bounded contacts while achieving precise shape and task-space regulation. This work thus lays a foundation for the deployment of soft robots in human-centric environments with provable safety and performance.

MPC/Planning0 citations2025-04-10arXiv ->

ES-HPC-MPC: Exponentially Stable Hybrid Perception Constrained MPC for Quadrotor with Suspended Payloads

Luis F. Recalde, Mrunal Sarvaiya, Giuseppe Loianno, Guanrui Li

Aerial transportation using quadrotors with cable-suspended payloads holds great potential for applications in disaster response, logistics, and infrastructure maintenance. However, their hybrid and underactuated dynamics pose significant control and perception challenges. Traditional approaches often assume a taut cable condition, limiting their effectiveness in real-world applications where slack-to-taut transitions occur due to disturbances. We introduce ES-HPC-MPC, a model predictive control framework that enforces exponential stability and perception-constrained control under hybrid dynamics. Our method leverages Exponentially Stabilizing Control Lyapunov Functions (ES-CLFs) to enforce stability during the tasks and Control Barrier Functions (CBFs) to maintain the payload within the onboard camera's field of view (FoV). We validate our method through both simulation and real-world experiments, demonstrating stable trajectory tracking and reliable payload perception. We validate that our method maintains stability and satisfies perception constraints while tracking dynamically infeasible trajectories and when the system is subjected to hybrid mode transitions caused by unexpected disturbances.

Other Papers
Robotics0 citations2025-10-28arXiv ->

VOCALoco: Viability-Optimized Cost-aware Adaptive Locomotion

Stanley Wu, Mohamad H. Danesh, Simon Li, Hanna Yurchyk, Amin Abyaneh et al.

Recent advancements in legged robot locomotion have facilitated traversal over increasingly complex terrains. Despite this progress, many existing approaches rely on end-to-end deep reinforcement learning (DRL), which poses limitations in terms of safety and interpretability, especially when generalizing to novel terrains. To overcome these challenges, we introduce VOCALoco, a modular skill-selection framework that dynamically adapts locomotion strategies based on perceptual input. Given a set of pre-trained locomotion policies, VOCALoco evaluates their viability and energy-consumption by predicting both the safety of execution and the anticipated cost of transport over a fixed planning horizon. This joint assessment enables the selection of policies that are both safe and energy-efficient, given the observed local terrain. We evaluate our approach on staircase locomotion tasks, demonstrating its performance in both simulated and real-world scenarios using a quadrupedal robot. Empirical results show that VOCALoco achieves improved robustness and safety during stair ascent and descent compared to a conventional end-to-end DRL policy

Robotics0 citations2025-06-22arXiv ->

GeNIE: A Generalizable Navigation System for In-the-Wild Environments

Jiaming Wang, Diwen Liu, Jizhuo Chen, Jiaxuan Da, Nuowen Qian et al.

Reliable navigation in unstructured, real-world environments remains a significant challenge for embodied agents, especially when operating across diverse terrains, weather conditions, and sensor configurations. In this paper, we introduce GeNIE (Generalizable Navigation System for In-the-Wild Environments), a robust navigation framework designed for global deployment. GeNIE integrates a generalizable traversability prediction model built on SAM2 with a novel path fusion strategy that enhances planning stability in noisy and ambiguous settings. We deployed GeNIE in the Earth Rover Challenge (ERC) at ICRA 2025, where it was evaluated across six countries spanning three continents. GeNIE took first place and achieved 79% of the maximum possible score, outperforming the second-best team by 17%, and completed the entire competition without a single human intervention. These results set a new benchmark for robust, generalizable outdoor robot navigation. We will release the codebase, pretrained model weights, and newly curated datasets to support future research in real-world navigation.

Robotics0 citations2025-04-27arXiv ->

LRFusionPR: A Polar BEV-Based LiDAR-Radar Fusion Network for Place Recognition

Zhangshuo Qi, Luqi Cheng, Zijie Zhou, Guangming Xiong

In autonomous driving, place recognition is critical for global localization in GPS-denied environments. LiDAR and radar-based place recognition methods have garnered increasing attention, as LiDAR provides precise ranging, whereas radar excels in adverse weather resilience. However, effectively leveraging LiDAR-radar fusion for place recognition remains challenging. The noisy and sparse nature of radar data limits its potential to further improve recognition accuracy. In addition, heterogeneous radar configurations complicate the development of unified cross-modality fusion frameworks. In this paper, we propose LRFusionPR, which improves recognition accuracy and robustness by fusing LiDAR with either single-chip or scanning radar. Technically, a dual-branch network is proposed to fuse different modalities within the unified polar coordinate bird's eye view (BEV) representation. In the fusion branch, cross-attention is utilized to perform cross-modality feature interactions. The knowledge from the fusion branch is simultaneously transferred to the distillation branch, which takes radar as its only input to further improve the robustness. Ultimately, the descriptors from both branches are concatenated, producing the multimodal global descriptor for place retrieval. Extensive evaluations on multiple datasets demonstrate that our LRFusionPR achieves accurate place recognition, while maintaining robustness under varying weather conditions. Our open-source code will be released at https://github.com/QiZS-BIT/LRFusionPR.

Robotics0 citations2025-04-20arXiv ->

ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusion

Mingjie Zhang, Yuheng Du, Chengkai Wu, Jinni Zhou, Zhenchao Qi et al.

Navigating unknown environments to find a target object is a significant challenge. While semantic information is crucial for navigation, relying solely on it for decision-making may not always be efficient, especially in environments with weak semantic cues. Additionally, many methods are susceptible to misdetections, especially in environments with visually similar objects. To address these limitations, we propose ApexNav, a zero-shot object navigation framework that is both more efficient and reliable. For efficiency, ApexNav adaptively utilizes semantic information by analyzing its distribution in the environment, guiding exploration through semantic reasoning when cues are strong, and switching to geometry-based exploration when they are weak. For reliability, we propose a target-centric semantic fusion method that preserves long-term memory of the target and similar objects, enabling robust object identification even under noisy detections. We evaluate ApexNav on the HM3Dv1, HM3Dv2, and MP3D datasets, where it outperforms state-of-the-art methods in both SR and SPL metrics. Comprehensive ablation studies further demonstrate the effectiveness of each module. Furthermore, real-world experiments validate the practicality of ApexNav in physical environments. The code will be released at https://github.com/Robotics-STAR-Lab/ApexNav.

Robotics0 citations2025-02-14arXiv ->

Diffusion Trajectory-guided Policy for Long-horizon Robot Manipulation

Shichao Fan, Quantao Yang, Yajie Liu, Kun Wu, Zhengping Che et al.

Recently, Vision-Language-Action models (VLA) have advanced robot imitation learning, but high data collection costs and limited demonstrations hinder generalization and current imitation learning methods struggle in out-of-distribution scenarios, especially for long-horizon tasks. A key challenge is how to mitigate compounding errors in imitation learning, which lead to cascading failures over extended trajectories. To address these challenges, we propose the Diffusion Trajectory-guided Policy (DTP) framework, which generates 2D trajectories through a diffusion model to guide policy learning for long-horizon tasks. By leveraging task-relevant trajectories, DTP provides trajectory-level guidance to reduce error accumulation. Our two-stage approach first trains a generative vision-language model to create diffusion-based trajectories, then refines the imitation policy using them. Experiments on the CALVIN benchmark show that DTP outperforms state-of-the-art baselines by 25% in success rate, starting from scratch without external pretraining. Moreover, DTP significantly improves real-world robot performance.

Robotics0 citations2024-10-25arXiv ->

Image-Based Visual Servoing for Enhanced Cooperation of Dual-Arm Manipulation

Zizhe Zhang, Yuan Yang, Wenqiang Zuo, Guangming Song, Aiguo Song et al.

The cooperation of a pair of robot manipulators is required to manipulate a target object without any fixtures. The conventional control methods coordinate the end-effector pose of each manipulator with that of the other using their kinematics and joint coordinate measurements. Yet, the manipulators' inaccurate kinematics and joint coordinate measurements can cause significant pose synchronization errors in practice. This paper thus proposes an image-based visual servoing approach for enhancing the cooperation of a dual-arm manipulation system. On top of the classical control, the visual servoing controller lets each manipulator use its carried camera to measure the image features of the other's marker and adapt its end-effector pose with the counterpart on the move. Because visual measurements are robust to kinematic errors, the proposed control can reduce the end-effector pose synchronization errors and the fluctuations of the interaction forces of the pair of manipulators on the move. Theoretical analyses have rigorously proven the stability of the closed-loop system. Comparative experiments on real robots have substantiated the effectiveness of the proposed control.

MPC/Planning0 citations2024-09-10arXiv ->

Kino-PAX: Highly Parallel Kinodynamic Sampling-based Planner

Nicolas Perrault, Qi Heng Ho, Morteza Lahijanian

Sampling-based motion planners (SBMPs) are effective for planning with complex kinodynamic constraints in high-dimensional spaces, but they still struggle to achieve real-time performance, which is mainly due to their serial computation design. We present Kinodynamic Parallel Accelerated eXpansion (Kino-PAX), a novel highly parallel kinodynamic SBMP designed for parallel devices such as GPUs. Kino-PAX grows a tree of trajectory segments directly in parallel. Our key insight is how to decompose the iterative tree growth process into three massively parallel subroutines. Kino-PAX is designed to align with the parallel device execution hierarchies, through ensuring that threads are largely independent, share equal workloads, and take advantage of low-latency resources while minimizing high-latency data transfers and process synchronization. This design results in a very efficient GPU implementation. We prove that Kino-PAX is probabilistically complete and analyze its scalability with compute hardware improvements. Empirical evaluations demonstrate solutions in the order of 10 ms on a desktop GPU and in the order of 100 ms on an embedded GPU, representing up to 1000 times improvement compared to coarse-grained CPU parallelization of state-of-the-art sequential algorithms over a range of complex environments and systems.

MPC/Planning0 citations2024-08-01arXiv ->

RESC: A Reinforcement Learning Based Search-to-Control Framework for Quadrotor Local Planning in Dense Environments

Zhaohong Liu, Wenxuan Gao, Yinshuai Sun, Peng Dong

Agile flight in complex environments poses significant challenges to current motion planning methods, as they often fail to fully leverage the quadrotor dynamic potential, leading to performance failures and reduced efficiency during aggressive maneuvers.Existing approaches frequently decouple trajectory optimization from control generation and neglect the dynamics, further limiting their ability to generate aggressive and feasible motions.To address these challenges, we introduce an enhanced Search-to-Control planning framework that integrates visibility path searching with reinforcement learning (RL) control generation, directly accounting for dynamics and bridging the gap between planning and control.Our method first extracts control points from collision-free paths using a proposed heuristic search, which are then refined by an RL policy to generate low-level control commands for the quadrotor controller, utilizing reduced-dimensional obstacle observations for efficient inference with lightweight neural networks.We validate the framework through simulations and real-world experiments, demonstrating improved time efficiency and dynamic maneuverability compared to existing methods, while confirming its robustness and applicability.

TRO 2025 | 3 papers
CBF Related Papers
Robotics0 citations2025-04-12arXiv ->

Concurrent-Allocation Task Execution for Multi-Robot Path-Crossing-Minimal Navigation in Obstacle Environments

Bin-Bin Hu, Weijia Yao, Yanxin Zhou, Henglai Wei, Chen Lv

Reducing undesirable path crossings among trajectories of different robots is vital in multi-robot navigation missions, which not only reduces detours and conflict scenarios, but also enhances navigation efficiency and boosts productivity. Despite recent progress in multi-robot path-crossing-minimal (MPCM) navigation, the majority of approaches depend on the minimal squared-distance reassignment of suitable desired points to robots directly. However, if obstacles occupy the passing space, calculating the actual robot-point distances becomes complex or intractable, which may render the MPCM navigation in obstacle environments inefficient or even infeasible. In this paper, the concurrent-allocation task execution (CATE) algorithm is presented to address this problem (i.e., MPCM navigation in obstacle environments). First, the path-crossing-related elements in terms of (i) robot allocation, (ii) desired-point convergence, and (iii) collision and obstacle avoidance are encoded into integer and control barrier function (CBF) constraints. Then, the proposed constraints are used in an online constrained optimization framework, which implicitly yet effectively minimizes the possible path crossings and trajectory length in obstacle environments by minimizing the desired point allocation cost and slack variables in CBF constraints simultaneously. In this way, the MPCM navigation in obstacle environments can be achieved with flexible spatial orderings. Note that the feasibility of solutions and the asymptotic convergence property of the proposed CATE algorithm in obstacle environments are both guaranteed, and the calculation burden is also reduced by concurrently calculating the optimal allocation and the control input directly without the path planning process.

Other Papers
Robotics0 citations2025-05-19arXiv ->

OPA-Pack: Object-Property-Aware Robotic Bin Packing

Jia-Hui Pan, Yeok Tatt Cheah, Zhengzhe Liu, Ka-Hei Hui, Xiaojie Gao et al.

Robotic bin packing aids in a wide range of real-world scenarios such as e-commerce and warehouses. Yet, existing works focus mainly on considering the shape of objects to optimize packing compactness and neglect object properties such as fragility, edibility, and chemistry that humans typically consider when packing objects. This paper presents OPA-Pack (Object-Property-Aware Packing framework), the first framework that equips the robot with object property considerations in planning the object packing. Technical-wise, we develop a novel object property recognition scheme with retrieval-augmented generation and chain-of-thought reasoning, and build a dataset with object property annotations for 1,032 everyday objects. Also, we formulate OPA-Net, aiming to jointly separate incompatible object pairs and reduce pressure on fragile objects, while compacting the packing. Further, OPA-Net consists of a property embedding layer to encode the property of candidate objects to be packed, together with a fragility heightmap and an avoidance heightmap to keep track of the packed objects. Then, we design a reward function and adopt a deep Q-learning scheme to train OPA-Net. Experimental results manifest that OPA-Pack greatly improves the accuracy of separating incompatible object pairs (from 52% to 95%) and largely reduces pressure on fragile objects (by 29.4%), while maintaining good packing compactness. Besides, we demonstrate the effectiveness of OPA-Pack on a real packing platform, showcasing its practicality in real-world scenarios.

Robotics0 citations2023-11-22arXiv ->

Applications of Spiking Neural Networks in Visual Place Recognition

Somayeh Hussaini, Michael Milford, Tobias Fischer

In robotics, Spiking Neural Networks (SNNs) are increasingly recognized for their largely-unrealized potential energy efficiency and low latency particularly when implemented on neuromorphic hardware. Our paper highlights three advancements for SNNs in Visual Place Recognition (VPR). Firstly, we propose Modular SNNs, where each SNN represents a set of non-overlapping geographically distinct places, enabling scalable networks for large environments. Secondly, we present Ensembles of Modular SNNs, where multiple networks represent the same place, significantly enhancing accuracy compared to single-network models. Each of our Modular SNN modules is compact, comprising only 1500 neurons and 474k synapses, making them ideally suited for ensembling due to their small size. Lastly, we investigate the role of sequence matching in SNN-based VPR, a technique where consecutive images are used to refine place recognition. We demonstrate competitive performance of our method on a range of datasets, including higher responsiveness to ensembling compared to conventional VPR techniques and higher R@1 improvements with sequence matching than VPR techniques with comparable baseline performance. Our contributions highlight the viability of SNNs for VPR, offering scalable and robust solutions, and paving the way for their application in various energy-sensitive robotic tasks.

TAC 2025 | 3 papers
CBF Related Papers
MPC/Planning0 citations2025-09-26arXiv ->

Safe-by-Design: Approximate Nonlinear Model Predictive Control with Real Time Feasibility

Jan Olucak, Arthur Castello B. de Oliveira, Torbjørn Cunis

This paper establishes relationships between continuous-time, receding horizon, nonlinear model predictive control (MPC) and control Lyapunov and control barrier functions (CLF/CBF). We show that, if the cost function "behaves well" for points in the terminal set, then the optimal value function and the feasible set, respectively, define a compatible CLF/CBF pair on the MPC's region of attraction. We then proceed to prove that any approximation of the value function and the feasible set also define a CLF/CBF pair, as long as those approximations satisfy the same "well behavedness" condition; and that a feasible state feedback can be computed by solving an infinitesimal version of the MPC problem. This methodology permits the formulation of continuous-time small-sized quadratic programs for feedback and enables approximate solutions of the nonlinear model predictive controller with theoretical safety and convergence guarantee. Finally, we demonstrate the effectiveness of the proposed approach when compared to other constrained control techniques through numerical experiments for nonlinear constrained spacecraft control.

MPC/Planning0 citations2025-09-23arXiv ->

Verification and Synthesis of Discrete-Time Control Barrier Functions

Erfan Shakhesi, W. P. M. H. Heemels, Alexander Katriniok

Discrete-time Control Barrier Functions (DTCBFs) have recently attracted interest for guaranteeing safety and synthesizing safe controllers for discrete-time dynamical systems. This paper addresses the open challenges of verifying candidate DTCBFs and synthesizing DTCBFs for general nonlinear discrete-time systems with input constraints and arbitrary safe sets. In particular, we propose a branch-and-bound method, inspired by the $α$BB algorithm, for the verification of candidate DTCBFs in both cases, whether a corresponding control policy is known or unknown. We prove that this method, in a finite number of iterations, either verifies a given candidate function as a valid DTCBF or falsifies it by providing a counterexample (within predefined tolerances). As a second main contribution, we propose a novel bilevel optimization approach to synthesize a DTCBF and a corresponding control policy in finite time. This involves determining the unknown coefficients of a parameterized DTCBF and a parameterized control policy. Furthermore, we introduce various strategies to reduce the computational burden of the bilevel approach. We also demonstrate our methods using numerical case studies.

Robotics0 citations2025-08-15arXiv ->

Matrix Control Barrier Functions

Pio Ong, Yicheng Xu, Ryan M. Bena, Faryar Jabbari, Aaron D. Ames

This paper generalizes the control barrier function framework by replacing scalar-valued functions with matrix-valued ones. Specifically, we develop barrier conditions for safe sets defined by matrix inequalities -- both semidefinite and indefinite. Matrix inequalities can be used to describe a richer class of safe sets, including nonsmooth ones. The safety filters constructed from our proposed matrix control barrier functions via semidefinite programming (CBF-SDP) are shown to be continuous. Our matrix formulation naturally provides a continuous safety filter for Boolean-based control barrier functions, notably for disjunctions (OR), without relaxing the safe set. We illustrate the effectiveness of the proposed framework with applications in drone network connectivity maintenance and nonsmooth obstacle avoidance, both in simulations and hardware experiments.