12 papers
Unified Overview of Safety Certificate Functions: Techniques from Hamilton--Jacobi Reachability and Control Barrier Functions
Hao Wang, Max Cohen, Zeyuan Feng +9
Safety is a central concern in modern autonomous systems. Safety certificates---functions whose existence guarantees that a system meets its safety specification---have long been u…
Active Reachability Learning for Humanoid Recoverability Monitoring
Zeyuan Feng, Baljeet Singh, Sarthak Ranjeet Kaingade +2
Deploying humanoid task policies requires reliable runtime monitors that anticipate unrecoverable falls in time to trigger a fallback. We formulate this task as learning the stocha…
Neural Backward Reach-Avoid Tubes with MPC Supervision for High-Dimensional Systems: An Application to Safe Spacecraft Docking
Santiago Thorup, Luca Castelletto, Zeyuan Feng +1
Autonomous spacecraft docking requires control policies that simultaneously ensure collision avoidance and target reachability under coupled, high-dimensional translational-rotatio…
From Words to Safety: Language-Conditioned Safety Filtering for Robot Navigation
Zeyuan Feng, Haimingyue Zhang, Somil Bansal
As robots become increasingly integrated into open-world, human-centered environments, their ability to interpret natural language instructions and adhere to safety constraints is…
MADR: MPC-guided Adversarial DeepReach
Ryan Teoh, Sander Tonkens, William Sharpless +4
Hamilton-Jacobi (HJ) Reachability offers a framework for generating safe value functions and policies in the face of adversarial disturbance, but is limited by the curse of dimensi…
Safety Evaluation of Motion Plans Using Trajectory Predictors as Forward Reachable Set Estimators
Kaustav Chakraborty, Zeyuan Feng, Sushant Veer +6
The advent of end-to-end autonomy stacks - often lacking interpretable intermediate modules - has placed an increased burden on ensuring that the final output, i.e., the motion pla…
Bridging Model Predictive Control and Deep Learning for Scalable Reachability Analysis
Zeyuan Feng, Le Qiu, Somil Bansal
Hamilton-Jacobi (HJ) reachability analysis is a widely used method for ensuring the safety of robotic systems. Traditional approaches compute reachable sets by numerically solving…
Linear Supervision for Nonlinear, High-Dimensional Neural Control and Differential Games
William Sharpless, Zeyuan Feng, Somil Bansal +1
As the dimension of a system increases, traditional methods for control and differential games rapidly become intractable, making the design of safe autonomous agents challenging i…
Reachability Analysis for Black-Box Dynamical Systems
Vamsi Krishna Chilakamarri, Zeyuan Feng, Somil Bansal
Hamilton-Jacobi (HJ) reachability analysis is a powerful framework for ensuring safety and performance in autonomous systems. However, existing methods typically rely on a white-bo…
System-Level Safety Monitoring and Recovery for Perception Failures in Autonomous Vehicles
Kaustav Chakraborty, Zeyuan Feng, Sushant Veer +4
The safety-critical nature of autonomous vehicle (AV) operation necessitates development of task-relevant algorithms that can reason about safety at the system level and not just a…
SAFE-GIL: SAFEty Guided Imitation Learning for Robotic Systems
Yusuf Umut Ciftci, Darren Chiu, Zeyuan Feng +2
Behavior cloning (BC) is a widely-used approach in imitation learning, where a robot learns a control policy by observing an expert supervisor. However, the learned policy can make…
Exact Imposition of Safety Boundary Conditions in Neural Reachable Tubes
Aditya Singh, Zeyuan Feng, Somil Bansal
Hamilton-Jacobi (HJ) reachability analysis is a widely adopted verification tool to provide safety and performance guarantees for autonomous systems. However, it involves solving a…