Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes

2022-10-19 · Niklas Kochdumper, Hanna Krasowski, Xiao Wang, Stanley Bak, Matthias Althoff

While reinforcement learning produces very promising results for many applications, its main disadvantage is the lack of safety guarantees, which prevents its use in safety-critical systems. In this work, we address this issue by a safety shield for nonlinear continuous systems that solve reach-avoid tasks. Our safety shield prevents applying potentially unsafe actions from a reinforcement learning agent by projecting the proposed action to the closest safe action. This approach is called action projection and is implemented via mixed-integer optimization. The safety constraints for action projection are obtained by applying parameterized reachability analysis using polynomial zonotopes, which enables to accurately capture the nonlinear effects of the actions on the system. In contrast to other state-of-the-art approaches for action projection, our safety shield can efficiently handle input constraints and dynamic obstacles, eases incorporation of the spatial robot dimensions into the safety constraints, guarantees robust safety despite process noise and measurement errors, and is well suited for high-dimensional systems, as we demonstrate on several challenging benchmark systems.

📄 PDF Abstract BibTeX arXiv:2210.10691

Code (0)

등록된 구현이 없습니다.

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)Safe Reinforcement Learning

Provably Safe Reinforcement Learning: Conceptual Analysis, Survey, and Benchmarking

2022-05-13 · Hanna Krasowski, Jakob Thumm, Marlon Müller, Lukas Schäfer 외

Ensuring the safety of reinforcement learning (RL) algorithms is crucial to unlock their potential for many real-world tasks. However, vanilla RL and most safe RL approaches do not guarantee safety. In recent years, seve…

Benchmarking reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+2

HJ-SafeDMP: Hamilton-Jacobi Reachability-Guided Dynamic Movement Primitives for Provably Safe Robot Motion

2026-06-27 · Siddhanth Ramesh, Ravi Prakash arxiv

Robots deployed in safety-critical environments must execute motions that are simultaneously robust to disturbances and provably safe from collisions. Dynamic Movement Primitives (DMPs) offer inherent stability, temporal…

Computational Efficiency

SanDRA: Safe Large-Language-Model-Based Decision Making for Automated Vehicles Using Reachability Analysis

2025-10-08 · Yuanfei Lin, Sebastian Illing, Matthias Althoff arxiv

Large language models have been widely applied to knowledge-driven decision-making for automated vehicles due to their strong generalization and reasoning capabilities. However, the safety of the resulting decisions cann…

Decision Making

Safe Reinforcement Learning Using Black-Box Reachability Analysis

2022-04-15 · Mahmoud Selim, Amr Alanwar, Shreyas Kousik, Grace Gao 외

Reinforcement learning (RL) is capable of sophisticated motion planning and control for robots in uncertain environments. However, state-of-the-art deep RL approaches typically lack safety guarantees, especially when the…

Motion Planning reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)+1

Conformal Reachability for Safe Control in Unknown Environments

2026-02-03 · Xinhang Ma, Junlin Wu, Yiannis Kantaros, Yevgeniy Vorobeychik arxiv

Designing provably safe control is a core problem in trustworthy autonomy. However, most prior work in this regard assumes either that the system dynamics are known or deterministic, or that the state and action space ar…