Provably Safe Reinforcement Learning via Action Projection using Reachability Analysis and Polynomial Zonotopes
Authors:
Preprint
Abstract
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.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Safe Reinforcement Learning Using Black-Box Reachability AnalysisIEEE Robotics and Automation Letters, 2022
- Provably Safe Deep Reinforcement Learning for Robotic Manipulation in Human Environments2022
- A predictive safety filter for learning-based control of constrained nonlinear dynamical systemsAutomatica, 2021
- Reachability-Based Trajectory Safeguard (RTS): A Safe and Fast Reinforcement Learning Safety Layer for Continuous ControlIEEE Robotics and Automation Letters, 2021
- Safe reinforcement learning: A control barrier function optimization approachInternational Journal of Robust and Nonlinear Control, 2020
- Constrained zonotopes: A new tool for set-based estimation and fault detectionAutomatica, 2016
- Generalized Convex Disjunctive Programming: Nonlinear Convex Hull RelaxationComputational Optimization and Applications, 2003
- Robust Monte Carlo localization for mobile robotsArtificial Intelligence, 2001
- Applied Interval Analysis2001
- Disjunctive programming: Properties of the convex hull of feasible pointsDiscrete Applied Mathematics, 1998