Tolerance of Reinforcement Learning Controllers against Deviations in Cyber Physical Systems

TL;DR

This paper introduces a new notion of system tolerance for RL-controlled cyber-physical systems, proposing a framework and heuristic to identify small deviations that violate system requirements, enhancing safety analysis.

Contribution

It presents a novel, expressive definition of tolerance, a new analysis problem called tolerance falsification, and a simulation-based framework with heuristics for finding small violations.

Findings

Effective identification of small tolerance violations

Framework applicable to various uncertainties and disturbances

Demonstrated success on benchmark problems

Abstract

Cyber-physical systems (CPS) with reinforcement learning (RL)-based controllers are increasingly being deployed in complex physical environments such as autonomous vehicles, the Internet-of-Things(IoT), and smart cities. An important property of a CPS is tolerance; i.e., its ability to function safely under possible disturbances and uncertainties in the actual operation. In this paper, we introduce a new, expressive notion of tolerance that describes how well a controller is capable of satisfying a desired system requirement, specified using Signal Temporal Logic (STL), under possible deviations in the system. Based on this definition, we propose a novel analysis problem, called the tolerance falsification problem, which involves finding small deviations that result in a violation of the given requirement. We present a novel, two-layer simulation-based analysis framework and a novel search heuristic for finding small tolerance violations. To evaluate our approach, we construct a set of benchmark problems where system parameters can be configured to represent different types of uncertainties and disturbancesin the system. Our evaluation shows that our falsification approach and heuristic can effectively find small tolerance violations.