Closed-Loop Policies for Operational Tests of Safety-Critical Systems

TL;DR

This paper models the testing process of safety-critical systems as a Markov decision process to develop optimal, closed-loop testing policies that help manufacturers and regulators make strategic testing decisions.

Contribution

It introduces a novel framework for test scheduling of safety-critical systems using Markov decision processes, providing strategic guidance for testing and regulation.

Findings

Optimal testing policies can be derived efficiently.

Guidance on testing strategies under different incident scenarios.

Recommendations for regulators on adjusting testing requirements.

Abstract

Manufacturers of safety-critical systems must make the case that their product is sufficiently safe for public deployment. Much of this case often relies upon critical event outcomes from real-world testing, requiring manufacturers to be strategic about how they allocate testing resources in order to maximize their chances of demonstrating system safety. This work frames the partially observable and belief-dependent problem of test scheduling as a Markov decision process, which can be solved efficiently to yield closed-loop manufacturer testing policies. By solving for policies over a wide range of problem formulations, we are able to provide high-level guidance for manufacturers and regulators on issues relating to the testing of safety-critical systems. This guidance spans an array of topics, including circumstances under which manufacturers should continue testing despite observed incidents, when manufacturers should test aggressively, and when regulators should increase or reduce the real-world testing requirements for an autonomous vehicle.