Learning Critical Scenarios in Feedback Control Systems for Automated Driving

TL;DR

This paper introduces a learning-based optimization framework to efficiently generate critical test scenarios for automated driving control systems, focusing on safety validation within the operational design domain.

Contribution

It formalizes a novel approach combining learning and optimization to identify critical scenarios, addressing the challenge of infinite possible test cases.

Findings

Successfully identified critical scenarios with limited experiments

Demonstrated effectiveness on two logical driving scenarios

Framework tailored for feedback control systems in automated driving

Abstract

Testing is essential for verifying and validating control designs, especially in safety-critical applications. In particular, the control system governing an automated driving vehicle must be proven reliable enough for its acceptance on the market. Recently, much research has focused on scenario-based methods. However, the number of possible driving scenarios to test is in principle infinite. In this paper, we formalize a learning-based optimization framework to generate corner test-cases, where we take into account the operational design domain. We examine the approach on the case of a feedback control system for automated driving, for which we suggest the design of the objective function expressing the criticality of scenarios. Numerical tests on two logical scenarios of the case study demonstrate that the approach can identify critical scenarios within a limited number of closed-loop experiments.