An Application of Scenario Exploration to Find New Scenarios for the Development and Testing of Automated Driving Systems in Urban Scenarios

TL;DR

This paper proposes a method using Bayesian optimization and Gaussian processes to identify relevant and critical scenarios for testing automated driving systems in urban environments, enhancing scenario-based testing effectiveness.

Contribution

It introduces a novel approach to efficiently explore and select important scenarios for automated driving validation using probabilistic optimization techniques.

Findings

Bayesian optimization effectively identifies critical scenarios.

Six different metrics evaluated for scenario relevance.

Method applied to two urban intersection scenarios.

Abstract

Verification and validation are major challenges for developing automated driving systems. A concept that gets more and more recognized for testing in automated driving is scenario-based testing. However, it introduces the problem of what scenarios are relevant for testing and which are not. This work aims to find relevant, interesting, or critical parameter sets within logical scenarios by utilizing Bayes optimization and Gaussian processes. The parameter optimization is done by comparing and evaluating six different metrics in two urban intersection scenarios. Finally, a list of ideas this work leads to and should be investigated further is presented.