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

Abstract

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