A Survey on Data-Driven Scenario Generation for Automated Vehicle Testing

Automated driving is a promising tool for reducing traffic accidents. While some companies claim that many cutting-edge automated functions have been developed, how to evaluate the safety of vehicles remains an open question, which has become crucial bottleneck. Scenario-based testing introduced test vehicles, and much progress achieved. data-driven knowledge-based approaches are hot research topics, this survey mainly about Data-Driven Scenario Generation (DDSG) vehicle testing. Rather than describe contributions every study respectively, in survey, methodologies from various studies anatomized as solutions several significant problems compared with each other. This way, scholars engineers can quickly find state-of-the-art issues they might encounter. Furthermore, critical challenges hinder DDSG described, responding presented at end survey.