Automated scenario generation for testing advanced driver assistance systems based on post-processed reference laser scanner data

Abstract

Efficient testing of advanced driver assistance systems is a crucial element for guaranteeing the safe operation of such systems on the road. This paper presents the use of advanced perception systems for automated generation of simulated driving scenarios. The authors describe their progress in the fields of laser scanning processing for reference generation, for both relevant users and road information, and present the entire pipeline for constructing simulated virtual scenarios from real data that can be imported, manipulated and used within a virtual environment.