Assessing the Completeness of Traffic Scenario Categories for Automated Highway Driving Functions via Cluster-based Analysis

Personal use of this material is permitted. Abstract-- The ability to operate safely in increasingly complex traffic scenarios is a fundamental requirement for Automated Driving Systems (ADS). T o support this objective, this work introduces a pipeline for traffic scenario clustering and the analysis of scenario category completeness. The Clustering V ector Quantized - V ariational Autoencoder (CVQ-V AE) is employed for the clustering of highway traffic scenarios and utilized to create various catalogs with differing numbers of traffic scenario categories. Subsequently, the impact of the number of categories on the completeness considerations of the traffic scenario categories is analyzed. The results show an outperforming clustering performance compared to previous work. The trade-off between cluster quality and the amount of required data to maintain completeness is discussed based on the publicly available highD dataset. A key challenge for the safe release of automated driving is equipping Automated Driving System (ADS) functions with the ability to accurately interpret and respond to the wide range of driving conditions they encounter. To ensure the safety of the system and maintain compliance with legal and regulatory requirements, this challenge is typically addressed through the concept of an Operational Design Domain (ODD).