all AI news
Toward Unsupervised Test Scenario Extraction for Automated Driving Systems from Urban Naturalistic Road Traffic Data. (arXiv:2202.06608v2 [cs.SE] UPDATED)
cs.LG updates on arXiv.org arxiv.org
Scenario-based testing is a promising approach to solve the challenge of
proving the safe behavior of vehicles equipped with automated driving systems.
Since an infinite number of concrete scenarios can theoretically occur in
real-world road traffic, the extraction of scenarios relevant in terms of the
safety-related behavior of these systems is a key aspect for their successful
verification and validation. Therefore, a method for extracting multimodal
urban traffic scenarios from naturalistic road traffic data in an unsupervised
manner, minimizing the …
arxiv automated behavior challenge concrete data driving extraction multimodal safety systems terms test testing traffic unsupervised validation verification world