Citation

Berk M, Schubert O, Kroll HM, Buschardt B, Straub D. SAE Int. J. Transp. Safety 2020; 8(1): 49-74.

Copyright

(Copyright © 2020, SAE International)

DOI

10.4271/09-08-01-0004

PMID

unavailable

Abstract

The development of automated driving systems (ADS) necessitates procedures to validate system safety. The reliability of an ADS's environment perception provided by lidar, radar, and camera sensors is of special interest in this context, because perception errors can be safety-critical. In this article, we formalize the reliability-based validation of environment perception for safe automated driving and discuss associated challenges. We describe a potential solution to a perception reliability validation by deriving performance requirements at the sensor level. We then summarize statistical methods to learn sensor perception reliabilities in field tests, on proving grounds, and through virtual simulations. With the developed safety validation framework, we show that, potentially, one can validate the safety of an ADS with feasible test effort.

Language: en