Authors:
Philip Elspas
1
;
Jonas Lindner
1
;
Mathis Brosowsky
1
;
Johannes Bach
1
and
Eric Sax
2
Affiliations:
1
Dr. Ing. h.c. F. Porsche AG, Weissach, Germany
;
2
Karlsruhe Institute of Technology, Karlsruhe, Germany
Keyword(s):
Scenario Database, Scenario Detection, Automated Driving, Data-driven Development.
Abstract:
With increasing capabilities of Advanced Driver Assistance Systems (ADAS) and Automated Driving Systems (ADS) established automotive development processes are challenged. The specification phase faces an open world problem, with an exploding space of different driving situations and various corner cases. Scenario-based development provides a systematic approach to describe the operational design domain of ADAS and ADS with scenarios, that can be used along the development process until system qualification. However, deriving all relevant scenarios, that need to be considered remains an open challenge. Recorded driving data provides a valuable source of real-world scenarios with highest validity. A database with such scenarios can be used to validate requirements early in the specification phase. For system qualification, detected scenarios can be extended with test conditions or can be (re-)simulated. Furthermore, function development can leverage a scenario database for data-driven
and machine learning methods. While a scenario database is a common concept most approaches remain abstract and vague in the description. In this work we analyze requirements and expectations on a scenarios database and propose a detailed design and concept. For the necessary scenario detection, we suggest a new method to identify complex pattern in multivariate time series based on regular expressions.
(More)