Citation

Guyonvarch L, Hermitte T, Kroger R, Chauvel C, Arnoux E, Geronimi S. Transp. Res. Proc. 2023; 72: 9-16.

Copyright

(Copyright © 2023, Elsevier Publications)

DOI

10.1016/j.trpro.2023.11.316

PMID

unavailable

Abstract

Automated systems such as SAE AD level 2 and higher, face the difficult challenge of proving safe in the field, in actual traffic conditions. Scenario-based simulation approaches are, therefore, necessary complements to the traditional approach, allowing computation of a controlled diversity of key variables in many iterations in a safe, fast, and documented way. ADSCENE capitalizes scenarios to be considered during the design & validation phases of Advanced Driving Assistance Systems as well as Automated Driving systems into a common data base. Several data sources are used to fill in ADSCENE: near crash data, normal driving data, scenarios defined by experts in AD/S ADAS, scenarios from the regulations. This paper describes how accident data complements the scope of the other sources and the methodology used to extract and code relevant accidents into ADSCENE.

Language: en

Keywords

ADAS validation; Road safety Accident analysis; scenarios data base