This content is not included in your SAE MOBILUS subscription, or you are not logged in.
Self-Driving Car Safety Quantification via Component-Level Analysis
- Juozas Vaicenavicius - Sensmetry UAB, Lithuania ,
- Tilo Wiklund - Sensmetry UAB, Lithuania Uppsala University, Sweden ,
- Auste Grigaite - Sensmetry UAB, Lithuania ,
- Antanas Kalkauskas - Sensmetry UAB, Lithuania ,
- Ignas Vysniauskas - Sensmetry UAB, Lithuania ,
- Steve Dale Keen - Sensmetry UAB, Lithuania
ISSN: 2574-0741, e-ISSN: 2574-075X
Published March 29, 2021 by SAE International in United States
Citation: Vaicenavicius, J., Wiklund, T., Grigaite, A., Kalkauskas, A. et al., "Self-Driving Car Safety Quantification via Component-Level Analysis," SAE Intl. J CAV 4(1):35-45, 2021, https://doi.org/10.4271/12-04-01-0004.
In this article, we present a rigorous modular statistical approach for arguing the safety or its insufficiency of an autonomous vehicle through a concrete illustrative example. The methodology relies on making appropriate quantitative studies of the performance of constituent components. We explain the importance of sufficient and necessary conditions at the component level for the overall safety of the vehicle, as well as the cost-saving benefits of the approach. A simple concrete automated braking example studied illustrates how the separate perception system and Operational Design Domain (ODD) statistical analyses can be used to prove or disprove safety at the vehicle level.