Visualization of scenario-based risk quantification of automated driving systems
conference paper
Before the introduction and deployment of an automated driving system, it is important to ensure that safety has not been compromised. A data-driven, scenario-based assessment is widely supported as a constituent for determining that the risk is acceptable. This work shows how visualization can help to identify what parts of the scenario space contributes most to the overall risk, where risk is a combination of exposure and severity. We also illustrate how to quantify the confidence in the estimated risk. This work helps developers to identify how to improve their system to improve its safety.
TNO Identifier
995504
Source title
JSAE 2024
Files
To receive the publication files, please send an e-mail request to TNO Repository.