AV/ADAS Safety Critical Testing Scenario Generation from Vehicle Crash Data
2022-01-0104
03/29/2022
- Event
- Content
- This research leverages publicly available crash data to construct safety critical scenarios focusing primarily on level 3 autonomous driving systems (ADS) safety assessment under highway driving conditions. NHTSA’s Crashworthiness Data System (CDS) has a rich dataset of a representative crashes of varying fatalities randomly sampled from across the country. Each of these datasets includes the storyline, road geometry information, detailed description of actors involved in the crash, weather information, scene diagrams, crash images and a myriad of other crash specific details. The methodology adopted aims to generate critical scenarios from real-world driving to complement the existent regulatory tests for validation of L3 ADS. For this work, a four-step approach was adopted to extract safety critical scenarios from crash data. Firstly, development of a methodology to filter crash cases relevant to the scope and download pdf files, and numerical crash data from the CDS website. Then, the numerical data is utilized to characterize cases into crash categories. Thirdly, the numeric data and pdf data are used to combine multiple crash cases into fewer representative ‘logical scenarios’ which define the road network, number and type of actors and the storyline. Finally, the generated logical scenarios are used to develop specific safety critical scenarios. The key outcome of this research is a set of safety critical scenarios based on real world crash data, categorized according to specific ADS control objectives that can be utilized to validate ADS functionalities.
- Citation
- Kibalama, D., Tulpule, P., and Chen, B., "AV/ADAS Safety Critical Testing Scenario Generation from Vehicle Crash Data," SAE Technical Paper 2022-01-0104, 2022, .