The introduction of the SOTIF (Safety of the Intended Functionality) standard has brought a fundamental shift in the safety case for higher autonomous vehicles (AVs). The main challenge for autonomous vehicle system development to meet the SOTIF standard is to have a robust and scalable way to automatically generate unknown-unsafe scenarios and evaluate the system under test in such scenarios. The more scenarios that can be evaluated, the lesser the impact of the unknown-unsafe scenarios on system safety.
Our Critical Scenario Creation methodology is a proprietary and patented methodology that systematically and automatically generates unsafe-unknown scenarios for a specific operational design domain based on a map of that scene and recorded data. We've developed a severity indicator to measure criticality, combining a criticality KPI with a proprietary KPI for novelty. The combination of these two generates a normalized severity value which indicates how unsafe and unknown a scenario is for the vehicle under test.
By adopting and implementing the Critical Scenario Creation process, automotive OEMs and autonomous vehicle (AV) suppliers can have a methodology to generate unknown-unsafe scenarios derived from the Safety of the Intended Functionality (SOTIF) standards automatically.
Explore the content below to learn more about our Critical Scenario Creation methodology that we offer as a service based on the Simcenter Prescan360 toolchain.