Purpose and goal
ASVAM is a collaboration between AstaZero, University of California, Berkeley and Einride that develops AI-supported, scenario-based validation for automated mobility. By combining use cases, AI-based scenario analysis, simulation and physical testing, a more systematic, scalable and data-driven method for validating safety-critical systems is created. The project builds on AVATAR and strengthens the long-term R&D collaboration between Sweden and the US in automated mobility.
Expected effects and result
ASVAM will have developed and evaluated a common methodology that links AI-supported scenario analysis to structured test planning, simulation and physical testing. The result is not a finished product but a validated method that shows how industrial use cases can be translated into scenario families, parameterized scenario variants and executable test cases in the AstaZeros Test Planning Factory. The project takes the step from concept to practical method development and initial validation.
Planned approach and implementation
ASVAM develops a common workflow that connects industrial use cases and AI-supported scenario analysis to test planning, simulation and physical testing. The project develops scenario families for ADAS/ADS, uses AI/LLM-based scenario generation and prioritization, and translation into parameterized test cases. This includes simulation, feedback for scenario improvement, interoperability between Swedish and American methods, and recommendations for future safety validation.
The project description has been provided by the project members themselves and the text has not been looked at by our editors.
