Maneuver and Data Optimization for High Confidence Testing of Future Automotive Cyber-Physical Systems
Our research addresses urgent challenges in high confidence testing of automotive systems due to on-going and anticipated introduction of advanced, connected, and autonomous vehicle technologies. We have pursued the development of tools for maneuver and data optimization to determine test trajectories and scenarios to facilitate vehicle testing. Our approaches exploit game theoretic traffic interaction modeling to inform in-traffic relevant trajectories, model-free optimization to identify trajectories falsifying time domain specifications, and the development of Smart Black Box to identify and record high-priority data for diagnostics, testing and validation. This project is a GOALI involving investigators from the University of Michigan and an industrial partner AVL.
- PDF document
- 12.87 MB
- 51 downloads
- Download
- PDF version
- Printer-friendly version