Summary:

Vehicle autonomy capabilities such as driver assistance systems and partial automation are becoming available in the marketplace. However, to reach high or full automation capabilities, the most critical leap is required in the verification of AV technologies. Various studies show that the “real world” testing for verification is extremely time-consuming, ineffective, converges too slowly, and has no framework for certification. In addition to real-life testing, there are several AV testing methods such as Vehicle-in-the-loop (ViL) and driving simulators. All of these require a standard method for the identification of test scenarios and certification. The reduction of sample space for possible scenarios is an urgent requirement for proving the systems to be safe in a time and cost-efficient manner.

Results:

• A database of AV crashes is developed and can be found HERE.
• Ala’ J. Alnaser, Mustafa Ilhan Akbas, Arman Sargolzaei, Rahul Razdan, “Autonomous Vehicles Scenario Testing Framework and Model of Computation”.
• Saleem Sahawneh, Ala’ J. Alnaser, Mustafa Ilhan Akbas, Rahul Razdan, Arman Sargolzaei, “Autonomous Vehicles, An In-Depth Analysis of Major Crashes and Recommended Mitigation Plans”.
• Mustafa Akbas, Arman Sargolzaei, Ala Alnaser, Rahul Razdan, “Autonomous Vehicle Verification: Challenges, State-of-the-Art and a Framework for Future Directions”.