Adaptive Stress Testing with Reward Augmentation for Autonomous Vehicle Validation

Anthony Corso1, Peter Du2, Katherine Driggs-Campbell2, Mykel Kochenderfer1

  • 1Stanford University
  • 2University of Illinois at Urbana-Champaign



Special Session


11:00 - 12:00 | Mon 28 Oct | Gallery Room 4 | MoC-T7

Special Session on Solving the Automated Vehicle Safety Assurance Challenge (I)

Full Text


Determining possible failure scenarios is a critical step in the evaluation of autonomous vehicle systems. Real world vehicle testing is commonly employed for autonomous vehicle validation, but the costs and time requirements are high. Consequently, simulation driven methods such as Adaptive Stress Testing (AST) have been proposed to aid in validation. AST formulates the problem of finding the most likely failure scenarios as a Markov decision process, which can be solved using reinforcement learning. In practice, AST tends to find scenarios where failure is unavoidable and tends to repeatedly discover the same types of failures of a system. This work addresses these issues by encoding domain relevant information into the search procedure. With this modification, the AST method discovers a larger and more expressive subset of the failure space when compared to the original AST formulation. We show that our approach is able to identify useful failure scenarios of an autonomous vehicle policy.

Additional Information

No information added


No videos found