Discovering Avoidable Planner Failures of Autonomous Vehicles using Counterfactual Analysis in Behaviorally Diverse Simulation
This work addresses the critical problem of exhaustively testing autonomous vehicle planners for safety-critical failures, which is important for developers and regulators to ensure safe deployment.
This paper introduces a planner testing framework for autonomous vehicles that uses behaviorally diverse simulations to generate and characterize dynamic scenarios leading to collisions. It distinguishes between unavoidable and avoidable accidents to identify planner-specific defects, demonstrating its ability to find a wide range of critical planner failures in complex multi-agent intersection scenarios.
Automated Vehicles require exhaustive testing in simulation to detect as many safety-critical failures as possible before deployment on public roads. In this work, we focus on the core decision-making component of autonomous robots: their planning algorithm. We introduce a planner testing framework that leverages recent progress in simulating behaviorally diverse traffic participants. Using large scale search, we generate, detect, and characterize dynamic scenarios leading to collisions. In particular, we propose methods to distinguish between unavoidable and avoidable accidents, focusing especially on automatically finding planner-specific defects that must be corrected before deployment. Through experiments in complex multi-agent intersection scenarios, we show that our method can indeed find a wide range of critical planner failures.