How Do We Fail? Stress Testing Perception in Autonomous Vehicles
This addresses the challenge of robust perception for autonomous vehicles in adverse weather, which is incremental as it builds on existing validation methods.
The paper tackled the problem of validating LiDAR-based perception systems for autonomous vehicles in adverse weather by developing a reinforcement learning method to find likely failures in object tracking and trajectory prediction, showing that it identifies high likelihood failures with smaller input disturbances compared to baselines across real-world driving scenarios.
Autonomous vehicles (AVs) rely on environment perception and behavior prediction to reason about agents in their surroundings. These perception systems must be robust to adverse weather such as rain, fog, and snow. However, validation of these systems is challenging due to their complexity and dependence on observation histories. This paper presents a method for characterizing failures of LiDAR-based perception systems for AVs in adverse weather conditions. We develop a methodology based in reinforcement learning to find likely failures in object tracking and trajectory prediction due to sequences of disturbances. We apply disturbances using a physics-based data augmentation technique for simulating LiDAR point clouds in adverse weather conditions. Experiments performed across a wide range of driving scenarios from a real-world driving dataset show that our proposed approach finds high likelihood failures with smaller input disturbances compared to baselines while remaining computationally tractable. Identified failures can inform future development of robust perception systems for AVs.