Robust Planning for Autonomous Vehicles with Diffusion-Based Failure Samplers
This work addresses safety for autonomous vehicles in high-risk traffic zones like intersections, representing an incremental improvement in planning methods.
The study tackled the problem of autonomous vehicle safety at intersections by using a diffusion-based generative model to sample collision-causing sensor noise, resulting in a robust planner that significantly reduced failure and delay rates compared to a baseline controller.
High-risk traffic zones such as intersections are a major cause of collisions. This study leverages deep generative models to enhance the safety of autonomous vehicles in an intersection context. We train a 1000-step denoising diffusion probabilistic model to generate collision-causing sensor noise sequences for an autonomous vehicle navigating a four-way intersection based on the current relative position and velocity of an intruder. Using the generative adversarial architecture, the 1000-step model is distilled into a single-step denoising diffusion model which demonstrates fast inference speed while maintaining similar sampling quality. We demonstrate one possible application of the single-step model in building a robust planner for the autonomous vehicle. The planner uses the single-step model to efficiently sample potential failure cases based on the currently measured traffic state to inform its decision-making. Through simulation experiments, the robust planner demonstrates significantly lower failure rate and delay rate compared with the baseline Intelligent Driver Model controller.