Robust Planning for Autonomous Vehicles with Diffusion-Based Failure Samplers

TL;DR

This paper introduces a diffusion-based failure sampler to generate collision scenarios for autonomous vehicles, enabling a robust planner that significantly reduces failure rates at intersections.

Contribution

The study develops a diffusion-based failure sampler distilled into a single-step model for fast inference, improving autonomous vehicle safety planning in high-risk traffic zones.

Findings

Robust planner reduces failure rate compared to baseline.

Single-step diffusion model achieves fast inference.

Effective generation of collision scenarios for safety testing.

Abstract

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.