Diffusion Models for Safety Validation of Autonomous Driving Systems
By: Juanran Wang , Marc R. Schlichting , Harrison Delecki and more
Potential Business Impact:
Creates realistic car mistakes for testing.
Safety validation of autonomous driving systems is extremely challenging due to the high risks and costs of real-world testing as well as the rarity and diversity of potential failures. To address these challenges, we train a denoising diffusion model to generate potential failure cases of an autonomous vehicle given any initial traffic state. Experiments on a four-way intersection problem show that in a variety of scenarios, the diffusion model can generate realistic failure samples while capturing a wide variety of potential failures. Our model does not require any external training dataset, can perform training and inference with modest computing resources, and does not assume any prior knowledge of the system under test, with applicability to safety validation for traffic intersections.
Similar Papers
Controllable Latent Diffusion for Traffic Simulation
Robotics
Creates realistic driving tests for self-driving cars.
Safety-Critical Traffic Simulation with Guided Latent Diffusion Model
Robotics
Makes self-driving cars safer by testing them.
DiffAD: A Unified Diffusion Modeling Approach for Autonomous Driving
Robotics
Cars drive themselves by creating driving pictures.