Using Ensemble Diffusion to Estimate Uncertainty for End-to-End Autonomous Driving

Florian Wintel, Sigmund Hennum Høeg, Gabriel Kiss, Frank Lindseth

Keywords: Computer Vision, CARLA, Transformers, Diffusion models, Uncertainty, Autonomous Vehicles

Abstract:

End-to-end planning systems for autonomous driving are rapidly improving, especially in closed-loop simulation environments like CARLA. Many such driving systems either do not consider uncertainty as part of the plan itself or obtain it by using specialized representations that do not generalize. In this paper, we propose EnDfuser, an end-to-end driving system that uses a diffusion model as the trajectory planner.
EnDfuser effectively leverages complex perception information like fused camera and LiDAR features, through combining attention pooling and trajectory planning into a single diffusion transformer module.
Instead of committing to a single plan, EnDfuser produces a distribution of candidate trajectories ($128$ for our case) from a single perception frame through ensemble diffusion.
By observing the full set of candidate trajectories, EnDfuser provides interpretability for uncertain, multimodal future trajectory spaces.
Using this information can directly increase safety by introducing a simple safety rule that improves the system's driving score by $1.7\%$ on the LAV benchmark.
Our findings suggest that ensemble diffusion, used as a drop-in replacement for traditional point-estimate trajectory planning modules, can help improve the safety of driving decisions by modeling the uncertainty of the posterior trajectory distribution.

Serve As Reviewer: ~Florian_Wintel1

Submission Number: 22