Multimodal Action Diffusion for Robust End-to-End Autonomous Driving
For autonomous driving researchers, this work demonstrates that modeling multimodal action distributions is both practically efficient and conceptually essential for robust end-to-end driving, challenging the prevailing deterministic trajectory prediction paradigm.
The paper introduces the Action Diffusion Transformer (ADT) for end-to-end autonomous driving, which models multimodal action distributions instead of deterministic outputs. ADT achieves state-of-the-art performance on the Bench2Drive benchmark with ten times lower latency, showing that action multimodality improves driving performance, representation quality, and training stability.
End-to-End Autonomous Driving (E2E-AD) systems have largely converged on predicting intermediate trajectory waypoints, delegating final control to hand-crafted controllers with GPS access. Direct control-signal prediction (outputting throttle, steer and brake in an end-to-end fashion) remains underexplored, and critically, the role of action multimodality in such systems is not well understood. We argue that moving beyond deterministic, single-action outputs is not merely a modelling choice, but a key driver of driving performance, representational quality, and training stability. To validate this, we introduce the Action Diffusion Transformer (ADT), an anchor-free diffusion transformer trained with a MSE objective that natively models the multimodal distribution of plausible driving actions. Rather than committing to a single deterministic command, ADT generates K action candidates and selects the most suitable one at inference via Nearest Neighbour Matching (NNM). Beyond strong benchmark numbers, we show that action multimodality yields measurable benefits in learned representations and behavioral consistency, effects that deterministic architectures cannot replicate. ADT surpasses previous state-of-the-art on the challenging closed-loop Bench2Drive benchmark while achieving ten times lower latency, demonstrating that expressive, multimodal action modelling is both practically efficient and conceptually essential for robust end-to-end driving.