AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
This work addresses efficiency and generalization challenges in autonomous driving planning, representing an incremental improvement over existing diffusion-based methods.
The paper tackles the high computational cost of generative models in end-to-end autonomous driving by proposing AnchDrive, a framework that bootstraps a diffusion policy with hybrid trajectory anchors, achieving state-of-the-art results on the NAVSIM benchmark.
End-to-end multi-modal planning has become a transformative paradigm in autonomous driving, effectively addressing behavioral multi-modality and the generalization challenge in long-tail scenarios. We propose AnchDrive, a framework for end-to-end driving that effectively bootstraps a diffusion policy to mitigate the high computational cost of traditional generative models. Rather than denoising from pure noise, AnchDrive initializes its planner with a rich set of hybrid trajectory anchors. These anchors are derived from two complementary sources: a static vocabulary of general driving priors and a set of dynamic, context-aware trajectories. The dynamic trajectories are decoded in real-time by a Transformer that processes dense and sparse perceptual features. The diffusion model then learns to refine these anchors by predicting a distribution of trajectory offsets, enabling fine-grained refinement. This anchor-based bootstrapping design allows for efficient generation of diverse, high-quality trajectories. Experiments on the NAVSIM benchmark confirm that AnchDrive sets a new state-of-the-art and shows strong generalizability