AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chai, Jinhao, Jiang, Anqing, Jiang, Hao, Mu, Shiyi, Gu, Zichong, Sun, Hao, Xu, Shugong
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909808400007168
author Chai, Jinhao
Jiang, Anqing
Jiang, Hao
Mu, Shiyi
Gu, Zichong
Sun, Hao
Xu, Shugong
author_facet Chai, Jinhao
Jiang, Anqing
Jiang, Hao
Mu, Shiyi
Gu, Zichong
Sun, Hao
Xu, Shugong
contents 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
format Preprint
id arxiv_https___arxiv_org_abs_2509_20253
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
Chai, Jinhao
Jiang, Anqing
Jiang, Hao
Mu, Shiyi
Gu, Zichong
Sun, Hao
Xu, Shugong
Robotics
Artificial Intelligence
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
title AnchDrive: Bootstrapping Diffusion Policies with Hybrid Trajectory Anchors for End-to-End Driving
topic Robotics
Artificial Intelligence
url https://arxiv.org/abs/2509.20253