HE-Drive: Human-Like End-to-End Driving with Vision Language Models

Junming Wang, Xingyu Zhang, Zebin Xing, songen gu, Xiaoyang Guo, Yang Hu, Ziying Song, Qian Zhang, Xiaoxiao Long, Wei Yin

Keywords: autonomous driving, motion planning, trajectory generation, diffusion model

Abstract: In this paper, we propose HE-Drive: the first human-like-centric end-to-end autonomous driving system to generate trajectories that are both temporally consistent and comfortable. Recent studies have shown that imitation learning-based planners and learning-based trajectory scorers can effectively generate and select accuracy trajectories that closely mimic expert demonstrations. However, such trajectory planners and scorers face the dilemma of generating temporally inconsistent and uncomfortable trajectories. To solve the above problems, Our HE-Drive first extracts key 3D spatial representations through sparse perception, which then serves as conditional inputs for a Conditional Denoising Diffusion Probabilistic Models (DDPMs)-based motion planner to generate temporal consistency multi-modal trajectories. A Vision-Language Models (VLMs)-guided trajectory scorer subsequently selects the most comfortable trajectory from these candidates to control the vehicle, ensuring human-like end-to-end driving. Experiments show that HE-Drive not only achieves state-of-the-art performance (i.e., reduces the average collision rate by 71% than VAD) and efficiency (i.e., 1.9X faster than SparseDrive) on the challenging nuScenes and OpenScene datasets but also provides the most comfortable driving experience on real-world data.

Primary Area: applications to robotics, autonomy, planning

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.

Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 905