PADriver: Towards Personalized Autonomous Driving

Genghua Kou, Fan Jia, Weixin Mao, Yingfei Liu, Ziheng Zhang, Yucheng Zhao, Osamu Yoshie, Tiancai Wang, Ying Li, Xiangyu Zhang

Keywords: Personalized, Planning, Autonomous Driving, MLLM

Abstract: In this paper, we propose PADriver, a novel closed-loop framework for personalized autonomous driving (PAD). Built upon Multi-modal Large Language Model (MLLM), PADriver takes streaming frames and personalized textual prompts as inputs. It autoaggressively performs scene understanding, danger level estimation and action decision. The predicted danger level reflects the risk of the potential action and provides an explicit reference for the final action, which corresponds to the preset personalized prompt. Moreover, we construct a closed-loop benchmark named PAD-Highway based on Highway-Env simulator to comprehensively evaluate the decision performance under traffic rules. The dataset contains 250 hours videos with high-quality annotation to facilitate the development of PAD behavior analysis. Experimental results on the constructed benchmark show that PADriver outperforms state-of-the-art approaches on different evaluation metrics, and enables various driving modes.

Primary Area: applications to computer vision, audio, language, and other modalities

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: 10030