DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model

Zhenhua Xu, Yujia Zhang, Enze Xie, Zhen Zhao, Yong Guo, Kwan-Yee K. Wong, Zhenguo Li, Hengshuang Zhao

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.

Keywords: Interpretable autonomous driving, large language model, robotics, computer vision

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Abstract:

In the past decade, autonomous driving has experienced rapid development in both academia and industry. However, its limited interpretability remains a significant unsolved problem, severely hindering autonomous vehicle commercialization and further development. Previous approaches utilizing small language models have failed to address this issue due to their lack of flexibility, generalization ability, and robustness. Recently, multimodal large language models (LLMs) have gained considerable attention from the research community for their capability to process and reason non-text data (e.g., images and videos) by text.
In this paper, we present DriveGPT4, an interpretable end-to-end autonomous driving system utilizing LLMs. DriveGPT4 is capable of interpreting vehicle actions and providing corresponding reasoning, as well as answering diverse questions posed by human users for enhanced interaction. Additionally, DriveGPT4 predicts vehicle low-level control signals in an end-to-end fashion. These capabilities stem from a customized visual instruction tuning dataset specifically designed for autonomous driving. To the best of our knowledge, DriveGPT4 is the first work focusing on interpretable end-to-end autonomous driving. When evaluated on multiple tasks alongside conventional methods and video understanding LLMs, DriveGPT4 demonstrates superior qualitative and quantitative performance. Additionally, DriveGPT4 can be generalized in a zero-shot fashion to accommodate more unseen scenarios.

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: 7421