语言模型与自动驾驶：历史阅读清单

原整理者：Jingxin Wang（王京新）。原记录整理于 2024 年（据 Git），文献检索范围由原记录标为 2022–2025 年。2026-10-22 整理并入个人主页。内容保留原记录的研究背景与判断；文献覆盖以原记录时期为准。

文献检索范围

谷歌学术检索（标题）：intitle:(autonomous driving OR driving OR self-driving AND LLM OR Large Language Model OR Vision-Language OR Agent OR Multi-Modal) 时间范围：2022年——2025年

arXiv Xplorer检索(全文)：LLM 、large language models、vision language models、AND autonomous driving 按照相似性排序 时间范围：2022年——2024年

➢综述类（★推荐指数）

★★★★ LLM4Drive: A Survey of Large Language Models for Autonomous Driving paper code
Authors: Zhenjie Yang, Xiaosong Jia, Hongyang Li, Junchi Yan
institution: School of AI and Department of CSE, Shanghai Jiao Tong University, OpenDriveLab
year: 2023
eprint: [v4] Mon, 12 Aug 2024 11:53:28 UTC (538 KB)

★★★★★ A Survey on Multimodal Large Language Models for Autonomous Driving paper code

Authors: Cui, Can and Ma, Yunsheng and Cao, Xu and Ye, Wenqian and Zhou, Yang and Liang, Kaizhao and Chen, Jintai and Lu, Juanwu and Yang, Zichong and Liao, Kuei-Da and others
institution: Purdue University, West Lafayette, IN, USA; Tencent T Lab, Beijing, China; University of Illinois Urbana-Champaign, Champaign, IL, USA

year: 2024
booktitle: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

★★★★ Will Large Language Models be a Panacea to Autonomous Driving? paper

Authors:Yuxuan Zhu, Shiyi Wang, Wenqing Zhong, Nianchen Shen, Yunqi Li, Siqi Wang, Zhiheng Li, Cathy Wu, Zhengbing He, Li Li

institution:Department of Automation, Tsinghua University, Beijing, China

year: 2024

eprint:arxiv

Authors: Sonda Fourati, Wael Jaafar, Noura Baccar, Safwan Alfattani

Institution:Mediterranean Institute of Technology (MedTech), Tunis, Tunisia、

Year: 2024

Publication Title: arXiv preprint arXiv:2409.10484

➢研究类（★推荐指数）

Authors: Chen, Long; Sinavski, Oleg; Hünermann, Jan; Karnsund, Alice; Willmott, Andrew James; Birch, Danny; Maund, Daniel; Shotton, Jamie
Institution: Wayve

Year: 2024

Publication Title: 2024 IEEE International Conference on Robotics and Automation (ICRA)

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

Institution:The University of Hong Kong、Zhejiang University、Huawei Noah’s Ark Lab

Year: 2024

Publication Title: IEEE Robotics and Automation Letters

Authors: Yunsheng Ma, Can Cui, Xu Cao, Wenqian Ye, Peiran Liu, Juanwu Lu, Amr Abdelraouf, Rohit Gupta, Kyungtae Han, Aniket Bera

Institution:Purdue University、University of Illinois Urbana-Champaign、University of Virginia

Year: 2024

Publication Title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Authors: Jiageng Mao, Junjie Ye, Yuxi Qian, Marco Pavone, Yue Wang

Institution:University of Southern California、Stanford University

Year: 2023

Publication Title: arXiv preprint arXiv:2311.10813

Authors: Xingcheng Zhou, Mingyu Liu, Bare Luka Zagar, Ekim Yurtsever, Alois C. Knoll

Institution:

Year: 2023

Publication Title: arXiv preprint arXiv:2310.14414

Authors: Shihao Wang, Zhiding Yu, Xiaohui Jiang, Shiyi Lan, Min Shi, Nadine Chang, Jan Kautz, Ying Li, Jose M. Alvarez

Institution:Beijing Inst of Tech、NVIDIA

Year: 2024

Publication Title: arXiv preprint arXiv:2405.01533

Authors: Daocheng Fu, Xin Li, Licheng Wen, Min Dou, Pinlong Cai, Botian Shi, Yu Qiao

Institution:Shanghai AI Lab

Year: 2024

Publication Title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

Authors: Yidong Huang, Jacob Sansom, Ziqiao Ma, Felix Gervits, Joyce Chai

Institution:University of Michigan、Army Research Lab

Year: 2024

Publication Title: arXiv preprint arXiv:2406.03008

Authors: Licheng Wen, Daocheng Fu, Xin Li, Xinyu Cai, Tao Ma, Pinlong Cai, Min Dou, Botian Shi, Liang He, Yu Qiao

Institution:Shanghai Artificial Intelligence Laboratory

Year: 2023

Publication Title: arXiv preprint arXiv:2309.16292

Authors: Yuxi Wei, Zi Wang, Yifan Lu, Chenxin Xu, Changxing Liu, Hao Zhao, Siheng Chen, Yanfeng Wang

Institution:Shanghai Jiao Tong University、Shanghai AI Laboratory

Year: 2024

Publication Title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition

Authors: Xiaoyu Tian, Junru Gu, Bailin Li, Yicheng Liu, Chenxu Hu, Yang Wang, Kun Zhan, Peng Jia, Xianpeng Lang, Hang Zhao

Institution:IIIS, Tsinghua University、Li Auto

Year: 2024

Publication Title: arXiv preprint arXiv:2402.12289

Authors: SungYeon Park, MinJae Lee, JiHyuk Kang, Hahyeon Choi, Yoonah Park, Juhwan Cho, Adam Lee, DongKyu Kim

Institution:Seoul National University、University of California, Berkeley

Year: 2024

Publication Title: Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision

Authors: Yuan Chen, Zi-han Ding, Ziqin Wang, Yan Wang, Lijun Zhang, Si Liu

Institution: Beihang University、AIR, Tsinghua University

Year: 2024

Publication Title: arXiv preprint arXiv:2406.14556

Authors: Yixuan Wang, Ruochen Jiao, Chengtian Lang, Sinong Simon Zhan, Chao Huang, Zhaoran Wang, Zhuoran Yang, Qi Zhu

Institution: Northwestern University

Year: 2023

Publication Title: Arxiv

Authors: Zhenjie Yang, Xiaosong Jia, Hongyang Li, Junchi Yan

Institution: Shanghai Jiao Tong University

Year: 2023

Publication Title: Arxiv

Authors: Peiru Zheng, Yun Zhao, Zhan Gong, Hong Zhu, Shaohua Wu

Institution: Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences

Year: 2024

Publication Title: Arxiv

LLM and Existing AD Challenges paper

• Solution Insight A: LLMs have demonstrated significant capability in solving the corresponding challenge, and comprehensive solution based on LLMs can be expected.
• Solution Insight B: LLMs have demonstrated capability in solving the corresponding challenge, but the challenge may not be fully solved given current drawbacks of LLMs.
• Solution Insight C: LLMs can improve performance in related tasks, but might not be able to solve the key problems within the challenges.

LLMs在AD任务中的表现主要源于以下几个方面：

1. Common Sense.
2. Reasoning Capability.
3. Communication ability.(就是与人类互动交流的能力，一定程度上解决了神经网络作为黑盒模型的问题，可信问题)

➢ LLM Related AD Datasets.

Reason2Drive
NuPrompt
DriveGPT4
LingoQA
WEDGE
DriveLM-nuScenes
DriveLM-Carla
NuScenes-QA
Rank2Tell
LaMPilot
MAPLM
LMDrive Nuscenes OpenLane-V2 OmniDrive

原始记录

来源：OpenVisualLab 原始笔记。原仓库、版本差异及未完成的记录保留在本地历史档案。