This repository is a curated list of research papers and resources focused on the application of Large Language Models (LLMs) in Autonomous Driving (LLM4AD). It aims to track the frontier of LLM4AD research, providing a valuable resource for researchers and engineers in the field.

How It Works

The repository categorizes LLM4AD research based on application perspectives: planning, perception, question answering, and generation. It highlights the motivation for using LLMs in autonomous driving, which is to achieve human-like driving competence by leveraging vast amounts of data and advanced deep learning techniques, addressing challenges like the sim2real gap and the long-tailed nature of driving data.

Quick Start & Requirements

• Installation: No installation is required as this is a resource list.
• Requirements: Access to the internet to view linked papers and resources.
• Links:
  • Survey Paper: https://arxiv.org/abs/2311.01043
  • GitHub Repository: https://github.com/Thinklab-SJTU/Awesome-LLM4AD

Highlighted Details

• Continuously updated list of LLM4AD research papers.
• Categorization of research by task (planning, perception, QA, generation).
• Includes links to papers, code, datasets, and project pages.
• Provides BibTeX for citing the survey paper.

Maintenance & Community

• Maintained by SJTU-ReThinklab.
• Open to contributions via Pull Requests.
• Contact emails provided for suggestions: yangzhenjie@sjtu.edu.cn or jiaxiaosong@sjtu.edu.cn.

Licensing & Compatibility

• License: Apache 2.0 License.
• Compatibility: Permissive license suitable for commercial use and integration into closed-source projects.

Limitations & Caveats

This repository is a curated list and does not contain executable code or models itself. The actual implementation and performance depend on the individual research papers linked within.