LLMs in Autonomous Driving — Part 1
!! Note: AI tools are used in this blog post!
In this series of blog posts, as I work on my PhD topic on multi-agent decision-making in self-driving cars, I will review some papers related to the usage of LLMs in the field of Autonomous Driving. Let’s start with some survey papers.
Here are the other parts of this series:
A Survey on Multimodal Large Language Models for Autonomous Driving
The paper “A Survey on Multimodal Large Language Models for Autonomous Driving” provides a systematic investigation into the use of Multimodal Large Language Models (MLLMs) in autonomous driving. It covers the background of MLLMs, their development, and their application in driving systems, transportation, and map systems. The paper reviews existing tools, datasets, and benchmarks, and summarizes works from the 1st WACV Workshop on Large Language and Vision Models for Autonomous Driving. It discusses key challenges and opportunities in integrating MLLMs into autonomous driving systems, aiming to promote further development in this field. For a detailed exploration, you can view the full paper.
Resources:
LLM4Drive: A Survey of Large Language Models for Autonomous Driving
The paper titled “LLM4Drive: A Survey of Large Language Models for Autonomous Driving” provides a systematic review of using large language models (LLMs) in autonomous driving. It covers various areas including planning & control, perception, question answering, and generation within autonomous driving systems. The study evaluates current technological advancements, outlines principal challenges, and prospective directions for the field. Datasets reviewed span multiple aspects of autonomous driving, focusing on how LLMs can enhance capabilities in open-world understanding, reasoning, and few-shot learning, crucial for improving autonomous driving technologies.
Resources:
In the next parts, I will go into more survey papers and also the interesting papers mentioned above and those survey papers and also what I find interesting and related from other resources.
Thank you for taking the time to read my post. If you found it helpful or enjoyable, please consider giving it a like and sharing it with your friends. Your support means the world to me and helps me to continue creating valuable content for you.
