Chain-of-Thought for Autonomous Driving: A Comprehensive Survey and Future Prospects

TL;DR

This paper provides a comprehensive survey of Chain-of-Thought reasoning in autonomous driving, analyzing its benefits, challenges, and future prospects, and introduces a repository of related literature and projects.

Contribution

It offers a systematic review of CoT methods in autonomous driving and proposes integrating CoT with self-learning for system evolution.

Findings

CoT enhances reasoning in complex driving scenarios

Systematic analysis of motivations and challenges of CoT in autonomous driving

A publicly available repository of related literature and projects

Abstract

The rapid evolution of large language models in natural language processing has substantially elevated their semantic understanding and logical reasoning capabilities. Such proficiencies have been leveraged in autonomous driving systems, contributing to significant improvements in system performance. Models such as OpenAI o1 and DeepSeek-R1, leverage Chain-of-Thought (CoT) reasoning, an advanced cognitive method that simulates human thinking processes, demonstrating remarkable reasoning capabilities in complex tasks. By structuring complex driving scenarios within a systematic reasoning framework, this approach has emerged as a prominent research focus in autonomous driving, substantially improving the system's ability to handle challenging cases. This paper investigates how CoT methods improve the reasoning abilities of autonomous driving models. Based on a comprehensive literature review, we present a systematic analysis of the motivations, methodologies, challenges, and future research directions of CoT in autonomous driving. Furthermore, we propose the insight of combining CoT with self-learning to facilitate self-evolution in driving systems. To ensure the relevance and timeliness of this study, we have compiled a dynamic repository of literature and open-source projects, diligently updated to incorporate forefront developments. The repository is publicly available at https://github.com/cuiyx1720/Awesome-CoT4AD.