The Role of World Models in Shaping Autonomous Driving: A Comprehensive Survey

TL;DR

This survey reviews the development and application of Driving World Models (DWM) in autonomous driving, highlighting recent progress, categorization by scene modality, and discussing future research directions.

Contribution

It provides a comprehensive overview of DWM approaches, datasets, metrics, and applications, offering insights to foster broader adoption in autonomous driving.

Findings

Categorization of DWM approaches by scene modality

Evaluation of DWM performance across tasks

Discussion of limitations and future directions

Abstract

The Driving World Model (DWM), which focuses on predicting scene evolution during the driving process, has emerged as a promising paradigm in the pursuit of autonomous driving (AD). DWMs enable AD systems to better perceive, understand, and interact with dynamic driving environments. In this survey, we provide a comprehensive overview of the latest progress in DWM. First, we review the DWM ecosystem, which is constructed using mainstream simulators, high-impact datasets, and various metrics that evaluate DWMs across multiple dimensions. We then categorize existing approaches based on the modalities of the predicted scenes, including video, point cloud, occupancy, latent feature, and traffic map, and summarize their specific applications in AD research. In addition, the performance of representative approaches across generating and driving tasks is presented. Finally, we discuss the potential limitations of current research and propose future directions. This survey provides valuable insights into the development and application of DWM, fostering its broader adoption in AD. The relevant papers are collected at https://github.com/LMD0311/Awesome-World-Model.