A Survey on Vision-Language-Action Models for Autonomous Driving

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jiang, Sicong, Huang, Zilin, Qian, Kangan, Luo, Ziang, Zhu, Tianze, Zhong, Yang, Tang, Yihong, Kong, Menglin, Wang, Yunlong, Jiao, Siwen, Ye, Hao, Sheng, Zihao, Zhao, Xin, Wen, Tuopu, Fu, Zheng, Chen, Sikai, Jiang, Kun, Yang, Diange, Choi, Seongjin, Sun, Lijun
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866912458234396672
author Jiang, Sicong
Huang, Zilin
Qian, Kangan
Luo, Ziang
Zhu, Tianze
Zhong, Yang
Tang, Yihong
Kong, Menglin
Wang, Yunlong
Jiao, Siwen
Ye, Hao
Sheng, Zihao
Zhao, Xin
Wen, Tuopu
Fu, Zheng
Chen, Sikai
Jiang, Kun
Yang, Diange
Choi, Seongjin
Sun, Lijun
author_facet Jiang, Sicong
Huang, Zilin
Qian, Kangan
Luo, Ziang
Zhu, Tianze
Zhong, Yang
Tang, Yihong
Kong, Menglin
Wang, Yunlong
Jiao, Siwen
Ye, Hao
Sheng, Zihao
Zhao, Xin
Wen, Tuopu
Fu, Zheng
Chen, Sikai
Jiang, Kun
Yang, Diange
Choi, Seongjin
Sun, Lijun
contents The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.
format Preprint
id arxiv_https___arxiv_org_abs_2506_24044
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle A Survey on Vision-Language-Action Models for Autonomous Driving
Jiang, Sicong
Huang, Zilin
Qian, Kangan
Luo, Ziang
Zhu, Tianze
Zhong, Yang
Tang, Yihong
Kong, Menglin
Wang, Yunlong
Jiao, Siwen
Ye, Hao
Sheng, Zihao
Zhao, Xin
Wen, Tuopu
Fu, Zheng
Chen, Sikai
Jiang, Kun
Yang, Diange
Choi, Seongjin
Sun, Lijun
Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
The rapid progress of multimodal large language models (MLLM) has paved the way for Vision-Language-Action (VLA) paradigms, which integrate visual perception, natural language understanding, and control within a single policy. Researchers in autonomous driving are actively adapting these methods to the vehicle domain. Such models promise autonomous vehicles that can interpret high-level instructions, reason about complex traffic scenes, and make their own decisions. However, the literature remains fragmented and is rapidly expanding. This survey offers the first comprehensive overview of VLA for Autonomous Driving (VLA4AD). We (i) formalize the architectural building blocks shared across recent work, (ii) trace the evolution from early explainer to reasoning-centric VLA models, and (iii) compare over 20 representative models according to VLA's progress in the autonomous driving domain. We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, accuracy, and explanation quality. Finally, we detail open challenges - robustness, real-time efficiency, and formal verification - and outline future directions of VLA4AD. This survey provides a concise yet complete reference for advancing interpretable socially aligned autonomous vehicles. Github repo is available at \href{https://github.com/JohnsonJiang1996/Awesome-VLA4AD}{SicongJiang/Awesome-VLA4AD}.
title A Survey on Vision-Language-Action Models for Autonomous Driving
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Robotics
url https://arxiv.org/abs/2506.24044