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

Engineering notes

We also consolidate existing datasets and benchmarks, highlighting protocols that jointly measure driving safety, instruction fidelity, and explanation quality.

Chinese explanation / 中文解读

中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。

Original abstract

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, instruction fidelity, and explanation quality. Finally, we detail open challenges—robustness, real-time efficiency, and formal verification—and outline future directions toward foundation-scale driving models and a standardised “traffic language.” This survey provides a concise yet complete reference for advancing interpretable, instruction-following, and socially aligned autonomous vehicles.

Links and sources

• Official / arXiv page
• PDF from original source

Comments