A primary hurdle of autonomous driving in urban environments is understanding complex and long-tail scenarios, such as challenging road conditions and delicate human behaviors. We introduce DriveVLM, an autonomous driving system leveraging Vision-Language Models (VLMs) for enhanced scene understanding and planning capabilities. DriveVLM integrates a unique combination of reasoning modules for scene description, scene analysis, and hierarchical planning. Furthermore, recognizing the limitations of VLMs in spatial reasoning and heavy computational requirements, we propose DriveVLM-Dual, a hybrid system that synergizes the strengths of DriveVLM with the traditional autonomous driving pipeline. Experiments on both the nuScenes dataset and our SUP-AD dataset demonstrate the efficacy of DriveVLM and DriveVLM-Dual in handling complex and unpredictable driving conditions. Finally, we deploy the DriveVLM-Dual on a production vehicle, verifying it is effective in real-world autonomous driving environments.
@article{arxiv.2402.12289,
title = {DriveVLM: The Convergence of Autonomous Driving and Large Vision-Language Models},
author = {Xiaoyu Tian and Junru Gu and Bailin Li and Yicheng Liu and Yang Wang and Zhiyong Zhao and Kun Zhan and Peng Jia and Xianpeng Lang and Hang Zhao},
journal= {arXiv preprint arXiv:2402.12289},
year = {2024}
}