The paper introduces DriveVLM, a system that leverages Vision-Language Models for scene understanding in autonomous driving. It comprises modules for Scene Description, Scene Analysis, and Hierarchical Planning to handle complex driving scenarios. DriveVLM outperformed other models in handling uncommon objects and unexpected events, while DriveVLM-Dual achieved state-of-the-art performance in planning tasks, showing promise for future improvements in autonomous driving.Read full paper: https://arxiv.org/abs/2402.12289Tags: Autonomous Driving, Computer Vision, Multimodal AI