Drive-R1: Bridging Reasoning and Planning in VLMs for Autonomous Driving with Reinforcement Learning
This addresses a critical challenge in autonomous driving by improving how VLMs integrate reasoning with planning, though it appears incremental as it builds on existing VLM and RL methods.
The paper tackles the problem of vision-language models (VLMs) in autonomous driving relying on shortcuts and misaligned reasoning for motion planning, proposing Drive-R1 which combines supervised fine-tuning and reinforcement learning to bridge reasoning and planning, achieving superior performance on nuScenes and DriveLM-nuScenes benchmarks.
Large vision-language models (VLMs) for autonomous driving (AD) are evolving beyond perception and cognition tasks toward motion planning. However, we identify two critical challenges in this direction: (1) VLMs tend to learn shortcuts by relying heavily on history input information, achieving seemingly strong planning results without genuinely understanding the visual inputs; and (2) the chain-ofthought (COT) reasoning processes are always misaligned with the motion planning outcomes, and how to effectively leverage the complex reasoning capability to enhance planning remains largely underexplored. In this paper, we start from a small-scale domain-specific VLM and propose Drive-R1 designed to bridges the scenario reasoning and motion planning for AD. Drive-R1 first undergoes the supervised finetuning on a elaborate dataset containing both long and short COT data. Drive-R1 is encouraged to reason step-by-step from visual input to final planning decisions. Subsequently, Drive-R1 is trained within a reinforcement learning framework that incentivizes the discovery of reasoning paths that are more informative for planning, guided by rewards based on predicted trajectories and meta actions. Experimental evaluations on the nuScenes and DriveLM-nuScenes benchmarks demonstrate that Drive-R1 achieves superior performance compared to existing state-of-the-art VLMs. We believe that Drive-R1 presents a promising direction for bridging reasoning and planning in AD, offering methodological insights for future research and applications.