DriveMA: 重新思考驾驶VLAs中的语言接口以单步元动作
DriveMA: Rethinking Language Interfaces in Driving VLAs with One-Step Meta-Actions
AI总结：
本文提出DriveMA，通过单步元动作替代传统的自然语言推理，解决了驾驶VLAs中语言接口的三个瓶颈问题，实现了更高效的端到端规划。
摘要：
驾驶视觉-语言-动作模型（Driving VLAs）通常将自然语言推理作为端到端规划的中间接口，但以推理为中心的接口面临三个实际瓶颈：获得高质量的推理注释困难，生成和理解长推理链对紧凑模型具有挑战性，且推理延迟显著增加。本文重新思考了驾驶VLAs中的语言接口设计，表明简洁的单步元动作是替代冗长推理的有效替代方案。元动作提供语义决策基础，同时保持低熵，并能自动从专家轨迹推导出来，从而实现可扩展的监督和可靠的轨迹条件化。基于此接口，我们提出了DriveMA，结合以动作为中心的监督训练和基于转弯级别的信用分配强化学习框架，共同优化元动作的正确性、轨迹质量和轨迹-元动作一致性。实验表明，DriveMA在Waymo端到端驾驶挑战中已使用2B模型达到新的状态，Rater Feedback Score（RFS）为8.060，其4B版本进一步将状态提升至8.079；DriveMA在NAVSIM上也取得了具有竞争力的性能。消融实验显示，单步元动作在表达性、可预测性和推理效率之间提供了更好的实际权衡，优于自然语言推理或更细粒度的动作序列。代码、数据和模型将被发布以促进未来研究。
英文摘要：
Driving Vision-Language-Action Models (Driving VLAs) commonly introduce natural-language reasoning as an intermediate interface for end-to-end planning, but reasoning-centric interfaces face three practical bottlenecks: obtaining high-quality reasoning annotations is difficult, generating and understanding long reasoning chains is challenging for compact models, and inference latency is substantially increased. In this paper, we rethink the design of language interfaces in Driving VLAs and show that concise one-step meta-actions are a simple yet effective alternative to verbose reasoning. Meta-actions provide semantic decision grounding while remaining low-entropy, and being automatically derivable from expert trajectories, enabling scalable supervision and reliable trajectory conditioning. Building on this interface, we propose DriveMA, which combines action-centric supervised training with a turn-level credit-assignment reinforcement learning framework that jointly optimizes meta-action correctness, trajectory quality, and trajectory--meta-action consistency. Experiments show that DriveMA already achieves a new state of the art on the Waymo End-to-End Driving Challenge with a 2B model, reaching a Rater Feedback Score (RFS) of 8.060, while its 4B version further improves the state of the art to 8.079; DriveMA also obtains competitive performance on NAVSIM. Ablations demonstrate that one-step meta-actions offer a better practical trade-off between expressiveness, predictability, and inference efficiency than natural-language reasoning or finer-grained action sequences. Code, data, and models will be released to facilitate future research.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
