无需推理标注，用更少数据训练出高效自动驾驶模型
NoRD: A Data-Efficient Vision-Language-Action Model that Drives without Reasoning
- 采用无推理标注的简化训练策略，降低数据依赖
- 在Waymo和NAVSIM上达竞品性能，训练数据减少60%以上
- 改进算法缓解难例偏差，适合资源受限的自动驾驶研发
视觉-语言-动作（VLA）模型通过统一端到端架构推动自动驾驶发展，但现有方法面临两大高成本需求：海量数据采集与密集推理标注。本文提出NoRD（无推理驾驶），相比现有VLA，在不到60%的数据上微调且无需推理标注，训练令牌数减少3倍。研究发现，标准组相对策略优化（GRPO）在小规模、无推理数据上效果不佳，根源在于难度偏差——该偏差对高方差回放场景的奖励信号过度惩罚。NORD通过引入针对大模型难度偏差设计的Dr. GRPO算法克服此问题。最终，NORD在Waymo和NAVSIM基准上实现竞争力表现，仅需少量数据与无推理开销，显著提升自动驾驶系统训练效率。
原文摘要 · Abstract (English)
Vision-Language-Action (VLA) models are advancing autonomous driving by replacing modular pipelines with unified end-to-end architectures. However, current VLAs face two expensive requirements: (1) massive dataset collection, and (2) dense reasoning annotations. In this work, we address both challenges with NORD (No Reasoning for Driving). Compared to existing VLAs, NORD achieves competitive performance while being fine-tuned on <60% of the data and no reasoning annotations, resulting in 3x fewer tokens. We identify that standard Group Relative Policy Optimization (GRPO) fails to yield significant improvements when applied to policies trained on such small, reasoning-free datasets. We show that this limitation stems from difficulty bias, which disproportionately penalizes reward signals from scenarios that produce high-variance rollouts within GRPO. NORD overcomes this by incorporating Dr. GRPO, a recent algorithm designed to mitigate difficulty bias in LLMs. As a result, NORD achieves competitive performance on Waymo and NAVSIM with a fraction of the training data and no reasoning overhead, enabling more efficient autonomous systems. Website: https://nord-vla-ai.github.io/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。