Alpamayo-R1: 联结推理与动作预测以实现通用的自动驾驶在长尾场景
Alpamayo-R1: Bridging Reasoning and Action Prediction for Generalizable Autonomous Driving in the Long Tail
AI总结：
Alpamayo-R1通过整合因果推理与轨迹规划，提升了自动驾驶在长尾场景中的规划准确性和安全性。
摘要：
端到端架构通过模仿学习训练已通过扩大模型规模和数据提升了自动驾驶水平，但其在安全关键的长尾场景中的性能仍脆弱，因为这些场景中监督稀少且因果理解有限。我们引入了Alpamayo-R1（AR1），一种视觉-语言-动作模型（VLA），它将因果链推理与轨迹规划相结合以应对复杂驾驶场景。我们的方法有三个关键创新：（1）因果链（CoC）数据集，通过混合自动标注和人工在环管道构建，产生决策基础、因果联系的推理轨迹，与驾驶行为对齐；（2）一种模块化的VLA架构，结合Cosmos-Reason，一种为物理AI预训练的视觉-语言模型，以及基于扩散的轨迹解码器，能够实时生成动态可行的轨迹；（3）一种多阶段训练策略，使用监督微调来提取推理，并用强化学习（RL）来强制推理与动作的一致性并优化推理质量。AR1在挑战性案例中的规划准确性比仅轨迹的基线提高了12%，在闭环模拟中接近率减少了35%。RL后训练使推理质量提高了45%，推理-动作一致性提高了37%。模型规模从0.5B到7B参数显示了一致的改进。车载道路测试确认了实时性能（99毫秒延迟）和成功的城市部署。通过将可解释的推理与精确的控制相结合，AR1展示了实现Level 4自动驾驶的实用路径。模型权重可在https://huggingface.co/nvidia/Alpamayo-R1-10B获取，推理代码在https://github.com/NVlabs/alpamayo。
英文摘要：
End-to-end architectures trained via imitation learning have advanced autonomous driving by scaling model size and data, yet performance remains brittle in safety-critical long-tail scenarios where supervision is sparse and causal understanding is limited. We introduce Alpamayo-R1 (AR1), a vision-language-action model (VLA) that integrates Chain of Causation reasoning with trajectory planning for complex driving scenarios. Our approach features three key innovations: (1) the Chain of Causation (CoC) dataset, built through a hybrid auto-labeling and human-in-the-loop pipeline producing decision-grounded, causally linked reasoning traces aligned with driving behaviors; (2) a modular VLA architecture combining Cosmos-Reason, a vision-language model pre-trained for Physical AI, with a diffusion-based trajectory decoder that generates dynamically feasible trajectories in real time; (3) a multi-stage training strategy using supervised fine-tuning to elicit reasoning and reinforcement learning (RL) to enforce reasoning-action consistency and optimize reasoning quality. AR1 achieves up to a 12% improvement in planning accuracy on challenging cases compared to a trajectory-only baseline, with a 35% reduction in close encounter rate in closed-loop simulation. RL post-training improves reasoning quality by 45% and reasoning-action consistency by 37%. Model scaling from 0.5B to 7B parameters shows consistent improvements. On-vehicle road tests confirm real-time performance (99 ms latency) and successful urban deployment. By bridging interpretable reasoning with precise control, AR1 demonstrates a practical path towards Level 4 autonomous driving. Model weights are available at https://huggingface.co/nvidia/Alpamayo-R1-10B with inference code at https://github.com/NVlabs/alpamayo.
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。
