外观
论文arXiv 2503.147342025-03-18
NVIDIA开源GR00T N1人形机器人VLA基座模型
本文由 AI 根据公开内容整理，可能有误，请以原文为准：GR00T N1: An Open Foundation Model for Generalist Humanoid Robots（arXiv 2503.14734）
核心内容
NVIDIA正式开源面向通用人形机器人的基础模型GR00T N1，旨在解决具身智能在开放世界中的推理与适应难题。该模型作为Vision-Language-Action（VLA）范式的新进展，通过融合真实机器人轨迹、人类视频及合成数据构成的异构数据集进行端到端训练。实验表明，GR00T N1在多个标准仿真基准测试中性能优于当前最先进的模仿学习基线，并成功部署于Fourier GR-1人形机器人，完成了语言条件约束下的双臂操作任务，展现出显著的数据效率优势。
GR00T N1采用紧耦合的双系统架构：System 2为视觉语言模块，负责解析环境语义与指令；System 1为扩散Transformer模块，实时生成流畅的运动控制信号，两模块联合优化以弥合认知与执行的鸿沟。这种设计使模型具备处理现实世界多变性的鲁棒性。在落地验证环节，研究团队利用该模型驱动傅利叶GR-1执行复杂双臂 manipulation 任务，证实了其在真实物理本体上的零样本或少样本迁移潜力，为人形机器人通用基座模型的工程化提供了可复现的技术路径。
关键看点
- 双系统VLA架构：集成视觉语言理解(System 2)与扩散Transformer动作生成(System 1)，端到端联合训练实现认知与控制紧耦合
- 异构数据混合训练：融合真实机器人轨迹、人类演示视频及合成数据集，提升模型对新颖场景的推理与泛化能力
- 仿真性能超越SOTA：在多个标准仿真基准测试中，各项指标均优于当前最先进的模仿学习基线模型
- 真机双臂操作验证：部署于傅利叶GR-1人形机器人，成功执行语言条件双臂操作任务，验证高数据效率与实机可用性
工程与产业观察
GR00T N1确立了“VLA+扩散策略”作为人形机器人通用基座的主流技术路线，其开源特性降低了具身大模型研发门槛。双系统紧耦合设计有效缓解了高层语义到低层控制的对齐难题，结合异构数据训练策略，为解决真机数据稀缺痛点提供了工程范本，加速了人形机器人从单一任务向通用自主能力的演进。
英文摘要 (Abstract)
General-purpose robots need a versatile body and an intelligent mind. Recent advancements in humanoid robots have shown great promise as a hardware platform for building generalist autonomy in the human world. A robot foundation model, trained on massive and diverse data sources, is essential for enabling the robots to reason about novel situations, robustly handle real-world variability, and rapidly learn new tasks. To this end, we introduce GR00T N1, an open foundation model for humanoid robots. GR00T N1 is a Vision-Language-Action (VLA) model with a dual-system architecture. The vision-language module (System 2) interprets the environment through vision and language instructions. The subsequent diffusion transformer module (System 1) generates fluid motor actions in real time. Both modules are tightly coupled and jointly trained end-to-end. We train GR00T N1 with a heterogeneous mixture of real-robot trajectories, human videos, and synthetically generated datasets. We show that our generalist robot model GR00T N1 outperforms the state-of-the-art imitation learning baselines on standard simulation benchmarks across multiple robot embodiments. Furthermore, we deploy our model on the Fourier GR-1 humanoid robot for language-conditioned bimanual manipulation tasks, achieving strong performance with high data efficiency.
作者：NVIDIA, :, Johan Bjorck, Fernando Castañeda, Nikita Cherniadev, Xingye Da, Runyu Ding, Linxi "Jim" Fan, Yu Fang, Dieter Fox, Fengyuan Hu, Spencer Huang, Joel Jang, Zhenyu Jiang, Jan Kautz, Kaushil Kun…
来源
本页事实对应的公开页面，以原文为准。