GR00T N1：面向通用人形机器人的开放基础模型
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
AI总结：
GR00T N1是面向人形机器人的开放基础模型，采用双系统VLA架构，通过异构数据训练，在仿真基准上超越最先进基线，并在真实机器人上实现高效双臂操作。
摘要：
通用机器人需要多功能的机体和智能的头脑。近期人形机器人的进展显示出其作为在人类世界中构建通用自主性硬件平台的巨大潜力。一个在大量多样化数据源上训练的机器人基础模型，对于使机器人能够推理新情况、稳健处理现实世界的多变性以及快速学习新任务至关重要。为此，我们提出了GR00T N1，一个面向人形机器人的开放基础模型。GR00T N1是一个具有双系统架构的视觉-语言-动作（VLA）模型。视觉-语言模块（系统2）通过视觉和语言指令解释环境。随后的扩散变换器模块（系统1）实时生成流畅的电机动作。两个模块紧密耦合，并共同进行端到端训练。我们使用真实机器人轨迹、人类视频和合成数据集的异构混合来训练GR00T N1。我们展示了我们的通用机器人模型GR00T N1在多个机器人形态的标准仿真基准上优于最先进的模仿学习基线。此外，我们将模型部署在傅利叶GR-1人形机器人上，用于语言条件双臂操作任务，实现了高数据效率下的强大性能。
英文摘要：
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.
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。
