GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915214841085952 |
|---|---|
| author | NVIDIA : Bjorck, Johan Castañeda, Fernando Cherniadev, Nikita Da, Xingye Ding, Runyu Fan, Linxi "Jim" Fang, Yu Fox, Dieter Hu, Fengyuan Huang, Spencer Jang, Joel Jiang, Zhenyu Kautz, Jan Kundalia, Kaushil Lao, Lawrence Li, Zhiqi Lin, Zongyu Lin, Kevin Liu, Guilin Llontop, Edith Magne, Loic Mandlekar, Ajay Narayan, Avnish Nasiriany, Soroush Reed, Scott Tan, You Liang Wang, Guanzhi Wang, Zu Wang, Jing Wang, Qi Xiang, Jiannan Xie, Yuqi Xu, Yinzhen Xu, Zhenjia Ye, Seonghyeon Yu, Zhiding Zhang, Ao Zhang, Hao Zhao, Yizhou Zheng, Ruijie Zhu, Yuke |
| author_facet | NVIDIA : Bjorck, Johan Castañeda, Fernando Cherniadev, Nikita Da, Xingye Ding, Runyu Fan, Linxi "Jim" Fang, Yu Fox, Dieter Hu, Fengyuan Huang, Spencer Jang, Joel Jiang, Zhenyu Kautz, Jan Kundalia, Kaushil Lao, Lawrence Li, Zhiqi Lin, Zongyu Lin, Kevin Liu, Guilin Llontop, Edith Magne, Loic Mandlekar, Ajay Narayan, Avnish Nasiriany, Soroush Reed, Scott Tan, You Liang Wang, Guanzhi Wang, Zu Wang, Jing Wang, Qi Xiang, Jiannan Xie, Yuqi Xu, Yinzhen Xu, Zhenjia Ye, Seonghyeon Yu, Zhiding Zhang, Ao Zhang, Hao Zhao, Yizhou Zheng, Ruijie Zhu, Yuke |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_14734 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GR00T N1: An Open Foundation Model for Generalist Humanoid Robots NVIDIA : Bjorck, Johan Castañeda, Fernando Cherniadev, Nikita Da, Xingye Ding, Runyu Fan, Linxi "Jim" Fang, Yu Fox, Dieter Hu, Fengyuan Huang, Spencer Jang, Joel Jiang, Zhenyu Kautz, Jan Kundalia, Kaushil Lao, Lawrence Li, Zhiqi Lin, Zongyu Lin, Kevin Liu, Guilin Llontop, Edith Magne, Loic Mandlekar, Ajay Narayan, Avnish Nasiriany, Soroush Reed, Scott Tan, You Liang Wang, Guanzhi Wang, Zu Wang, Jing Wang, Qi Xiang, Jiannan Xie, Yuqi Xu, Yinzhen Xu, Zhenjia Ye, Seonghyeon Yu, Zhiding Zhang, Ao Zhang, Hao Zhao, Yizhou Zheng, Ruijie Zhu, Yuke Robotics Artificial Intelligence Machine Learning 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. |
| title | GR00T N1: An Open Foundation Model for Generalist Humanoid Robots |
| topic | Robotics Artificial Intelligence Machine Learning |
| url | https://arxiv.org/abs/2503.14734 |