1. [Publications](/publications)
2. NVIDIA Isaac GR00T N1: An Open Foundation Model for Humanoid Robots
 
 # NVIDIA Isaac GR00T N1: An Open Foundation Model for Humanoid Robots

  ![Publication image](/sites/default/files/styles/wide/public/default_images/default.jpeg?itok=qUFsuJCP "Publication image")

 At NVIDIA, we are developing AI solutions to enable general-purpose humanoid robots to understand the human world, follow language instructions, and perform diverse tasks. A robust Vision-Language-Action (VLA) model is crucial for such advanced capabilities. To this end, we developed GR00T N1, a generalist robot model trained on a diverse dataset that includes egocentric human videos, real and simulated robot trajectories, and synthetic data.

GR00T N1 outperforms state-of-the-art imitation learning models in simulation benchmarks across multiple robot embodiments. Additionally, it demonstrates effective language-conditioned bimanual manipulation on the Fourier GR-1 and 1X humanoids in household tasks.

To help Physical AI builders solve the most critical problems of our society, we make our models open-weight with permissive licenses available via NVIDIA Isaac GR00T.



 ## Authors



[Yuke Zhu](/person/yuke-zhu)

[Linxi "Jim" Fan](/person/linxi-jim-fan)

NVIDIA GEAR Team

 

 

 ## Publication Date



Monday, March 17, 2025

 

 ## Research Area



[Artificial Intelligence and Machine Learning ](/research-area/machine-learning-artificial-intelligence)

[Autonomous Vehicles](/research-area/autonomous-vehicles)

[Generative AI](/research-area/generative-ai)

[Physical AI](/research-area/physical-ai)

[Robotics](/research-area/robotics)

 

 

 ## Uploaded Files



[GR00T\_1\_Whitepaper.pdf](https://d1qx31qr3h6wln.cloudfront.net/publications/GR00T_1_Whitepaper.pdf "Open file in new window")18.43 MB