NVIDIA Project GR00T

Generalist Robot 00 Technology

Project GR00T is an initiative to develop general-purpose foundation models for humanoid robots that take multimodal instructions and past interactions as input and output robot actions. These advanced models are modular, with systems for both high-level reasoning and planning and low-level fast, accurate, and reactive motion.

Project GR00T is an active research project. If you are a humanoid robot maker, robot software/ hardware vendor, request early access.

Apply for Early Access

See GR00T in Action

Next-Gen Robots, Powered by NVIDIA

Building Robotic Systems With Three Computers

Project GR00T uses every part of NVIDIA’s three-computer robotics stack. This includes NVIDIA AI and DGX for training the model, NVIDIA Isaac Lab for reinforcement learning, and the NVIDIA Jetson Thor high-performance computing platform, designed for humanoid robots, with Isaac ROS for accelerated robot runtime.

Building Robotics Systems with Three Computers

NVIDIA DGX

NVIDIA DGX Cloud is an end-to-end AI platform for developers, giving you scalable capacity built on the latest NVIDIA architecture and co-engineered with the world’s leading cloud service providers.

Try DGX Now

Simulation

NVIDIA Isaac Lab

This lightweight reference application is built on the NVIDIA Omniverse platform that’s specifically optimized for robot learning and is pivotal for robot foundation model training. It optimizes for reinforcement, imitation, and transfer learning and is capable of training all types of robot embodiments.

Learn More About Isaac Lab

Runtime

Isaac ROS on Jetson Thor

NVIDIA Isaac ROS is a collection of accelerated computing packages and AI models designed to streamline and expedite the development of advanced AI robotics applications. For humanoids, Isaac ROS is deployed on Jetson Thor, optimized for fast, humanoid cognition and action.

Learn More About Isaac ROS

How It Works

Click to Enlarge

Model Operation

Project GR00T enables humanoid embodiments to perform tasks from multimodal instructions and dynamically react to the world through self-observation.

Development and Training

The model uses multimodal learning from a variety of data sources—including instructions, demonstrations, video, and imitation learning for robots—to acquire new skills, accelerating the development of humanoid robots.

NVIDIA Isaac Lab is ideal for training Project GR00T at scale. You can also take advantage of the NVIDIA OSMO robot cloud computing orchestration service to coordinate workflows across NVIDIA DGX systems for training, NVIDIA OVX systems for simulation, and NVIDIA IGX systems for hardware-in-the-loop validation.