NVIDIA Project GR00T

Generalist Robot 00 Technology

Project GR00T is an active research initiative led by NVIDIA to develop general-purpose foundation models, tools and technologies for accelerating humanoid robot development.

If you are a humanoid robot maker, robot software or hardware vendor, request to join the NVIDIA humanoid robot developer program.

Apply Now


See GR00T in Action


Accelerate Humanoid Robotics Development

Building Robotic Systems With Three Computers

For humanoid robots to autonomously pick, pack, and transport items, as well as perform intricate maintenance tasks across various industries, a three-computer framework is vital: one to create the AI, one to simulate the AI, and one to run the AI.

Project GR00T utilizes NVIDIA’s three-computer robotics stack. This includes NVIDIA AI and DGX for training the model, NVIDIA Isaac Lab and Isaac Sim for robot learning in simulation environments, 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
img-alt-text

AI

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.

img-alt-text

Simulation

NVIDIA Isaac Lab

NVIDIA Isaac Lab is an open-source unified framework for robot learning to train robot policies. Apply reinforcement learning and imitation learning techniques to any type of robot embodiment.

img-alt-text

Runtime

NVIDIA Jetson Thor

Jetsonâ„¢ Thor was built to expedite the development of advanced humanoid robot development and run multimodal AI models for humanoid robots. Jetsonâ„¢ Thor was built on NVIDIA Blackwell architecture and comes with an integrated functional safety processor, a high-performance CPU cluster, and 100Gb of Ethernet bandwidth.


Advancing Humanoid Robot Development With GR00T Workflows

With Project GR00T, NVIDIA is building advanced technology, tools, and workflows that can be used standalone or together based on humanoid robot developer needs. These enhancements contribute to the development of more intelligent, adaptive, and capable humanoid robots, pushing the boundaries of what these robots can achieve in real-world applications.

Read Blog

How GR00T Foundation Model Training Works

Workflow for GR00T model training

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.

Workflow for Isaac Lab, OSMO Service, and GR00T model

Click to Enlarge

Workflow for Isaac OSMO Service, and GR00T model

Click to Enlarge

OSMO

NVIDIA OSMO is a cloud-native workflow orchestration platform that lets you easily scale your humanoid robotics workload across distributed environments—from on-premises to private and public cloud resource clusters. It provides a single pane of glass for scheduling complex multi-stage and multi-container heterogeneous computing workflows.

Learn More

Humanoid Robotics Ecosystem

Our humanoid robot ecosystem members are actively integrating NVIDIA AI models, tools and technologies to train their robots and robot foundation models for various environments and use-cases in simulation to accelerate humanoid robot development at scale.


Project GR00T Learning Library

Tech Blog

Advancing Humanoid Robot Sight and Skill Development With NVIDIA Project GR00T

NVIDIA Project GR00T

Discover the latest GR00T workflows that can help you create more intelligent, adaptive, and capable humanoid robots.

Tech Blog

Fast-Track Robot Learning in Simulation Using NVIDIA Isaac Lab

NVIDIA Project GR00T

The complexity of modeling humanoid dynamics increases exponentially with each added degree of freedom. Robot learning and imitation learning are the only scalable ways to develop policies for humanoids that work across a wide variety of tasks and environments.

Tech Video

Advancing Humanoid Robots With Foundation Model NVIDIA Project Groot

NVIDIA Project GR00T

NVIDIA announces Project GR00T, a general-purpose foundation model for humanoid robot learning. GR00T is trained in NVIDIA Isaac Lab, a robot learning application built in NVIDIA Omniverseâ„¢ Isaac Sim.


More Resources

A decorative image representing Developer Community

Explore the Community

img-alt-text

Get Training and Certification

A decorative image representing Inception for Startups

Meet the Program for Startups

    Accelerate Your Humanoid Development

    Apply for the NVIDIA Humanoid Robot Developer Program.

    Get Started