NVIDIA Project GR00T
Generalist Robot 00 Technology
Project GR00T is an active research project that is developing a general-purpose foundation model that is expected to transform humanoid robot learning in simulation and the real world. Trained in NVIDIA GPU-accelerated simulation, GR00T enables humanoid embodiments to learn from a handful of human demonstrations with imitation learning and NVIDIA Isaac Lab for reinforcement learning, as well as generating robot movements from video data. The GR00T model takes multimodal instructions and past interactions as input and produces the actions for the robot to execute.
Project GROOT is an active research project. Sign up below for updates and information on availability.
GR00T Model Training Workflow
Robot Learning and Scaling Development Workloads
We developed NVIDIA Isaac Lab to train GR00T at scale and built NVIDIA OSMO, a compute orchestration service that coordinates the training and inference workflows across NVIDIA DGX systems for training, NVIDIA OVX systems for simulation, and NVIDIA IGX and NVIDIA AGX systems for hardware-in-the-loop validation.
Robot Learning and Orchestration Setup
NVIDIA Isaac Lab
Isaac Lab is a lightweight reference application built on the NVIDIA Isaac Sim platform specifically optimized for robot learning and is pivotal for robot foundation model training. Isaac Lab optimizes for reinforcement, imitation, and transfer learning, and is capable of training all types of robot embodiments.
NVIDIA OSMO
OSMO is a cloud-native workflow orchestration platform that lets you easily scale your workloads 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.