← Back to Models & Policies

GR00T-H-N1.7

GR00T-H-N1.7 is a post-trained variant of NVIDIA Isaac GR00T N1.7 for surgical robots. It builds on the GR00T N1.7 VLA foundation and adapts it using the Open-H-Embodiment dataset. Cosmos-Reason2-2B encodes the camera frames and language instruction, and a flow-matching diffusion transformer generates continuous actions. Post-trained on a 601-hour real-world surgical subset of Open-H-Embodiment across 7 robot platforms. Ready for commercial use under the NVIDIA Open Model License; intended for robotics research and development, not clinical deployment.

Property	Details
Model size	3B parameters (GR00T N1.7)
Model type	Vision Language Action (VLA); PyTorch, TensorRT. Input: vision (variable RGB frames), state (proprioception vector), language instruction. Output: continuous-value action vectors. Supported: Ampere, Blackwell, Hopper, Lovelace, Jetson. Ubuntu.
Performance	Post-trained on 601 hours from Open-H-Embodiment (58 datasets, 7 robot platforms). Evaluations conducted on real-world robots.
Workflow	—
Hugging Face	nvidia/GR00T-H-N1.7