GR00T post-trained for Liver Scan
GR00T post-trained for Liver Scan#
GR00T-N1 VLA fine-tuned to mimic a simple liver ultrasound sweep in the Isaac for Healthcare ultrasound environment. Uses relative action space and Cosmos data augmentation. Input: wrist + room camera (224×224 RGB), text prompt (250 tokens), 7D joint state. Output: next 16 6D relative actions. Trained on 400 simulated liver ultrasound sweeps at 30 Hz (~210 steps each). For use within Isaac for Healthcare only.
| Property | Details |
|---|---|
| Model size | 2.2B parameters (GR00T N1) |
| Model type | Vision Language Action (VLA); PyTorch 2.5.1; Eagle-2 VLM + Diffusion Transformer |
| Performance | 83.8% average success rate @ 0.01 m (50 eval examples, 3 runs). Inference: Ampere RTX A6000 350 ms, 9.45 GB. Supported: Ampere, Blackwell, Hopper. |
| Workflow | Robotic Ultrasound |
| Hugging Face | nvidia/Liver_Scan_Gr00t_Cosmos_Rel |