Hyundai Uiwang — Diffusion Policy (FlowMatch, DINOv3-base) — LEFT (image-only)
LeRobot Diffusion Policy, FlowMatch scheduler (num_inference_steps=1), vision encoder
facebook/dinov3-vitb16-pretrain-lvd1689m (ViT-B/16, pretrained+frozen).
Long action chunk: horizon=64, n_action_steps=30. Robot: HDRB + DG-5F-M-LEFT (left).
- Model inputs: front_rgb + wrist_rgb images ONLY (
use_robot_state=false; state is ignored) - Output: action(26) = arm 6 + hand 20.
- Trained on the Hyundai Uiwang left-arm dataset (131 ep / 110,568 frames, 30 Hz).
Load-time requirements
- DINOv3 gated access — loading builds the backbone via
AutoModel.from_pretrained("facebook/dinov3-vitb16-pretrain-lvd1689m")(accept its license first). - lerobot fork with: DINOv3 register-token support + the
use_robot_stateconfig option (image-only).