g1-inspire-nut-in-box-pi05

Ο€0.5 (3.6B) full fine-tune for the Unitree G1 + Inspire "nut in box" tweezer task ("pick up the tweezers and put the nut in the box") β€” our recipe, trained with openpi's PyTorch path (config pi05_g1_nut_full).

  • Dataset: MLeggiero/g1-inspire-nut-in-box-twist2, LeRobot v2.1 conversion, success-gated 29 episodes (~58k frames @ 60 fps).
  • Cameras: head (1280x720) + both wrist fisheyes (1920x1080), full-frame (openpi resizes to 224 internally).
  • State: 34-D body+imu, delivered as Ο€0.5's discrete prompt tokens, with our fork's state-token dropout p=0.8 at train time (inference always sees state) β€” the anti-shortcut regulariser.
  • Actions (27-D contract): arms 14 + right-hand Inspire registers 6 + root height / lin-vel-xy / yaw-rate 4 + waist 3 β€” ABSOLUTE (use_delta_actions=False), horizon 30, quantile (q01/q99) norm. Norm stats ship inside assets/ (the checkpoint's own).
  • Training: 20,000 steps, batch 32, AdamW (Ξ²2 0.95), cosine warmup 1k β†’ peak 2.5e-5 (30k decay horizon β†’ final LR ~8e-6), bf16, single B200.
  • Open-loop gate (3 episodes, 15 probe frames, vs dataset GT): arms RMS 0.004/0.010 rad, hand ~2.0 registers (0-1000 scale), waist 0.002 rad, root 0.011 β€” corr 1.00 on every group; 4-5x tighter than the GR00T N1.6 twins trained on the same capture. Monotonic across 16k/18k/20k.
  • This is the final step-20000 checkpoint (weights + norm-stats assets + metadata; no optimizer state).

Serving: load with openpi's create_trained_policy(get_config( "pi05_g1_nut_full"), <this dir>) β€” pass the bundled assets' norm stats if your config's repo_id differs from the training one.

Siblings: g1-inspire-nut-in-box-n16-abs / -n16-rel (GR00T N1.6 twins on the same contract).

Downloads last month

-

Downloads are not tracked for this model. How to track
Safetensors
Model size
4B params
Tensor type
F32
Β·
BF16
Β·
Video Preview
loading