π0.5 Piper Peg-Insertion LoRA
OpenPI/JAX π0.5 LoRA checkpoint trained for 12,000 steps on
peg_insertion_40_dual14d_pi05_rgb224_v21 (40 episodes, 42,614 frames).
The exact language prompt is:
pick up the gray peg and insert it into the hole in the orange block
Runtime contract
- RGB inputs: top, left wrist, and right wrist, letterboxed to 224×224.
- State/action: 14-D
[L_j1..j6, L_gripper_m, R_j1..j6, R_gripper_m]; the 12 joint targets are trained as state-relative deltas and both grippers remain absolute. - Recorded action supervision contains absolute joint-angle targets in radians.
- Grippers are meters and are clipped to
[0, 0.08]at the policy boundary. - Action horizon: 30.
- OpenPI config:
pi05_piper_peg_insertion_lora.
Normalization statistics under assets/ and the bundled OpenPI overlay are
required. The validation report checks checkpoint loading and inference pipeline
integrity; it is not a real-robot success-rate evaluation.