Views
No views yet
| Field | Value |
|---|---|
| Policy | pi05 |
| Robot | openarm |
| Task | pick-and-place |
| State / Action dims | 8 / 8 |
| Extra state inputs | — |
| Cameras | chest, waist, wrist_r (3) |
| Base model | lerobot/pi05_base |
| Field | Value |
|---|---|
| n_obs_steps | 1 |
| Chunk size | 50 |
| n_action_steps | 50 |
| Vision backbone | paligemma (gemma_2b) + gemma_300m |
| Action normalization | MEAN_STD |
| Action feature names | right_finger_joint1 … right_joint7 (8 total) |
| Field | Value |
|---|---|
| Source dataset | openarm-pick-and-place-ikea-red-block |
| Total episodes | 250 |
| Episodes used (train) | 200 |
| Splits | 200 / 25 / 25 (train / val / test) |
| Training steps | 50,000 |
| Batch size | 16 |
| Optimizer | adamw, lr=3e-05 |
| Image augmentation | no |
| W&B | placing-one-block-r4-fisheye / 21ysh10k |
| Field | Value |
|---|---|
| Source dataset | openarm-pick-and-place-ikea-red-block |
| Total episodes | 250 |
| Train / val / test | 200 / 25 / 25 (train / val / test) |
| Trained with | anvil-embodied-ai |
apache-2.0