---
base_model: lerobot/pi05_base
datasets: masato-ka/transfer_cube_20260704_230228
library_name: lerobot
license: apache-2.0
model_name: pi05
pipeline_tag: robotics
tags:
- pi05
- robotics
- lerobot
---

# Model Card for pi05

<!-- Provide a quick summary of what the model is/does. -->


[π₀.₅ (Pi05)](https://www.physicalintelligence.company/blog/pi05) is a Vision-Language-Action model from Physical Intelligence designed for open-world generalization: it evolves π₀ to generalize to entirely new environments and situations that were never seen during training. The LeRobot implementation is adapted from their open-source OpenPI repository.




<!-- A short demo is worth more than any description! Record a GIF/video of the policy
running on your robot, upload it to this repo, and embed it here:
<p align="center">
  <img src="https://huggingface.co/<hf_user>/<policy_repo_id>/resolve/main/demo.gif" width="60%"/>
</p>
-->

This policy has been trained and pushed to the Hub using [LeRobot](https://github.com/huggingface/lerobot).

Learn how to train and run it in the [LeRobot pi05 guide](https://huggingface.co/docs/lerobot/main/en/pi05), or browse the [full documentation](https://huggingface.co/docs/lerobot/index).


---

## Model Details

- **License:** apache-2.0
- **Fine-tuned from:** [lerobot/pi05_base](https://huggingface.co/lerobot/pi05_base)
- **Robot type:** `so_follower`
- **Cameras:** `overhead`


## Inputs & Outputs

The policy consumes these observation features and produces these action features.

**Inputs**

| Feature | Type | Shape |
| --- | --- | --- |
| `observation.state` | STATE | `(6,)` |
| `observation.images.overhead` | VISUAL | `(3, 480, 640)` |

**Outputs**

| Feature | Type | Shape |
| --- | --- | --- |
| `action` | ACTION | `(6,)` |


## Training Dataset

- **Repository:** [masato-ka/transfer_cube_20260704_230228](https://huggingface.co/datasets/masato-ka/transfer_cube_20260704_230228)
- **Episodes:** 50
- **Frames:** 22385
- **Frame rate:** 30 FPS
- **Task(s):** "Pick up the block in the center and place it in the center.", "Move the center block to the center area.", "Grab the block from the middle and put it back in the middle.", "Take the block at the center and drop it in the center zone.", "Relocate the center block within the middle area.", "Pick up the block in the center and place it on the right.", "Move the center block to the right side.", "Grab the block from the middle and put it on the right.", "Take the center block and drop it at the right end.", "Relocate the block from the center to the right area.", "Transport the center block to the rightmost spot.", "Pick up the block in the center and place it on the left.", "Move the center block to the left side.", "Grab the block from the middle and put it on the left.", "Take the center block and drop it at the left end.", "Relocate the block from the center to the left area.", "Transport the center block to the leftmost spot.", "Pick up the block on the right and place it on the left.", "Move the right block all the way to the left side.", "Grab the block from the right end and put it on the left end.", "Take the block on the right and drop it at the far left.", "Pick up the block on the left and place it on the right.", "Move the left block all the way to the right side.", "Grab the block from the left end and put it on the right end.", "Take the block on the left and drop it at the far right."

<a class="flex" href="https://huggingface.co/spaces/lerobot/visualize_dataset?path=masato-ka/transfer_cube_20260704_230228">
<img class="block dark:hidden" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl.svg"/>
<img class="hidden dark:block" src="https://huggingface.co/datasets/huggingface/badges/resolve/main/visualize-this-dataset-xl-dark.svg"/>
</a>


## Training Configuration

| Setting | Value |
| --- | --- |
| Training steps | 3000 |
| Batch size | 32 |
| Optimizer | adamw |
| Learning rate | 2.5e-05 |
| Seed | 1000 |
| LeRobot version | 0.5.2 |

---

## How to Get Started with the Model

New to LeRobot? These guides cover the full workflow:

- **[Install LeRobot](https://huggingface.co/docs/lerobot/main/en/installation)** — set up the `lerobot` package.
- **[Hardware setup](https://huggingface.co/docs/lerobot/main/en/hardware_guide)** — assemble, wire, and calibrate your robot and cameras.
- **[Record data & train a policy](https://huggingface.co/docs/lerobot/en/il_robots)** — the end-to-end imitation-learning walkthrough.
- **[CLI cheat-sheet](https://huggingface.co/docs/lerobot/main/en/cheat-sheet)** — quick reference for the `lerobot-*` commands.

The short version to run and train this policy:

### Run the policy on your robot

```bash
lerobot-rollout \
  --strategy.type=base \
  --robot.type=so_follower \
  --robot.port=<your_robot_port> \
  --robot.cameras="{ <camera_1>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}, <camera_2>: {type: opencv, index_or_path: <index_or_path>, width: 640, height: 480, fps: 30}}" \
  --policy.path=masato-ka/pi05-transfer_cube_quantile_bug \
  --task="Pick up the block in the center and place it in the center." \
  --duration=60
```

Replace the remaining `<...>` placeholders with your own values: `--robot.port` and the camera names/indices are specific to your machine, and the camera names must match the observation keys this policy was trained on.

When `--strategy.type=base` is used the script doesn't record the episodes. Skipping duration will make the policy run indefinitely. For more information look at [rollout documentation](https://huggingface.co/docs/lerobot/main/en/inference).

### Train your own policy

This policy type is usually fine-tuned from the pretrained base model [lerobot/pi05_base](https://huggingface.co/lerobot/pi05_base):

```bash
lerobot-train \
  --dataset.repo_id=${HF_USER}/<dataset> \
  --policy.path=lerobot/pi05_base \
  --output_dir=outputs/train/<policy_repo_id> \
  --job_name=lerobot_training \
  --policy.device=cuda \
  --policy.repo_id=${HF_USER}/<policy_repo_id> \
  --wandb.enable=true
```

_Writes checkpoints to `outputs/train/<policy_repo_id>/checkpoints/`._

---

## Evaluation

<!-- Report real-robot results here: run the policy several times per task and count the
successes. Delete the "No evaluation results" line and fill in this table instead:

| Task | Trials | Successes | Success rate |
| ---- | ------ | --------- | ------------ |
| pick the lego brick | 10 | 8 | 80% |

Also worth noting: anything that affects difficulty (new object positions, lighting,
distractors, a different robot of the same type, ...).
-->

_No evaluation results have been provided for this policy yet._

---

## Citation

If you use this policy, please cite the method linked in the description above, along with LeRobot:

```bibtex
@misc{cadene2024lerobot,
    author = {Cadene, Remi and Alibert, Simon and Soare, Alexander and Gallouedec, Quentin and Zouitine, Adil and Palma, Steven and Kooijmans, Pepijn and Aractingi, Michel and Shukor, Mustafa and Aubakirova, Dana and Russi, Martino and Capuano, Francesco and Pascal, Caroline and Choghari, Jade and Moss, Jess and Wolf, Thomas},
    title = {LeRobot: State-of-the-art Machine Learning for Real-World Robotics in Pytorch},
    howpublished = "\url{https://github.com/huggingface/lerobot}",
    year = {2024}
}
```