masato-ka/pi05-transfer_cube_3804

Model Card for pi05

π₀.₅ (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.

This policy has been trained and pushed to the Hub using LeRobot.

Learn how to train and run it in the LeRobot pi05 guide, or browse the full documentation.

---

Model Details

• License: apache-2.0
• Fine-tuned from: 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
• 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."

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 — set up the lerobot package.
• Hardware setup — assemble, wire, and calibrate your robot and cameras.
• Record data & train a policy — the end-to-end imitation-learning walkthrough.
• CLI cheat-sheet — quick reference for the lerobot-* commands.

The short version to run and train this policy:

Run the policy on your robot

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_3804 \
  --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.

Train your own policy

This policy type is usually fine-tuned from the pretrained base model lerobot/pi05_base:

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

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:

@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}
}