SciEdu_3097epi_steps_pi05

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: bi_openarm_follower
• Cameras: follower_d455f, left_wrist, right_wrist

Inputs & Outputs

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

Inputs

Outputs

Training Dataset

• Repository: leapshared/SciEdu_3097epi_steps
• Episodes: 3097
• Frames: 887125
• Frame rate: 30 FPS
• Task(s): "put the leaf on the right side", "put the leaf on the left side", "lift the metal plate out of the left beaker", "move the plate over the blue solution", "point at the plate with the left hand", "lower the plate into the blue solution", "hold the plate still in the solution", "raise the plate out of the solution", "point at the dipped plate with the left hand", "move the plate over the left beaker", "put the plate into the left beaker", "return to the home posture", "pick up the white charging plate", "bring the plate to the electroscope and point at the metal foil", "move the plate toward and away from the electroscope", "rub the plate on the fur", "move the plate toward and away from the electroscope, then stop above it", "hold the plate still at the electroscope", "put the plate down on the right", "pick up the right mineral with the left hand", "move the mineral over the streak plate", "rub the mineral on the streak plate", "put the right mineral back", "pick up the middle mineral with the left hand", "rub the mineral on the streak plate below the first streak", "put the middle mineral back", "pick up the dropper by the top with the right hand", "draw acid from the petri dish", "move the dropper over the left mineral", "squeeze the dropper onto the mineral", "move the dropper over the empty beaker", "put the dropper in the beaker", "pick up the left mineral with the left hand", "move the mineral over the iron filings", "lower the mineral onto the iron filings and hold still", "lift the mineral", "put the mineral in the empty petri dish"

Training Configuration

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=bi_openarm_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=leapshared/SciEdu_3097epi_steps_pi05 \
  --task="put the leaf on the right side" \
  --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}
}