Saurabh-sinha-209/so101_hl-diffusion

Model Card for diffusion

Diffusion Policy treats visuomotor control as a generative diffusion process, producing smooth, multi-step action trajectories that excel at contact-rich manipulation.

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

See the full LeRobot documentation.

---

Model Details

• License: apache-2.0
• Robot type: so101_follower
• Cameras: bench, wrist

Inputs & Outputs

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

Inputs

Feature	Type	Shape
observation.state	STATE	(6,)
observation.images.bench	VISUAL	(3, 240, 320)
observation.images.wrist	VISUAL	(3, 240, 320)

Outputs

Feature	Type	Shape
action	ACTION	(6,)

Training Dataset

• Repository: Saurabh-sinha-209/so101_hl
• Episodes: 27
• Frames: 27332
• Frame rate: 30 FPS
• Task(s): "pick up the green plastic piece and place it in the white bin", "pick up the pink marker and place it in the white bin", "pick up the pink highlighter and place it in the white tray", "pick up the white tube and place it in the white tray", "pick up the pink marker and place it in the white tray", "pick up the pink marker and place it in the white foam tray", "pick up the white strap and place it in the white foam tray", "pick up the green plastic piece and place it in the white foam tray", "pick up the pink highlighter and place it in the white foam tray", "pick up the red can and place it in the white foam tray", "pick up the pink bottle and place it in the white foam tray", "pick up the green spiky ball and place it in the white foam tray", "pick up the blue bottle and place it in the white foam tray", "pick up the green spiky ball and place it in the white bin", "pick up the blue cap and place it in the white bin", "pick up the white tube and place it in the white bin", "pick up the red cylindrical object and place it in the white bin", "pick up the pink object and place it in the white tray", "pick up the blue object and place it in the white tray", "pick up the white packet with pink design and place it in the white tray", "pick up the green spiky ball and place it in the white tray", "pick up the white tube with pink label and place it in the white tray"

Training Configuration

Setting	Value
Training steps	30000
Batch size	32
Optimizer	adam
Learning rate	0.0001
Seed	1000
LeRobot version	0.6.0

---

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=so101_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=Saurabh-sinha-209/so101_hl-diffusion \
  --task="pick up the green plastic piece and place it in the white bin" \
  --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

lerobot-train \
  --dataset.repo_id=${HF_USER}/<dataset> \
  --policy.type=diffusion \
  --output_dir=outputs/train/<policy_repo_id> \
  --job_name=lerobot_training \
  --policy.device=cuda \
  --policy.repo_id=${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}
}