Instructions to use leapshared/sciedu_bench_props8_act_10k with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use leapshared/sciedu_bench_props8_act_10k with LeRobot:
# No code snippets available yet for this library. # To use this model, check the repository files and the library's documentation. # Want to help? PRs adding snippets are welcome at: # https://github.com/huggingface/huggingface.js
- Notebooks
- Google Colab
- Kaggle
Model Card for act
Action Chunking with Transformers (ACT) is an imitation-learning method that predicts short action chunks instead of single steps. It learns from teleoperated data and often achieves high success rates.
This policy has been trained and pushed to the Hub using LeRobot.
Learn how to train and run it in the LeRobot act guide, or browse the full documentation.
Model Details
- License: apache-2.0
- Robot type:
openarm_sciedu_sim - Cameras:
follower_d455f,left_wrist,right_wrist
Inputs & Outputs
The policy consumes these observation features and produces these action features.
Inputs
| Feature | Type | Shape |
|---|---|---|
observation.state |
STATE | (16,) |
observation.images.follower_d455f |
VISUAL | (3, 480, 640) |
observation.images.left_wrist |
VISUAL | (3, 480, 640) |
observation.images.right_wrist |
VISUAL | (3, 480, 640) |
Outputs
| Feature | Type | Shape |
|---|---|---|
action |
ACTION | (16,) |
Training Dataset
- Repository: leapshared/sciedu_bench_v2_sim_props8_all
- Episodes: 2365
- Frames: 1438051
- Frame rate: 30 FPS
- Task(s): "pick up the black charging rod", "move the rod toward and away from the electroscope", "rub the rod on the fur", "put the rod down on the white holder", "hold the rod still at the electroscope", "return to the home posture", "put the leaf on the left side", "put the leaf on the right side", "lift the metal plate out of the left beaker", "move the plate over the blue solution", "put the plate into the left beaker", "lower the plate into the blue solution", "move the plate over the left beaker", "raise the plate out of the solution", "hold the plate still in the solution", "point at the plate with the left hand", "point at the dipped plate with the left hand", "pick up the right mineral with the left hand", "pick up the middle mineral with the left hand", "pick up the left mineral with the left hand", "pick up the dropper by the top with the right hand", "rub the mineral on the streak plate", "lower the mineral onto the iron filings and hold still", "put the middle mineral back", "draw acid from the petri dish", "squeeze the dropper onto the mineral", "put the dropper in the beaker", "put the mineral in the empty petri dish", "put the right mineral back", "rub the mineral on the streak plate below the first streak"
Training Configuration
| Setting | Value |
|---|---|
| Training steps | 10000 |
| Batch size | 32 |
| Optimizer | adamw |
| Learning rate | 1e-05 |
| Seed | 1000 |
| LeRobot version | 0.6.1 |
How to Get Started with the Model
New to LeRobot? These guides cover the full workflow:
- Install LeRobot β set up the
lerobotpackage. - Hardware setup β assemble, wire, and calibrate your robot and cameras.
- Record data & train a policy β the end-to-end imitation-learning walkthrough.
- CLI cheat-sheet β 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=openarm_sciedu_sim \
--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_bench_props8_act_10k \
--task="pick up the black charging rod" \
--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=${HF_USER}/<dataset> \
--policy.type=act \
--output_dir=outputs/train/<policy_repo_id> \
--job_name=lerobot_training \
--policy.device=cuda \
--policy.repo_id=${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}
}
- Downloads last month
- 46