J Duck
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.
Source du modèle
- Type
- Other
- Taille du fichier
- 7,41 KB–197 MB
- Version
- vRevision e33d0ff
- Mis à jour
- 26 sept. 2026
- Téléchargements
- 38
- Source
- Hugging Face
Extrait de la source
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.
Sources
1 source
Sources
1 sourceVérifié 7 août
Artefacts du modèle
3 artefacts
Artefacts du modèle
3 artefactspolicy_postprocessor_step_0_unnormalizer_processor.safetensors
safetensors · 7,41 KB · SHA-256 56523a9102c7…aa13 · Hugging Face
Téléchargerpolicy_preprocessor_step_3_normalizer_processor.safetensors
safetensors · 7,42 KB · SHA-256 50ef49bf6b9c…702d · Hugging Face
TéléchargerExtraits de sources
2 extraits
Extraits de sources
2 extraits--- datasets: NLTuan/j_duck library_name: lerobot license: apache-2.0 model_name: act pipeline_tag: robotics tags: - act - lerobot - robotics --- # Model Card for act <!-- Provide a quick summary of what the model is/does. --> [Action Chunking with Transformers (ACT)](https://huggingface.co/papers/2304.13705) 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. <!-- 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 act guide](https://huggingface.co/docs/lerobot/main/en/act), or browse the [full documentation](https://huggingface.co/docs/lerobot/index). --- ## Model Details - **License:** apache-2.0 - **Robot type:** `so_follower` - **Cameras:** `camera1`, `camera2` ## Inputs & Outputs The policy consumes these observation features and produces these action features. **Inputs** | Feature | Type | Shape | | --- | --- | --- | | `observation.state` | STATE | `(6,)` | | `observation.images.camera1` | VISUAL | `(3, 240, 320)` | | `observation.images.camera2` | VISUAL | `(3, 240, 320)` | **Outputs** | Feature | Type | Shape | | --- | --- | --- | | `action` | ACTION | `(6,)` | ## Training Dataset - **Repository:** [NLTuan/j_duck](https://huggingface.co/datasets/NLTuan/j_duck) - **Episodes:** 50 - **Frames:** 29546 - **Frame rate:** 30 FPS - **Task(s):** "pick and place duck" <a class="flex" href="https://huggingface.co/spaces/lerobot/visualize_dataset?path=NLTuan/j_duck"> <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 | 20000 | | Batch size | 32 | | Optimizer | adamw | | Learning rate | 3e-05 | | Seed | 1000 | | LeRobot version | 0.6.1 | --- ## How to Get Started...
Source context: 38 downloads · 0 likes · Pipeline robotics · Library lerobot · Repo J-Hua/j_duck
