Instructions to use RobotControlStack/duobench-act-sim-join_blocks with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- LeRobot
How to use RobotControlStack/duobench-act-sim-join_blocks 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
|
Download README.md from RobotControlStack/duobench-act-sim-join_blocks: direct link, hf CLI and curl.
- Browser
- Download file 2.36 kB
-
https://huggingface.co/RobotControlStack/duobench-act-sim-join_blocks/resolve/main/README.md
- Command line
-
hf download hf://RobotControlStack/duobench-act-sim-join_blocks/README.md
-
curl -L -o README.md https://huggingface.co/RobotControlStack/duobench-act-sim-join_blocks/resolve/main/README.md
2.36 kB
| license: apache-2.0 | |
| library_name: lerobot | |
| pipeline_tag: robotics | |
| datasets: | |
| - RobotControlStack/duobench | |
| tags: | |
| - duobench | |
| - bimanual | |
| - manipulation | |
| - simulation | |
| - act | |
| # DuoBench ACT (sim) | |
| ACT policy for the bimanual FR3 Duo setup of [DuoBench](https://arxiv.org/abs/2606.11901), trained on simulation data only for the DuoBench `join_blocks` sim task (single-task policy). | |
| Trained from scratch with [LeRobot](https://github.com/huggingface/lerobot) on the [DuoBench dataset](https://huggingface.co/datasets/RobotControlStack/duobench). | |
| Project page: https://duobench.github.io/ | |
| DuoBench Code: https://github.com/RobotControlStack/duobench | |
| ## Training | |
| - Data: 50 demonstrations per task from the `<task>/sim` folders of [RobotControlStack/duobench](https://huggingface.co/datasets/RobotControlStack/duobench) | |
| - Inputs: `head`, `left_wrist` and `right_wrist` cameras (224x224) and the 16-D state (2 x 7 joints + 2 grippers); output: 16-D joint and gripper action | |
| - 150,000 steps, batch size 64, learning rate 1e-5, action chunk 100, seed 1000 | |
| - LeRobot commit [`c8ce413d`](https://github.com/huggingface/lerobot/tree/c8ce413d738da15a2eed2d0832315779ea28cbf9); the full configuration is in `train_config.json` | |
| ## Results | |
| Success rate (%) in DuoBench simulation over 300 rollouts per task (seeds 0-299) with a Wilson 95% interval. | |
| | Task | Success | 95% CI | | |
| |---|---|---| | |
| | join_blocks | 2.3 | [1.1, 4.7] | | |
| ## Usage | |
| ```python | |
| # LeRobot at commit c8ce413d | |
| from lerobot.policies.act.modeling_act import ACTPolicy | |
| policy = ACTPolicy.from_pretrained("RobotControlStack/duobench-act-sim-join_blocks") | |
| ``` | |
| See the [DuoBench code](https://github.com/RobotControlStack/duobench) for the simulation environments and evaluation. | |
| ## Limitations | |
| - Trained on simulation data only; not meant for the real robot. | |
| - Loading needs a LeRobot version compatible with the commit above. | |
| ## Citation | |
| If you find this model or DuoBench useful for your work, please consider citing it: | |
| ``` | |
| @misc{duobench, | |
| title={{DuoBench}: A Reproducible Benchmark for Bimanual Manipulation in Simulation and the Real World}, | |
| author={Tobias J{\"u}lg and Seongjin Bien and Simon Hilber and Yannik Blei and Pierre Krack and Maximilian Li and Sven Parusel and Rudolf Lioutikov and Florian Walter and Wolfram Burgard}, | |
| year={2026}, | |
| url={https://arxiv.org/abs/2606.11901} | |
| } | |
| ``` | |