---
license: mit
tags:
  - robotics
  - diffusion-policy
  - imitation-learning
  - manipulation
---

# UMI-on-Air - Pre-trained Checkpoints

Pre-trained diffusion policy checkpoints for **UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies**.

📄 **Paper:** [UMI-on-Air (PDF)](https://umi-on-air.github.io/static/umi-on-air.pdf) | [arXiv](https://arxiv.org/abs/2510.02614)

🌐 **Project Website:** [umi-on-air.github.io](https://umi-on-air.github.io/)

💻 **Code:** [GitHub](https://github.com/LeCAR-Lab/UMI-on-Air)

## Checkpoints Included

| Task | Description |
|------|-------------|
| `umi_cabinet` | Cabinet door opening task |
| `umi_peg` | Peg insertion task |
| `umi_pick` | Object picking task |
| `umi_valve` | Valve turning task |

## Usage

```bash
# Download and extract
wget https://huggingface.co/LeCAR-Lab/umi-on-air_checkpoints/resolve/main/checkpoints.tar.gz
tar -xzf checkpoints.tar.gz
```

Each checkpoint folder contains:
- `checkpoints/latest.ckpt` - Model weights
- `normalizer.pkl` - Data normalization parameters
- `.hydra/config.yaml` - Training configuration

## Citation

If you use these checkpoints, please cite our work:

```bibtex
@misc{gupta2025umionairembodimentawareguidanceembodimentagnostic,
      title={UMI-on-Air: Embodiment-Aware Guidance for Embodiment-Agnostic Visuomotor Policies}, 
      author={Harsh Gupta and Xiaofeng Guo and Huy Ha and Chuer Pan and Muqing Cao and Dongjae Lee and Sebastian Scherer and Shuran Song and Guanya Shi},
      year={2025},
      eprint={2510.02614},
      archivePrefix={arXiv},
      primaryClass={cs.RO},
      url={https://arxiv.org/abs/2510.02614}, 
}
```