Diffusion Policy

The model was trained with the MujocoUR5eCable dataset.

Install

See GitHub for installation.

Policy rollout

Run a trained policy:

# Go to the top directory of this repository
$ cd robo_manip_baselines
$ python ./bin/Rollout.py DiffusionPolicy MujocoUR5eCable --checkpoint ./checkpoint/DiffusionPolicy/<checkpoint_name>/policy_last.ckpt

Technical Details

For more information on the technical details, please see the following paper:

@INPROCEEDINGS{DiffusionPolicy_RSS23,,
  author = {Chi, Cheng and Feng, Siyuan and Du, Yilun and Xu, Zhenjia and Cousineau, Eric and Burchfiel, Benjamin and Song, Shuran},
  title = {Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},
  booktitle = {Proceedings of Robotics: Science and Systems},
  year = {2023},
  month = {July},
  doi = {10.15607/RSS.2023.XIX.026}
}