PushT Diffusion Policy - Robot Control Model
This model is an implementation of Diffusion Policy for the PushT environment, which simulates robotic pushing tasks.
Model
This model uses a conditional diffusion architecture to predict robotic actions based on visual observations.
Performance
The model achieves a success rate of 40.0% in the PushT environment with different initial configurations.
Demonstration Videos
The repository includes demonstration videos in the videos/ folder.
Usage
from lerobot.common.policies.diffusion.modeling_diffusion import DiffusionPolicy
policy = DiffusionPolicy.from_pretrained("RafaelJaime/pusht-diffusion")
Citation
@article{chi2024diffusionpolicy,
author = {Cheng Chi and Zhenjia Xu and Siyuan Feng and Eric Cousineau and Yilun Du and Benjamin Burchfiel and Russ Tedrake and Shuran Song},
title = {Diffusion Policy: Visuomotor Policy Learning via Action Diffusion},
journal = {The International Journal of Robotics Research},
year = {2024},
}
Published on 2025-04-28