Awesome
ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation
Project Page | Paper
<div style="text-align: center"> <img src="_media/model_figure.png" width="600"/> </div>This repository contains the codebase used in ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation, which will appear in RSS 2022 and is nominated for Best Student Paper Award. Specifically, the repo contains code for:
- PlushSim, the simulation environment used to generate all manipulation data.
- ACID model, the implicit visual dynamics model's model and training code.
If you find our code or paper useful, please consider citing
@article{shen2022acid,
title={ACID: Action-Conditional Implicit Visual Dynamics for Deformable Object Manipulation},
author={Shen, Bokui and Jiang, Zhenyu and Choy, Christopher and J. Guibas, Leonidas and Savarese, Silvio and Anandkumar, Anima and Zhu, Yuke},
journal={Robotics: Science and Systems (RSS)},
year={2022}
}
ACID model
Please see the README for more detailed information.
PlushSim
Please see the README for more detailed information.
License
Please check the LICENSE file. ACID may be used non-commercially, meaning for research or evaluation purposes only. For business inquiries, please contact researchinquiries@nvidia.com.