---
license: gpl-3.0
pipeline_tag: robotics
---


![](doc/img/logo/logo8.png)

---

# Rofunc: The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation

> **Repository address: [https://github.com/Skylark0924/Rofunc](https://github.com/Skylark0924/Rofunc)** <br>
> **Documentation: [https://rofunc.readthedocs.io/](https://rofunc.readthedocs.io/)**


<style>
    /* 通用表格样式 */
    table {
        width: 100%;
        border-collapse: collapse;
        table-layout: fixed;
        margin-bottom: 20px;
    }
    
    td {
        padding: 0;
        overflow: hidden;
        vertical-align: middle;
    }
    
    img {
        width: 100%;
        display: block;
        object-fit: contain;
    }
    
    /* 第一个表格样式 - 每行4列 */
    .table-four-cols tr {
        height: 180px;
    }
    
    .table-four-cols td {
        width: 25%;
    }
    
    /* 第二个表格样式 - 每行3列 */
    .table-three-cols tr {
        height: 180px;
    }
    
    .table-three-cols td {
        width: 33.33%;
    }
    
    /* 隐藏第二个表格的空单元格 */
    .table-three-cols td:empty {
        display: none;
    }
</style>

<!-- 第一个表格 - 4列布局 -->
<table class="table-four-cols">
    <tr>
        <td><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspSpatulaRofuncRLPPO.gif"></td>
        <td><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspPower_drillRofuncRLPPO.gif"></td>
        <td><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspPhillips_Screw_DriverRofuncRLPPO.gif"></td>
        <td><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspLarge_clampRofuncRLPPO.gif"></td>
    </tr>
    <tr>
        <td><img src="doc/img/task_gif/UDH_Random_Motion.gif"></td>     
        <td><img src="doc/img/task_gif/H1_Random_Motion.gif"></td>
        <td><img src="doc/img/task_gif/Bruce_Random_Motion.gif"></td>
        <td><img src="doc/img/task_gif/Walker_Random_Motion.gif"></td>
    </tr>
</table>

<!-- 第二个表格 - 3列布局 -->
<table class="table-three-cols">
    <tr>
        <td><img src="doc/img/task_gif/CURICoffeeStirring.gif"></td>
        <td><img src="doc/img/task_gif/CURIScrew.gif"></td>
        <td><img src="doc/img/task_gif/CURITaichiPushingHand.gif"></td>
    </tr>
    <tr>
        <td><img src="doc/img/task_gif/HumanoidFlipRofuncRLAMP.gif"></td>
        <td><img src="doc/img/task_gif/HumanoidDanceRofuncRLAMP.gif"></td>
        <td><img src="doc/img/task_gif/HumanoidRunRofuncRLAMP.gif"></td>
    </tr>
    <tr>
        <td><img src="doc/img/task_gif/HumanoidASEHeadingSwordShieldRofuncRLASE.gif"></td>
        <td><img src="doc/img/task_gif/HumanoidASEStrikeSwordShieldRofuncRLASE.gif"></td>
        <td><img src="doc/img/task_gif/HumanoidASELocationSwordShieldRofuncRLASE.gif"></td>
    </tr>
    <tr>
        <td><img src="doc/img/task_gif/BiShadowHandLiftUnderarmRofuncRLPPO.gif"></td>
        <td><img src="doc/img/task_gif/BiShadowHandDoorOpenOutwardRofuncRLPPO.gif"></td>
        <td><img src="doc/img/task_gif/BiShadowHandSwingCupRofuncRLPPO.gif"></td>
    </tr>
</table>

Rofunc package focuses on the **Imitation Learning (IL), Reinforcement Learning (RL) and Learning from Demonstration (LfD)** for **(Humanoid) Robot Manipulation**. It provides valuable and convenient python functions, including
_demonstration collection, data pre-processing, LfD algorithms, planning, and control methods_. We also provide an
`IsaacGym` and `OmniIsaacGym` based robot simulator for evaluation. This package aims to advance the field by building a full-process
toolkit and validation platform that simplifies and standardizes the process of demonstration data collection,
processing, learning, and its deployment on robots.

## Citation

If you use rofunc in a scientific publication, we would appreciate citations to the following paper:

```
@software{liu2023rofunc, 
          title = {Rofunc: The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation},
          author = {Liu, Junjia and Dong, Zhipeng and Li, Chenzui and Li, Zhihao and Yu, Minghao and Delehelle, Donatien and Chen, Fei},
          year = {2023},
          publisher = {Zenodo},
          doi = {10.5281/zenodo.10016946},
          url = {https://doi.org/10.5281/zenodo.10016946},
          dimensions = {true},
          google_scholar_id = {0EnyYjriUFMC},
}
```
> [!WARNING]
> **If our code is found to be used in a published paper without proper citation, we reserve the right to address this issue formally by contacting the editor to report potential academic misconduct!**
> 
> **如果我们的代码被发现用于已发表的论文而没有被恰当引用，我们保留通过正式联系编辑报告潜在学术不端行为的权利。**