---

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

<img src="https://img.shields.io/badge/%F0%9F%A4%97%20models-hugging%20face-F8D521">

Repository address: https://github.com/Skylark0924/Rofunc <br> Documentation: https://rofunc.readthedocs.io/

<img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspSpatulaRofuncRLPPO.gif" width=25% /><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspPower_drillRofuncRLPPO.gif" width=25% /><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspPhillips_Screw_DriverRofuncRLPPO.gif" width=25% /><img src="doc/img/task_gif/CURIQbSoftHandSynergyGraspLarge_clampRofuncRLPPO.gif" width=25% /> <img src="doc/img/task_gif/CURICoffeeStirring.gif" width=33.3% /><img src="doc/img/task_gif/CURIScrew.gif" width=33.3% /><img src="doc/img/task_gif/CURITaichiPushingHand.gif" width=33.3% /> <img src="doc/img/task_gif/UDH_Random_Motion.gif" width=25% /><img src="doc/img/task_gif/H1_Random_Motion.gif" width=25% /><img src="doc/img/task_gif/Bruce_Random_Motion.gif" width=25% /><img src="doc/img/task_gif/Walker_Random_Motion.gif" width=25% /> <img src="doc/img/task_gif/HumanoidFlipRofuncRLAMP.gif" width=33.3% /><img src="doc/img/task_gif/HumanoidDanceRofuncRLAMP.gif" width=33.3% /><img src="doc/img/task_gif/HumanoidRunRofuncRLAMP.gif" width=33.3% /> <img src="doc/img/task_gif/HumanoidASEHeadingSwordShieldRofuncRLASE.gif" width=33.3% /><img src="doc/img/task_gif/HumanoidASEStrikeSwordShieldRofuncRLASE.gif" width=33.3% /><img src="doc/img/task_gif/HumanoidASELocationSwordShieldRofuncRLASE.gif" width=33.3% /> <img src="doc/img/task_gif/BiShadowHandLiftUnderarmRofuncRLPPO.gif" width=33.3% /><img src="doc/img/task_gif/BiShadowHandDoorOpenOutwardRofuncRLPPO.gif" width=33.3% /><img src="doc/img/task_gif/BiShadowHandSwingCupRofuncRLPPO.gif" width=33.3% />

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.

• Rofunc: The Full Process Python Package for Robot Learning from Demonstration and Robot Manipulation
  • Citation
  • Update News 🎉🎉🎉
    • v0.0.2.6 Support dexterous grasping and human-humanoid robot skill transfer
  • Installation
  • Documentation
  • RofuncRL
  • Star History
  • Related Papers
  • The Team
  • Acknowledge
    • Learning from Demonstration
    • Planning and Control

Citation

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

@article{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},
	journal={Zenodo, https://github.com/Skylark0924/Rofunc},
	doi={10.5281/zenodo.10016946},
}

[!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。

Update News 🎉🎉🎉

• [2024-12-24] 🎮 Start trying to support Genesis simulator.

v0.0.2.6 Support dexterous grasping and human-humanoid robot skill transfer

• [2024-12-20] 🎉🚀 Human-level skill transfer from human to heterogeneous humanoid robots have been completed and are awaiting release. Preview
• [2024-01-24] 🚀 CURI Synergy-based Softhand grasping tasks are supported to be trained by RofuncRL.
• [2023-10-31] 🚀 RofuncRL: A modular easy-to-use Reinforcement Learning sub-package designed for Robot Learning tasks is released. It has been tested with simulators like OpenAIGym, IsaacGym, OmniIsaacGym (see example gallery), and also differentiable simulators like PlasticineLab and DiffCloth.
• ...
• If you want to know more about the update news, please refer to the changelog.

Installation

Please refer to the installation guide.

Documentation

To give you a quick overview of the pipeline of rofunc, we provide an interesting example of learning to play Taichi from human demonstration. You can find it in the Quick start section of the documentation.

<details> <summary>The available functions and plans can be found as follows.</summary>

Note ✅: Achieved 🔃: Reformatting ⛔: TODO

| Data | | Learning | | P&C | | Tools | | Simulator | | |:-------------------------------------------------------------------------------------------------------:|---|:------------------------------------------------------------------------------------------------------:|----|:------------------------------------------------------------------------------------------------------------------:|----|:-------------------------------------------------------------------------------------------------------------------:|---|:------------------------------------------------------------------------------------------------------------:|----| | xsens.record | ✅ | DMP | ⛔ | LQT | ✅ | config | ✅ | Franka | ✅ | | xsens.export | ✅ | GMR | ✅ | LQTBi | ✅ | logger | ✅ | CURI | ✅ | | xsens.visual | ✅ | TPGMM | ✅ | LQTFb | ✅ | datalab | ✅ | CURIMini | 🔃 | | [`opti.reco