rofunc 0.0.2.1

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

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

Repository address: https://github.com/Skylark0924/Rofunc

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 Isaac Gym-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
  • Installation
    • Install from PyPI (stable version)
    • Install from Source (nightly version, recommended)
  • Documentation
  • Star History
  • Citation
  • Related Papers
  • The Team
  • Acknowledge
    • Learning from Demonstration
    • Planning and Control

Installation

Install from PyPI (stable version)

The installation is very easy,

pip install rofunc

# [Option] Install with baseline RL frameworks (SKRL, RLlib, Stable Baselines3) and Envs (gymnasium[all], mujoco_py)
pip install rofunc[baselines]

and as you'll find later, it's easy to use as well!

import rofunc as rf

Thus, have fun in the robotics world!

Note Several requirements need to be installed before using the package. Please refer to the installation guide for more details.

Install from Source (nightly version, recommended)

git clone https://github.com/Skylark0924/Rofunc.git
cd Rofunc

# Create a conda environment
# Python 3.8 is strongly recommended
conda create -n rofunc python=3.8

# For Linux user
sh ./scripts/install.sh
# [Option] Install with baseline RL frameworks (SKRL, RLlib, Stable Baselines3)
sh ./scripts/install_w_baselines.sh
# [Option] For MacOS user (brew is required, Isaac Gym based simulator is not supported on MacOS)
sh ./scripts/mac_install.sh

Note If you want to use functions related to ZED camera, you need to install ZED SDK manually. (We have tried to package it as a .whl file to add it to requirements.txt, unfortunately, the ZED SDK is not very friendly and doesn't support direct installation.)

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.

The available functions and plans can be found as follows.

Note ✅: Achieved 🔃: Reformatting ⛔: TODO

Data		Learning		P&C		Tools		Simulator
xsens.record	✅	DMP	⛔	LQT	✅	Config	✅	Franka	✅
xsens.export	✅	GMR	✅	LQTBi	✅	robolab.coord	✅	CURI	✅
xsens.visual	✅	TPGMM	✅	LQTFb	✅	robolab.fk	✅	CURIMini	🔃
opti.record	✅	TPGMMBi	✅	LQTCP	✅	robolab.ik	✅	CURISoftHand	✅
opti.export	✅	TPGMM_RPCtl	✅	LQTCPDMP	✅	robolab.fd	⛔	Walker	✅
opti.visual	✅	TPGMM_RPRepr	✅	LQR	✅	robolab.id	⛔	Gluon	🔃
zed.record	✅	TPGMR	✅	PoGLQRBi	✅	visualab.dist	✅	Baxter	🔃
zed.export	✅	TPGMRBi	✅	iLQR	🔃	visualab.ellip	✅	Sawyer	🔃
zed.visual	✅	TPHSMM	✅	iLQRBi	🔃	visualab.traj	✅	Multi-Robot	✅
emg.record	✅	BCO(RofuncIL)	🔃	iLQRFb	🔃
emg.export	✅	BC-Z(RofuncIL)	⛔	iLQRCP	🔃
emg.visual	✅	STrans(RofuncIL)	⛔	iLQRDyna	🔃
mmodal.record	⛔	RT-1(RofuncIL)	⛔	iLQRObs	🔃
mmodal.export	✅	PPO(SKRL)	✅	MPC	⛔
		SAC(SKRL)	✅	RMP	⛔
		TD3(SKRL)	✅
		PPO(StB3)	⛔
		SAC(StB3)	⛔
		TD3(StB3)	⛔
		PPO(RLlib)	✅
		SAC(RLlib)	✅
		TD3(RLlib)	✅
		PPO(ElegRL)	✅
		SAC(ElegRL)	✅
		TD3(ElegRL)	✅
		PPO(RofuncRL)	✅
		SAC(RofuncRL)	✅
		TD3(RofuncRL)	✅
		ODTrans(RofuncRL)	⛔
		RT-1(RofuncRL)	⛔
		CQL(RofuncRL)	⛔
		TD3BC(RofuncRL)	⛔
		DTrans(RofuncRL)	🔃
		EDAC(RofuncRL)	⛔

Star History

Citation

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

@misc{Rofunc2022,
      author = {Liu, Junjia and Li, Chenzui and Delehelle, Donatien and Li, Zhihao and Chen, Fei},
      title = {Rofunc: The full process python package for robot learning from demonstration and robot manipulation},
      year = {2022},
      publisher = {GitHub},
      journal = {GitHub repository},
      howpublished = {\url{https://github.com/Skylark0924/Rofunc}},
}

Related Papers

1. Robot cooking with stir-fry: Bimanual non-prehensile manipulation of semi-fluid objects (IEEE RA-L 2022 | Code)

@article{liu2022robot,
         title={Robot cooking with stir-fry: Bimanual non-prehensile manipulation of semi-fluid objects},
         author={Liu, Junjia and Chen, Yiting and Dong, Zhipeng and Wang, Shixiong and Calinon, Sylvain and Li, Miao and Chen, Fei},
         journal={IEEE Robotics and Automation Letters},
         volume={7},
         number={2},
         pages={5159--5166},
         year={2022},
         publisher={IEEE}
}

2. SoftGPT: Learn Goal-oriented Soft Object Manipulation Skills by Generative Pre-trained Heterogeneous Graph Transformer (IROS 2023)
3. Learning Robot Generalized Bimanual Coordination using Relative Parameterization Method on Human Demonstration (IEEE CDC 2023 | Code)

The Team

Rofunc is developed and maintained by the CLOVER Lab (Collaborative and Versatile Robots Laboratory), CUHK.

Acknowledge

We would like to acknowledge the following projects:

Learning from Demonstration

1. pbdlib
2. Ray RLlib
3. ElegantRL
4. SKRL

Planning and Control

1. Robotics codes from scratch (RCFS)