RobotToolKit

An open-source robot simulator developed for researchers and robot hackers.

Getting it Installation instructions Quick start / Examples Setting-up packages Source code documentation Packages documentation

Currently available research packages

At the LASA laboratory, we are commited to publish the source code of our research projects.
The research work developed using RobotToolKit will be constantly be provided as software packages.
Their documentation can be found here and they can directly be downloaded below.

Important: To install these packages, please follow the instructions provided on the following pages
to uncompress and set them up.

• GolfPackage (tar.gz)
  Learning to Control Planar Hitting Motions in a Minigolf-like task


• DSPackage (tar.gz)
  Imitation learning of Globally Stable Non-Linear Point-to-Point Robot Motions using Nonlinear Programming

Features

• Fully open-source C++ code
  
• Physics simulation, Real-time 3D rendering
  
• Customizable environment and robots
  
• Modular architecture for programming robot controllers and environment and object behaviors
  
• Robot models: Barrett WAM Arm, iCub, Fujitsu's Hoap-3
  
• Plug-n-play interface to real platforms: Barrett WAM Arm, and a partial version of the iCub robot
  
• Example codes
  
• Research packages of the work done at LASA-EPFL
  
• And more...
  

Legalities

The package contains a number of open-source libraries and models of commercial and open-source robots. I am including them here with the knowledge that this might not be entirely compatible with the distribution policies of each respective library and robot company. I will try to contact and get the necessary permissions, to the extent to which this is possible, from the related parties. In the meantime, I distribute this software in good faith, my goal is for people to be able to study and work with this simulator. See the acknowledgements section below for a list of the people who contributed.
You are free to use this software for personal and educational purposes, you are not allowed to use it for commercial purposes. You can redistribute the software as long as you provide a link to this page. Then again, this page will always link to the latest version of the software so you may be better off taking the version here anyway.

Acknowledgments

Many thanks to all people that have been testing, debugging, improving and using this software:

Florent D'halluin, Klas Kronander, Mohammad Khansari,
Elena Gribovskaya, Dan Grollman, Martin Duvanel,
Seungsu Kim, Sarah Degallier, Ashwini Shukla, Sylvain Calinon,
Jérome Sovilla, Lauren Blanchet, Christophe Paccolat

and particularly Prof. Aude Billard who supported this project.

Developed by Eric Sauser
Learning Algorithms and Systems Laboratory (LASA)
Swiss Federal Institute of Technology Lausanne (EPFL)
Lausanne, Switzerland, 2011

Personal webpage: www.sauser.org