coordination_oru

Robot-agnostic online coordination for multiple robots

Executable

Rviz Img

Developed by
License
GNU General Public License (GPL) v3

Main Characteristic

This software implements an online coordination method for multiple robots. Its main features are:

  • Goals can be posted and paths computed online
  • Precedences are inferred online, accounting for robot dynamics via provided dynamic models
  • Very few assumptions are made on robot controllers
  • The coordination method is not specific to a particular motion planning technique

 

 

Research areas
Integrative AI Physical AI
Technical Categories
Robotics and automation
Last updated
02.08.2022 - 20:38
Detailed Description

Execution environment: linux

Version of the environment: Ubuntu > 16.04

Install & Run: This is a Java library, so it should run on any platform with a Java Runtime Environment. Some features require the OMPL and MRPT libraries, namely, a builti-in example path planner. For these to work, you need to install these libraries for your platform, please see the instructions in the readme or on the Github page: https://github.com/FedericoPecora/coordination_oru

Additional information: The software includes a basic 2D robot simulation and a simple built-in motion planner (which depends on the OMPL and MRPT libraries). A separate interface package is provided to enable the use of this software in conjunction with ROS and the navigation_oru stack to obtain a fully implemented stack for multi-robot coordination and motion planning.

Trustworthy AI
The implemented algorithm guarantees safety, as proved in the papers: [1,2]. The implementation has been empirically validated, however: This program is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for more details.

[1] https://ojs.aaai.org/index.php/ICAPS/article/view/13923
[2] https://doi.org/10.1109/LRA.2019.2924849
GDPR Requirements
The resource does not involve personal data of any kind, hence GDPR does not apply.