Common Data Fusion Framework: An open-source Common Data Fusion Framework for space robotics. (18th March 2020)

• Record Type: Journal Article
• Authors: Dominguez, Raul; Post, Mark; Fabisch, Alexander; Michalec, Romain; Bissonnette, Vincent; Govindaraj, Shashank
• Is Part Of: International journal of advanced robotic systems. Volume 17:Number 2(2020:Mar./Apr.)
• Publication Date: 2020-03-18
• Subjects: Multisensor data fusion -- robotics software frameworks -- planetary robotics -- orbital robotics; Robotics -- Periodicals; Robotics; Periodicals; 629.892
• DOI: 10.1177/1729881420911767
• Languages: English
• ISSNs: 1729-8806

Abstract

Multisensor data fusion plays a vital role in providing autonomous systems with environmental information crucial for reliable functioning. In this article, we summarize the modular structure of the newly developed and released Common Data Fusion Framework and explain how it is used. Sensor data are registered and fused within the Common Data Fusion Framework to produce comprehensive 3D environment representations and pose estimations. The proposed software components to model this process in a reusable manner are presented through a complete overview of the framework, then the provided data fusion algorithms are listed, and through the case of 3D reconstruction from 2D images, the Common Data Fusion Framework approach is exemplified. The Common Data Fusion Framework has been deployed and tested in various scenarios that include robots performing operations of planetary rover exploration and tracking of orbiting satellites.