Skip to main content

Research Repository

Advanced Search

Semi-automatic pose estimation of a fleet of robots with embedded stereoscopic cameras.

Cort�s, Xavier; Serratosa, Francesc; Moreno-Garcia, Carlos-Francisco

Authors

Xavier Cort�s

Francesc Serratosa



Abstract

Given a fleet of robots, automatic estimation of the relative poses between them could be inaccurate in specific environments. We propose a framework composed by the fleet of robots with embedded stereoscopic cameras providing 2D and 3D images of the scene, a human coordinator and a Human-Machine Interface. We suppose auto localising each robot through GPS or landmarks is not possible. 3D-images are used to automatically align them and deduce the relative position between robots. 2Dimages are used to reduce the alignment error in an interactive manner. A human visualises both 2D-images and the current automatic alignment, and imposes a new alignment through the Human-Machine Interface. Since the information is shared through the whole fleet, robots can deduce the position of other ones that do not visualise the same scene. Practical evaluation shows that in situations where there is a large difference between images, the interactive processes are crucial to achieve an acceptable result.

Citation

CORTÉS, X., SERRATOSA, F. and MORENO-GARCIA, C.-F. 2016. Semi-automatic pose estimation of a fleet of robots with embedded stereoscopic cameras. In Proceedings of 21st Institute of Electrical Electronic Engineers (IEEE) Emerging technologies and factory automation international conference 2016 (ETFA 2016), 6-9 September 2016, Berlin, Germany. Piscataway: IEEE [online], article ID 7733640. Available from: https://doi.org/10.1109/ETFA.2016.7733640

Conference Name 21st Institute of Electrical and Electronics Engineers (IEEE) Emerging technologies and factory automation international conference 2016 (ETFA 2016)
Conference Location Berlin, Germany
Start Date Sep 6, 2016
End Date Sep 9, 2016
Acceptance Date Oct 13, 2016
Online Publication Date Sep 9, 2016
Publication Date Nov 7, 2016
Deposit Date Oct 17, 2020
Publicly Available Date Oct 26, 2020
Publisher Institute of Electrical and Electronics Engineers (IEEE)
ISBN 9781509013142
DOI https://doi.org/10.1109/ETFA.2016.7733640
Keywords Homography estimation; Image alignment; Interactive method; Human-robot interaction; Cooperative robotics
Public URL https://rgu-repository.worktribe.com/output/977243

Files





You might also like



Downloadable Citations