Articles liés à Multi-Agent Visual-SLAM Algorithms on Autonomous Robots:...

Multi-Agent Visual-SLAM Algorithms on Autonomous Robots: Multi-Robot Mapping - Couverture souple

Özkucur, Nezih Ergin

 
9783838382265: Multi-Agent Visual-SLAM Algorithms on Autonomous Robots: Multi-Robot Mapping
Couverture souple
ISBN 10 : 3838382269 ISBN 13 : 9783838382265
Editeur : LAP LAMBERT Academic Publishing, 2010

Synopsis

The Simultaneous Localization and Mapping (SLAM) problem is one of the most challenging problems in robot navigation. The problem addresses autonomously exploring and mapping an unknown environment without prior knowledge (of features). The robot should generate the map of the environment and estimate its pose with respect to the map. An extension of this problem to the distributed multi-robot platform is a popular research topic for its challenges and commitments. Multiple cooperative robots exploring an area would decrease exploration time and increase the accuracy. This work introduces the application of two successful SLAM solution techniques to the multi-robot domain using visual sensors and non-unique landmarks. There are two contributions to the literature: Evolutionary Strategies (ES) is used to calibrate the parameters of the Extended Kalman Filter-SLAM (EKF-SLAM) method with supervised data, and a novel map merging method with uncertainty propagation is introduced for the Fast-SLAM algorithm. The developed algorithms are tested in both simulated and real robot experiments and the improvements and applicability of the developed methods are shown with the results.

Les informations fournies dans la section « Synopsis » peuvent faire référence à une autre édition de ce titre.

Présentation de l'éditeur

The Simultaneous Localization and Mapping (SLAM) problem is one of the most challenging problems in robot navigation. The problem addresses autonomously exploring and mapping an unknown environment without prior knowledge (of features). The robot should generate the map of the environment and estimate its pose with respect to the map. An extension of this problem to the distributed multi-robot platform is a popular research topic for its challenges and commitments. Multiple cooperative robots exploring an area would decrease exploration time and increase the accuracy. This work introduces the application of two successful SLAM solution techniques to the multi-robot domain using visual sensors and non-unique landmarks. There are two contributions to the literature: Evolutionary Strategies (ES) is used to calibrate the parameters of the Extended Kalman Filter-SLAM (EKF-SLAM) method with supervised data, and a novel map merging method with uncertainty propagation is introduced for the Fast-SLAM algorithm. The developed algorithms are tested in both simulated and real robot experiments and the improvements and applicability of the developed methods are shown with the results.

Biographie de l'auteur

Nezih Ergin Özkucur is a PhD Candidate in Computer Science atBoğaziçi University's Artificial Intelligence Lab. His researchinterests are intelligent robots, Bayesian state estimation andmapping.

Les informations fournies dans la section « A propos du livre » peuvent faire référence à une autre édition de ce titre.

Éditeur
LAP LAMBERT Academic Publishing
Date d'édition
2010
Langue
anglais
ISBN 10 
3838382269
ISBN 13 
9783838382265
Reliure
Broché
Nombre de pages
120
Coordonnées du fabricant
non disponible
Personne responsable
KreGa Onlinehandel GmbH
4950000000000
info@krega-onlinehandel.de

Birkenweg 31
Brakel
33034
Allemagne