Authors:
Younes Raoui
1
;
Michel Devy
2
;
El Houssine Bouyakhf
3
and
Fakhita Regragui
3
Affiliations:
1
University Mohamed, CNRS, LAAS and Université de Toulouse, Morocco
;
2
CNRS, LAAS and Université de Toulouse, France
;
3
University Mohamed, Morocco
Keyword(s):
Mobile robot, Mapping, Extended Kalman filter, Particle filter, Monte-Carlo Localization, RFID.
Related
Ontology
Subjects/Areas/Topics:
Informatics in Control, Automation and Robotics
;
Mobile Robots and Autonomous Systems
;
Modeling, Simulation and Architectures
;
Robotics and Automation
;
Vehicle Control Applications
Abstract:
This article deals with Simultaneous Localization andMapping for an indoor robot equipped with a camera and RFID antennas. RFID tags are sparsely disseminated in the environment. First RFID-based self-localization is considered; the robot position is predicted from odometry; it is corrected first by a sequential Monte-Carlo localization based on a particle filter. An active strategy built on the theoretical basis of information entropy is applied in order to improve the position accuracy. Then two methods for RFID-based mapping are described, considering the robot pose is given from natural visual landmarks learnt by a classical visual SLAM function.