Authors:
Patricio Nebot
and
Enric Cervera
Affiliation:
Jaume-I University, Spain
Keyword(s):
Mobile robots, Visual localization, Color vision, Common objects.
Related
Ontology
Subjects/Areas/Topics:
Image Processing
;
Informatics in Control, Automation and Robotics
;
Mobile Robots and Autonomous Systems
;
Robotics and Automation
;
Vision, Recognition and Reconstruction
Abstract:
Robot localization is one of the fundamental problems in mobile robotics. Using sensory information to localize the robot in its environment is the most fundamental problem that has to be solved in order to provide a mobile robot with autonomous capabilities, But, if robots can detect each other, there is the opportunity to do better. In this paper, it is explained how one robot, the leader, with a pan-tilt-zoom camera mounted on it can localize a team of robots. Camera images are used to detect other robots and to determine the relative position of the detected robot and its orientation with respect to the leader. Each robot carries a colored target that helps the leader to recognize it and calculate their position and orientation. Moreover, the zoom is used to enhance the perception and get a higher accuracy and a larger field of view.