Title
Explicit coordinated localization using common visual objects
Abstract
Localization in multi-robot systems is a key prob- lem in multi agent systems. In many cases, specially involving legged robots, like the Robocup soccer competition, it relies on predefined landmarks at known locations. However, when several objects are in motion, vision occlusions due to agents in the field of view make this kind of localization unfeasible for mild time periods. This also happens if landmarks are not within the field of view. This paper presents a technique to le t a robot estimate its position with respect to objects or robots by sharing whatever visual data it has with its teammates. Shared data is used to estimate the relative positions of robots watching the same object via stereoscopy. The rest of the robots can be localized via triangulation and acquire information on the position of hidden or unknown objects that other members of the team can see. The system has been tested with two Aibo ERS 7 robots from Sony and an Aiball. estimate the position of one robot with respect to its refere nce system. In our case, our environment will be a typical test one for MAS: the RoboCup robot league. In RoboCup, specially when legged robots are involved, localization is mostly visual rather than based on dead-reckoning. Indeed, the soccer fiel ds typically include color landmarks at known positions that the robot may use for global localization. Landmark based localization, though, presents two major drawbacks. First, robots may locate themselves with respect to the landmark, but do not know the positions of the others. Second, these systems are very prone to occlusions, specially when there are many robots in the field. Naturally, it is possible to take advantage of communication with other team members, so that the field of view of the team is larger than that of a robot alone.
Year
DOI
Venue
2010
10.1109/ROBOT.2010.5509398
ICRA
Keywords
Field
DocType
legged locomotion,multi-robot systems,position control,stereo image processing,Aibo ERS 7 robots,Robocup soccer competition,common visual objects,explicit coordinated localization,legged robots,multi-agent systems,multi-robot systems,position estimation,stereoscopy,triangulation,visual data sharing
Visual Objects,Computer vision,Visualization,Stereoscopy,Robot kinematics,Multi-agent system,Triangulation (social science),AIBO,Artificial intelligence,Engineering,Robot
Conference
Volume
Issue
ISSN
2010
1
1050-4729
Citations 
PageRank 
References 
0
0.34
19
Authors
4
Name
Order
Citations
PageRank
Jose Manuel Peula1275.49
Javier Cebolla200.34
C. Urdiales325133.14
Francisco Sandoval Hernández4771104.15