DocumentCode
1386416
Title
View-invariant regions and mobile robot self-localization
Author
Simsarian, Kristian T. ; Olson, Thomas J. ; Nandhakumar, N.
Author_Institution
Swedish Inst. of Comput. Sci., Kista, Sweden
Volume
12
Issue
5
fYear
1996
fDate
10/1/1996 12:00:00 AM
Firstpage
810
Lastpage
816
Abstract
This paper addresses the problem of mobile robot self-localization given a polygonal map and a set of observed edge segments. The standard approach uses interpretation tree search with pruning heuristics to match observed edges to map edges. Our approach introduces a preprocessing step in which the map is decomposed into view-invariant regions (VIRs). The VIR decomposition captures information about map edge visibility, and can be used for a variety of robot navigation tasks
Keywords
edge detection; feature extraction; image segmentation; mobile robots; navigation; path planning; robot vision; self-adjusting systems; 2D polygonal map; line segment extraction; map edge visibility; mobile robot; navigation; observed edge segments; polygonal map; self-localization; view-invariant regions; Computer science; Costs; Data mining; Mobile robots; Monitoring; Navigation; Orbital robotics; Path planning; Robot sensing systems; Search methods;
fLanguage
English
Journal_Title
Robotics and Automation, IEEE Transactions on
Publisher
ieee
ISSN
1042-296X
Type
jour
DOI
10.1109/70.538985
Filename
538985
Link To Document