Self-Localization for Mobile Robots Based on Omni-Directional Imaging of Floor Region and Dead Reckoning.

Accession number;02A0713951
Title;Self-Localization for Mobile Robots Based on Omni-Directional Imaging of Floor Region and Dead Reckoning.
Author; USUI TOMOYA (Osaka Univ.) SEKIMORI DAISUKE (Akashi National Coll. Technol., JPN) MASUTANI YASUHIRO (Osaka Univ.) MIYAZAKI FUMIO (Osaka Univ.)
Journal Title;Nippon Kikai Gakkai Robotikusu, Mekatoronikusu Koenkai Koen Ronbunshu
Journal Code:L0318A
ISSN:
VOL.2002;NO.Pt.5;PAGE.2P2.D02(1)-2P2.D02(2)(2002)
Figure&Table&Reference;FIG.7, REF.2
Pub. Country;Japan
Language;Japanese
Abstract;This paper describes a self-localization method to estimate much better values than individual methods by integrating omni-directional vision and dead reckoning with the Kalman filter. The self-localization can be executed robustly when robot position differs dramatically by collision with other obstacles or human break-in. Furthermore, Several experiments on the real robot proved the effectiveness of these methods. (author abst.)