Self-localization and control of an omni-directional mobile robot based on an omni-directional camera

Author

Song, Kai-Tai ; Wang, Chao-Wu

Author_Institution

Dept. of Electr. & Control Eng., Nat. Chiao Tung Univ., Hsinchu, Taiwan

fYear

2009

Firstpage

899

Lastpage

904

Abstract

This paper presents a design of simultaneous localization and mapping (SLAM) for an omni-directional mobile robot using an omni-directional camera. A method is proposed to realize visual SLAM of the omni-directional mobile robot based on extended Kalman filter (EKF). Taking advantage of the 360deg view of omni-directional images, visual reference scan approach is adopted in the SLAM design. Features of previously visited places can be used repeatedly to reduce the complexity of EKF calculation. Practical experiments of the proposed self-localization and control algorithms have been carried out by using a self-constructed omni-directional mobile robot. The localization error between the start point and target point is less than 0.15 m and 1deg after traveling more than 40 meters in an indoor environment.

Keywords

Kalman filters; SLAM (robots); cameras; feature extraction; geometry; image matching; mobile robots; nonlinear filters; robot vision; EKF; extended Kalman filter; feature detection; omni-directional camera; omni-directional image matching; self-constructed omni-directional mobile robot; simultaneous localization-and-mapping; triangulation method; vision-SLAM design; visual reference scan approach; Cameras; Chaos; Feature extraction; Filtering algorithms; Indoor environments; Mobile robots; Navigation; Robot vision systems; Simultaneous localization and mapping; Vehicles;

fLanguage

English

Publisher

ieee

Conference_Titel

Asian Control Conference, 2009. ASCC 2009. 7th

Conference_Location

Hong Kong

Print_ISBN

978-89-956056-2-2

Electronic_ISBN

978-89-956056-9-1

Type

conf

Filename

5276265