Localization of mobile robot by matching three-dimensional data of SOKUIKI sensor and aerial imagery

Author

Ito, Kei ; Yokota, K. ; Ohya, Akihisa

Author_Institution

Dept. of Mech. Eng., Kanazawa Tech. Coll., Kanazawa, Japan

fYear

2012

fDate

16-18 Dec. 2012

Firstpage

49

Lastpage

54

Abstract

In recent years, the demand for autonomous mobile robots in outdoors environments has been increasing. In order to guide the robot, it is essential to get the current position. In this study, we propose a method to correct the self-position of the robot, which is estimated by odometry, aerial imagery, and the SOKUIKI sensor. First, we explore how to superimpose the reflection point cloud on top of the aerial imagery. Next, matching the edge data of aerial imagery and the upper edge of the building from the inclined reflection point cloud corrects the self-correction of the robot, by which the robot is able to run on the straight road for about 60m autonomously.

Keywords

edge detection; image matching; laser ranging; mobile robots; robot vision; SOKUIKI sensor; aerial imagery; autonomous mobile robots; edge data matching; inclined reflection point cloud; mobile robot Localization; odometry; outdoor environment; reflection point cloud superimposition; robot self-position correction method; three-dimensional data matching; Buildings; Educational institutions; Equations; Image edge detection; Mobile robots; Robot sensing systems;

fLanguage

English

Publisher

ieee

Conference_Titel

System Integration (SII), 2012 IEEE/SICE International Symposium on

Conference_Location

Fukuoka

Print_ISBN

978-1-4673-1496-1

Type

conf

DOI

10.1109/SII.2012.6426962

Filename

6426962