Object recognition using local EGI and 3D models with M-estimators

Author

Kawarnura, K. ; Hasegawa, Kiminori ; Yamashita, Osamu ; Sato, Yoichi ; Ikeuchi, Katsushi

Author_Institution

Kyushu Electr. Power Co. Inc., Fukuoka, Japan

fYear

1999

fDate

1999

Firstpage

80

Lastpage

86

Abstract

A robot using a tele-operated system greatly reduces the demands on the human operator, although some human intervention is still required. In order to automate some of the robot´s capabilities, we have developed a 3D object-localization method for the robot´s positional adjustment. The method is designed to be insensitive to noise and outliers while, at the same time, it has optimal run-time efficiency. Our algorithm is general enough to be applied not only to our dual-armed mobile robots but also to other tele-operation robots. This paper first describes our algorithm, and then presents the performance evaluation

Keywords

mobile robots; object recognition; position control; robot vision; stereo image processing; telerobotics; 3D models; extended Gaussian images; mobile robots; object recognition; object-localization; performance evaluation; pose estimation; position control; robot vision; telerobotics; Design methodology; Employee welfare; Humans; Insulation; Iterative closest point algorithm; Mobile robots; Object recognition; Power system modeling; Robotics and automation; Runtime;

fLanguage

English

Publisher

ieee

Conference_Titel

Multisensor Fusion and Integration for Intelligent Systems, 1999. MFI '99. Proceedings. 1999 IEEE/SICE/RSJ International Conference on

Conference_Location

Taipei

Print_ISBN

0-7803-5801-5

Type

conf

DOI

10.1109/MFI.1999.815969

Filename

815969