Human behavior imitation for a robot to play table tennis

Author

Wang, Qizhi ; Zhang, Xianqiang ; Xu, De

Author_Institution

Sch. of Comput. & Inf. Technol., Beijing Jiaotong Univ., Beijing, China

fYear

2012

fDate

23-25 May 2012

Firstpage

1482

Lastpage

1487

Abstract

The main purpose of this paper is to make table tennis robots complete the hit table tennis ball action by imitating human´s behavior. The main strategy is to record a video of action which people played the table tennis, then analysis the video of the racket trajectory. The racket in the image is extracted by image processing when the each frame is captured in the video. Then three-dimensional coordinates of the center of the racket and racket posture are obtained via PnP positioning approach based on the intrinsic parameters of the camera. The table tennis robot will off-line learn to complete the imitation of basic actions of the racket trajectory and postures. A large number of experimental data is used to establish basic actions of table tennis robot.

Keywords

feature extraction; learning (artificial intelligence); robot vision; sport; video cameras; video signal processing; PnP positioning method; action video recording; basic action imitation; frame capture; hit table tennis ball action; human behavior imitation; image processing; intrinsic camera parameters; offline learning; racket center; racket image extraction; racket posture; racket trajectory video analysis; table tennis robots; three-dimensional coordinates; Cameras; Fitting; Humans; Image color analysis; Image edge detection; Robot kinematics; Imitation; PnP positioning method; off-line learning; table tennis robot; the trajectory of the racket;

fLanguage

English

Publisher

ieee

Conference_Titel

Control and Decision Conference (CCDC), 2012 24th Chinese

Conference_Location

Taiyuan

Print_ISBN

978-1-4577-2073-4

Type

conf

DOI

10.1109/CCDC.2012.6243007

Filename

6243007