Presentation 2003/10/17
Classification of Object-handling Tasks based on Qualitative Expression on Human Motion Data
Tomomasa SATO, Hideyuki KUBOTERA, Tatsuya HARADA, Taketoshi MORI,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper proposes an algorithm to acquire object-handling tasks abstracted from multiple observations of human motion in their dairy life. The algorithm consists of the following procedures; 1) Firstly, the system measures multiple human object-handling tasks on a table. Qualitatively expressed values are calculated from measured trajectory data of a human hand and an object together with table force data. This expressions are then converted to probabilistic description. 2) Secondary, the system classifies human tasks by utilizing the probabilistic description. 3) Thirdly the trajectory which enables the robot-hand to imitate each classified task is acquired. The experiment proves the validity of the algorithm.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) imitation / probability / qualitative expression / typical task
Paper # PRMU2003-139,NC2003-70
Date of Issue

Conference Information
Committee NC
Conference Date 2003/10/17(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair
Vice Chair
Secretary
Assistant

Paper Information
Registration To Neurocomputing (NC)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Classification of Object-handling Tasks based on Qualitative Expression on Human Motion Data
Sub Title (in English)
Keyword(1) imitation
Keyword(2) probability
Keyword(3) qualitative expression
Keyword(4) typical task
1st Author's Name Tomomasa SATO
1st Author's Affiliation Department of Mechano-Informatics, Graduate School of Information Science and Technology, Univ. of Tokyo()
2nd Author's Name Hideyuki KUBOTERA
2nd Author's Affiliation Department of Mechano-Informatics, Graduate School of Information Science and Technology, Univ. of Tokyo
3rd Author's Name Tatsuya HARADA
3rd Author's Affiliation Department of Mechano-Informatics, Graduate School of Information Science and Technology, Univ. of Tokyo
4th Author's Name Taketoshi MORI
4th Author's Affiliation Department of Mechano-Informatics, Graduate School of Information Science and Technology, Univ. of Tokyo
Date 2003/10/17
Paper # PRMU2003-139,NC2003-70
Volume (vol) vol.103
Number (no) 392
Page pp.pp.-
#Pages 6
Date of Issue