Presentation 2017-03-21
Object grasping by multi-fingered robot based on transcription of human hand shape
Hiroya Fukuhara, Kawakami Takuya, Yano Masaki, Matsuo Tadashi, Shimada Nobutaka,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this research,we use the depth image of the human hand recalled as input and wake the robot hand of 3 fingers × 3 joints take the posture having the same function to grasp the object by the robot.Using Shift Invariant Auto Encoder,we create a subspace that expresses the depth image of the hand in a sub dimension.A small number of hand depth images are projected in the created sub dimensional space, and a regression model is created by associating the posture (joint angle) of the robot hand having the same function as the posture of the hand. The depth image of the hand was projected to the actually created sub dimensional space,the projected one was input to the regression model,and the estimated result was taken as the posture of the robot hand.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Shift Invariant Auto Encoder / Hand-Arm Robot / Imitation of hand / Semi-supervised learning
Paper # BioX2016-65,PRMU2016-228
Date of Issue 2017-03-13 (BioX, PRMU)

Conference Information
Committee PRMU / BioX
Conference Date 2017/3/20(2days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Eisaku Maeda(NTT) / Masakatsu Nishigaki(Shizuoka Univ.)
Vice Chair Seiichi Uchida(Kyushu Univ.) / Hironobu Fujiyoshi(Chubu Univ.) / Akira Otsuka(AIST) / Hiroshi Takano(Toyama Pref. Univ.)
Secretary Seiichi Uchida(Kyoto Univ.) / Hironobu Fujiyoshi(NTT) / Akira Otsuka(NEC) / Hiroshi Takano(AIST)
Assistant Masaki Oonishi(AIST) / Takuya Funatomi(NAIST) / Masatsugu Ichino(Univ. of Electro-Comm.) / Naoyuki Takada(Secom) / Takahiro Aoki(Fujitsu Labs.)

Paper Information
Registration To Technical Committee on Pattern Recognition and Media Understanding / Technical Committee on Biometrics
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Object grasping by multi-fingered robot based on transcription of human hand shape
Sub Title (in English)
Keyword(1) Shift Invariant Auto Encoder
Keyword(2) Hand-Arm Robot
Keyword(3) Imitation of hand
Keyword(4) Semi-supervised learning
1st Author's Name Hiroya Fukuhara
1st Author's Affiliation Ritsumeikan University(Ritsumeikan Univ)
2nd Author's Name Kawakami Takuya
2nd Author's Affiliation Ritsumeikan University(Ritsumeikan Univ)
3rd Author's Name Yano Masaki
3rd Author's Affiliation Ritsumeikan University(Ritsumeikan Univ)
4th Author's Name Matsuo Tadashi
4th Author's Affiliation Ritsumeikan University(Ritsumeikan Univ)
5th Author's Name Shimada Nobutaka
5th Author's Affiliation Ritsumeikan University(Ritsumeikan Univ)
Date 2017-03-21
Paper # BioX2016-65,PRMU2016-228
Volume (vol) vol.116
Number (no) BioX-527,PRMU-528
Page pp.pp.191-196(BioX), pp.191-196(PRMU),
#Pages 6
Date of Issue 2017-03-13 (BioX, PRMU)