Presentation 2004/6/11
Application of Multiple Linear Regression Models to Robotic Hand Control with Data Glove
Yuki UEYAMA, Kiyoshi HOSHINO,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) We built the master-slave system for humanoid robotic hand control with data glove for the purpose of obtaining optimal and automatic matching between a motion-measurement device and output device both of which have many degree of freedom. The relationship of inputs and outputs between data glove and robotic hand was described multiple linear regression model for multiple linear regression coefficient which was resulted singular value decomposition to decrease the influence of system noise with an algorithm which be abele to avoid amplification of noise. By this way, it was been possible to match the relationship of inputs and outputs automatically and at fast. The result of experiments from viewpoints of positioning accuracy and time subordinate characteristic, the robotic hand could be controlled with no offset and below 80ms delay including communication and waste of actuators times.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) robotic hand / data glove / linear regression model / singular value decomposition / minimum mean-squared error criterion
Paper # PRMU2004-36
Date of Issue

Conference Information
Committee PRMU
Conference Date 2004/6/11(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 Pattern Recognition and Media Understanding (PRMU)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Application of Multiple Linear Regression Models to Robotic Hand Control with Data Glove
Sub Title (in English)
Keyword(1) robotic hand
Keyword(2) data glove
Keyword(3) linear regression model
Keyword(4) singular value decomposition
Keyword(5) minimum mean-squared error criterion
1st Author's Name Yuki UEYAMA
1st Author's Affiliation University of Tsukuba, Graduate School, System and Information Engineering()
2nd Author's Name Kiyoshi HOSHINO
2nd Author's Affiliation University of Tsukuba, Graduate School, System and Information Engineering and JST
Date 2004/6/11
Paper # PRMU2004-36
Volume (vol) vol.104
Number (no) 125
Page pp.pp.-
#Pages 6
Date of Issue