Presentation 2014/2/6
A role recognition model for an assistant robot in poster session
Kan OGAWA, Shogo OKADA, Katsumi NITTA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) This paper reports our research on a role recognition model for an assistant robot in a poster session. For helping a poster presenter, the robot recognize participants and guides them to the better locations according to their roles. We classify participants role into 4 types such as; a speaker, an addressee, a side-participant, ant the other. To recognize participants of the poster session, several sensors are used to cope with occlusion of participants. Among them, some sensors are mounted to the robot, and others are set to the poster room and they capture interaction scene among participants by depth sensors. We analyse which position is appropriate for robot to recognize human and human role.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Sensor fusion / Human detection / Participation structure recognition
Paper # CNR2013-37,PRMU2013-129
Date of Issue

Conference Information
Committee CNR
Conference Date 2014/2/6(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 Cloud Network Robotics (CNR)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) A role recognition model for an assistant robot in poster session
Sub Title (in English)
Keyword(1) Sensor fusion
Keyword(2) Human detection
Keyword(3) Participation structure recognition
1st Author's Name Kan OGAWA
1st Author's Affiliation Tokyo Institute of Technology()
2nd Author's Name Shogo OKADA
2nd Author's Affiliation Tokyo Institute of Technology
3rd Author's Name Katsumi NITTA
3rd Author's Affiliation Tokyo Institute of Technology
Date 2014/2/6
Paper # CNR2013-37,PRMU2013-129
Volume (vol) vol.113
Number (no) 432
Page pp.pp.-
#Pages 4
Date of Issue