Presentation 2007-01-25
Collaborative Object Recognition through Interactions with an Artificial Agent
Yasushi MIYATA, Hideki AOYAMA, Motoyuki OZEKI, Yuichi NAKAMURA,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) In this paper, we propose a novel framework for supporting our work or daily life by realizing an artificial agent mediate between a automated supportingsystem and a human using the system. In this framework, we have two modules: one is a recognition module for recognizing objects and human motions, the other is an agent module for interacting with human for informing the system state and requesting cooperative action of the human. With these modules, the support system can realize sufficient accuracy with natural cooperation of a human. We made a prototype system witha dog-style robot (AIBO) as an agent, and implemented some functions mentioned above. We conducted an experiment with the prototype system, and got the results that the performance of recognition is improved and users' impressions are mostly better than the case of without the agent.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) Object recongniition / robot agent / non-verbal interaction
Paper # MVE2006-74
Date of Issue

Conference Information
Committee MVE
Conference Date 2007/1/18(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 Media Experience and Virtual Environment (MVE)
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) Collaborative Object Recognition through Interactions with an Artificial Agent
Sub Title (in English)
Keyword(1) Object recongniition
Keyword(2) robot agent
Keyword(3) non-verbal interaction
1st Author's Name Yasushi MIYATA
1st Author's Affiliation Graduate School of Engineering, Kyoto University()
2nd Author's Name Hideki AOYAMA
2nd Author's Affiliation Graduate School of Engineering, Kyoto University
3rd Author's Name Motoyuki OZEKI
3rd Author's Affiliation Academic Center for Computing and Media Studies, Kyoto University
4th Author's Name Yuichi NAKAMURA
4th Author's Affiliation Academic Center for Computing and Media Studies, Kyoto University
Date 2007-01-25
Paper # MVE2006-74
Volume (vol) vol.106
Number (no) 496
Page pp.pp.-
#Pages 6
Date of Issue