Agent auto-generation system

Interact with your favorite things

Shiori Sawada, Taichi Sono, Michita Imai

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper proposes a framework for an Agent Auto-Generation System (AAGS) which gets information from sensor devices and improvises a conversational agent from arbitrary things. AAGS has agent-Types to prepare a perception for an improvised agent according to the shape of the agentization targets. It also has virtual-input, which generates knowledge representation related to information extracted from the networked sensor devices. The virtual-input employs a viewpoint based on the agent-Type to generate a knowledge expression, and gives it to the improvised agent. Experiments to evaluate AAGS revealed that it is necessary to consider the perception of the improvised agents based on the agent-Types. In addition, the agent's viewpoint for the perception has an effect on how people recognize the improvised agent.

Original languageEnglish
Title of host publicationRO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages201-206
Number of pages6
Volume2017-January
ISBN (Electronic)9781538635186
DOIs
Publication statusPublished - 2017 Dec 8
Event26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017 - Lisbon, Portugal
Duration: 2017 Aug 282017 Sep 1

Other

Other26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017
CountryPortugal
CityLisbon
Period17/8/2817/9/1

Fingerprint

Thing
Sensor
Agent Systems
Knowledge Representation
Sensors
Knowledge representation
Target
Necessary
Evaluate
Arbitrary

ASJC Scopus subject areas

  • Artificial Intelligence
  • Computer Networks and Communications
  • Human-Computer Interaction
  • Control and Optimization

Cite this

Sawada, S., Sono, T., & Imai, M. (2017). Agent auto-generation system: Interact with your favorite things. In RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication (Vol. 2017-January, pp. 201-206). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROMAN.2017.8172302

Agent auto-generation system : Interact with your favorite things. / Sawada, Shiori; Sono, Taichi; Imai, Michita.

RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. p. 201-206.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Sawada, S, Sono, T & Imai, M 2017, Agent auto-generation system: Interact with your favorite things. in RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication. vol. 2017-January, Institute of Electrical and Electronics Engineers Inc., pp. 201-206, 26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017, Lisbon, Portugal, 17/8/28. https://doi.org/10.1109/ROMAN.2017.8172302
Sawada S, Sono T, Imai M. Agent auto-generation system: Interact with your favorite things. In RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication. Vol. 2017-January. Institute of Electrical and Electronics Engineers Inc. 2017. p. 201-206 https://doi.org/10.1109/ROMAN.2017.8172302
Sawada, Shiori ; Sono, Taichi ; Imai, Michita. / Agent auto-generation system : Interact with your favorite things. RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication. Vol. 2017-January Institute of Electrical and Electronics Engineers Inc., 2017. pp. 201-206
@inproceedings{8cc82a85d4644046935b395a087586b7,
title = "Agent auto-generation system: Interact with your favorite things",
abstract = "This paper proposes a framework for an Agent Auto-Generation System (AAGS) which gets information from sensor devices and improvises a conversational agent from arbitrary things. AAGS has agent-Types to prepare a perception for an improvised agent according to the shape of the agentization targets. It also has virtual-input, which generates knowledge representation related to information extracted from the networked sensor devices. The virtual-input employs a viewpoint based on the agent-Type to generate a knowledge expression, and gives it to the improvised agent. Experiments to evaluate AAGS revealed that it is necessary to consider the perception of the improvised agents based on the agent-Types. In addition, the agent's viewpoint for the perception has an effect on how people recognize the improvised agent.",
author = "Shiori Sawada and Taichi Sono and Michita Imai",
year = "2017",
month = "12",
day = "8",
doi = "10.1109/ROMAN.2017.8172302",
language = "English",
volume = "2017-January",
pages = "201--206",
booktitle = "RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Agent auto-generation system

T2 - Interact with your favorite things

AU - Sawada, Shiori

AU - Sono, Taichi

AU - Imai, Michita

PY - 2017/12/8

Y1 - 2017/12/8

N2 - This paper proposes a framework for an Agent Auto-Generation System (AAGS) which gets information from sensor devices and improvises a conversational agent from arbitrary things. AAGS has agent-Types to prepare a perception for an improvised agent according to the shape of the agentization targets. It also has virtual-input, which generates knowledge representation related to information extracted from the networked sensor devices. The virtual-input employs a viewpoint based on the agent-Type to generate a knowledge expression, and gives it to the improvised agent. Experiments to evaluate AAGS revealed that it is necessary to consider the perception of the improvised agents based on the agent-Types. In addition, the agent's viewpoint for the perception has an effect on how people recognize the improvised agent.

AB - This paper proposes a framework for an Agent Auto-Generation System (AAGS) which gets information from sensor devices and improvises a conversational agent from arbitrary things. AAGS has agent-Types to prepare a perception for an improvised agent according to the shape of the agentization targets. It also has virtual-input, which generates knowledge representation related to information extracted from the networked sensor devices. The virtual-input employs a viewpoint based on the agent-Type to generate a knowledge expression, and gives it to the improvised agent. Experiments to evaluate AAGS revealed that it is necessary to consider the perception of the improvised agents based on the agent-Types. In addition, the agent's viewpoint for the perception has an effect on how people recognize the improvised agent.

UR - http://www.scopus.com/inward/record.url?scp=85045755456&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045755456&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2017.8172302

DO - 10.1109/ROMAN.2017.8172302

M3 - Conference contribution

VL - 2017-January

SP - 201

EP - 206

BT - RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication

PB - Institute of Electrical and Electronics Engineers Inc.

ER -