Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence

Chan Mi Park, Jung Yeon Lee, Hyoung Woo Baek, Hae Sung Lee, Jee Hang Lee, Jinwoo Kim

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

Abstract

Human's direct supervision on robot's erroneous behavior is crucial to enhance a robot intelligence for a 'flawless' human-robot interaction. Motivating humans to engage more actively for this purpose is however difficult. To alleviate such strain, this research proposes a novel approach, a growth and regression metaphoric interaction design inspired from human's communicative, intellectual, social competence aspect of developmental stages. We implemented the interaction design principle unto a conversational agent combined with a set of synthetic sensors. Within this context, we aim to show that the agent successfully encourages the online labeling activity in response to the faulty behavior of robots as a supervision process. The field study is going to be conducted to evaluate the efficacy of our proposal by measuring the annotation performance of real-time activity events in the wild. We expect to provide a more effective and practical means to supervise robot by real-time data labeling process for long-term usage in the human-robot interaction.

Original languageEnglish
Title of host publicationHRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction
PublisherIEEE Computer Society
Pages646-647
Number of pages2
ISBN (Electronic)9781538685556
DOIs
Publication statusPublished - 2019 Mar 22
Event14th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2019 - Daegu, Korea, Republic of
Duration: 2019 Mar 112019 Mar 14

Publication series

NameACM/IEEE International Conference on Human-Robot Interaction
Volume2019-March
ISSN (Electronic)2167-2148

Conference

Conference14th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2019
CountryKorea, Republic of
CityDaegu
Period19/3/1119/3/14

Fingerprint

Robots
Human robot interaction
Labeling
Social aspects
Sensors

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Human-Computer Interaction
  • Electrical and Electronic Engineering

Cite this

Park, C. M., Lee, J. Y., Baek, H. W., Lee, H. S., Lee, J. H., & Kim, J. (2019). Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence. In HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction (pp. 646-647). [8673212] (ACM/IEEE International Conference on Human-Robot Interaction; Vol. 2019-March). IEEE Computer Society. https://doi.org/10.1109/HRI.2019.8673212
Park, Chan Mi ; Lee, Jung Yeon ; Baek, Hyoung Woo ; Lee, Hae Sung ; Lee, Jee Hang ; Kim, Jinwoo. / Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence. HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction. IEEE Computer Society, 2019. pp. 646-647 (ACM/IEEE International Conference on Human-Robot Interaction).
@inproceedings{5e8c5a98ce88450a92b433628244a6ae,
title = "Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence",
abstract = "Human's direct supervision on robot's erroneous behavior is crucial to enhance a robot intelligence for a 'flawless' human-robot interaction. Motivating humans to engage more actively for this purpose is however difficult. To alleviate such strain, this research proposes a novel approach, a growth and regression metaphoric interaction design inspired from human's communicative, intellectual, social competence aspect of developmental stages. We implemented the interaction design principle unto a conversational agent combined with a set of synthetic sensors. Within this context, we aim to show that the agent successfully encourages the online labeling activity in response to the faulty behavior of robots as a supervision process. The field study is going to be conducted to evaluate the efficacy of our proposal by measuring the annotation performance of real-time activity events in the wild. We expect to provide a more effective and practical means to supervise robot by real-time data labeling process for long-term usage in the human-robot interaction.",
author = "Park, {Chan Mi} and Lee, {Jung Yeon} and Baek, {Hyoung Woo} and Lee, {Hae Sung} and Lee, {Jee Hang} and Jinwoo Kim",
year = "2019",
month = "3",
day = "22",
doi = "10.1109/HRI.2019.8673212",
language = "English",
series = "ACM/IEEE International Conference on Human-Robot Interaction",
publisher = "IEEE Computer Society",
pages = "646--647",
booktitle = "HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction",
address = "United States",

}

Park, CM, Lee, JY, Baek, HW, Lee, HS, Lee, JH & Kim, J 2019, Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence. in HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction., 8673212, ACM/IEEE International Conference on Human-Robot Interaction, vol. 2019-March, IEEE Computer Society, pp. 646-647, 14th Annual ACM/IEEE International Conference on Human-Robot Interaction, HRI 2019, Daegu, Korea, Republic of, 19/3/11. https://doi.org/10.1109/HRI.2019.8673212

Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence. / Park, Chan Mi; Lee, Jung Yeon; Baek, Hyoung Woo; Lee, Hae Sung; Lee, Jee Hang; Kim, Jinwoo.

HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction. IEEE Computer Society, 2019. p. 646-647 8673212 (ACM/IEEE International Conference on Human-Robot Interaction; Vol. 2019-March).

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

TY - GEN

T1 - Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence

AU - Park, Chan Mi

AU - Lee, Jung Yeon

AU - Baek, Hyoung Woo

AU - Lee, Hae Sung

AU - Lee, Jee Hang

AU - Kim, Jinwoo

PY - 2019/3/22

Y1 - 2019/3/22

N2 - Human's direct supervision on robot's erroneous behavior is crucial to enhance a robot intelligence for a 'flawless' human-robot interaction. Motivating humans to engage more actively for this purpose is however difficult. To alleviate such strain, this research proposes a novel approach, a growth and regression metaphoric interaction design inspired from human's communicative, intellectual, social competence aspect of developmental stages. We implemented the interaction design principle unto a conversational agent combined with a set of synthetic sensors. Within this context, we aim to show that the agent successfully encourages the online labeling activity in response to the faulty behavior of robots as a supervision process. The field study is going to be conducted to evaluate the efficacy of our proposal by measuring the annotation performance of real-time activity events in the wild. We expect to provide a more effective and practical means to supervise robot by real-time data labeling process for long-term usage in the human-robot interaction.

AB - Human's direct supervision on robot's erroneous behavior is crucial to enhance a robot intelligence for a 'flawless' human-robot interaction. Motivating humans to engage more actively for this purpose is however difficult. To alleviate such strain, this research proposes a novel approach, a growth and regression metaphoric interaction design inspired from human's communicative, intellectual, social competence aspect of developmental stages. We implemented the interaction design principle unto a conversational agent combined with a set of synthetic sensors. Within this context, we aim to show that the agent successfully encourages the online labeling activity in response to the faulty behavior of robots as a supervision process. The field study is going to be conducted to evaluate the efficacy of our proposal by measuring the annotation performance of real-time activity events in the wild. We expect to provide a more effective and practical means to supervise robot by real-time data labeling process for long-term usage in the human-robot interaction.

UR - http://www.scopus.com/inward/record.url?scp=85063983913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063983913&partnerID=8YFLogxK

U2 - 10.1109/HRI.2019.8673212

DO - 10.1109/HRI.2019.8673212

M3 - Conference contribution

AN - SCOPUS:85063983913

T3 - ACM/IEEE International Conference on Human-Robot Interaction

SP - 646

EP - 647

BT - HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction

PB - IEEE Computer Society

ER -

Park CM, Lee JY, Baek HW, Lee HS, Lee JH, Kim J. Lifespan Design of Conversational Agent with Growth and Regression Metaphor for the Natural Supervision on Robot Intelligence. In HRI 2019 - 14th ACM/IEEE International Conference on Human-Robot Interaction. IEEE Computer Society. 2019. p. 646-647. 8673212. (ACM/IEEE International Conference on Human-Robot Interaction). https://doi.org/10.1109/HRI.2019.8673212