Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults

Frank Kaptein, Joost Broekens, Koen Hindriks, Mark Neerincx

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

A good explanation takes the user who is receiving the explanation into account. We aim to get a better understanding of user preferences and the differences between children and adults who receive explanations from a robot. We implemented a Nao-robot as a belief-desire-intention (BDI)-based agent and explained its actions using two different explanation styles. Both are based on how humans explain and justify their actions to each other. One explanation style communicates the beliefs that give context information on why the agent performed the action. The other explanation style communicates the goals that inform the user of the agent's desired state when performing the action. We conducted a user study (19 children, 19 adults) in which a Nao-robot performed actions to support type 1 diabetes mellitus management. We investigated the preference of children and adults for goalversus belief-based action explanations. From this, we learned that adults have a significantly higher tendency to prefer goal-based action explanations. This work is a necessary step in addressing the challenge of providing personalised explanations in human-robot and human-agent interaction.

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.
Pages676-682
Number of pages7
Volume2017-January
ISBN (Electronic)9781538635186
DOIs
Publication statusPublished - 8 Dec 2017
Externally publishedYes
Event26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017 - Lisbon, Portugal
Duration: 28 Aug 20171 Sep 2017

Conference

Conference26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017
CountryPortugal
CityLisbon
Period28/08/171/09/17

Fingerprint

Robot
Robots
Medical problems
Diabetes Mellitus
User Studies
User Preferences
Beliefs
Children
Justify
Necessary
Interaction
Human
Style

Cite this

Kaptein, F., Broekens, J., Hindriks, K., & Neerincx, M. (2017). Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults. In RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication (Vol. 2017-January, pp. 676-682). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ROMAN.2017.8172376
Kaptein, Frank ; Broekens, Joost ; Hindriks, Koen ; Neerincx, Mark. / Personalised self-explanation by robots : The role of goals versus beliefs in robot-action explanation for children and adults. 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. 676-682
@inproceedings{e6ad82e89cf04c15930c9eb6f9931326,
title = "Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults",
abstract = "A good explanation takes the user who is receiving the explanation into account. We aim to get a better understanding of user preferences and the differences between children and adults who receive explanations from a robot. We implemented a Nao-robot as a belief-desire-intention (BDI)-based agent and explained its actions using two different explanation styles. Both are based on how humans explain and justify their actions to each other. One explanation style communicates the beliefs that give context information on why the agent performed the action. The other explanation style communicates the goals that inform the user of the agent's desired state when performing the action. We conducted a user study (19 children, 19 adults) in which a Nao-robot performed actions to support type 1 diabetes mellitus management. We investigated the preference of children and adults for goalversus belief-based action explanations. From this, we learned that adults have a significantly higher tendency to prefer goal-based action explanations. This work is a necessary step in addressing the challenge of providing personalised explanations in human-robot and human-agent interaction.",
author = "Frank Kaptein and Joost Broekens and Koen Hindriks and Mark Neerincx",
year = "2017",
month = "12",
day = "8",
doi = "10.1109/ROMAN.2017.8172376",
language = "English",
volume = "2017-January",
pages = "676--682",
booktitle = "RO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
address = "United States",

}

Kaptein, F, Broekens, J, Hindriks, K & Neerincx, M 2017, Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults. 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. 676-682, 26th IEEE International Symposium on Robot and Human Interactive Communication, RO-MAN 2017, Lisbon, Portugal, 28/08/17. https://doi.org/10.1109/ROMAN.2017.8172376

Personalised self-explanation by robots : The role of goals versus beliefs in robot-action explanation for children and adults. / Kaptein, Frank; Broekens, Joost; Hindriks, Koen; Neerincx, Mark.

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. 676-682.

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Personalised self-explanation by robots

T2 - The role of goals versus beliefs in robot-action explanation for children and adults

AU - Kaptein, Frank

AU - Broekens, Joost

AU - Hindriks, Koen

AU - Neerincx, Mark

PY - 2017/12/8

Y1 - 2017/12/8

N2 - A good explanation takes the user who is receiving the explanation into account. We aim to get a better understanding of user preferences and the differences between children and adults who receive explanations from a robot. We implemented a Nao-robot as a belief-desire-intention (BDI)-based agent and explained its actions using two different explanation styles. Both are based on how humans explain and justify their actions to each other. One explanation style communicates the beliefs that give context information on why the agent performed the action. The other explanation style communicates the goals that inform the user of the agent's desired state when performing the action. We conducted a user study (19 children, 19 adults) in which a Nao-robot performed actions to support type 1 diabetes mellitus management. We investigated the preference of children and adults for goalversus belief-based action explanations. From this, we learned that adults have a significantly higher tendency to prefer goal-based action explanations. This work is a necessary step in addressing the challenge of providing personalised explanations in human-robot and human-agent interaction.

AB - A good explanation takes the user who is receiving the explanation into account. We aim to get a better understanding of user preferences and the differences between children and adults who receive explanations from a robot. We implemented a Nao-robot as a belief-desire-intention (BDI)-based agent and explained its actions using two different explanation styles. Both are based on how humans explain and justify their actions to each other. One explanation style communicates the beliefs that give context information on why the agent performed the action. The other explanation style communicates the goals that inform the user of the agent's desired state when performing the action. We conducted a user study (19 children, 19 adults) in which a Nao-robot performed actions to support type 1 diabetes mellitus management. We investigated the preference of children and adults for goalversus belief-based action explanations. From this, we learned that adults have a significantly higher tendency to prefer goal-based action explanations. This work is a necessary step in addressing the challenge of providing personalised explanations in human-robot and human-agent interaction.

UR - http://www.scopus.com/inward/record.url?scp=85045841587&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85045841587&partnerID=8YFLogxK

U2 - 10.1109/ROMAN.2017.8172376

DO - 10.1109/ROMAN.2017.8172376

M3 - Conference contribution

VL - 2017-January

SP - 676

EP - 682

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

PB - Institute of Electrical and Electronics Engineers Inc.

ER -

Kaptein F, Broekens J, Hindriks K, Neerincx M. Personalised self-explanation by robots: The role of goals versus beliefs in robot-action explanation for children and adults. 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. 676-682 https://doi.org/10.1109/ROMAN.2017.8172376