Exploring embodiment and dueling bandit learning for preference adaptation in human-robot interaction

Sebastian Schneider, Franz Kummert

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

2 Scopus citations

Abstract

Adaptation for social companions is a crucial requirement for future applications. Personalized interaction seems to be an important factor for long-Term commitment to interact with a social robot. We present a study evaluating the feasibility of a dueling bandit learning approach for preference learning (PL) in Human-Robot Interaction (HRI). Furthermore, we explore whether the embodiment of the PL agent has an influence on the user's evaluation of the learner. We conducted a study (n=53) comparing a graphical user interface (GUI), a virtual robot and a real robot. We found no difference regarding the preference for the virtual or real robot. We used the obtained study data to compare the PL approach against a strategy that randomly selects preference rankings. The results show that that the dueling bandit PL approach can be used to learn a user's preference in HRI.

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.
Pages1325-1331
Number of pages7
ISBN (Electronic)9781538635186
DOIs
StatePublished - 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

Publication series

NameRO-MAN 2017 - 26th IEEE International Symposium on Robot and Human Interactive Communication
Volume2017-January

Conference

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

Fingerprint

Dive into the research topics of 'Exploring embodiment and dueling bandit learning for preference adaptation in human-robot interaction'. Together they form a unique fingerprint.

Cite this