Robotic Gaze and Human Views

DOI

Similar to human-human interaction, gaze is an important modality in conversational human-robot interaction settings. Previously, human-inspired gaze parameters have been used to implement gaze behavior for humanoid robots in conversational settings and indeed improve the user experience. Other robotic gaze implementations disregard social aspects of gaze behavior and pursue a technical goal, e.g., face tracking. However, it is unclear how deviating from human-inspired gaze parameters affects the user experience. In this study, we use eye-tracking, interaction duration, and self-reported attitudinal measures to study the impact of non-human inspired gaze timings on the user experience of the participants in a conversational setting. We show the results for systematically varying the gaze aversion ratio of a humanoid robot over a broad parameter range from almost always gazing at the human conversation partner to almost always averting the gaze. The main results reveal that on a behavioral level a low gaze aversion ratio leads to shorter interaction durations and that human participants change their own gaze aversion ratio to mimic the robot, however they do not copy the robotic gaze behavior strictly. Additionally, in the lowest gaze aversion setting, participants do not gaze back as much as expected, which indicates a user aversion to the robot gaze behavior. However, participants do not report different attitudes toward the robot during the interaction for different gaze aversion ratios. To summarize, the urge of humans in conversational settings with a humanoid robot to adapt to the perceived gaze aversion ratio is stronger than the urge of intimacy regulation through gaze aversion and high mutual gaze is not always a sign of high comfort, as suggested earlier. This result can be used as a justification to deviate from human-inspired gaze parameters when it is necessary for specific robot behavior implementations.

Identifier
DOI https://doi.org/10.48436/frswc-4dn44
Related Identifier IsVersionOf https://doi.org/10.48436/1d7wa-b3926
Metadata Access https://researchdata.tuwien.ac.at/oai2d?verb=GetRecord&metadataPrefix=oai_datacite&identifier=oai:researchdata.tuwien.ac.at:frswc-4dn44
Provenance
Creator Koller, Michael ORCID logo; Weiss, Astrid ORCID logo; Hirschmanner, Matthias (ORCID: 0000-0002-0534-385X); Vincze, Markus (ORCID: 0000-0002-2799-491X)
Publisher TU Wien
Contributor Michael, Koller; Weiss, Astrid; Matthias, Hirschmanner; Markus, Vincze
Publication Year 2022
Funding Reference FWF Austrian Science Fund 013tf3c58 ROR I3969-N30 InDex; European Commission 00k4n6c32 ROR 101017089 Tracebot
Rights Creative Commons Attribution 4.0 International; https://creativecommons.org/licenses/by/4.0/legalcode
OpenAccess true
Contact Michael, Koller (TU Wien)
Representation
Resource Type Dataset
Version 1.0.0
Discipline Other