Using Speech to Reduce Loss of Trust in Humanoid Social Robots

Amandus Krantz; Christian Balkenius; Birger Johansson

doi:10.48550/arXiv.2208.13688

Using Speech to Reduce Loss of Trust in Humanoid Social Robots

Amandus Krantz, Christian Balkenius, Birger Johansson

Research output: Contribution to conference › Paper, not in proceeding › peer-review

Abstract

We present data from two online human-robot interaction experiments where 227 participants viewed videos of a humanoid robot exhibiting faulty or non-faulty behaviours while either remaining mute or speaking. The participants were asked to evaluate their perception of the robot's trustworthiness, as well as its likeability, animacy, and perceived intelligence. The results show that, while a non-faulty robot achieves the highest trust, an apparently faulty robot that can speak manages to almost completely mitigate the loss of trust that is otherwise seen with faulty behaviour. We theorize that this mitigation is correlated with the increase in perceived intelligence that is also seen when speech is present.

Original language	English
Number of pages	4
DOIs	https://doi.org/10.48550/arXiv.2208.13688
Publication status	Published - 2022
Event	31st IEEE International Conference on Robot & Human Interactive Communication, IEEE RO-MAN - Naples, Italy Duration: 2022 Aug 29 → 2022 Sept 2 Conference number: 31 http://www.smile.unina.it/ro-man2022/

Conference

Conference	31st IEEE International Conference on Robot & Human Interactive Communication, IEEE RO-MAN
Abbreviated title	IEEE RO-MAN 2022
Country/Territory	Italy
City	Naples
Period	2022/08/29 → 2022/09/02
Internet address	http://www.smile.unina.it/ro-man2022/

Bibliographical note

SCRITA Workshop Proceedings (arXiv:2208.11090) held in conjunction with 31st IEEE International Conference on Robot & Human Interactive Communication, 29/08 - 02/09 2022, Naples (Italy)

Subject classification (UKÄ)

Social Psychology
Computer Vision and Robotics (Autonomous Systems)
Robotics

Access to Document

10.48550/arXiv.2208.13688Licence: CC BY

Cite this

@conference{ba3b4d1856124b5cb683c2e5fd077846,

title = "Using Speech to Reduce Loss of Trust in Humanoid Social Robots",

abstract = "We present data from two online human-robot interaction experiments where 227 participants viewed videos of a humanoid robot exhibiting faulty or non-faulty behaviours while either remaining mute or speaking. The participants were asked to evaluate their perception of the robot's trustworthiness, as well as its likeability, animacy, and perceived intelligence. The results show that, while a non-faulty robot achieves the highest trust, an apparently faulty robot that can speak manages to almost completely mitigate the loss of trust that is otherwise seen with faulty behaviour. We theorize that this mitigation is correlated with the increase in perceived intelligence that is also seen when speech is present. ",

author = "Amandus Krantz and Christian Balkenius and Birger Johansson",

note = "SCRITA Workshop Proceedings (arXiv:2208.11090) held in conjunction with 31st IEEE International Conference on Robot & Human Interactive Communication, 29/08 - 02/09 2022, Naples (Italy); 31st IEEE International Conference on Robot & Human Interactive Communication, IEEE RO-MAN, IEEE RO-MAN 2022 ; Conference date: 29-08-2022 Through 02-09-2022",

year = "2022",

doi = "10.48550/arXiv.2208.13688",

language = "English",

url = "http://www.smile.unina.it/ro-man2022/",

}

TY - CONF

T1 - Using Speech to Reduce Loss of Trust in Humanoid Social Robots

AU - Krantz, Amandus

AU - Balkenius, Christian

AU - Johansson, Birger

N1 - Conference code: 31

PY - 2022

Y1 - 2022

N2 - We present data from two online human-robot interaction experiments where 227 participants viewed videos of a humanoid robot exhibiting faulty or non-faulty behaviours while either remaining mute or speaking. The participants were asked to evaluate their perception of the robot's trustworthiness, as well as its likeability, animacy, and perceived intelligence. The results show that, while a non-faulty robot achieves the highest trust, an apparently faulty robot that can speak manages to almost completely mitigate the loss of trust that is otherwise seen with faulty behaviour. We theorize that this mitigation is correlated with the increase in perceived intelligence that is also seen when speech is present.

AB - We present data from two online human-robot interaction experiments where 227 participants viewed videos of a humanoid robot exhibiting faulty or non-faulty behaviours while either remaining mute or speaking. The participants were asked to evaluate their perception of the robot's trustworthiness, as well as its likeability, animacy, and perceived intelligence. The results show that, while a non-faulty robot achieves the highest trust, an apparently faulty robot that can speak manages to almost completely mitigate the loss of trust that is otherwise seen with faulty behaviour. We theorize that this mitigation is correlated with the increase in perceived intelligence that is also seen when speech is present.

UR - https://arxiv.org/html/2208.11090

U2 - 10.48550/arXiv.2208.13688

DO - 10.48550/arXiv.2208.13688

M3 - Paper, not in proceeding

T2 - 31st IEEE International Conference on Robot & Human Interactive Communication, IEEE RO-MAN

Y2 - 29 August 2022 through 2 September 2022

ER -

Using Speech to Reduce Loss of Trust in Humanoid Social Robots

Abstract

Conference

Bibliographical note

Subject classification (UKÄ)

Access to Document

Other files and links

Fingerprint

Non-Verbal Signals of Trust and Group Identification in Humans and Robots

Lund University Cognitive Robotics Lab

SCRITA 2022

Cite this

Using Speech to Reduce Loss of Trust in Humanoid Social Robots

Abstract

Conference

Bibliographical note

Subject classification (UKÄ)

Access to Document

Other files and links

Fingerprint

Projects

Non-Verbal Signals of Trust and Group Identification in Humans and Robots

Equipment

Lund University Cognitive Robotics Lab

Activities

SCRITA 2022

Cite this