Exploring Theory of Mind for Human-Robot Collaboration

Marta Romeo; Peter E. Mckenna; David  Robb; Gnanathusharan  Rajendran; Birthe  Nesset; Angelo Cangelosi; Helen Hastie

Exploring Theory of Mind for Human-Robot Collaboration

Marta Romeo, Peter E. Mckenna, David Robb, Gnanathusharan Rajendran, Birthe Nesset, Angelo Cangelosi, Helen Hastie

Machine Learning and Robotics

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

268 Downloads (Pure)

Abstract

The ability to impute mental states to oneself or others, or Theory of Mind (ToM), has been intrinsically linked to trust between humans. However, less is known about how a robot mimicking ToM affects users’ trust and behaviour. We explore this through an online study, where we compare three robot personas in a cooperative maze navigation task: one neutral, one that explains its reasoning in technical terms, and one that mimics ToM. We show that ToM influences human decision-making behaviour and trust in a way that makes it more appropriate with respect to the competencies of the robot. This is key for human-robot collaboration and adoption of robotics moving forward.

Index Terms—trust, theory of mind, online experiment

Original language	English
Title of host publication	31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022)
Publication status	Accepted/In press - 30 May 2022

Access to Document

Romeo-exploring-theory-of-mind-for-human-robot-collaboation_preprintAccepted author manuscript, 356 KB

Cite this

@inproceedings{9bb77f5796d44c53bdcdb98282ac9f05,

title = "Exploring Theory of Mind for Human-Robot Collaboration",

abstract = "The ability to impute mental states to oneself or others, or Theory of Mind (ToM), has been intrinsically linked to trust between humans. However, less is known about how a robot mimicking ToM affects users{\textquoteright} trust and behaviour. We explore this through an online study, where we compare three robot personas in a cooperative maze navigation task: one neutral, one that explains its reasoning in technical terms, and one that mimics ToM. We show that ToM influences human decision-making behaviour and trust in a way that makes it more appropriate with respect to the competencies of the robot. This is key for human-robot collaboration and adoption of robotics moving forward.Index Terms—trust, theory of mind, online experiment",

author = "Marta Romeo and Mckenna, {Peter E.} and David Robb and Gnanathusharan Rajendran and Birthe Nesset and Angelo Cangelosi and Helen Hastie",

year = "2022",

month = may,

day = "30",

language = "English",

booktitle = "31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022)",

}

TY - GEN

T1 - Exploring Theory of Mind for Human-Robot Collaboration

AU - Romeo, Marta

AU - Mckenna, Peter E.

AU - Robb, David

AU - Rajendran, Gnanathusharan

AU - Nesset, Birthe

AU - Cangelosi, Angelo

AU - Hastie, Helen

PY - 2022/5/30

Y1 - 2022/5/30

N2 - The ability to impute mental states to oneself or others, or Theory of Mind (ToM), has been intrinsically linked to trust between humans. However, less is known about how a robot mimicking ToM affects users’ trust and behaviour. We explore this through an online study, where we compare three robot personas in a cooperative maze navigation task: one neutral, one that explains its reasoning in technical terms, and one that mimics ToM. We show that ToM influences human decision-making behaviour and trust in a way that makes it more appropriate with respect to the competencies of the robot. This is key for human-robot collaboration and adoption of robotics moving forward.Index Terms—trust, theory of mind, online experiment

AB - The ability to impute mental states to oneself or others, or Theory of Mind (ToM), has been intrinsically linked to trust between humans. However, less is known about how a robot mimicking ToM affects users’ trust and behaviour. We explore this through an online study, where we compare three robot personas in a cooperative maze navigation task: one neutral, one that explains its reasoning in technical terms, and one that mimics ToM. We show that ToM influences human decision-making behaviour and trust in a way that makes it more appropriate with respect to the competencies of the robot. This is key for human-robot collaboration and adoption of robotics moving forward.Index Terms—trust, theory of mind, online experiment

M3 - Conference contribution

BT - 31st IEEE International Conference on Robot and Human Interactive Communication (RO-MAN 2022)

ER -

Exploring Theory of Mind for Human-Robot Collaboration

Abstract

Access to Document

Fingerprint

Cite this