Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

Abstract

We propose a method of human-robot trust assessment in close-proximity human-robot collaboration involving body tracking for recognition of physical signs of apprehension. We tested this by performing skeleton tracking on 30 participant while they repeated a shared task with a Sawyer robot while reporting trust between tasks. We tested different robot velocity and environment conditions with an unannounced increase in velocity midway through to provoke a dip trust. Initial analysis show significant effect for the test conditions on participant movements and reported trust as well as linear correlations between tracked signs of apprehension and reported trust.
Original languageEnglish
Title of host publication28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN)
Place of PublicationThe 28th IEEE International Conference on Robot and Human Interactive Communication
PublisherIEEE Computer Society Press
Publication date2019
Publication statusPublished - 2019
EventThe 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN): Ro-man2019 - New Delhi, India
Duration: 14 Oct 201918 Nov 2019
https://ro-man2019.org/

Conference

ConferenceThe 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
CountryIndia
CityNew Delhi
Period14/10/201918/11/2019
Internet address

Fingerprint

Robots

Keywords

  • Human Robot Interaction
  • Human Robot Collaboration
  • human robot trust

Cite this

Hald, K., Rehm, M., & Moeslund, T. B. (2019). Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration. In 28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN) The 28th IEEE International Conference on Robot and Human Interactive Communication: IEEE Computer Society Press.
Hald, Kasper ; Rehm, Matthias ; Moeslund, Thomas B. / Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration. 28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN). The 28th IEEE International Conference on Robot and Human Interactive Communication : IEEE Computer Society Press, 2019.
@inproceedings{ce5a35d984bd4cc089cd6ab8bdccf6dc,
title = "Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration",
abstract = "We propose a method of human-robot trust assessment in close-proximity human-robot collaboration involving body tracking for recognition of physical signs of apprehension. We tested this by performing skeleton tracking on 30 participant while they repeated a shared task with a Sawyer robot while reporting trust between tasks. We tested different robot velocity and environment conditions with an unannounced increase in velocity midway through to provoke a dip trust. Initial analysis show significant effect for the test conditions on participant movements and reported trust as well as linear correlations between tracked signs of apprehension and reported trust.",
keywords = "Human Robot Interaction, Human Robot Collaboration, human robot trust",
author = "Kasper Hald and Matthias Rehm and Moeslund, {Thomas B.}",
year = "2019",
language = "English",
booktitle = "28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN)",
publisher = "IEEE Computer Society Press",
address = "United States",

}

Hald, K, Rehm, M & Moeslund, TB 2019, Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration. in 28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN). IEEE Computer Society Press, The 28th IEEE International Conference on Robot and Human Interactive Communication, The 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN), New Delhi, India, 14/10/2019.

Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration. / Hald, Kasper; Rehm, Matthias; Moeslund, Thomas B.

28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN). The 28th IEEE International Conference on Robot and Human Interactive Communication : IEEE Computer Society Press, 2019.

Research output: Contribution to book/anthology/report/conference proceedingArticle in proceedingResearchpeer-review

TY - GEN

T1 - Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration

AU - Hald, Kasper

AU - Rehm, Matthias

AU - Moeslund, Thomas B.

PY - 2019

Y1 - 2019

N2 - We propose a method of human-robot trust assessment in close-proximity human-robot collaboration involving body tracking for recognition of physical signs of apprehension. We tested this by performing skeleton tracking on 30 participant while they repeated a shared task with a Sawyer robot while reporting trust between tasks. We tested different robot velocity and environment conditions with an unannounced increase in velocity midway through to provoke a dip trust. Initial analysis show significant effect for the test conditions on participant movements and reported trust as well as linear correlations between tracked signs of apprehension and reported trust.

AB - We propose a method of human-robot trust assessment in close-proximity human-robot collaboration involving body tracking for recognition of physical signs of apprehension. We tested this by performing skeleton tracking on 30 participant while they repeated a shared task with a Sawyer robot while reporting trust between tasks. We tested different robot velocity and environment conditions with an unannounced increase in velocity midway through to provoke a dip trust. Initial analysis show significant effect for the test conditions on participant movements and reported trust as well as linear correlations between tracked signs of apprehension and reported trust.

KW - Human Robot Interaction

KW - Human Robot Collaboration

KW - human robot trust

UR - https://ras.papercept.net/conferences/conferences/ROMAN19/program/ROMAN19_ContentListWeb_1.html#tubs1_06

M3 - Article in proceeding

BT - 28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN)

PB - IEEE Computer Society Press

CY - The 28th IEEE International Conference on Robot and Human Interactive Communication

ER -

Hald K, Rehm M, Moeslund TB. Proposing Human-Robot Trust Assessment Through Tracking Physical Apprehension Signals in Close-Proximity Human-Robot Collaboration. In 28th IEEE International Conference on Robot and Human Interactive Communication (ROMAN). The 28th IEEE International Conference on Robot and Human Interactive Communication: IEEE Computer Society Press. 2019