Robot Transparency, Trust and Utility

Research output: Contribution to conferencePaper

Abstract

As robot reasoning becomes more complex, debugging
becomes increasingly hard based solely on observable behaviour,
even for robot designers and technical specialists. Similarly, nonspecialist
users find it hard to create useful mental models of robot
reasoning solely from observed behaviour. The EPSRC Principles of
Robotics mandate that our artefacts should be transparent, but what
does this mean in practice, and how does transparency affect both
trust and utility? We investigate this relationship in the literature and
find it to be complex, particularly in non industrial environments
where transparency may have a wider range of effects on trust and
utility depending on the application and purpose of the robot. We
outline our programme of research to support our assertion that it is
nevertheless possible to create transparent agents that are emotionally
engaging despite having a transparent machine nature.

Workshop

WorkshopAISB Workshop on Principles of Robotics
CountryUK United Kingdom
CitySheffield
Period4/04/164/04/16
Internet address

Fingerprint

Transparency
Robots
Robotics

Keywords

  • artificial intelligence
  • ai
  • robot
  • robotics
  • roboethics
  • ethics
  • transparency

Cite this

Wortham, R. H., Theodorou, A., & Bryson, J. J. (2016). Robot Transparency, Trust and Utility. Paper presented at AISB Workshop on Principles of Robotics, Sheffield, UK United Kingdom.

Robot Transparency, Trust and Utility. / Wortham, Robert H; Theodorou, Andreas; Bryson, Joanna J.

2016. Paper presented at AISB Workshop on Principles of Robotics, Sheffield, UK United Kingdom.

Research output: Contribution to conferencePaper

Wortham, RH, Theodorou, A & Bryson, JJ 2016, 'Robot Transparency, Trust and Utility' Paper presented at AISB Workshop on Principles of Robotics, Sheffield, UK United Kingdom, 4/04/16 - 4/04/16, .
Wortham RH, Theodorou A, Bryson JJ. Robot Transparency, Trust and Utility. 2016. Paper presented at AISB Workshop on Principles of Robotics, Sheffield, UK United Kingdom.
Wortham, Robert H ; Theodorou, Andreas ; Bryson, Joanna J. / Robot Transparency, Trust and Utility. Paper presented at AISB Workshop on Principles of Robotics, Sheffield, UK United Kingdom.3 p.
@conference{e423f20d66f34939b98d8ffecdf820ca,
title = "Robot Transparency, Trust and Utility",
abstract = "As robot reasoning becomes more complex, debuggingbecomes increasingly hard based solely on observable behaviour,even for robot designers and technical specialists. Similarly, nonspecialistusers find it hard to create useful mental models of robotreasoning solely from observed behaviour. The EPSRC Principles ofRobotics mandate that our artefacts should be transparent, but whatdoes this mean in practice, and how does transparency affect bothtrust and utility? We investigate this relationship in the literature andfind it to be complex, particularly in non industrial environmentswhere transparency may have a wider range of effects on trust andutility depending on the application and purpose of the robot. Weoutline our programme of research to support our assertion that it isnevertheless possible to create transparent agents that are emotionallyengaging despite having a transparent machine nature.",
keywords = "artificial intelligence, ai, robot, robotics, roboethics, ethics, transparency",
author = "Wortham, {Robert H} and Andreas Theodorou and Bryson, {Joanna J}",
year = "2016",
month = "4",
day = "4",
language = "English",
note = "AISB Workshop on Principles of Robotics ; Conference date: 04-04-2016 Through 04-04-2016",
url = "http://www.sheffieldrobotics.ac.uk/aisb-workshop-por/",

}

TY - CONF

T1 - Robot Transparency, Trust and Utility

AU - Wortham, Robert H

AU - Theodorou, Andreas

AU - Bryson, Joanna J

PY - 2016/4/4

Y1 - 2016/4/4

N2 - As robot reasoning becomes more complex, debuggingbecomes increasingly hard based solely on observable behaviour,even for robot designers and technical specialists. Similarly, nonspecialistusers find it hard to create useful mental models of robotreasoning solely from observed behaviour. The EPSRC Principles ofRobotics mandate that our artefacts should be transparent, but whatdoes this mean in practice, and how does transparency affect bothtrust and utility? We investigate this relationship in the literature andfind it to be complex, particularly in non industrial environmentswhere transparency may have a wider range of effects on trust andutility depending on the application and purpose of the robot. Weoutline our programme of research to support our assertion that it isnevertheless possible to create transparent agents that are emotionallyengaging despite having a transparent machine nature.

AB - As robot reasoning becomes more complex, debuggingbecomes increasingly hard based solely on observable behaviour,even for robot designers and technical specialists. Similarly, nonspecialistusers find it hard to create useful mental models of robotreasoning solely from observed behaviour. The EPSRC Principles ofRobotics mandate that our artefacts should be transparent, but whatdoes this mean in practice, and how does transparency affect bothtrust and utility? We investigate this relationship in the literature andfind it to be complex, particularly in non industrial environmentswhere transparency may have a wider range of effects on trust andutility depending on the application and purpose of the robot. Weoutline our programme of research to support our assertion that it isnevertheless possible to create transparent agents that are emotionallyengaging despite having a transparent machine nature.

KW - artificial intelligence

KW - ai

KW - robot

KW - robotics

KW - roboethics

KW - ethics

KW - transparency

M3 - Paper

ER -