What Does the Robot Think? Transparency as a Fundamental Design Requirement for Intelligent Systems

Robert H Wortham, Andreas Theodorou, Joanna J Bryson

Research output: Chapter in Book/Report/Conference proceedingConference contribution

128 Downloads (Pure)

Abstract

Deciphering the behaviour of intelligent others is a
fundamental characteristic of our own intelligence.
As we interact with complex intelligent artefacts,
humans inevitably construct mental models to understand
and predict their behaviour. If these models
are incorrect or inadequate, we run the risk of
self deception or even harm. This paper reports
progress on a programme of work investigating approaches
for implementing robot transparency, and
the effects of these approaches on utility, trust and
the perception of agency. Preliminary findings indicate
that building transparency into robot action
selection can help users build a more accurate understanding
of the robot.
Original languageEnglish
Title of host publicationProceedings of the IJCAI Workshop on Ethics for Artificial Intelligence
Subtitle of host publicationInternational Joint Conference on Artificial Intelligence
Number of pages6
Publication statusPublished - 9 Jun 2016
EventIJCAI 2016 Ethics for AI Workshop - New York Hilton Hotel, New York, USA United States
Duration: 9 Jul 20169 Jul 2016

Workshop

WorkshopIJCAI 2016 Ethics for AI Workshop
CountryUSA United States
CityNew York
Period9/07/169/07/16

Fingerprint Dive into the research topics of 'What Does the Robot Think? Transparency as a Fundamental Design Requirement for Intelligent Systems'. Together they form a unique fingerprint.

  • Cite this

    Wortham, R. H., Theodorou, A., & Bryson, J. J. (2016). What Does the Robot Think? Transparency as a Fundamental Design Requirement for Intelligent Systems. In Proceedings of the IJCAI Workshop on Ethics for Artificial Intelligence : International Joint Conference on Artificial Intelligence