Research

Improving robot transparency:real-time visualisation of robot AI substantially improves understanding in naive observers


Reference:

Wortham, R. H., Theodorou, A. and Bryson, J. J., 2017. Improving robot transparency:real-time visualisation of robot AI substantially improves understanding in naive observers. In: IEEE RO-MAN 2017, 2017-08-28 - 2017-09-01, Pestana Palace Hotel.

Related documents:

[img]
Preview
PDF (robot-transparency-experiment) - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
Download (1220kB) | Preview

    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. Here we demonstrate that providing even a simple, abstracted real-time visualisation of a robot’s AI can radically improve the transparency of machine cognition. Findings from both an online experiment using a video recording of a robot, and from direct observation of a robot show substantial improvements in observers’ understanding of the robot’s behaviour. Unexpectedly, this improved understanding was correlated in one condition with an increased perception that the robot was ‘thinking’, but in no conditions was the robot’s assessed intelligence impacted. In addition to our results, we describe our approach, tools used, implications, and potential future research directions.

    Details

    Item Type Conference or Workshop Items (Paper)
    CreatorsWortham, R. H., Theodorou, A. and Bryson, J. J.
    DepartmentsFaculty of Science > Computer Science
    Research CentresCentre for Mathematical Biology
    RefereedYes
    StatusPublished
    ID Code55793

    Export

    Actions (login required)

    View Item

    Document Downloads

    More statistics for this item...