Designing and implementing transparency for real time inspection of autonomous robots

Research output: Contribution to journalArticle

  • 4 Citations

Abstract

The EPSRC's Principles of Robotics advises the implementation of transparency in robotic systems, however research related to AI transparency is in its infancy. This paper introduces the reader of the importance of having transparent inspection of intelligent agents and provides guidance for good practice when developing such agents.

By considering and expanding upon other prominent definitions found in literature, we provide a robust definition of transparency as a mechanism to expose the decision making of a robot. The paper continues by addressing potential design decisions developers need to consider when designing and developing transparent systems. Finally, we describe our new interactive intelligence editor, designed to visualise, develop and debug real-time intelligence.
LanguageEnglish
Pages230-241
Number of pages12
JournalConnection Science
Volume29
Issue number3
DOIs
StatusPublished - 30 May 2017

Fingerprint

Transparency
Inspection
Robots
Robotics
Intelligent agents
Decision making

Cite this

@article{509067a82a8d4e509af9ff6b312e0e05,
title = "Designing and implementing transparency for real time inspection of autonomous robots",
abstract = "The EPSRC's Principles of Robotics advises the implementation of transparency in robotic systems, however research related to AI transparency is in its infancy. This paper introduces the reader of the importance of having transparent inspection of intelligent agents and provides guidance for good practice when developing such agents.By considering and expanding upon other prominent definitions found in literature, we provide a robust definition of transparency as a mechanism to expose the decision making of a robot. The paper continues by addressing potential design decisions developers need to consider when designing and developing transparent systems. Finally, we describe our new interactive intelligence editor, designed to visualise, develop and debug real-time intelligence.",
author = "Andreas Theodorou and Wortham, {Robert H} and Bryson, {Joanna J}",
year = "2017",
month = "5",
day = "30",
doi = "10.1080/09540091.2017.1310182",
language = "English",
volume = "29",
pages = "230--241",
journal = "Connection Science",
issn = "0954-0091",
publisher = "Taylor & Francis",
number = "3",

}

TY - JOUR

T1 - Designing and implementing transparency for real time inspection of autonomous robots

AU - Theodorou,Andreas

AU - Wortham,Robert H

AU - Bryson,Joanna J

PY - 2017/5/30

Y1 - 2017/5/30

N2 - The EPSRC's Principles of Robotics advises the implementation of transparency in robotic systems, however research related to AI transparency is in its infancy. This paper introduces the reader of the importance of having transparent inspection of intelligent agents and provides guidance for good practice when developing such agents.By considering and expanding upon other prominent definitions found in literature, we provide a robust definition of transparency as a mechanism to expose the decision making of a robot. The paper continues by addressing potential design decisions developers need to consider when designing and developing transparent systems. Finally, we describe our new interactive intelligence editor, designed to visualise, develop and debug real-time intelligence.

AB - The EPSRC's Principles of Robotics advises the implementation of transparency in robotic systems, however research related to AI transparency is in its infancy. This paper introduces the reader of the importance of having transparent inspection of intelligent agents and provides guidance for good practice when developing such agents.By considering and expanding upon other prominent definitions found in literature, we provide a robust definition of transparency as a mechanism to expose the decision making of a robot. The paper continues by addressing potential design decisions developers need to consider when designing and developing transparent systems. Finally, we describe our new interactive intelligence editor, designed to visualise, develop and debug real-time intelligence.

UR - https://doi.org/10.1080/09540091.2017.1310182

U2 - 10.1080/09540091.2017.1310182

DO - 10.1080/09540091.2017.1310182

M3 - Article

VL - 29

SP - 230

EP - 241

JO - Connection Science

T2 - Connection Science

JF - Connection Science

SN - 0954-0091

IS - 3

ER -