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.
Keywords
Transparency (behavior)Computer scienceDebuggingRobotRoboticsArtificial intelligenceHuman–computer interactionData scienceSoftware engineeringComputer security
Affiliated Institutions
Related Publications
Stable flocking of mobile agents. II. Dynamic topology
This is the second of a two-part paper, investigating the stability properties of a system of multiple mobile agents with double integrator dynamics. In this second part, we all...
Stable flocking of mobile agents. I. Fixed topology
This is the first of a two-part paper that investigates the stability properties of a system of multiple mobile agents with double integrator dynamics. In this first part we gen...
Microsoft robotics studio: A technical introduction
Microsoft robotics studio (MSRS) was publicly released in December 2006 with the explicit goal of providing an industry software standard for robot control. To become a viable s...
HindSight: Encouraging Exploration through Direct Encoding of Personal Interaction History
Physical and digital objects often leave markers of our use. Website links turn purple after we visit them, for example, showing us information we have yet to explore. These "fo...
CrowdWorkSheets: Accounting for Individual and Collective Identities Underlying Crowdsourced Dataset Annotation
Human annotated data plays a crucial role in machine learning (ML) research\nand development. However, the ethical considerations around the processes and\ndecisions that go int...
Publication Info
- Year
- 2017
- Type
- article
- Volume
- 29
- Issue
- 3
- Pages
- 230-241
- Citations
- 144
- Access
- Closed
External Links
Social Impact
Altmetric
PlumX Metrics
Social media, news, blog, policy document mentions
Citation Metrics
144
OpenAlex
6
Influential
79
CrossRef
Cite This
Andreas Theodorou,
Robert H. Wortham,
Joanna J. Bryson
(2017).
Designing and implementing transparency for real time inspection of autonomous robots.
Connection Science
, 29
(3)
, 230-241.
https://doi.org/10.1080/09540091.2017.1310182
Identifiers
- DOI
- 10.1080/09540091.2017.1310182