Publications

2017

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

In the conference proceedings of IEEE RO-MAN 2017, Lisbon, Portugal, 2017

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. Read more

Recommended citation: Wortham, R. H., Theodorou, A., & Bryson, J. J. (2017). Improving robot transparency: real-time visualisation of robot AI substantially improves understanding in naive observers.IEEE RO-MAN 2017. Lisbon, Portugal https://ieeexplore.ieee.org/document/8172491/

Robot transparency: Improving understanding of intelligent behaviour for designers and users

Published in Towards Autonomous Robotic Systems: 18th Annual Conference, TAROS 2017, Guildford, UK, 2017

Autonomous robots can be difficult to design and understand. Designers have difficulty decoding the behaviour of their own robots simply by observing them. Read more

Recommended citation: Wortham, R. H., Theodorou, A., & Bryson, J. J. (2017). Improving robot transparency: real-time visualisation of robot AI substantially improves understanding in naive observers. Gao Y., Fallah S., Jin Y., Lekakou C. (eds) Towards Autonomous Robotic Systems. TAROS 2017. Lecture Notes in Computer Science, vol 10454 (Lecture Notes in Artificial Intelligence; Vol. 10454). Springer. DOI: 10.1007/978-3-319-64107-2_22 https://link.springer.com/book/10.1007%2F978-3-319-64107-2_22

Robot Transparency, Trust and Utility

Published in Connection Science, 2017

As robot reasoning becomes more complex, debugging becomes increasingly hard based solely on observable behaviour, even for robot designers and technical specialists. Similarly, non-specialist users have difficulty creating useful mental models of robot reasoning from observations of robot behaviour. Read more

Recommended citation: Wortham, R. H., Theodorou, A. (2017). Robot Transparency, Trust and Utility. Connection Science, 29:3, 242-247 DOI: 10.1080/09540091.2017.1313816 https://www.tandfonline.com/doi/abs/10.1080/09540091.2017.1313816

Designing and implementing transparency for real time inspection of autonomous robots

Published in Connection Science, 2017

The EPSRC 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. Read more

Recommended citation: Theodorou, A., Wortham, R. H., & Bryson, J. J. (2017). Designing and implementing transparency for real time inspection of autonomous robots. Connection Science, 29:3, 230-241 DOI: 10.1080/09540091.2017.1310182 https://www.tandfonline.com/doi/abs/10.1080/09540091.2017.1310182

2016

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

In the conference proceedings of IJCAI Workshop on Ethics for Artificial Intelligence, New York, NY, USA, 2016

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. Read more

Recommended citation: Wortham, R. H., Theodorou, A., & Bryson, J. J. (2016). What Does the Robot Think? Transparency as a Fundamental Design Requirement for Intelligent Systems.IJCAI Workshop on Ethics for Artificial Intelligence New York, NY, USA https://goo.gl/dLU9zd