Andreas Theodorou
University of Bath, Umeå University, Universitat Politècnica de Catalunya
Papers
14
Total Citations
475
H-Index
8
About
Andreas Theodorou is a leading researcher in AI transparency, robot ethics, and human-robot interaction, whose work has fundamentally shaped how we think about making autonomous systems understandable and trustworthy. His research addresses a critical challenge in modern robotics: as robot reasoning grows increasingly complex, how do we ensure that both technical specialists and everyday users can meaningfully comprehend and trust machine behaviour? Theodorou's most influential contributions centre on designing transparency frameworks for autonomous robots. His 2017 paper on real-time inspection of autonomous robots has garnered 150 citations, while companion works on robot transparency and trust have collectively accumulated hundreds more, establishing him as a defining voice in the field. Notably, he demonstrated empirically that real-time AI visualisation substantially improves understanding among non-specialist observers, bridging the gap between sophisticated machine reasoning and human comprehension. Grounded in the EPSRC's Principles of Robotics, his research provides both theoretical foundations and practical implementation guidance for transparent intelligent systems. His more recent work on variable autonomy and trustworthy AI signals an evolving research agenda that addresses human-robot teaming in increasingly dynamic environments. For students entering AI ethics or human-robot interaction, Theodorou's body of work represents an essential intellectual foundation.
Research Focus
Key Achievements
Top Papers
- 1
- 2Robot transparency, trust and utility101 citations · 2017
- 3
- 4
- 5
- 6
- 7Improving Robot Transparency: An Investigation With Mobile Augmented Reality20 citations · 2019
- 8
- 9Robot Transparency, Trust and Utility7 citations · 2016
- 10Variable Autonomy for Human-Robot Teaming (VAT)5 citations · 2023