Umeå University
printicon
Main menu hidden.
Staff photo Andreas Theodorou

Andreas Theodorou

My research is focused on Responsible Artificial Intelligence.

Contact

E-mail
andreas.theodorou@umu.se
Phone
+46 90 786 67 97

Works at

Affiliation
Research fellow at Department of Computing Science
Location
MIT-huset, Umeå universitet, MIT / B2.31.06 Umeå universitet, 901 87 Umeå

My research is focused on Responsible Artificial Intelligence. More specifically, I am looking at the computational methods, formalisms, and socio-technical practices we need to effectively audit, verify, and validate intelligent systems while ensuring their trustworthiness.

My research spans multiple fields; including AI ethics, KR, software development practices for AI, cognitive architectures, HRI, policymaking, and moral philosophy. In parallel to my research efforts, I am a member of AI policy initiatives; e.g. IEEE SA’ P7001 series, ISO JTC1/42, EU’s AI Alliance, and others.

Read a full version of my CV, pre/postprints of publications, and list of upcoming public engagement events.  

Interrogating the black box: Transparency through information-seeking dialogues
Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems, AAMAS, International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS) 2021 : 106-114
Aler Tubella, Andrea; Theodorou, Andreas; Nieves, Juan Carlos
Let Me Take Over: Variable Autonomy for Meaningful Human Control
Frontiers in Artificial Intelligence, Frontiers Media S.A. 2021, Vol. 4
Methnani, Leila; Aler Tubella, Andrea; Dignum, Virginia; et al.
IEEE P7001: A Proposed Standard on Transparency
Frontiers in Robotics and AI, Frontiers Media S.A. 2021, Vol. 8
Winfield, Alan F. T.; Booth, Serena; Dennis, Louise A.; et al.
Contestable Black Boxes
Rules and Reasoning. RuleML+RR 2020., Springer 2020 : 159-167
Aler Tubella, Andrea; Theodorou, Andreas; Dignum, Virginia; et al.
Why Artificial Intelligence is a Matter of Design
Artificial Intelligence: Reflections in Philosophy, Theology, and the Social Sciences, Mentis Verlag GmbH 2020 : 105-131
Theodorou, Andreas
Towards ethical and socio-legal governance in AI
Nature Machine Intelligence, Nature Publishing Group 2020, Vol. 2, (1) : 10-12
Theodorou, Andreas; Dignum, Virginia
A socio-technical framework for digital contact tracing
Results in Engineering (RINENG), Elsevier 2020, Vol. 8
Vinuesa, Ricardo; Theodorou, Andreas; Battaglini, Manuela; et al.
Governance by Glass-Box: Implementing Transparent Moral Bounds for AI Behaviour
Proceedings of the 28th International Joint Conference on Artificial Intelligence
Aler Tubella, Andrea; Theodorou, Andreas; Dignum, Frank; et al.
How society can maintain human-centric artificial intelligence
Human-centered digitalization and services, Springer 2019 : 305-323
Bryson, Joanna J.; Theodorou, Andreas
2nd International Workshop on Artificial Intelligence Safety Engineering (WAISE 2019)
Computer Safety, Reliability, And Security, Safecomp 2019, Springer Publishing Company 2019 : 276-280
Chihani, Zakaria; Gerasimou, Simos; Theodorou, Andreas; et al.
Improving Robot Transparency: An Investigation With Mobile Augmented Reality
2019 28th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)
Rotsidis, Alexandros; Theodorou, Andreas; Bryson, Joanna J.; et al.
Robots That Make Sense: Transparent Intelligence Through Augmented Reality
CEUR Workshop Proceedings 2019
Rotsidis, Alexandros; Theodorou, Andreas; Wortham, Robert H.
The Sustainability Game: AI Technology as an Intervention for Public Understanding of Cooperative Investment
2019 IEEE Conference on Games (CoG)
Theodorou, Andreas; Bandt-Law, Bryn; Bryson, Joanna J.
Slam the Brakes: Perceptions of Moral Decisions in Driving Dilemmas
IJCAI 2019 Workshop on AISafety, Macao, China, August 11-12, 2019.
Wilson, Holly; Theodorou, Andreas
View publications in DiVA

Research groups

Group member
Responsible Artificial Intelligence

Research projects

1 September 2020
GEDAI Growing Ethical Designers of Artificial Intelligence
1 September 2020 until 31 August 2022
Trust AI - Trustworthy AI
1 March 2020
ASSOCC
1 January 2020 until 31 December 2021
Responsible Artificial INtelligence (RAIN)
1 May 2019 until 1 May 2021
Sustainable AI
1 January 2019 until 31 December 2022
AI4EU
1 January 2019 until 31 December 2024
AI Glass Box

I am teaching probabilistic reasoning and knowledge representation in the course 5DV063 Artificial Intelligence: Methods and Applications.