Skip to main content

Research Repository

Advanced Search

Towards verifiably ethical robot behaviour

Dennis, Louise A.; Fisher, Michael; Winfield, Alan F.T.

Towards verifiably ethical robot behaviour Thumbnail


Authors

Louise A. Dennis

Michael Fisher



Abstract

Ensuring that autonomous systems work ethically is both complex and difficult. However, the idea of having an additional ‘governor’ that assesses options the system has, and prunes them to select the most ethical choices is well understood. Recent work has produced such a governor consisting of a ‘consequence engine’ that assesses the likely future outcomes of actions then applies a Safety/Ethical logic to select actions. Although this is appealing, it is impossible to be certain that the most ethical options are actually taken. In this paper we extend and apply a well-known agent verification approach to our consequence engine, allowing us to verify the correctness of its ethical decision-making.

Citation

Dennis, L. A., Fisher, M., & Winfield, A. F. (2015, January). Towards verifiably ethical robot behaviour. Presented at Twenty-Ninth AAAI Conference on Artificial Intelligence, Texas, USA

Presentation Conference Type Other
Conference Name Twenty-Ninth AAAI Conference on Artificial Intelligence
Conference Location Texas, USA
Start Date Jan 25, 2015
End Date Jan 30, 2015
Acceptance Date Jan 1, 2015
Publication Date Jan 1, 2015
Deposit Date Jul 6, 2016
Publicly Available Date Jul 6, 2016
Peer Reviewed Peer Reviewed
Keywords robot behaviour, ethics
Public URL https://uwe-repository.worktribe.com/output/841632
Publisher URL http://www.aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10119
Additional Information Title of Conference or Conference Proceedings : Proceedings of the twenty-ninth AAAI conference on artificial intelligence

Files







You might also like



Downloadable Citations