Towards Verifiably Ethical Robot Behaviour

Dennis, Louise A ORCID: 0000-0003-1426-1896, Fisher, Michael and Winfield, Alan FT (2015) Towards Verifiably Ethical Robot Behaviour. AAAI Workshop - Technical Report, WS-15-. pp. 45-52.

This is the latest version of this item.

	Text main.pdf - Unspecified Download (599kB)
	Text main.pdf - Author Accepted Manuscript Access to this file is embargoed until Unspecified. Download (612kB)

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.

Item Type:	Article
Additional Information:	Presented at the 1st International Workshop on AI and Ethics, Sunday 25th January 2015, Hill Country A, Hyatt Regency Austin. Will appear in the workshop proceedings published by AAAI
Uncontrolled Keywords:	cs.AI, cs.AI
Depositing User:	Symplectic Admin
Date Deposited:	27 Mar 2015 10:01
Last Modified:	16 Dec 2022 04:43
Related URLs:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/2009138