An Approach to Computing Ethics

Authors:
Michael Anderson;Susan Leigh Anderson;Chris Armen
Affiliations:
University of Hartford;University of Connecticut;Amherst College
Venue:
IEEE Intelligent Systems
Year:
2006

Citing 1
Cited 6

Proceedings of the 7th International Workshop on Inductive Logic Programming

ILP '97 Proceedings of the 7th International Workshop on Inductive Logic Programming

Ethical Trust and Social Moral Norms Simulation: A Bio-inspired Agent-Based Modelling Approach

WI-IAT '08 Proceedings of the 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology - Volume 02
Review of trust and machine ethics research: towards a bio-inspired computational model of ethical trust (CMET)

Proceedings of the 3rd International Conference on Bio-Inspired Models of Network, Information and Computing Sytems
An integrated reasoning approach to moral decision-making

AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
Robot minds and human ethics: the need for a comprehensive model of moral decision making

Ethics and Information Technology
Particularism, Analogy, and Moral Cognition

Minds and Machines
Granny and the robots: ethical issues in robot care for the elderly

Ethics and Information Technology

Quantified Score

Hi-index	0.00

Visualization

Abstract

To make ethics computable, we've adopted an approach to ethics that involves considering multipleprima facie duties in deciding how one should act in an ethical dilemma. We believe this approach is morelikely to capture the complexities of ethical decision making than a single, absolute-duty ethical theory.However, it requires a decision procedure for determining the ethically correct action when the duties giveconflicting advice. To solve this problem, we employ inductive-logic programming to enable a machine toabstract information from ethical experts' intuitions about particular ethical dilemmas, to create adecision principle. We've tested our method in the MedEthEx proof-of-concept system, using a type ofethical dilemma that involves 18 possible combinations of three prima facie duties. The system needed justfour training cases to create an ethically significant decision principle that covered the remaining cases. This article is part of a special issue on Machine Ethics.