BANIASADI, Zohreh ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
PARENT, Xavier ; University of Luxembourg > Faculty of Science, Technology and Communication (FSTC) > Computer Science and Communications Research Unit (CSC)
MAX, Charles ; University of Luxembourg > Faculty of Language and Literature, Humanities, Arts and Education (FLSHASE) > Education, Culture, Cognition and Society (ECCS) ; University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT)
Creamer, Marcos
Co-auteurs externes :
no
Langue du document :
Anglais
Titre :
A Model for Regulating of Ethical Preferences in Machine Ethics
Date de publication/diffusion :
2018
Nom de la manifestation :
HCI international 2018
Date de la manifestation :
from 15-07-2018 to 20-07-2018
Manifestation à portée :
International
Titre du périodique :
Proceedings of International Conference on Human-Computer Interaction
Maison d'édition :
Springer
Titre particulier du numéro :
Security, Privacy and Ethics in HCI
Pagination :
481-506
Peer reviewed :
Peer reviewed
Commentaire :
Relying upon machine intelligence with reductions in the
supervision of human beings requires us to be able to count on a certain
level of ethical behavior from it. Formalizing ethical theories is one of the
plausible ways to add ethical dimensions to machines. Rule-based and
consequence-based ethical theories are proper candidates for Machine
Ethics. It is debatable that methodologies for each ethical theory separately
might result in an action that is not always justifiable by human
values. This inspires us to combine the reasoning procedure of two ethical
theories, deontology and utilitarianism, in a utilitarian-based deontic
logic which is an extension of STIT (Seeing To It That) logic. We keep
the knowledge domain regarding the methodology in a knowledge base
system called IDP. IDP supports inferences to examine and evaluate the
process of ethical decision making in our formalization. To validate our
proposed methodology we perform a Case Study for some real scenarios
in the domain of robotics and automatous agents.
