Conference paper by Ari Saptawijaya and Luís Moniz Pereira.
Presented at the 2015 Portuguese Conference on Artificial Intelligence.
Abstract:
This paper summarizes our investigation on the application of LP-based reasoning to machine ethics, a field that emerges from the need of imbuing autonomous agents with the capacity for moral decision-making. We identify morality viewpoints (concerning moral permissibility and the dual-process model) as studied in moral philosophy and psychology, which are amenable to computational modeling. Subsequently, various LP-based reasoning features are applied to model these identified morality viewpoints, via classic moral examples taken off-the-shelf from the literature.