Logic Programming Applied to Machine Ethics

This paper investigates the appropriateness of LP-based reasoning to machine ethics, an interdisciplinary field of inquiry that emerges from the need of imbuing autonomous agents with the capacity for moral decision making. The first contribution of the paper is that of identifying morality viewpoints, as studied in moral philosophy and psychology, which are amenable to computational modeling, and then mapping them to appropriate LP-based reasoning features. The identified viewpoints are covered by two morality themes: moral permissibility and the dual-process model. In the second contribution, various LP-based reasoning features are applied to model these identified morality viewpoints, via classic moral examples taken off-the-shelf from the literature. For this purpose, our QUALM system, which features a combination of LP abduction, updating, and counterfactuals, supported by LP tabling mechanisms, are mainly employed. The applications are also supported by other existing LP-based systems, featuring preference handling and probabilistic reasoning, which complement QUALM in addressing the morality viewpoints in question.