Formalizing Kantian Ethics: Formula of the Universal Law Logic (FULL)

In the field of machine ethics, researchers are working to develop Artificial Moral Agents (AMAs) that can better understand morality and make decisions that align with human values. To achieve this goal, many approaches have focused on encoding human moral intuition as a set of axioms on actions. However, these axioms are often based on a limited understanding of human morality and can lead to inconsistent or even contradictory results. In their new paper, researchers propose a novel approach to formalize Kantian ethics, specifically the Formula of the Universal Law, for AMAs. This method, known as FULL, aims to provide a more comprehensive and consistent framework for AI decision-making. By encoding human moral principles into a logical framework, FULL can help ensure that AI agents make decisions that are fair, just, and respectful of human values.