摘要：Within the diverse and rich debate around the so called “Ethical Artificial Intelligence” one of the major setbacks is the accepted lack of a unified ethical system that can be used for modelling the behavior of AI run systems like artificial moral advisors (Savulescu and Maslen 2015), autonomous vehicles, autonomous weapons and robots. Following upon an earlier suggestion for an artificial moral agent (2020) I will suggest a more general method for the quantification of key ethical concepts like consequence, behavior, rule, justification, state and property. The method would allow to harness the enormous computational power of modern computers for the purposes of in-depth ethical analysis of normative non-trivial cases. If successful it would provide a transmission mechanism, susceptible to rational evaluation, between ethics as a traditional discipline from the field of humanities and computation, as a mathematical structure of the kind found in natural sciences, where it provides not merely means of rigorous formulation but also of testing, evaluation, proofs and growth of scientific knowledge. The method introduces numerical weights assignment on the basis of ethical non-identity. Thus, if between a certain ethical dilemma with two possible actions we observe that the actions are normatively non-identical we can continue and capture this non-identity in graph-numerical terms thus effectively quantifying the normative setting. This quantification would provide us with the rigorously formalized content that would allow us to transfer this rigor onto a subsequent logical reasoning, enabling inferences, preference, justification and choice.
关键词：ethical artificial intelligence;AI;ethics;artificial moral agent;ethical consequences;graphs;justification
