Issue No.04 - July/August (2006 vol.21)
Thomas M. Powers , University of Delaware
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/MIS.2006.77
Rule-based ethical theories like Kant's appear to be promising for machine ethics because of the computational structure of their judgments. Kant's categorical imperative is a procedure for mapping action plans (maxims) onto traditional deontic categories--forbidden, permissible, obligatory--by a simple consistency test on the maxim. This test alone, however, would be trivial. We might enhance it by adding a declarative set of "buttressing" rules. The ethical judgment is then an outcome of the consistency test, in light of the supplied rules. While this kind of test can generate nontrivial results, it might do no more than reflect the prejudices of the builder of the declarative set; the machine will "reason" straightforwardly, but not intelligently. A more promising (though speculative) option would be to build a machine with the power of nonmonotonic inference. But this option too faces formal challenges. The author discusses these challenges to a rule-based machine ethics, starting from a Kantian framework. This article is part of a special issue on Machine Ethics.
machine ethics, rules, nonmonotonic reasoning, commonsense reasoning
Thomas M. Powers, "Prospects for a Kantian Machine", IEEE Intelligent Systems, vol.21, no. 4, pp. 46-51, July/August 2006, doi:10.1109/MIS.2006.77