8
views
0
recommends
+1 Recommend
0 collections
    0
    shares
      • Record: found
      • Abstract: found
      • Article: found
      Is Open Access

      On Automating the Doctrine of Double Effect

      Preprint
      ,

      Read this article at

      Bookmark
          There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

          Abstract

          The doctrine of double effect (\(\mathcal{DDE}\)) is a long-studied ethical principle that governs when actions that have both positive and negative effects are to be allowed. The goal in this paper is to automate \(\mathcal{DDE}\). We briefly present \(\mathcal{DDE}\), and use a first-order modal logic, the deontic cognitive event calculus, as our framework to formalize the doctrine. We present formalizations of increasingly stronger versions of the principle, including what is known as the doctrine of triple effect. We then use our framework to simulate successfully scenarios that have been used to test for the presence of the principle in human subjects. Our framework can be used in two different modes: One can use it to build \(\mathcal{DDE}\)-compliant autonomous systems from scratch, or one can use it to verify that a given AI system is \(\mathcal{DDE}\)-compliant, by applying a \(\mathcal{DDE}\) layer on an existing system or model. For the latter mode, the underlying AI system can be built using any architecture (planners, deep neural networks, bayesian networks, knowledge-representation systems, or a hybrid); as long as the system exposes a few parameters in its model, such verification is possible. The role of the \(\mathcal{DDE}\) layer here is akin to a (dynamic or static) software verifier that examines existing software modules. Finally, we end by presenting initial work on how one can apply our \(\mathcal{DDE}\) layer to the STRIPS-style planning model, and to a modified POMDP model.

          Related collections

          Most cited references5

          • Record: found
          • Abstract: found
          • Article: not found

          The role of conscious reasoning and intuition in moral judgment: testing three principles of harm.

          Is moral judgment accomplished by intuition or conscious reasoning? An answer demands a detailed account of the moral principles in question. We investigated three principles that guide moral judgments: (a) Harm caused by action is worse than harm caused by omission, (b) harm intended as the means to a goal is worse than harm foreseen as the side effect of a goal, and (c) harm involving physical contact with the victim is worse than harm involving no physical contact. Asking whether these principles are invoked to explain moral judgments, we found that subjects generally appealed to the first and third principles in their justifications, but not to the second. This finding has significance for methods and theories of moral psychology: The moral principles used in judgment must be directly compared with those articulated in justification, and doing so shows that some moral principles are available to conscious reasoning whereas others are not.
            Bookmark
            • Record: found
            • Abstract: not found
            • Article: not found

            A Dissociation Between Moral Judgments and Justifications

              Bookmark
              • Record: found
              • Abstract: not found
              • Conference Proceedings: not found

              Akratic robots and the computational logic thereof

                Bookmark

                Author and article information

                Journal
                2017-03-27
                Article
                1703.08922
                821e8f87-4586-4ab9-956f-8fd925e9b27a

                http://arxiv.org/licenses/nonexclusive-distrib/1.0/

                History
                Custom metadata
                cs.AI cs.LO cs.RO

                Theoretical computer science,Robotics,Artificial intelligence
                Theoretical computer science, Robotics, Artificial intelligence

                Comments

                Comment on this article