Cake, Death, and Trolleys: Dilemmas as benchmarks of ethical decision-making

Artificial intelligence (AI) systems are becoming part of our lives and societies. The more decisions such systems make for us, the more we need to ensure that the decisions they make have a positive individual and societal ethical impact. How can we estimate how good a system is at making ethical decisions? Benchmarking is used to evaluate how good a machine or a process performs with respect to industry bests. In this paper we argue that (some) ethical dilemmas can be used as benchmarks for estimating the ethical performance of an autonomous system. We advocate that an open source repository of such dilemmas should be maintained. We present a prototype of such a repository available at https://imdb. uib.no/dilemmaz/articles/all1.

[1]  Oren Etzioni,et al.  Incorporating Ethics into Artificial Intelligence , 2017, The Journal of Ethics.

[2]  B. Gert,et al.  The Definition of Morality , 2002 .

[3]  Noel Stewart.  Ethics: An Introduction to Moral Philosophy , 2009 .

[4]  Luís Moniz Pereira,et al.  Programming Machine Ethics , 2016, Studies in Applied Philosophy, Epistemology and Rational Ethics.

[5]  Nikolaos Aletras,et al.  Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective , 2016, PeerJ Comput. Sci..

[6]  Michael Anderson,et al.  GenEth: a general ethical dilemma analyzer , 2014, AAAI.

[7]  Rights, Restitution, and Risk: Essays in Moral Theory. , 1989 .

[8]  James H. Moor,et al.  The Nature, Importance, and Difficulty of Machine Ethics , 2006, IEEE Intelligent Systems.

[9]  T. Beauchamp,et al.  Principles of biomedical ethics , 1991 .

[10]  Christian Blum,et al.  Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection , 2014, TAROS.

[11]  Thomas M. Powers.  Prospects for a Kantian Machine , 2006, IEEE Intelligent Systems.

[12]  Michael Fisher,et al.  Formal verification of ethical choices in autonomous systems , 2016, Robotics Auton. Syst..

[13]  Michael Anderson,et al.  Machine Ethics: Creating an Ethical Intelligent Agent , 2007, AI Mag..

[14]  Christian List,et al.  Engineering Moral Agents - from Human Morality to Artificial Morality (Dagstuhl Seminar 16222) , 2016, Dagstuhl Reports.

[15]  Matthias Scheutz,et al.  Sacrifice One For the Good of Many? People Apply Different Moral Norms to Human and Robot Agents , 2015, 2015 10th ACM/IEEE International Conference on Human-Robot Interaction (HRI).

[16]  Stuart Armstrong,et al.  Motivated Value Selection for Artificial Agents , 2015, AAAI Workshop: AI and Ethics.

[17]  I. Kant,et al.  Grounding for the metaphysics of morals ; with, On a supposed right to lie because of philanthropic concerns , 1993 .

[18]  Gregory Scopino.  Do Automated Trading Systems Dream of Manipulating the Price of Futures Contracts? Policing Markets for Improper Trading Practices by Algorithmic Robots , 2014 .

[19]  Bruce M. McLaren,et al.  Extensionally defining principles and cases in ethics: An AI model , 2003, Artif. Intell..

[20]  Felix Lindner,et al.  The Hybrid Ethical Reasoning Agent IMMANUEL , 2017, HRI.

[21]  Jason Millar,et al.  An Ethics Evaluation Tool for Automating Ethical Decision-Making in Robots and Self-Driving Cars , 2016, Appl. Artif. Intell..

[22]  J. Thomson.  The Trolley Problem , 1985 .

[23]  Michael Fisher,et al.  Towards Moral Autonomous Systems , 2017, ArXiv.

[24]  Martin Mose Bentzen,et al.  The Principle of Double Effect Applied to Ethical Dilemmas of Social Robots , 2016, Robophilosophy/TRANSOR.

[25]  W. D. Ross,et al.  The Right and the Good , 1930 .

[26]  P. Foot.  The Problem of Abortion and the Doctrine of the Double Effect , 2020, The Doctrine of Double Effect.

[27]  Michael Fisher,et al.  Towards Verifiably Ethical Robot Behaviour , 2015, AAAI Workshop: AI and Ethics.

[28]  John C. Harsanyi,et al.  Rule utilitarianism and decision theory , 1977 .

[29]  Michael Anderson,et al.  Toward ensuring ethical behavior from autonomous systems: a case-supported principle-based paradigm , 2015, Ind. Robot.

[30]  C. Allen,et al.  Artificial Morality: Top-down, Bottom-up, and Hybrid Approaches , 2005, Ethics and Information Technology.

[31]  Jaideep Srivastava,et al.  Automatic personalization based on Web usage mining , 2000, CACM.

[32]  Jean H. Gallier,et al.  Logic for Computer Science: Foundations of Automatic Theorem Proving , 1985 .

[33]  Selmer Bringsjord,et al.  Toward a General Logicist Methodology for Engineering Ethically Correct Robots , 2006, IEEE Intelligent Systems.

[34]  Joanna Bryson,et al.  Standardizing Ethical Design for Artificial Intelligence and Autonomous Systems , 2017, Computer.