Edvard P. Bjørgen
Marija Slavkovik
ABSTRACT
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.
- N. Aletras, D. Tsarapatsanis, D. Preotiuc-Pietro, and V. Lampos. 2016. Predicting judicial decisions of the European Court of Human Rights: a Natural Language Processing perspective. PeerJ Computer Science 2 (2016).Google Scholar
- C. Allen, I. Smit, andW.Wallach. 2005. Artificial morality: Top-down, bottom-up, and hybrid approaches. Ethics and information technology 7, 3 (2005), 149--155. Google ScholarDigital Library
- Michael Anderson and S. Leigh Anderson. 2007. Machine ethics: Creating an ethical intelligent agent. AI Magazine 28, 4 (2007), 15.Google ScholarDigital Library
- M. Anderson and S. Leigh Anderson. 2014. GenEth: A General Ethical Dilemma Analyzer. In Proceedings of the 28th AAAI Conference on Artificial Intelligence, July 27 -31, 2014, Québec City, Québec, Canada. 253--261. http://www.aaai.org/ ocs/index.php/AAAI/AAAI14/paper/view/8308 Google ScholarDigital Library
- M. Anderson and S. Leigh Anderson. 2015. Toward ensuring ethical behavior from autonomous systems: a case-supported principle-based paradigm. Industrial Robot 42, 4 (2015), 324--331.Google ScholarCross Ref
- S. Armstrong. 2015. Motivated Value Selection for Artificial Agents. In Artificial Intelligence and Ethics, Papers from the 2015 AAAI Workshop, Austin, Texas, USA, January 25, 2015. http://aaai.org/ocs/index.php/WS/AAAIW15/paper/view/ 10183.Google Scholar
- T. L. Beauchamp and J. F. Childress. 1979. Principles of Biomedical Ethics. Oxford University Press. https://books.google.no/books?id=nreKPwAACAAJGoogle Scholar
- M. M. Bentzen. 2016. The principle of double effect applied to ethical dilemmas of social robots. IOS Press, 268--279.Google Scholar
- S. Bringsjord, K. Arkoudas, and P. Bello. 2006. Toward a General Logicist Methodology for Engineering Ethically Correct Robots. IEEE Intelligent Systems 21, 4 (July 2006), 38--44. Google ScholarDigital Library
- J. Bryson and A.F.T. Winfield. 2017. Standardizing Ethical Design for Artificial Intelligence and Autonomous Systems. IEEE Computer 50, 5 (2017), 116--119. Google ScholarDigital Library
- V. Charisi, L.A. Dennis, M. Fisher, R. Lieck, A. Matthias, M. Slavkovik, J. Sombetzki, A.F.T. Winfield, and R. Yampolskiy. 2017. Towards Moral Autonomous Systems. CoRR abs/1703.04741 (2017). http://arxiv.org/abs/1703.04741Google Scholar
- L. A. Dennis, M. Fisher, M. Slavkovik, and M. P.Webster. 2016. Formal Verification of Ethical Choices in Autonomous Systems. Robotics and Autonomous Systems 77 (2016), 1--14. Google ScholarDigital Library
- L. A. Dennis, M. Fisher, and A. F. T. Winfield. 2015. Towards Verifiably Ethical Robot Behaviour. In Proceedings of AAAI Workshop on AI and Ethics. http: //aaai.org/ocs/index.php/WS/AAAIW15/paper/view/10119.Google Scholar
- ElasticSearch. https://www.elastic.co/products/elasticsearch. (????). Accessed: 2017-05-09.Google Scholar
- C. Elgin. 1996. Considered Judgment. Princeton: New Jersey: Princeton University Press.Google Scholar
- J.W. Ellington. 1993. Translation of: Grounding for the Metaphysics of Morals: with On a Supposed Right to Lie because of Philanthropic Concerns by Kant, I. {1785}. Hackett Publishing Company.Google Scholar
- A. Etzioni and O. Etzioni. 2017. Incorporating Ethics into Artificial Intelligence. The Journal of Ethics (2017), 1--16.Google Scholar
- M. Fisher, C. List, M. Slavkovik, and A. F. T. Winfield. 2016. Engineering Moral Agents - from Human Morality to Artificial Morality (Dagstuhl Seminar 16222). Dagstuhl Reports 6, 5 (2016), 114--137.Google Scholar
- P. Foot. 1967. The Problem of Abortion and the Doctrine of Double Effect. Oxford Review 5 (1967), 5--15.Google Scholar
- Jean H Gallier. 2015. Logic for computer science: foundations of automatic theorem proving. Courier Dover Publications. Google ScholarDigital Library
- J. Garrett. 2004. A Simple and Usable (Although Incomplete) Ethical Theory Based on the Ethics ofW.D. Ross. http://people.wku.edu/jan.garrett/ethics/rossethc.htm. (2004). http://people.wku.edu/jan.garrett/ethics/rossethc.htm Accessed: 2017-05- 09.Google Scholar
- B. Gert and J. Gert. 2017. The Definition of Morality. In The Stanford Encyclopedia of Philosophy (fall 2017 ed.), E.N. Zalta (Ed.). Metaphysics Research Lab, Stanford University.Google Scholar
- J.C. Harsanyi. 1977. Rule Utilitarianism and Decision Theory. Erkenntnis (1975-) 11, 1 (1977), 25--53. http://www.jstor.org/stable/20010532Google Scholar
- F. Lindner and M.M. Bentzen. 2017. The Hybrid Ethical Reasoning Agent IMMANUEL. In Companion of the 2017 ACM/IEEE International Conference on Human-Robot Interaction, HRI 2017, Vienna, Austria, March 6--9, 2017. 187--188. Google ScholarDigital Library
- B. F. Malle, M. Scheutz, T. Arnold, J. Voiklis, and C. Cusimano. 2015. Sacrifice One For the Good of Many?: People Apply Different Moral Norms to Human and Robot Agents. In Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction (HRI '15). ACM, 117--124. Google ScholarDigital Library
- B. McLaren. 2003. Extensionally defining principles and cases in ethics: An AI model. Artificial Intelligence 150, 1 (2003), 145 -- 181. Google ScholarDigital Library
- Jason Millar. 2016. An Ethics Evaluation Tool for Automating Ethical Decision- Making in Robots and Self-Driving Cars. Applied Artificial Intelligence 30, 8 (2016), 787--809. Google ScholarDigital Library
- B. Mobasher, R. Cooley, and J. Srivastava. 2000. Automatic Personalization Based on Web Usage Mining. Communications of ACM 43, 8 (2000), 142--151. Google ScholarDigital Library
- J. H. Moor. 2006. The Nature, Importance, and Difficulty of Machine Ethics. IEEE Intelligent Systems 21, 4 (July 2006), 18--21. Google ScholarDigital Library
- L. M. Pereira and A. Saptawijaya. 2016. Programming Machine Ethics. Studies in Applied Philosophy, Epistemology and Rational Ethics, Vol. 26. Springer. Google ScholarDigital Library
- Thomas M Powers. 2006. Prospects for a Kantian machine. IEEE Intelligent Systems 21, 4 (2006), 46--51. Google ScholarDigital Library
- W.D. Ross. 1930. The Right and the Good. Oxford University Press.Google Scholar
- G. Scopino. 2015. Do Automated Trading Systems Dream of Manipulating the Price of Futures Contracts? Policing Markets for Improper Trading Practices by Algorithmic Robots. Florida Law Review 67 (2015), 221--293.Google Scholar
- J.J. Thomson and W. Parent. 1986. The Trolley Problem. In Rights, Restitution, and Risk: Essays in Moral Theory. Harvard University Press. https://books.google. no/books?id=sLh4oBgJEtECGoogle Scholar
- L. Vaughn. 2014. Beginning Ethics: An Introduction to Moral Philosophy. W. W. Norton, Incorporated. https://books.google.no/books?id=BwChoAEACAAJGoogle Scholar
- A. F. T. Winfield, C. Blum, and W. Liu. 2014. Towards an Ethical Robot: Internal Models, Consequences and Ethical Action Selection. Springer International Publishing, 85--96.Google Scholar
Index Terms
- Cake, Death, and Trolleys: Dilemmas as benchmarks of ethical decision-making
Recommendations
Thinking otherwise: Ethics, technology and other subjects
Ethics is ordinarily understood as being concerned with questions of responsibility for and in the face of an other. This other is more often than not conceived of as another human being and, as such, necessarily excludes others --- most notably animals ...
Robot minds and human ethics: the need for a comprehensive model of moral decision making
Building artificial moral agents (AMAs) underscores the fragmentary character of presently available models of human ethical behavior. It is a distinctly different enterprise from either the attempt by moral philosophers to illuminate the "ought" of ...
Particularism, Analogy, and Moral Cognition
`Particularism' and `generalism' refer to families of positions in the philosophy of moral reasoning, with the former playing down the importance of principles, rules or standards, and the latter stressing their importance. Part of the debate has taken ...
Comments