Abstract
The implementation of moral decision making abilities in artificial intelligence (AI) is a natural and necessary extension to the social mechanisms of autonomous software agents and robots. Engineers exploring design strategies for systems sensitive to moral considerations in their choices and actions will need to determine what role ethical theory should play in defining control architectures for such systems. The architectures for morally intelligent agents fall within two broad approaches: the top-down imposition of ethical theories, and the bottom-up building of systems that aim at goals or standards which may or may not be specified in explicitly theoretical terms. In this paper we wish to provide some direction for continued research by outlining the value and limitations inherent in each of these approaches.
Similar content being viewed by others
References
Aleksander I, Dunmall B (2003) Axioms and tests for the presence of minimal consciousness in agents. J Conscious Stud 10(4–5):7–18
Aleksander I, Lahstein M, Lee R (2005) Will and emotions: A machine model that shuns illusion. In: Chrisley R, Clowes R, Torrance S (eds) Next generation approaches to machine consciousness: imagination, development, intersubjectivity, and embodiment. In: Proceedings of an AISB 2005 Workshop. University of Hertfordshire, Hatfield, pp 110–117
Allen C, Varner G, Zinser J (2000) Prolegomena to any future artificial moral agent. J Exp Theor Artif Intell 12:251–261
Allen C (2002) Calculated morality: ethical computing in the limit. In: Smit I, Lasker G (eds) Cognitive, emotive and ethical aspects of decision making and human action, vol I. IIAS, Windsor, Ontario
Asimov I (1950) I robot. Gnome Press, NY
Churchland PM (1995) The engine of reason, the seat of the soul: a philosophical journey into the brain. MIT Press, Cambridge, MA
Clark A (1998) Being there: putting brain, body, and world together again. MIT Press, Cambridge, MA
Clarke R (1993, 1994) Asimov’s laws of robotics: Implications for information technology. Published in two parts, in IEEE Computer 26, 12 53–61 and 27, 1, 57–66
Damasio A (1995) Descartes’ error. Pan Macmillan, New York
DeMoss D (1998) Aristotle, connectionism, and the morally excellent brain. In: Proceedings of the 20th world congress of philosophy. The Paideia Archive, available at http://www.bu.edu/wcp/Papers/Cogn/CognDemo.htm
Friedman B, Kahn P (1992) Human agency and responsible computing. J Syst Softw 17:7–14
Friedman B, Nissenbaum H (1996) Bias in computer systems. ACM Trans Inf Syst 14:330–347
Gips J (1995) Towards the ethical robot. In: Ford K, Glymour C, Hayes P (eds) Android epistemology. MIT Press, Cambridge, MA pp 243–252
Goleman D (1995) Emotional intelligence. Bantam Books, New York
Hsiao K, Roy D (2005) A habit system for an interactive robot. In: AAAI fall symposium 2005: from reactive to anticipatory cognitive embodied systems. available at http://www.media.mit.edu/cogmac/publications/habit_system_aaaifs_05.pdf
Hursthouse R (2003) “Virtue ethics”. The stanford encyclopedia of philosophy. In: Edward N Zalta (ed) available at http://plato.stanford.edu/archives/fall2003/entries/ethics-virtue/
Lang C (2002) Ethics for artificial intelligence. available at http://philosophy.wisc.edu/lang/AIEthics/index.htm
Picard R (1997) Affective computing. MIT Press, Cambridge, MA
Roy D (2005) Semiotic schemas: a framework for grounding language in the action and perception. Artif Intell 167(1–2):170–205
Scassellati B (2001) Foundations for a theory of mind for a humanoid robot. Ph.D. dissertation, MIT Department of Computer Science and Electrical Engineering, available at http://www.ai.mit.edu/projects/lbr/hrg/2001/scassellati-phd.pdf
Smith T, Husbands P, Philippides A (2002) Neuronal plasticity and temporal adaptivity: GasNet robot control networks. Adapt Behav 10:161–183
Wallach W (2003). Robot morals and human ethics. In: Smit I, Lasker G, Wallach W (eds) Cognitive, emotive and ethical aspects of decision making in humans and in artificial intelligence, vol II. IIAS, Windsor, Ontario
Wallach W (2004) Artificial morality: bounded rationality, bounded morality and emotions. In: Smit I, Lasker L, Wallach W (eds) Cognitive, emotive and ethical aspects of decision making and human action, vol III. IIAS, Windsor, Ontario
Williams B (1985) Ethics and the limits of philosophy. Harvard University Press, Cambridge, MA
Acknowledgments
An earlier version of the paper was prepared for and presented at the Android Science Cog Sci 2005 Workshop in Stresa, Italy. We wish to thank Karl MacDorman, coorganizer of workshop, for his encouragement, detailed comments, and editing suggestions. We are also grateful for the helpful comments provided by three anonymous reviewers arranged by the Workshop organizers.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wallach, W., Allen, C. & Smit, I. Machine morality: bottom-up and top-down approaches for modelling human moral faculties. AI & Soc 22, 565–582 (2008). https://doi.org/10.1007/s00146-007-0099-0
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00146-007-0099-0