Abstract
Machine ethics, also known as artificial morality, is a newly emerging field concerned with ensuring appropriate behavior of machines toward humans and other machines. In this article, we discuss the importance of machine ethics and present a computational model of ethical decision-making for autonomous agents. The proposed model implements a mechanism for integrating the results of diverse assessments into a unique cue, and takes into account the agent’s preferences, good and bad past experiences, ethical rules, and current emotional state as the main factors involved in choosing the most appropriate option. The design of the model is based on theories and models developed in fields such as neuroscience, psychology, artificial intelligence, and cognitive informatics. In particular, the model attempts to emulate neural mechanisms of the human brain involved in ethical decision-making.








Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.References
Fuster J. The prefrontal cortex. 4th ed. Waltham: Academic Press; 2008.
Kibele A. Non-consciously controlled decision making for fast motor reactions in sports: a priming approach for motor responses to non-consciously perceived movement features. Psychol Sport Exerc. 2006;7:591–610.
Bechara A, Damasio H, Damasio A. Emotion, decision making and the orbitofrontal cortex. Cereb Cortex. 2000;10:295–307.
Wallis JD. Orbitofrontal cortex and Its contribution to decision-making. Annu Rev Neurosci. 2007;30:31–56.
Wallach W, Allen C, Smit I. Machine morality: bottom-up and top-down approaches for modelling human moral faculties. AI Soc. 2008;22:565–82.
Wallach W. Implementing moral decision making faculties in computers and robots. AI Soc. 2008;22:463–75.
Harman G. The nature of morality: an introduction to ethics. Oxford: Oxford University Press; 1977.
Wallach W, Franklin S, Allen C. A conceptual and computational model of moral decision making in human and artificial agents. Top Cogn Sci. 2010;2:454–85.
Fong T, Nourbakhsh I, Dautenhahn K. A survey of socially interactive robots. Robot Auton Syst. 2003;42:143–66.
Czubenko M, Kowalczuk Z, Ordys A. Autonomous driver based on an intelligent system of decision-making. Cogn Comput 2015;7:569–581.
Juha R, Jukka H, Vili K, Antti T, Matti P. Minotaurus: a system for affective human-robot interaction in smart environments. Cogn Comput. 2014;6:940–53.
Paul W, Barbara LT. Affective robotics: modelling and testing cultural prototypes. Cogn Comput. 2014;6:814–40.
Bechara A. The role of emotion in decision-making: evidence from neurological patients with orbitofrontal damage. Brain Cogn. 2004;55:30–40.
Damasio AR, Everitt BJ, Bishop D. The somatic marker hypothesis and the possible functions of the prefrontal cortex [and discussion]. Philos Trans R Soc Lond B Biol Sci. 1996;351:1413–20.
Loewenstein GF, Weber EU, Hsee CK, Welch N. Risk as feelings. Psychol Bull. 2001;127:267–310.
Tom SM, Fox CR, Trepel C, Poldrack RA. The neural basis of loss aversion in decision-making under risk. Science. 2007;315:515–8.
Tversky A, Kahneman D. Rational choice and the framing of decisions. J Bus. 1986;211:251–78.
Gul FA. The joint and moderating role of personality and cognitive style on decision making. Account Rev. 1984;59:264–77.
Thatcher A, De La Cour A. Small group decision-making in face-to-face and computer-mediated environments: the role of personality. Behav Inf Technol. 2003;22:203–18.
Broeders R, Van den Bos K, Müller PA, Ham J. Should I save or should I not kill? How people solve moral dilemmas depends on which rule is most accessible. J Exp Soc Psychol. 2011;47:923–34.
Anderson M, Anderson SL. Machine ethics: creating an ethical intelligent agent. AI Mag. 2007;28:15–26.
Allen C, Wallach W, Smit I. Why machine ethics? Intell Syst. 2006;21:12–7.
Wallach W. Robot minds and human ethics: the need for a comprehensive model of moral decision making. Ethics Inf Technol. 2010;12:243–50.
Hagras H, Callaghan V, Colley M, Clarke G, Pounds-Cornish A, Duman H. Creating an ambient-intelligence environment using embedded agents. Intell Syst IEEE. 2004;19:12–20.
Ostos R, Cervantes JF, Ramos FF, Castillo B, Occello M. Context-sensitive ecosystem of intelligent environments. In: Proceedings of the 8th international conference on intelligent environments (IE); 2012 June 26–29; Guanajuato, Mexico. IEEE Computer Society; 2012. pp. 72–79.
Laird JE, Newell A, Rosenbloom PS. SOAR: an architecture for general intelligence. Artif Intell. 1987;33:1–64.
Laird JE. The Soar cognitive architecture. Cambridge: The MIT Press; 2012.
Baars BJ, Franklin S. An architectural model of conscious and unconscious brain functions: global workspace theory and IDA. Neural Netw. 2007;20:955–61.
Best BJ, Lebiere C. Cognitive agents interacting in real and virtual worlds. In: Ron S, editor. Cognition and multi-agent interaction: from cognitive modeling to social simulation. Cambridge: Cambridge University Press; 2006. p. 186–218.
Allen C, Varner G, Zinser J. Prolegomena to any future artificial moral agent. J Exp Theor Artif Intell. 2000;12:251–61.
Breazeal C. Toward sociable robots. Robot Auton Syst. 2003;42:167–75.
Kaplan F. Talking AIBO: First experimentation of verbal interactions with an autonomous four-legged robot. Learning to behave: interacting agents CELE-TWENTE Workshop on Language Technology 2000. pp. 57-63.
Tsagarakis NG, Metta G, Sandini G, Vernon D, Beira R, Becchi F, Righetti L, Santos-Victor J, Ijspeert AJ, Carrozza MC. iCub: the design and realization of an open humanoid platform for cognitive and neuroscience research. Adv Robot. 2007;21:1151–75.
Hirai K, Hirose M, Haikawa Y, Takenaka T. The development of Honda humanoid robot. IEEE international conference on robotics and automation 1998. pp. 1321-1326.
Gigerenzer G. Moral satisficing: rethinking moral behavior as bounded rationality. Top Cogn Sci. 2010;2:528–54.
Honarvar AR, Ghasem-Aghaee N. An artificial neural network approach for creating an ethical artificial agent. In: Proceedings of the IEEE international symposium on computational intelligence in robotics and automation (CIRA); 2009 December 15–18; Daejeon, Korea. IEEE Computer Society; 2009. pp. 290–295.
Dehghani M, Tomai E, Forbus KD, and Klenk M. An integrated reasoning approach to moral decision-making. In: Proceedings of the twenty-third AAAI conference on artificial intelligence; 2008 July 13–17; Chicago, USA. AAAI; 2008. pp. 1280–1286.
Coelho H, da Rocha C, António C, Trigo P. Decision making for agent moral conducts. In: Proceedings of the INForum 2010 - Simpósio de Informática; 2010 September 9–10; Braga, Portugal. INForum; 2010. pp. 721732.
Franklin S, Strain S, McCall R, Baars B. Conceptual commitments of the LIDA model of cognition. J Artif Gen Intell. 2013;4:1–22.
Snaider J, McCall R, Franklin S. The LIDA framework as a general tool for AGI. In: Schmidhuber J, Thórisson KR, Moshe L, editors. Artifical general intelligence. Berlin: Springer; 2011. p. 133–42.
Honarvar AR, Ghasem-Aghaee N. Casuist BDI-agent: a new extended BDI architecture with the capability of ethical reasoning. In: Deng H, Wang L, Wang FL, Lei J, editors. Artificial intelligence and computational intelligence. Berlin: Springer; 2009. p. 86–95.
Borg JS, Hynes C, Van HJ, Grafton S, Sinnott-Armstrong W. Consequences, action, and intention as factors in moral judgments: an fMRI Investigation. J Cogn Neurosci. 2006;18:803–17.
De Martino B, Kumaran D, Seymour B, Dolan RJ. Frames, biases, and rational decision-making in the human brain. Science. 2006;313:684–7.
Lu LC, Rose GM, Blodgett JG. The effects of cultural dimensions on ethical decision making in marketing: an exploratory study. J Bus Ethics. 1999;18:91–105.
O’Fallon MJ, Butterfield KD. A review of the empirical ethical decision-making literature: 1996–2003. J Bus Ethics. 2005;59:375–413.
Rolls ET. The orbitofrontal cortex and reward. Cereb Cortex. 2000;10:284–94.
O’Doherty J, Kringelbach ML, Rolls ET, Hornak J, Andrews C. Abstract reward and punishment representations in the human orbitofrontal cortex. 2001;4:95–102.
Opris I, Bruce CJ. Neural circuitry of judgment and decision mechanisms. Brain Res Rev. 2005;48:509–26.
Ernst M, Paulus MP. Neurobiology of decision making: a selective review from a neurocognitive and clinical perspective. Biol Psychiatry. 2005;58:597–604.
Gold JI, Shadlen MN. The neural basis of decision making. Annu Rev Neurosci. 2007;30:535–74.
Schultz W, Tremblay L, Hollerman JR. Reward processing in primate orbitofrontal cortex and basal ganglia. Cereb Cortex. 2000;10:272–83.
Crescentini C, Seyed-Allaei S, Vallesi A, Shallice T. Two networks involved in producing and realizing plans. Neuropsychologia. 2012;50:1521–35.
Hoshi E, Tanji J. Area-selective neuronal activity in the dorsolateral prefrontal cortex for information retrieval and action planning. J Neurophysiol. 2004;91:2707–22.
Markic O. Rationality and emotions in decision making. Interdiscip Descr Complex Syst. 2009;7:54–64.
Greene JD, Nystrom LE, Engell AD, Darley JM, Cohen JD. The neural bases of cognitive conflict and control in moral judgment. Neuron. 2004;44:389–400.
Miller EK, Cohen JD. An integrative theory of prefrontal cortex function. Ann Rev Neurosci. 2001;24:167–202.
Chambers RA, Taylor JR, Potenza MN. Developmental neurocircuitry of motivation in adolescence: a critical period of addiction vulnerability. Am J Psychiatry. 2003;160:1041–52.
Volkow ND, Fowler JS. Addiction, a disease of compulsion and drive: involvement of the orbitofrontal cortex. Cerebral cortex. 2000;10:318–25.
Haber SN, Calzavara R. The cortico-basal ganglia integrative network: the role of the thalamus. Brain Res Bull. 2009;78:69–74.
Kennerley SW, Walton ME, Behrens TEJ, Buckley MJ, Rushworth MFS. Optimal decision making and the anterior cingulate cortex. Nat Neurosci. 2006;9:940–7.
Van Staveren I. Beyond utilitarianism and deontology: ethics in economics. Rev Polit Econ. 2007;19:21–35.
Gross CG, Rodman HR, Gochin PM, Colombo MW. Inferior temporal cortex as a pattern recognition device. In: Baum EB, editor. Computational Learning and Cognition: proceedings of the 3rd NEC research symposium. Philadelphia: Siam; 1992. p. 44–73.
Rodman HR. Development of inferior temporal cortex in the monkey. Cereb Cortex. 1994;4:484–98.
Frey S, Kostopoulos P, Petrides M. Orbitofrontal involvement in the processing of unpleasant auditory information. Eur J Neurosci. 2000;12:3709–12.
O’Doherty JP. Reward representations and reward-related learning in the human brain: insights from neuroimaging. Curr Opin Neurobiol. 2004;14:769–76.
Rogers RD, Ramnani N, Mackay C, Wilson JL, Jezzard P, Carter CS, Smith SM. Distinct portions of anterior cingulate cortex and medial prefrontal cortex are activated by reward processing in separable phases of decision-making cognition. Biol Psychiatry. 2004;55:594–602.
Rizzolatti G, Fadiga L, Gallese V, Fogassi L. Premotor cortex and the recognition of motor actions. Cogn Brain Res. 1996;3:131–41.
Hoshi E, Tanji J. Integration of target and body-part information in the premotor cortex when planning action. Nature. 2000;408:466–70.
Ford RC, Richardson WD. Ethical decision making: a review of the empirical literature. J Bus Ethics. 1994;13:205–21.
Ferrell OC, Gresham LG. A contingency framework for understanding ethical decision making in marketing. J Market. 1985;49:87–96.
Wang Y, Liu D, Ruhe G. Formal description of the cognitive process of decision making. In: Proceedings of the third IEEE international conference on cognitive informatics; 2004 August 16–17; British Columbia, Canada. IEEE Computer Society; 2004. pp. 124–130.
Yingxu W. A novel decision grid theory for dynamic decision-making. In: Proceedings of the fourth IEEE conference on cognitive informatics; 2005 August 8–10; California, USA. IEEE Computer Society; 2005. pp. 308-314.
Wang Y. Inference algebra (IA): a denotational mathematics for cognitive computing and machine reasoning (I). Int J Cogn Inf Nat Intell. 2011;5:61–82.
Wang Y. Inference Algebra (IA): a denotational mathematics for cognitive computing and machine reasoning (II). Int J Cogn Inf Nat Intell. 2012;6:21–47.
Morten K. The human orbitofrontal cortex: linking reward to hedonic experience. Nat Rev Neurosci. 2005;6:691–702.
Wang Y. RTPA: a denotational mathematics for manipulating intelligent and computational behaviors. Int J Cogn Inf Nat Intell. 2008;2:44–62.
Forgas JP. Mood and judgment: the affect infusion model (AIM). Psychol Bull. 1995;117:39–66.
Hockey RJ, John MA, Clough PJ, Bdzola L. Effects of negative mood states on risk in everyday decision making. Cogn Emot. 2000;14:823–55.
Ekman P. Basic emotions. Handb Cogn Emot. 1999;98:45–60.
Ekman P. Are there basic emotions? Psychol Rev. 1992;99:550–3.
Hunt SD, Vitell S. A general theory of marketing ethics. J Macromarket. 1986;6:5–16.
Harsanyi JC. A theory of prudential values and a rule utilitarian theory of morality. Soc Choice Welfare. 1995;12:319–33.
Vitell SJ, Nwachukwu SL, Barnes JH. The effects of culture on ethical decision-making: an application of Hofstede’s typology. J Bus Ethics. 1993;12:753–60.
Hochschild AR. Emotion work, feeling rules, and social structure. Am J Sociol. 1979;85:551–75.
Rodríguez LF, Ramos F, Wang Y. Cognitive computational models of emotions and affective behaviors. Int J Softw Sci Comput Intell (IJSSCI). 2012;2:41–63.
Wang Y. On the cognitive processes of human perception with emotions, motivations, and attitudes. J Cogn Inf Nat Intell. 2007;1:1–13.
Author information
Authors and Affiliations
Corresponding author
Appendices
Appendix 1: Technical Information About First Case Study
The fuzzy rules used in the primary evaluation of option one “stop the car” in order to give way to a pedestrian are:

The fuzzy rules used in the primary evaluation of option two “continue driving” are:

The experiences given to the agent related to option one “stop the car” in order to give way to a pedestrian are:

The experiences given to the agent related to option two “continue driving” are:

Appendix 2: Fuzzy Ethical Rules Used in Both Cases
The fuzzy rules used by the agent in both cases are:

The norms and rules of the agent:

Appendix 3: Technical Information About Second Case
The fuzzy rules used in the primary evaluation of both options are:

The experiences of the agent in the second case are the following:

Rights and permissions
About this article
Cite this article
Cervantes, JA., Rodríguez, LF., López, S. et al. Autonomous Agents and Ethical Decision-Making. Cogn Comput 8, 278–296 (2016). https://doi.org/10.1007/s12559-015-9362-8
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s12559-015-9362-8