A Conceptual and Computational Model of Moral Decision Making in Human and Artificial Agents

Recently, there has been a resurgence of interest in general, comprehensive models of human cognition. Such models aim to explain higher-order cognitive faculties, such as deliberation and planning. Given a computational representation, the validity of these models can be tested in computer simulations such as software agents or embodied robots. The push to implement computational models of this kind has created the field of artificial general intelligence (AGI). Moral decision making is arguably one of the most challenging tasks for computational approaches to higher-order cognition. The need for increasingly autonomous artificial agents to factor moral considerations into their choices and actions has given rise to another new field of inquiry variously known as Machine Morality, Machine Ethics, Roboethics, or Friendly AI. In this study, we discuss how LIDA, an AGI model of human cognition, can be adapted to model both affective and rational features of moral decision making. Using the LIDA model, we will demonstrate how moral decisions can be made in many domains using the same mechanisms that enable general decision making. Comprehensive models of human cognition typically aim for compatibility with recent research in the cognitive and neural sciences. Global workspace theory, proposed by the neuropsychologist Bernard Baars (1988), is a highly regarded model of human cognition that is currently being computationally instantiated in several software implementations. LIDA (Franklin, Baars, Ramamurthy, & Ventura, 2005) is one such computational implementation. LIDA is both a set of computational tools and an underlying model of human cognition, which provides mechanisms that are capable of explaining how an agent's selection of its next action arises from bottom-up collection of sensory data and top-down processes for making sense of its current situation. We will describe how the LIDA model helps integrate emotions into the human decision-making process, and we will elucidate a process whereby an agent can work through an ethical problem to reach a solution that takes account of ethically relevant factors.

[1]  Linda B Smith,et al.  Known and novel noun extensions: attention at two levels of abstraction. , 2003, Child development.

[2]  William K. Estes,et al.  Classification and cognition , 1994 .

[3]  P. Petta,et al.  Emotions in Humans and Artifacts , 2003 .

[4]  Wendell Wallach,et al.  Implementing moral decision making faculties in computers and robots , 2008, AI & SOCIETY.

[5]  K. A. Ericsson,et al.  Long-term working memory. , 1995, Psychological review.

[6]  Marcello Guarini,et al.  Particularism and the Classification and Reclassification of Moral Cases , 2006, IEEE Intelligent Systems.

[7]  Cynthia Breazeal,et al.  Emotion and sociable humanoid robots , 2003, Int. J. Hum. Comput. Stud..

[8]  L. Barsalou,et al.  Whither structured representation? , 1999, Behavioral and Brain Sciences.

[9]  Stan Franklin,et al.  Deliberation and Voluntary Action in "Conscious" Software Agents , 2000 .

[10]  Dolores Canamero,et al.  Designing emotions for activity selection in autonomous agents , 2003 .

[11]  Fiorella de Rosis.  Review of “Emotions in humans and artifacts” by R. Trappl, P. Petta and S. Payr (Eds.) , 2004 .

[12]  C. Allen,et al.  Moral Machines: Teaching Robots Right from Wrong , 2008 .

[13]  Aaron Sloman,et al.  Damasio, Descartes, alarms and meta-management , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[14]  Stan Franklin,et al.  A "Consciousness"-Based Architecture for a Functioning Mind , 2005 .

[15]  Stan Franklin,et al.  An action selection mechanism for "conscious" software agents , 2002 .

[16]  D F Watt.  Affect and the limbic system: some hard problems. , 1998, The Journal of neuropsychiatry and clinical neurosciences.

[17]  Michael Tarsitano,et al.  Route selection by a jumping spider (Portia labiata) during the locomotory phase of a detour , 2006, Animal Behaviour.

[18]  P. Thagard,et al.  Emotion and action , 2002 .

[19]  I. Kant,et al.  Groundwork for the Metaphysics of Morals , 2002 .

[20]  B. Baars.  The conscious access hypothesis: origins and recent evidence , 2002, Trends in Cognitive Sciences.

[21]  G. Tononi,et al.  Breakdown of Cortical Effective Connectivity During Sleep , 2005, Science.

[22]  AllenColin,et al.  Machine morality: bottom-up and top-down approaches for modelling human moral faculties , 2008 .

[23]  W. Freeman.  How Brains Make Up Their Minds , 1999 .

[24]  E. Vesterinen,et al.  Affective Computing , 2009, Encyclopedia of Biometrics.

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

[26]  Andrew D. Engell,et al.  The Neural Bases of Cognitive Conflict and Control in Moral Judgment , 2004, Neuron.

[27]  D. Spalding.  The Principles of Psychology , 1873, Nature.

[28]  S. Globali,et al.  IEEE INTELLIGENT SYSTEMS , 2022, IEEE MultiMedia.

[29]  Peter Danielson.  Artificial Morality: Virtuous Robots for Virtual Games , 1992 .

[30]  Michael Anderson,et al.  Machine Ethics , 2011 .

[31]  Sidney K. D'Mello,et al.  Modified sparse distributed memory as transient episodic memory for cognitive software agents , 2004, 2004 IEEE International Conference on Systems, Man and Cybernetics (IEEE Cat. No.04CH37583).

[32]  Stan Franklin.  Evolutionary pressures and a stable world for animals and robots: A commentary on Merker , 2005, Consciousness and Cognition.

[33]  B. Merker.  The liabilities of mobility: A selection pressure for the transition to consciousness in animal evolution , 2005, Consciousness and Cognition.

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

[35]  M. Shanahan.  A cognitive architecture that combines internal simulation with a global workspace , 2006, Consciousness and Cognition.

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

[37]  Arthur C. Graesser,et al.  Is it an Agent, or Just a Program?: A Taxonomy for Autonomous Agents , 1996, ATAL.

[38]  J. Changeux,et al.  A neuronal network model linking subjective reports and objective physiological data during conscious perception , 2003, Proceedings of the National Academy of Sciences of the United States of America.

[39]  Lee McCauley,et al.  LIDA: A Computational Model of Global Workspace Theory and Developmental Learning , 2007, AAAI Fall Symposium: AI and Consciousness.

[40]  Lynn Nadel,et al.  Multiple Memory Systems: What and Why , 1992, Journal of Cognitive Neuroscience.

[41]  R. Mizen.  The embodied mind. , 2009, The Journal of analytical psychology.

[42]  J. Holzer,et al.  Buspirone and brain injury. , 1998, The Journal of neuropsychiatry and clinical neurosciences.

[43]  Nicholas J. Mulcahy,et al.  Apes Save Tools for Future Use , 2006, Science.

[44]  J. Kruschke.  Attention in Learning , 2003 .

[45]  Ron Sun,et al.  The importance of cognitive architectures: an analysis based on CLARION , 2007, J. Exp. Theor. Artif. Intell..

[46]  Wendell Wallach,et al.  Why Machine Ethics? , 2006, IEEE Intelligent Systems.

[47]  Michael S. Gazzaniga.  The Ethical Brain , 2005 .

[48]  M. Shermer,et al.  The Believing Brain , 2011 .

[49]  Allen Newell,et al.  SOAR: An Architecture for General Intelligence , 1987, Artif. Intell..

[50]  Victor S. Johnston.  Why We Feel: The Science Of Human Emotions , 1999 .

[51]  Stan Franklin,et al.  Cognitively Inspired Anticipation and Anticipatory Learning Mechanisms for Autonomous Agents , 2006 .

[52]  David DeMoss.  Aristotle, Connectionism, and the Morally Excellent Brain , 1998 .

[53]  J. Gips.  Towards the ethical robot , 1995 .

[54]  K M Heilman,et al.  The neurobiology of emotional experience. , 1997, The Journal of neuropsychiatry and clinical neurosciences.

[55]  Lee McCauley,et al.  Interacting with IDA , 2003 .

[56]  Cynthia Breazeal,et al.  Designing sociable robots , 2002 .

[57]  Wendell Wallach,et al.  Machine morality: bottom-up and top-down approaches for modelling human moral faculties , 2008, AI & SOCIETY.

[58]  Joshua D. Greene,et al.  How (and where) does moral judgment work? , 2002, Trends in Cognitive Sciences.

[59]  Roger Clarke,et al.  Asimov's Laws of Robotics: Implications for Information Technology - Part 2 , 1993, Computer.

[60]  L. Nadel,et al.  Memory consolidation, retrograde amnesia and the hippocampal complex , 1997, Current Opinion in Neurobiology.

[61]  R. Brooks.  Flesh and machines , 2001 .

[62]  Ludwig Huber,et al.  A case of quick problem solving in birds: string pulling in keas, Nestor notabilis , 2006, Animal Behaviour.

[63]  Melanie Mitchell,et al.  The Copycat project: a model of mental fluidity and analogy-making , 1995 .

[64]  Alan D Samples,et al.  SOAR Architecture , 1985 .

[65]  R. Stickgold,et al.  Memory consolidation and reconsolidation: what is the role of sleep? , 2005, Trends in Neurosciences.

[66]  John V. Jackson.  Idea for a mind , 1987, SGAR.

[67]  B. Baars.  A cognitive theory of consciousness , 1988 .

[68]  Wendell Wallach,et al.  Cognitive, Emotive, and Ethical Aspects of Decision Making in Humans and in Ai , 2005 .

[69]  Colin Allen,et al.  Prolegomena to any future artificial moral agent , 2000, J. Exp. Theor. Artif. Intell..

[70]  Adam Kepecs,et al.  Seeing at a glance, smelling in a whiff: rapid forms of perceptual decision making , 2006, Nature Reviews Neuroscience.

[71]  Sidney K. D'Mello,et al.  Cognitively Inspired Anticipatory Adaptation and Associated Learning Mechanisms for Autonomous Agents , 2007, SAB ABiALS.

[72]  Stan Franklin.  Perceptual Memory and Learning : Recognizing , Categorizing , and Relating , 2005 .

[73]  Michael Anderson,et al.  An Approach to Computing Ethics , 2006, IEEE Intelligent Systems.

[74]  Mary Johnson.  About our Guest Editor , 2008, Indian journal of pharmacology.

[75]  Igor Aleksander.  Machine consciousness , 2005, Scholarpedia.

[76]  M. D’Esposito.  Working memory. , 2008, Handbook of clinical neurology.

[77]  Jonathan D. Cohen,et al.  An fMRI Investigation of Emotional Engagement in Moral Judgment , 2001, Science.

[78]  Nicola S. Clayton,et al.  Episodic Memory , 2019, Encyclopedia of Animal Cognition and Behavior.

[79]  Eric Berne,et al.  Games People Play: The Basic Handbook of Transactional Analysis , 1996 .

[80]  Pentti Kanerva,et al.  Sparse Distributed Memory , 1988 .

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

[82]  Christopher Grau,et al.  There Is No "I" in "Robot": Robots and Utilitarianism , 2006, IEEE Intelligent Systems.

[83]  Bruce M. McLaren,et al.  Computational Models of Ethical Reasoning: Challenges, Initial Steps, and Future Directions , 2006, IEEE Intelligent Systems.

[84]  W. Davis.  The Ecological Approach to Visual Perception , 2012 .

[85]  Carol B. Perez,et al.  Principles of Biomedical Ethics, 4th Edition , 1995 .

[86]  John R. Anderson.  The Adaptive Character of Thought , 1990 .

[87]  Wendell Wallach.  Artificial Morality : Bounded Rationality , Bounded Morality and Emotions , 2004 .

[88]  Chris Armen,et al.  Towards Machine Ethics: Implementing Two Action-Based Ethical Theories , 2005 .

[89]  Stan Franklin,et al.  LIDA and a Theory of Mind , 2008, AGI.

[90]  Andrew H. Kemp,et al.  Pathways for fear perception: modulation of amygdala activity by thalamo-cortical systems , 2005, NeuroImage.

[91]  Brian Scassellati,et al.  Foundations for a theory of mind for a humanoid robot , 2001 .

[92]  B. Baars,et al.  The Role of Consciousness in Memory , 2005 .

[93]  H. Ford,et al.  Moving Forward , 1930 .

[94]  J. Gibson.  The Ecological Approach to Visual Perception , 1979 .

[95]  Stan Franklin,et al.  Motivations , Values and Emotions : Three Sides of the same Coin , 2006 .

[96]  Gary L. Drescher,et al.  Made-up minds - a constructivist approach to artificial intelligence , 1991 .

[97]  B. Baars,et al.  LIDA: A Working Model of Cognition , 2006 .

[98]  Michael Wooldridge,et al.  Intelligent Agents III , 1997 .

[99]  Michael Anderson,et al.  Guest Editors' Introduction: Machine Ethics , 2006, IEEE Intelligent Systems.

[100]  Stan Franklin,et al.  Cognitive robots: perceptual associative memory and learning , 2005, ROMAN 2005. IEEE International Workshop on Robot and Human Interactive Communication, 2005..

[101]  David C. Riccio,et al.  Memory Consolidation and Reconsolidation , 2012 .

[102]  Zoltán Vidnyánszky,et al.  Attentional learning: Learning to bias sensory competition , 2010 .

[103]  Sandra Clara Gadanho,et al.  Learning Behavior-Selection by Emotions and Cognition in a Multi-Goal Robot Task , 2003, J. Mach. Learn. Res..

[104]  J. Bentham.  An Introduction to the Principles of Morals and Legislation , 1945, Princeton Readings in Political Thought.

[105]  A. Glenberg,et al.  What memory is for: Creating meaning in the service of action , 1997, Behavioral and Brain Sciences.

[106]  Drew McDermott,et al.  Machine Ethics: What Matters to a Machine? , 2011 .

[107]  J. Flavell.  Metacognition and Cognitive Monitoring: A New Area of Cognitive-Developmental Inquiry. , 1979 .

[108]  Stan Franklin,et al.  THE LIDA ARCHITECTURE: ADDING NEW MODES OF LEARNING TO AN INTELLIGENT, AUTONOMOUS, SOFTWARE AGENT , 2006 .

[109]  Rosalind W. Picard.  Affective computing: (526112012-054) , 1997 .

[110]  J. D. Smith,et al.  Uncertainty Monitoring and Metacognition by Animals , 2005 .

[111]  G. Reeke.  The society of mind , 1991 .

[112]  Jeffrey M. Zacks,et al.  Event perception: a mind-brain perspective. , 2007, Psychological bulletin.

[113]  Algirdas Pakstas,et al.  Computer networks in Estonia, Latvia, and Lithuania , 1993, Computer.

[114]  Lee McCauley,et al.  IDA: a cognitive agent architecture , 1998, SMC'98 Conference Proceedings. 1998 IEEE International Conference on Systems, Man, and Cybernetics (Cat. No.98CH36218).

[115]  M. Conway.  Sensory-perceptual episodic memory and its context: autobiographical memory. , 2001, Philosophical transactions of the Royal Society of London. Series B, Biological sciences.

[116]  Stan Franklin,et al.  IDA, a Conscious Artifact? , 2006 .

[117]  Alan Baddeley,et al.  Consciousness and working memory , 1992, Consciousness and Cognition.

[118]  B. Baars,et al.  How conscious experience and working memory interact , 2003, Trends in Cognitive Sciences.

[119]  Aaron Sloman,et al.  What Sort of Architecture is Required for a Human-Like Agent? , 1999 .

[120]  Kenneth M. Ford,et al.  Android epistemology , 1995 .

[121]  Catriona M. Kennedy,et al.  Agents for Trustworthy Ethical Assistance , 2004 .

[122]  F. Salzano.  Primates and philosophers: how morality evolved , 2007 .

[123]  Andrew W. Moore,et al.  Reinforcement Learning: A Survey , 1996, J. Artif. Intell. Res..

[124]  John C. Marshall,et al.  Sight unseen? , 1992, Current Biology.

[125]  M. Sigman,et al.  Dynamics of the Central Bottleneck: Dual-Task and Task Uncertainty , 2006, PLoS biology.