Autonomous Agents and Multi-Agent Systems

, Volume 3, Issue 3, pp 219–257 | Cite as

FLAME—Fuzzy Logic Adaptive Model of Emotions

  • Magy Seif El-Nasr
  • John Yen
  • Thomas R. Ioerger

Abstract

Emotions are an important aspect of human intelligence and have been shown to play a significant role in the human decision-making process. Researchers in areas such as cognitive science, philosophy, and artificial intelligence have proposed a variety of models of emotions. Most of the previous models focus on an agent's reactive behavior, for which they often generate emotions according to static rules or pre-determined domain knowledge. However, throughout the history of research on emotions, memory and experience have been emphasized to have a major influence on the emotional process. In this paper, we propose a new computational model of emotions that can be incorporated into intelligent agents and other complex, interactive programs. The model uses a fuzzy-logic representation to map events and observations to emotional states. The model also includes several inductive learning algorithms for learning patterns of events, associations among objects, and expectations. We demonstrate empirically through a computer simulation of a pet that the adaptive components of the model are crucial to users' assessments of the believability of the agent's interactions.

emotions emotional agents social agents believable agents life-like agents 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. 1.
    J. Armony, J. Cohen, D. Servan-Schreiber, and J. LeDoux, “An anatomically constrained neural network model of fear conditioning”, Behav.Neurosci. vol. 109(2), pp. 240–257, 1995.Google Scholar
  2. 2.
    R. M. Baecker, J. Grudin, W. A. S. Buxlon, and S. Greenberg, (Eds.), Readings in Human-Computer Interaction: Toward the Year 2000, 2nd. ed. Morgan Kaufmann Publishers: San Francisco, CA, 1995.Google Scholar
  3. 3.
    J. Bates, “The role of emotion in believable agents”, Commun.ACM, vol. 37(7), pp. 122–125, 1992.Google Scholar
  4. 4.
    J. Bates, A. B. Loyall, and W. S. Reilly, “An architecture for action, emotion, and social behavior”,. School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, Technical Rep. CMU-CS-92–144, 1992.Google Scholar
  5. 5.
    J. Bates, A. B. Loyall, and W. S. Reilly, “Integrating reactivity, goals and emotion in a broad agent”,. School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, Technical Rep. CMU-CS-92–142, 1992.Google Scholar
  6. 6.
    D. R. Benyon and D. M. Murray, “Adaptive systems; from intelligent tutoring to autonomous agents”, Knowledge-based Syst. vol. 6(3), 1993.Google Scholar
  7. 7.
    B. M. Blumberg, P. M. Todd, and P. Maes, “No bad dogs: ethological lessons for learning”,. in From Animals To Animats, Proc.Fourth Inte.Conf.on the Simulation of Adaptive Behavior, 1996.Google Scholar
  8. 8.
    B. M. Blumberg, “Old tricks, new dogs: ethology and interactive creatures”, MIT Media Lab, Cambridge, MA, Ph.D. Thesis, 1996.Google Scholar
  9. 9.
    R. C. Bolles and M. S. Fanselow, “A perceptual defensive recuperative model of fear and pain”,. Behav.Brain Scie. vol. 3, pp. 291–301, 1980.Google Scholar
  10. 10.
    G. H. Bower and P. R. Cohen, “Emotional influences in memory and thinking: data and theory”,. in Affect and Cognition, M. Clark and S. Fiske, (Eds.), Lawrence Erlbaum Associated Publishers: London, 1982, pp. 291–331.Google Scholar
  11. 11.
    C. Breazeal and B. Scassellati, “Infant-like social interactions between a robot and a human caretaker”, Special Issue of Adaptive Behavior on Simulation Models of Social Agents, to appear.Google Scholar
  12. 12.
    R. Brooks, C. Breazeal, M. Marjanovic, B. Scassellati, and M. Williamson, “The cog project: building a humanoid robot”, Springer-Verlag Lecture Notes in Computer Science, to appear.Google Scholar
  13. 13.
    A. R. Damasio, Descartes' Error: Emotion, Reason, and the Human Brain, G.P. Putnam: New York, 1994.Google Scholar
  14. 14.
    K. Dautenhahn, “The art of designing socially intelligent agents: science, fiction and the human in the loop”, Appl.Artif.Intelli.j. Special Issue on Socially Intelligent Agents, vol. 12(7–8), pp. 573–619, 1998.Google Scholar
  15. 15.
    R. Descartes, The Passions of the Soul, Trans. Stephen Voss, Hackett Publishing Company: Cambridge, 1989.Google Scholar
  16. 16.
    M. Domjan, The Principles of Learning and Behavior, 4th ed., Brooks/Cole Publishing Co: Boston, 1998.Google Scholar
  17. 17.
    P. Ekman, “An argument for basic emotions”, in Cognition and Emotion, Lawrence Erlbaum Associated Publishers: London, 1992, pp. 169–200.Google Scholar
  18. 18.
    C. Elliott, “Research problems in the use of a shallow artificial intelligence model of personality and emotion”, AAAI '94, 1994.Google Scholar
  19. 19.
    C. Elliott, “The affective reasoner: a process model of emotions in a multi-agent system”, Institute for the Learning Sciences, Northwestern University, Evanston, IL, Ph.D. Thesis, 1992.Google Scholar
  20. 20.
    C. Elliott, J. Rickel, and J. Lester, “Integrating affective computing into animated tutoring agents”,. Fifteenth Int.Joint Conf.on Artificial Intelligence '97.Animated Interface Agents Workshop, 1997, pp. 113–121.Google Scholar
  21. 21.
    C. Elliott and J. Brzezinski, “Autonomous agents as synthetic characters”, AI Mag. pp. 13–30, 1998.Google Scholar
  22. 22.
    A. P. Fiske, “The four elementary forms of sociality: framework for a unified theory of social relations”, Psychol.Rev. vol. 99, pp. 689–723, 1992.Google Scholar
  23. 23.
    J. P. Forgas, “Mood and judgment: the affect infusion model (AIM)”, Psychol.Bull. vol. 117, pp. 39–66, 1995.Google Scholar
  24. 24.
    J. P. Forgas, “Sad and guilty?: affective influences on the explanation of conflict in close relationships. J.Pers.Soc.Psychol. vol. 66, pp. 56–68, 1994.Google Scholar
  25. 25.
    H. Gardner, Frames of Mind, Basic Books: New York, 1983.Google Scholar
  26. 26.
    D. Goleman, Emotional Intelligence, Bantam Books: New York, 1995.Google Scholar
  27. 27.
    M. Huhns and M. P. Singh, Eds., Reading in Agents, Morgan Kaufmann Publishers, Inc. San Francisco CA, 1998.Google Scholar
  28. 28.
    K. Inoue, K. Kawabata, and H. Kobayashi, “On a decision making system with emotion”, IEEE Int. Workshop on Robot and Human Commun. Tokyo, Japan, 1996, pp. 461–465.Google Scholar
  29. 29.
    C. E. Izard, Human Emotions, Plenum Press: New York, 1977.Google Scholar
  30. 30.
    W. James, “What is an emotion?. Mind vol. 9, pp. 188–205, 1984.Google Scholar
  31. 31.
    N. R. Jennings, K. Sycara, and M. Wooldridge, “A roadmap of agent research and development”,. Auton.Agents Multi-Agent Syst. vol. 1(1), pp. 7–38, 1998.Google Scholar
  32. 32.
    L. P. Kaelbling, M. L. Littman, and A. W. Moore, “Reinforcement learning: a survey”, J.Artif.Intell. Res. vol. 4, pp. 237–285, 1996.Google Scholar
  33. 33.
    J. Kim and J. Yun Moon, “Designing towards emotional usability in customer interfaces. trustworthiness of Cyber-banking system interfaces”, Interacting with Comput.Interdisplincary J. Human-Comput.Interaction vol. 10(1), 1998.Google Scholar
  34. 34.
    T. Koda and P. Maes, “Agents with faces: the effect of personification”, in Proc.5th Int.Workshop on Robot and Human Commun. 1996, pp. 189–194.Google Scholar
  35. 35.
    A. Konev, E. Sinisyn, and V. Kim, “Information theory of emotions in heuristic learning”, Z.Vysshei Nervnoi Deyatel'nosti imani vol. 37(5), pp. 875–879, 1987.Google Scholar
  36. 36.
    B. Kosko, Fuzzy Engineering, Prentice Hall: Upper Saddle River, NJ, 1997.Google Scholar
  37. 37.
    J. LeDoux, The Emotional Brain, Simon & Schuster: New York, 1996.Google Scholar
  38. 38.
    J. Lester, S. Converse, S. Kahler, T. Barlow, B. Stone, and R. Bhogal, “The persona effect: affective impact of animated pedagogical agents”, in Proc.CHI '97 Conference, Atlanta, GA, 1997.Google Scholar
  39. 39.
    A. B. Loyall and J. Bates, “Personality-based believable agents that use language”, in Proc.First Autonomous Agents Conf. Marina del Rey, CA, 1997.Google Scholar
  40. 40.
    P. Maes, “Agents that reduce work and information overload”, Communi.ACM vol. 37(7), pp. 37–45, 1994.Google Scholar
  41. 41.
    P. Maes, “Artificial life meets entertainment: lifelike autonomous agents”, Commun.ACM Special Issue on Novel Applications of AI vol. 38(11), pp. 108–114, 1995.Google Scholar
  42. 42.
    E. H. Mamdani and S. Assilian, “An experiment in linguistic synthesis with a fuzzy logic controller,. Int.J.Machine Stud. vol. 7(1), 1975.Google Scholar
  43. 43.
    M. A. Mark, The VCR Tutor: Design and Evaluation of an Intelligent Tutoring System, University of Saskatchewan, Saskatoon, Master's Thesis, 1991.Google Scholar
  44. 44.
    E. Masuyama, “A number of fundamental emotions and their definitions”, IEEE Inte.Workshop on Robot and Human Commun. Tokyo, Japan, 1994, pp. 156–161.Google Scholar
  45. 45.
    G. A. Miller, “The magical number seven, plus or minus two: some limits on our capacity for processing information”, Psychol.Rev. vol. 63, pp. 81–97.Google Scholar
  46. 46.
    M. Minsky, The Society of the Mind, Simon and Schuster: New York, 1986.Google Scholar
  47. 47.
    T. M. Mitchell, Machine Learning, McGraw-Hill Co.: New York, 1996.Google Scholar
  48. 48.
    H. Mizogouhi, T. Sato, and K. Takagi, “Realization of expressive mobil robot”, Proc.IEEE Int.Conf. Robotics and Automation, Albuquerque, NM, 1997, pp. 581–586.Google Scholar
  49. 49.
    H. S. Nwana, “Software agents: an overview”, Knowledge Engi.Rev. vol. 11(3), pp. 205–224, 1996.Google Scholar
  50. 50.
    J. L. Nye and A. M. Brower, What's Social About Social Cognition? Sage Publications: London, 1996.Google Scholar
  51. 51.
    A. Ohman, The Psychophysiology of Emotion; Evolutionary and Non-conscious Origins, Lawrence Erlbaum Associates, Inc.: London, 1994.Google Scholar
  52. 52.
    A. Ortony, G. Clore, and A. Collins, The Cognitive Structure of Emotions, Cambridge University Press: Cambridge, 1988.Google Scholar
  53. 53.
    R. Pfeifer, “Artificial intelligence models of emotions”, Cognitive Persp.Emotion and Motivat. 287–320, 1988.Google Scholar
  54. 54.
    R. W. Picard and J. Healy, “Affective wearables”, in Proc.of IEEE Conf.on Wearables, 1997, pp. 90–97.Google Scholar
  55. 55.
    R. W. Picard, “Affective computing”, MIT Media Lab, Cambridge, MA, Technical Rep. No. 221.Google Scholar
  56. 56.
    R. W. Picard, Affective Computing, MIT Press: Cambridge, MA, 1997.Google Scholar
  57. 57.
    D. D. Price, J. E. Barrell, and J. J. Barrell, “A quantitative-experiential analysis of human emotions”,. Motivat.Emotion vol. 9(1), 1985.Google Scholar
  58. 58.
    W. S. Reilly, “A methodology for building believable social agents”, in The First Autonomous Agent's Conf. Marina del Rey, CA, 1997.Google Scholar
  59. 59.
    W. S. Reilly, “Believable social and emotional agents”, School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, Ph.D. Thesis CMU-CS-96–138, 1996.Google Scholar
  60. 60.
    W. S. Reilly and J. Bates, “Building emotional agents”, Carnegie Mellon University, Pittsburgh, PA, Technical Rep. CMU-CS-92–143, 1992.Google Scholar
  61. 61.
    R. A. Rescorla, “Pavlovian conditioning: it's not what you think it is”, Am.Psychologist vol. 43(3), pp. 151–160, 1988.Google Scholar
  62. 62.
    R. A. Rescorla, “Associative relations in instrumental learning: the Eighteenth Bartlett Memorial Lecture”, Q.J.Exp.Psychol. vol. 43B(1), pp. 1–25, 1991.Google Scholar
  63. 63.
    W. Revelle, “Individual differences in personality and motivation: non-cognitive determinants of cognitive performance”, in Attention: Selection, Awareness and Control: A Tribute to Donald Broadbent, A. Baddeley & L. Weiskrantz (Eds.), Oxford University Press: Oxford, 1993, pp. 346–373.Google Scholar
  64. 64.
    W. Revelle, “Personality processes”, Ann.Rev.Psychol. vol. 46, pp. 295–328, 1995.Google Scholar
  65. 65.
    J. Rickel and W. L. Johnson, “Animated agents for procedural training in virtual reality: preception, cognition, and motor control”, J.Appl.Artif.Intell., to appear.Google Scholar
  66. 66.
    D. R. Riso and R. Hudson, Personality Types, Houghton Mifflin: New York, 1996.Google Scholar
  67. 67.
    I. J. Roseman, P. E. Jose, and M. S. Spindel, “Appraisals of emotion-eliciting events: testing a theory of discrete emotions”, J.Perso.Soc.Psychol. vol. 59(5), pp. 899–915, 1990.Google Scholar
  68. 68.
    D. Rousseau and B. Hayes-Roth, “Interacting with personality-rich characters, Stanford Knowledge Systems Laboratory Rep. KSL-97–06, 1997.Google Scholar
  69. 69.
    D. Rousseau, “Personality in computer characters”, in Working Notes of the AAAI-96 Workshop on AI/ALife, Menlo Park, CA: AAAI Press 1996.Google Scholar
  70. 70.
    S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, Upper Saddle River, NJ: Prentice-Hall Inc., 1995.Google Scholar
  71. 71.
    K. R. Scherer, “Studying the emotion antecedent appraisal process: an expert system approach”,. Cognition Emotion, vol. 7, pp. 325–355, 1993.Google Scholar
  72. 72.
    R. Schumacher and M. Velden, “Anxiety, pain experience and pain report: a signal-detection study”,. Perceptual Motor Skills vol. 58, pp. 339–349, 1984.Google Scholar
  73. 73.
    M. Seif El-Nasr, “Modeling emotional dynamics in intelligent agents”, Computer Science Department, Texas A&M University, Master's Thesis, 1998.Google Scholar
  74. 74.
    M. Seif El-Nasr, T. Ioerger, J. Yen, F. Parke, and D. House, “Emotionally expressive agents”, in Proc.of Computer Animation Conf.1999, Geneva, Switzerland, 1999.Google Scholar
  75. 75.
    M. Seif El-Nasr, T. Ioerger, and J. Yen, “PETEEI: A PET with evolving emotional intelligence”, in Proc.Third Int.Conf.on Autonomous Agents, Seattle, WA, 1999.Google Scholar
  76. 76.
    T. Shibata, K. Inoue, and R. Irie, “Emotional robot for intelligent system.artificial emotional creature project”, in IEEE Int.Workshop on Robot and Human Commun. Tokyo, Japan, 1996, pp. 466–471.Google Scholar
  77. 77.
    T. Shibata, K. Ohkawa, and K. Tanie, “Spontaneous behavior of robots for cooperation.emotionally intelligent robot system”, in Proc.IEEE Int.Conf.on Robotics and Automation, Japan, 1996, pp. 2426–2431.Google Scholar
  78. 78.
    T. Shiida, “An attempt to model emotions on a machine”, Emotion and Behav.Syst.Approach, vol. 2, pp. 275–287, 1989.Google Scholar
  79. 79.
    H. Simon, “Motivational and emotional controls of cognition”, Psychol.Rev. vol. 74(1), pp. 29–39, 1967.Google Scholar
  80. 80.
    H. Simon, The Science of the Artificial, MIT Press: Cambridge, MA, 1996.Google Scholar
  81. 81.
    L. Suchman, Plans and Situated Actions, Cambridge University Press: Cambridge, UK, 1981.Google Scholar
  82. 82.
    S. Sugano and T. Ogata, “Emergence of mind in robots for human interface-research methodology and robot model”, in Proc.IEEE Int.Conf.Robotics and Automation, Japan, 1996, pp. 1191–1198.Google Scholar
  83. 83.
    H. Takagi and M. Sugeno, “Fuzzy identification of systems and its application to modeling and control”, IEEE Transa.Syst.Man and Cybernet. vol. 15(1), 1985.Google Scholar
  84. 84.
    S. Tayrer (Ed.), Psychology, Psychiatry and Chronic Pain, Butterworth Heinemann: Oxford, England, 1992.Google Scholar
  85. 85.
    F. Thomas and O. Johnston, The Illusion of Life, Abbeville Press: New York, 1981.Google Scholar
  86. 86.
    J. Velasquez, “Modeling emotions and other motivations in synthetic agents”, in Proc.AAAI Conf.1997, Providence, RI, 1997, pp. 10–15.Google Scholar
  87. 87.
    J. Yen, “Fuzzy logic: a modern perspective”, IEEE Trans.Knowledge and Data Eng. vol. 11(1), pp. 153–165, 1999.Google Scholar
  88. 88.
    J. Yen and R. Langari, Fuzzy Logic: Intelligence, Control and Information, Upper Saddle River, NJ: Prentice Hall, 1999.Google Scholar
  89. 89.
    L. A. Zadeh, “Fuzzy sets”, Inf.Cont. vol. 8, 1965.Google Scholar

Copyright information

© Kluwer Academic Publishers 2000

Authors and Affiliations

  • Magy Seif El-Nasr
    • 1
  • John Yen
    • 2
  • Thomas R. Ioerger
    • 3
  1. 1.The Institute of Learning SciencesNorthwestern UniversityEvanston
  2. 2.Computer Science DepartmentTexas A&M University, College Station
  3. 3.Computer Science DepartmentTexas A&M University, College Station

Personalised recommendations