Minds and Machines

, Volume 17, Issue 1, pp 11–25 | Cite as

Integrated A.I. systems

  • Kristinn R. ThórissonEmail author
Original Paper


The broad range of capabilities exhibited by humans and animals is achieved through a large set of heterogeneous, tightly integrated cognitive mechanisms. To move artificial systems closer to such general-purpose intelligence we cannot avoid replicating some subset—quite possibly a substantial portion—of this large set. Progress in this direction requires that systems integration be taken more seriously as a fundamental research problem. In this paper I make the argument that intelligence must be studied holistically. I present key issues that must be addressed in the area of integration and propose solutions for speeding up rate of progress towards more powerful, integrated A.I. systems, including (a) tools for building large, complex architectures, (b) a design methodology for building realtime A.I. systems and (c) methods for facilitating code sharing at the community level.


Integration Holistic artificial intelligence Large-scale architectures Scientific progress 



I would like to thank my collaborators Thor List, John DiPirro, Chris Pennock and the many others who have worked with me on the projects described (too numerous to list—you know who you are!). Thanks to the pioneers who have already joined the Mindmakers effort. Thanks to Hrafn Th. Thórisson, Hannes Högni Vilhjálmsson and Bjorn Thor Jonsson for excellent comments on this paper. Psyclone is a trademark of Communicative Machines Inc. This work was supported in part by a Rannis grant and a Marie Curie European Reintegration Grant within the 6th European Community Framework Programme.


  1. Adler, R. (1992). Blackboard systems. In S. C. Shapiro (Ed.), The encyclopedia of artificial intelligence (pp. 110–116). New York, NY: Wiley Interscience.Google Scholar
  2. Albus, J. S. (1996). The engineering of mind. Proceedings of the fourth international conference on simulation of adaptive behavior: From animals to animats 4, Cape Code, MA, September.Google Scholar
  3. Arbib, M. A. (1992). Schema theory. In S. C. Shapiro (Ed.), Encyclopedia of artificial intelligence (pp. 1427–1443). New York: Wiley.Google Scholar
  4. Bischoff, R. (2000). Towards the development of ‘plug-and-play’ personal robots. 1st IEEE-RAS international conference on humanoid robots. Cambridge: MIT September 7–8.Google Scholar
  5. Buhmann, J., Burgard, W., Cremers, A. B., Fox, D., Hofmann, T., Schneider, F., Strikos, J., & Thrun, S. (1995). The mobile robot Rhino. A.I. Magazine, 16(1), 31–38.Google Scholar
  6. Brachman, R. (2005). (AA)AI: More than the sum of its parts. Presidential Address, AAAI ‘05, Pittsburgh, PA, July 9–14.Google Scholar
  7. Brooks, R. A. (1989). How to build complete creatures rather than isolated cognitive simulators. In K. Van Lehn (Ed.), Architectures for intelligence (pp. 225–239). Hillsdale, NJ: Erlbaum.Google Scholar
  8. Brooks, R. A. (1986). Robust layered control system for a mobile robot. IEEE Journal of Robotics and Automation, 2(1), 14–23. Also MIT A.I. Memo 864, September 1985.Google Scholar
  9. Bryson, J. J. (2003). The behavior-oriented design of modular agent intelligence. In Lecture notes in computer science, 2592, pp. 61–76. New York: Springer Verlag.Google Scholar
  10. Bryson, J. (2000). Making modularity work: Combining memory systems and intelligent processes in a dialog agent. In Sloman, A. (Ed.), AISB’00 Symposium on Designing a Functioning Mind, pp. 21–30.Google Scholar
  11. Bryson, J. J., & Stein, L. A. (2001). Modularity and specialized learning: mapping between agent architectures and brain organization. In S. Wermter, J. Austin, & D. Willshaw (Eds.), Emergent neural computational architectures based on neuroscience (pp. 98–113). New York: Springer Verlag.Google Scholar
  12. Campbell, G. G., Lunney, T., Mc Caughey, A., & Mc Kevitt, P. (2006). A new approach to decision-making within an intelligent multimedia distributed platform hub. Proc. of the 17th Irish conference on Artificial Intelligence and Cognitive Science (AICS 2006), QUB, Belfast, N. Ireland, September 11–13.Google Scholar
  13. Finin, T., Labrou, Y., & Mayfield, J. (1995). KQML as an agent communication language. In Jeff Bradshaw (Ed.), Software agents. Cambridge: MIT Press.Google Scholar
  14. Fink, G. A., Jungclaus, N., Kummer, F., Ritter H., & Sagerer, G. (1996). A distributed system for integrated speech and image understanding. International symposium on artificial intelligence (pp. 117–126). Cancun, Mexico.Google Scholar
  15. Fink, G. A., Jungclaus, N., Ritter, H., & Saegerer, G. (1995). A communication framework for heterogeneous distributed pattern analysis. International conference on algorithms and architectures for parallel processing, 881–890, Brisbane, Australia.Google Scholar
  16. Gratch, J., Rickel, J., André, E., Cassell, J., Petajan, E., & Badler, N. I. (2002). Creating interactive virtual humans: Some assembly required. IEEE Intelligent Systems, July-August, 17(4), 54–63.CrossRefGoogle Scholar
  17. Gupta, R., & Hennacy, K. (2005). Commonsense reasoning about task instructions. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), AAAI-05 Workshop on modular construction of human-like intelligence. Pittsburgh, PA, July 10. AAAI Technical Report WS-05–08, 86–91.Google Scholar
  18. Hackett, T. A., & Kaas, J. H., (2004). Auditory cortex in primates: Functional subdivisions, processing streams. In M. S. Gazzaniga (Ed.), The cognitive neurosciences III (3rd ed., pp. 215–232). Cambridge, MA: MIT Press.Google Scholar
  19. Hsiao, K., Gorniak, P., & Roy, D. (2005). NetP: A network api for building heterogeneous modular intelligent systems. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), Proceedings of AAAI 2005 workshop on modular construction of human-like intelligence. AAAI Technical Report WS-05–08, 24–31.Google Scholar
  20. Horton, J. C., & Sincich, L. C. (2004). A new foundation for the visual cortical hierarchy. In M. S. Gazzaniga (Eds.), The cognitive neurosciences III (3rd ed., pp. 233–243). Cambridge, MA: MIT Press.Google Scholar
  21. Johnson, W. L., Marsella, S., Mote, N., Si, M., Vilhjálmsson, H., & Wu, S. (2004). Balanced perception and action in the tactical language training system. workshop on embodied conversational agents: balanced perception & action, July 20th, 18–25. AAMAS 2004: The third international joint conference on autonomous agents & multi agent systems, New York, July 19–23.Google Scholar
  22. List, T., Bins, J., Fisher, R. B., Tweed, D., & Thórisson, K. R. (2005). Two approaches to a plug-and-play vision architecture, CAVIAR & psyclone. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), AAAI-05 Workshop on modular construction of human-like intelligence, Pittsburgh, PA, July 10. AAAI Technical Report WS-05-08, pp. 16–23.Google Scholar
  23. MacMahon, M. (2005). Representing language, action, perception, and space to follow route instructions. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), AAAI-05 Workshop on modular construction of human-like intelligence, Pittsburgh, PA, July 10. AAAI Technical Report WS-05-08, 48–55.Google Scholar
  24. Martin, D., Cheyer, A., & Moran, D. (1999). The open agent architecture: A framework for building distributed software systems. Applied Artificial Intelligence, 13(1–2), 91–128.CrossRefGoogle Scholar
  25. Martinho, C., Paiva, A., & Gomes, M. R. (2000). Emotions for a motion: Rapid development of believable pathematic agents in intelligent virtual environments. Applied Artificial Intelligence, 14(1), 33–68.CrossRefGoogle Scholar
  26. Mavridis, N., & Roy, D. (2005). Grounded situation models for robots: Bridging language, perception, and action. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), AAAI-05 Workshop on modular construction of human-like intelligence, Pittsburgh, PA, July 10. AAAI Technical Report WS-05–08, 32–39.Google Scholar
  27. Maxwell, B. A., Meeden, L. A., Addo, N. S., Dickson, P., Fairfield, N., Johnson, N., Jones, E. G., Kim, S., Malla, P., Murphy, M., Rutter, B., & Silk, E. (2001). REAPER: A relfexive architecture for perceptive agents. A.I. Magazine, spring, 53–66.Google Scholar
  28. McGuire, P., Fristch, J., Steil, J. J., Röthling, F., Fink, F. A., Wachsmuth, S., Sagerer, G., & Ritter, H. (2002). Multi-modal human-machine communicating for instructing robot grasping tasks. Proc. IROS, 1082–1089.Google Scholar
  29. Minsky, M. (1986). The society of mind. New York, NY: Simon & Schuster.Google Scholar
  30. Minsky, M., Singh, P., & Sloman, A. (2004). The St. Thomas common sense symposium: Designing architectures for human-level intelligence. A.I. Magazine, 25(2), 113–124. AAAI. Menlo Park, CA: AAAI Press.Google Scholar
  31. Minsky, M. (2003). Why A.I. is brain-dead. Wired, issue 11.08, August.Google Scholar
  32. Minsky, M. (1974). A framework for representing knowledge. MIT-AI Laboratory Memo 306, June. Reprinted in P. Winston (Ed.), The psychology of computer vision, McGraw-Hill, 1975. Shorter version in J. Haugeland, (Ed.), Mind Design, MIT Press, 1981.Google Scholar
  33. Moravec, H. (1998). When will computer hardware match the human brain? Journal of Evolution and Technology, 1. Scholar
  34. Newell, A. (1990). Unified theories of cognition. Cambridge, MA: Harvard University Press.Google Scholar
  35. Pagello, E., Mengegatti, E., Bredenfel, A., Costa, P., Christaller, T., Jacoff, A., Polani, D., Riedmiller, M., Saffiotti, A., Sklar, E., & Tomoichi, T. (2004). RoboCup-2003: New scientific and technical advances. A.I. Magazine, 25(2), 81–98. AAAI. Menlo Park, CA: AAAI Press.Google Scholar
  36. Pakkenberg, B., & Gundersen, H. J. G. (1997). Neocortical neuron number in humans: Effect of sex and age. Journal of Comparitive Neurology, 384, 312–320.CrossRefGoogle Scholar
  37. Rakic, P., Ang, E. S. B. C., & Breunig, J. (2004). Setting the stage for cognition: genesis of the primate cortex. In M. S. Gazzaniga (Ed.), The cognitive neurosciences III. (3rd ed., pp. 33–49). Cambridge, MA: MIT Press.Google Scholar
  38. Roy, D. (2005). Semiotic schemas: A framework for grounding language in action and perception. Artificial Intelligence, 167(1–2), 170–205.CrossRefGoogle Scholar
  39. Samuel, J. P., & Bryson, J. J. (2005). The behavior oriented design of an unreal tournament character. The fifth international working conference on intelligent virtual agents, 466–477.Google Scholar
  40. Saemundsson, R. J., Thórisson, K. R., Jónsdóttir, G. R., Arinbjarnar, M., Finnsson, H., Gudnason, H., Hafsteinsson, V., Hannesson, G., Ísleifsdóttir, J., Jóhannsson, Á. Th., Kristjánsson, G., & Sigmundarson, S. (2006). Modular Simulation of knowledge development in industry: A mutli-level approach. WEHIA—1st international conference on economic sciences with heterogeneous interacting agents, 15–17 June, University of Bologna, Italy.Google Scholar
  41. Simmons, R., Goldberg, D., Goode, A., Montemerlo, M., Roy, N., Sellner, B., Urmson, C., Schultz, A., Abramson, M., Adams, W., Atrash, A., Bugajska, M., Coblenz, M., MacMahon, M., Perzanowski, D., Horswill, I., Zubek, R., Kortenkamp, D., Wolfe, B., Milam, T., & Maxwell, B. (2003). GRACE: An Autonomous robot for the AAAI robot challenge. A.I. Magazine, 24(2), 51–72.Google Scholar
  42. Sloman, A. (1997). What sort of architecture is required for a human-like agent? In M. Wooldridge, & A. Rao (Eds.), Foundations of rational agency, New York: Kluwer Academic Publishers.Google Scholar
  43. Sun Microsystems (2002). Enterprise JavaBeans Specification V2.1. Palo Alto: Sun Microsystems.Google Scholar
  44. Swartout, W., Gratch, J., Hill, R. W., Hovy, E., Marsella, S., Rickel, J., & Traum, D. (2006). Towards virtual humans. A.I. Magazine, 27(2), 96–108.Google Scholar
  45. Tanguy, E., Bryson, J. J., & Willis, P. (2005). A dynamic emotion representation model within a facial animation system. Technical Report CSBU-2005–14, Department of Computer Science; University of Bath; Bath BA2 7AY, England. To appear in The International Journal of Humanoid Robotics, 2006.Google Scholar
  46. Tanenbaum, A. S., & van Steen, M. (2002). Distributed systems: Principles and paradigms. New York: Prentice-Hall.Google Scholar
  47. Thórisson, K. R. (1999). A mind model for multimodal communicative creatures and humanoids. International Journal of Applied Artificial Intelligence, 13(4–5), 449–486.CrossRefGoogle Scholar
  48. Thórisson, K. R., List, T., Pennock, C., & DiPirro, J. (2005). Whiteboards: scheduling blackboards for semantic routing of messages & streams. In K. R. Thórisson, H. Vilhjalmsson, & S. Marsela (Eds.), AAAI-05 Workshop on modular construction of human-like intelligence, Pittsburgh, PA, July 10. AAAI Technical Report WS-05-08, 8–15.Google Scholar
  49. Thórisson, K. R., List, T., Pennock, C., DiPirro, J., & Magnusson, F. (2005). Scheduling blackboards for interactive robots. Reykjavik University Department of Computer Science Technical Report RUTR-CS05002.Google Scholar
  50. Thórisson, K. R., Benko, H., Arnold, A., Abramov, D., Maskey, S. & Vaseekaran, A. (2004). A constructionist methodology for interactive intelligences. A.I. Magazine, 25(4), 70–90.Google Scholar
  51. Thrun, S. (1998). When robots meet people: Research directions in mobile robotics. IEEE Intelligent Systems, May/June.Google Scholar

Copyright information

© Springer Science+Business Media 2007

Authors and Affiliations

  1. 1.Center for Analysis & Design of Intelligent Agents, Department of Computer ScienceReykjavik UniversityReykjavikIceland

Personalised recommendations