Artificial Intelligence Review

, Volume 17, Issue 1, pp 39–64 | Cite as

Modular Models of Intelligence – Review, Limitations and Prospects

  • Amitabha Mukerjee
  • Amol Dattatraya Mali


AI applications are increasingly moving to modular agents, i.e.,systems that independently handle parts of the problem based on smalllocally stored information (Grosz and Davis 1994), (Russell and Norvig 1995). Many suchagents minimize inter-agent communication by relying on changes in theenvironment as their cue for action. Some early successes of thismodel, especially in robotics (``reactive agents''), have led to adebate over this class of models as a whole. One of theissues on which attention has been drawn is that of conflicts betweensuch agents. In this work we investigate a cyclic conflict thatresults in infinite looping between agents and has a severedebilitating effect on performance. We present some new results inthe debate, and compare this problem with similar cyclicity observedin planning systems, meta-level planners, distributed agent models andhybrid reactive models. The main results of this work are:

(a) The likelihood of such cycles developing increasesas the behavior sets become more useful.(b) Control methods for avoiding cycles such asprioritization are unreliable, and(c) Behavior refinement methods that reliably avoidthese conflicts (either by refining the stimulus, or by weakeningthe action) lead to weaker functionality.

Finally, we show how attempts to introduce learning into thebehavior modules will also increase the likelihood of cycles.

behavior cyclic conflicts intelligent agents modularity reactivity 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Abonamah A. A. and Elmagarmid A. K. (1994). A survey of deadlock detection algorithms in distributed database systems. In Tyrer H. W. (ed.) Advances in distributed and parallel processing - system paradigms and methods 1, 310-341. Ablex publishing corp.Google Scholar
  2. Anderson T. L. and Donath M. (1990). Animal Behavior As A Paradigm For Developing Robot Autonomy, Robotics and Autonomous Systems 6(1,2): 145–168.Google Scholar
  3. Arkin R. C. (1992). Behavior-Based Robot Navigation for Extended Domains, Adaptive Behavior 1(2): 201–225.Google Scholar
  4. Brooks R. A. (1986). A robust layered control system for a mobile robot, IEEE journal on robotics and automation 2(1): 14–23.Google Scholar
  5. Chu-Carroll Jennifer and Carberry Sandra (1995). Communication for Conflict Resolution in Multi-Agent Collaborative Planning, Proceedings of the First Int'l Conference on Multiagent Systems (ICMAS), 49-56.Google Scholar
  6. Congdon Clare, Huber Marcus, Kortenkamp David, Konolige Kurt, Myers Karen, Saffiotti Alessandro and Ruspini Enrique H. (1993). CARMEL versus FLAKEY: A comparison of two winners, AI Magazine, Spring issue: 49-57.Google Scholar
  7. Connell J. (1990). Minimalist mobile robotics, A colony style architecture for an artificial creature, Academic press Inc.Google Scholar
  8. Corkill Daniel D. and Lesser Victor R. (1983). The use of meta-level control for coordination in a distributed problem solving network, Proc. of International Joint Conference on Artificial Intelligence (IJCAI), 748-756.Google Scholar
  9. Durfee E. H. (1992). What Your Computer Really Needs to Know You Learned in Kindergarten. In Proc. of the National Conference on Artificial Intelligence (AAAI), San Jose, CA: 858-864.Google Scholar
  10. Durfee Edmund H., Kenny Patrick G. and Kluge Karl C. (1998). Integrated Permission Planning and Execution for Unmanned Ground Vehicles, Autonomous Robots 5: 1–14.Google Scholar
  11. Foster Ian (1995). Designing and building parallel programs, Addison-Wesley.Google Scholar
  12. Gat E. (1993). On the Role of Stored Internal State in the Control of Autonomous Mobile Robots, AI Magazine 14(1): 64–73.Google Scholar
  13. Georgeff M. P. and Lansky A. L. (1990). Reactive Reasoning and Planning. In James Allen, James Hendler and Austin Tate (eds.) Readings In Planning, 729-734. Morgan Kaufmann Publishers, Inc.Google Scholar
  14. Grosz Barbara J. and Davis Randall (1994). AAAI Report to ARPA on 21st century intelligent systems, AI Magazine Fall issue: 10-20.Google Scholar
  15. Hammond Kristian J. and Converse Timothy M. (1991). Stabilizing environments to facilitate planning and activity: An engineering argument, Proceedings of the National Conference on Artificial Intelligence (AAAI) 2.Google Scholar
  16. Hartley R. and Pipitone F. (1991). Experiments with the subsumption architecture, In Proceedings of the IEEE Conference on Robotics and Automation (ICRA), 1652-1658.Google Scholar
  17. Hickman Stephen and Shiels Martin (1991). Situated action as a basis for cooperation. In Yves Demazeau and Jean-Pierre Muller (eds.) Decentralized AI 2, 35-47. Elsevier Science Publishers B. V.Google Scholar
  18. Jennings N. R. (1995). Controlling cooperative problem solving in industrial multi-agent systems using joint intentions, Artificial Intelligence 75: 195–240.Google Scholar
  19. Kirsh, D. (1991). Today the earwig, tomorrow man?, Artificial Intelligence 47(1-3): 161–184.Google Scholar
  20. Konolige Kurt (1994). Designing the 1993 robot competition, AI Magazine Spring issue: 57-62.Google Scholar
  21. Kortenkamp David, Huber Marcus, Choen Charles, Raschke Ulrich, Bidlack Clint, Congdon Clare Bates, Koss Frank and Weymouth Terry (1993). Integrated mobile robot design: Winning the AAAI'92 robot competition, IEEE Expert, August issue: 61-73.Google Scholar
  22. Kube C. Ronald and Zhang Hong (1997). Task modeling in collective robotics, Autonomous Robots 4, 53–72.Google Scholar
  23. Laird John and Rosenbloom Paul (1990). Integrating execution, planning and learning in Soar for external environments, Proceedings of the National Conference on Artificial Intelligence (AAAI), 1022-1029.Google Scholar
  24. Lenat D. B., Guha R. V., Pittman K., Pratt D. and Shepherd M. (1990). CYC: towards programs with common sense, Communications of the ACM, August issue 33(8): 30–49Google Scholar
  25. Mahadevan S. and Connell J. (1992). Automatic programming of behavior-based robots using reinforcement learning, Artificial Intelligence 55, 311–365.Google Scholar
  26. Masthoff J. and Hoe Van R. (1995). A View on the Architecture and Design of Highly Autonomous and Situated Agents, Proceedings of the First International Conference on Multiagent Systems (ICMAS) Victor Lesser: 458 (Poster).Google Scholar
  27. Mataric Maja J. (1997). Using communication to reduce locality in multi-robot learning, Proceedings of the National Conference on Artificial Intelligence (AAAI): 643-648.Google Scholar
  28. Mitchell Tom (1990). Becoming increasingly reactive, Proceedings of the National Conference on Artificial Intelligence (AAAI), 1051-1058.Google Scholar
  29. Moravec H. P. (1984). Locomotion, Vision, and Intelligence, Proceedings of the First International Symposium on Robotics Research, Bretton Woods, NH, edited by Michael Brady and Richard Paul, MIT Press, Cambridge, MA, 215–224.Google Scholar
  30. Muscettola Nicola, Nayak Pandurang P., Pell Barney and Williams Brian C. (1998). Remote agent: To boldly go where no AI system has gone before, Artificial Intelligence 103(1-2): 5–47.Google Scholar
  31. Nicolescu Monica N. and Mataric Maja (2000). Deriving and using abstract representation in behavior-based system, Proceedings of the National Conference on Artificial Intelligence (AAAI) Student abstract: 1087.Google Scholar
  32. Parker Lynne E. (1996). On the design of behavior-based multi-robot teams, Advanced Robotics 10(6): 547–578.Google Scholar
  33. Payton, D. W., Rosenblatt J. K. and Keirsey D. M. (1990). Plan guided reaction, IEEE Transactions on Systems, Man and Cybernetics 20(6): 1370–1382.Google Scholar
  34. Reiter R. (1991). The frame problem in the situation calculus: A simple solution (sometimes) and a completeness result for goal regression. In Lifschitz V. (ed.) Artificial Intelligence and Mathematical Theory of Computation: Papers in Honor of John McCarthy 359–380. Academic Press, NY.Google Scholar
  35. Rish Irina and Dechter Rina (1996). To guess or to think? Hybrid algorithms for SAT, Proceedings of the Principles and Practices of Constraint Programming (PPCP).Google Scholar
  36. Hayes-Roth Frederick (1996). AI:What works and what doesn't? Invited talk at the Innovative Applications of Artificial Intelligence conference (IAAI), Portland.Google Scholar
  37. Russell Stuart and Norvig Peter (1995). Artificial Intelligence: A Modern Approach, Prentice-Hall, NJ.Google Scholar
  38. Samadi Behrokh and Muntz Richard (1988). A distributed algorithm to detect a global state of a distributed simulation system, In Barton M. H., Dagless E. L. and Reijns G. L. (eds.) Distributed processing, 19-34. North-Holland.Google Scholar
  39. Schaerf Andrea (1997). Combining local search and look-ahead for scheduling and constraint satisfaction problems, Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 1254-1259.Google Scholar
  40. Simmons Reid (1994). Structured control for autonomous robots, IEEE Transactions Robotics and Automation February issue.Google Scholar
  41. Simmons Reid, Apfelbaum David, Burgard Wolfram, Fox Dieter, Moors Mark, Thrun Sebastian and Younes Hakan, (2000). Coordination for multi-robot exploration and mapping, Proceedings of the National Conference on Artificial Intelligence (AAAI), 852-858.Google Scholar
  42. Stone Peter, Riley Patrick and Veloso Manuela (2000). Defining and using ideal template and opponent agent models, Proceedings of the National Conference on Artificial Intelligence (AAAI), 1040-1045.Google Scholar
  43. Tambe Milind (2000). Agent assistants for team analysis, AI Magazine Fall issue: 27-31.Google Scholar
  44. Vera A. H. and Simon Herbert A. (1993). Situated Action: A Symbolic Interpretation, Cognitive Science 17: 7–48.Google Scholar
  45. Wellman Michael P. (1992). A general-equillibrium approach to distributed transportation planning, Proceedings of the National Conference on Artificial Intelligence (AAAI), 282-289.Google Scholar
  46. Winner Elly and Veloso Manuela (2000). Multi-fidelity robotic behaviors: Acting with variable state information, Proceedings of the National Conference on Artificial Intelligence (AAAI), 872-877.Google Scholar
  47. Wooldridge Michael and Jennings Nick (1995). Agent Theories, Architectures, and Languages: A Survey, In Michael Wooldridge and Nicholas R. Jennings (ed.) Intelligent Agents - Theories, Architectures, and Languages, 1-32. Springer-Verlag Lecture Notes in Artificial Intelligence January issue.Google Scholar
  48. Yiu Leo and Shyamsundar R. K. (1990). Static analysis of deadlock, distributed termination and timing properties in real-time distributed systems, In Cosnard M. and Girault C. (eds.) Decentralized systems 411-425. Elsevier science publishers B. V. (North-Holland).Google Scholar

Copyright information

© Kluwer Academic Publishers 2002

Authors and Affiliations

  • Amitabha Mukerjee
  • Amol Dattatraya Mali

There are no affiliations available

Personalised recommendations