Advertisement

Abstract

The grounding problem is, generally speaking, the problem of how to embed an artificial agent into its environment such that its behaviour, as well as the mechanisms, representations, etc. underlying it, can be intrinsic and meaningful to the agent itself, rather than dependent on an external designer or observer. This paper briefly reviews Searle’s and Harnad’s analyses of the grounding problem, and then evaluates cognitivist and enactive approaches to overcoming it. It is argued that, although these two categories of approaches differ in their nature and the problems they have to face, both, so far, fall short of solving the grounding problem for similar reasons. Further it is concluded that the reason the problem is still somewhat underestimated lies in the fact that modern situated and embodied AI, despite its emphasis of agent-environment interaction, still fails to fully acknowledge the historically rooted integrated nature of living organisms and their environmental embedding.

Keywords

Artificial Agent Agent Function Intelligent Behaviour Cognitive Science Society Evolutionary Robotic 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

References

  1. Agre, P. E. & Chapman (1987) Pengi: An Implementation of a Theory of Activity. Proceedings of AAAI-87. Menlo Park, CA: AAAI, pp. 268–272.Google Scholar
  2. Beer, R. D. (1995) A dynamical systems perspective on agent-environment interaction. Artificial Intelligence 72: 173–215.CrossRefGoogle Scholar
  3. Beer, R. A. (1996) Toward the Evolution of Dynamical Neural Networks for Minimally Cognitive Behaviour. In: Maes, P., Mataric, M., Meyer, J. A., Pollack J. & Wilson, S. (eds.) From Animals to Animals 4. Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 421–429.Google Scholar
  4. Bickhard, M. & Terveen, L. (1995) Foundational Issues in Artificial Intelligence and Cognitive Science. Impasse and Solution. New York: Elsevier.Google Scholar
  5. Biro, Z. & Ziemke, T. (1998) Evolution of visually-guided approach behaviour in recurrent artificial neural network robot controllers. In: Pfeifer, R., Blumberg, B. Meyer, J.-A. & Wilson, S. W (eds.) From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 73–76.Google Scholar
  6. Brooks, R. A. (1986) A Robust Layered Control System for a Mobile Robot. IEEE Journal of Robotics and Automation 2: 14–23.Google Scholar
  7. Brooks, R. A. (1989) A Robot that Walks: Emergent Behavior from a Carefully Evolved Network. Neural Computation 1(2): 253–262.Google Scholar
  8. Brooks, R. A. (1990) Elephants Don’t Play Chess. Robotics and Autonomous Systems 6(1–2): 1–16.Google Scholar
  9. Brooks, R. A. (1991a) Intelligence Without Representation. Artificial Intelligence 47: 139–160.CrossRefGoogle Scholar
  10. Brooks, R. A. (1991b) Intelligence Without Reason. Proceedings of the Twelfth International Joint Conference on Artificial Intelligence (IJCAI-91). San Mateo, CA: Morgan Kauffmann, pp. 569–595.Google Scholar
  11. Brooks, R. A. (1993) The Engineering of Physical Grounding. Proceedings of the Fifteenth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum, pp. 153–154.Google Scholar
  12. Chalmers, D. J. (1992) Subsymbolic computation and the Chinese room. In: Dinsmore, J. (ed.) The Symbolic and Connectionist Paradigms: Closing the Gap. Hillsdale, NJ: Lawrence Erlbaum.Google Scholar
  13. Chiel, H. J. & Beer, R. A. (1997) The brain has a body: Adaptive Behavior emerges from interactions of nervous system, body, and environment. Trends in Neurosciences 20:553–557.PubMedCrossRefGoogle Scholar
  14. Clark, A. (1997) Being There. Putting Brain, Body and World Together Again. Cambridge, MA: MIT Press.Google Scholar
  15. Clark, A. & Wheeler, M. (1998) Bringing Representation Back to Life. In: Pfeifer, R., Blumberg, B. Meyer, J.-A. & Wilson, S. W (eds.) From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 3–12.Google Scholar
  16. Cliff, D. & Miller, G. F. (1996) Co-evolution of Pursuit and Evasion II: Simulation Methods and Results. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack J. & Wilson, S. (eds.) From Animals to Animats 4. Proceedings of the Fourth International. Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 506–515.Google Scholar
  17. Cottrell, G. W., Bartell, B. & Haupt, C. (1990) Grounding Meaning in Perception. Proceedings of the German Workshop on Artificial Intelligence (GWAI), pp. 307–321.Google Scholar
  18. Dorffner, G. & Prem, E. (1993) Connectionism, Symbol Grounding, and Autonomous Agents. Proceedings of the Fifteenth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum, pp. 144–148.Google Scholar
  19. Floreano, D. (1997) Reducing Human Design and Increasing Adaptability in Evolutionary Robotics. In: Gomi, T. (ed.) Evolutionary Robotics. From Intelligent Robots to Artificial Life. Kanata, Canada: AAI Books.Google Scholar
  20. Fodor, J. A. (1980) Methodological solipsism considered as a research strategy in cognitive science. Behavioral and Brain Sciences 3: 63–110.CrossRefGoogle Scholar
  21. Fodor, J. A. (1981) Representations: philosophical essays on the foundations of cognitive science. Cambridge, MA: MIT Press.Google Scholar
  22. Fodor, J. A. (1983) The Modularity of Mind. Cambridge, MA: MIT Press.Google Scholar
  23. Fodor, J. A. & Pylyshyn, Z. (1988) Connectionism and cognitive architecture: A critical analysis. Cognition 28:3–71.PubMedCrossRefGoogle Scholar
  24. Funes, P. & Pollack, J. B. (1997) Computer evolution of buildable objects. In: Husbands, P. & Harvey, I. (eds.) Proceedings of the Fourth European Conference on Artificial Life. Cambridge, MA: MIT Press, pp. 358–367.Google Scholar
  25. Globus, G. G. (1992) Toward a Noncomputational Cognitive Neuroscience. Journal of Cognitive Neuroscience 4(4):299–310.CrossRefGoogle Scholar
  26. Gruau, F. (1995) Automatic definition of modular neural networks. Adaptive Behavior 2: 151–183.Google Scholar
  27. Harnad, S. (1989) Minds, machines and Searle. Journal of Experimental and Theoretical Artificial Intelligence 1: 5–25.CrossRefGoogle Scholar
  28. Harnad, S. (1990) The Symbol Grounding Problem. Physica D 42: 335–346.CrossRefGoogle Scholar
  29. Harnad, S. (1993) Symbol Grounding is an Empirical Problem: Neural Nets are Just a Candidate Component. Proceedings of the Fifteenth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum, pp. 169–174.Google Scholar
  30. Harnad, S. (1995) Grounding Symbolic Capacity in Robotic Capacity. In: Steels, L. & Brooks, R. A. (eds.) The “artificial life” route to “artificial intelligence”. Building Situated Embodied Agents. New Haven: Lawrence Erlbaum, pp. 276–286.Google Scholar
  31. Lakoff, G. (1993) Grounded Concepts Without Symbols. Proceedings of the Fifteenth Annual Meeting of the Cognitive Science Society. Hillsdale, NJ: Lawrence Erlbaum, pp. 161–164.Google Scholar
  32. Law, D. and Miikkulainen, R. (1994) Grounding Robotic Control with Genetic Neural Networks. Tech. Rep. AI94-223. Austin: Dept. of Computer Sciences, The University of Texas at Austin.Google Scholar
  33. Loeb, J. (1918) Forced movements, tropisms, and animal conduct. Philadelphia: Lippincott Company.Google Scholar
  34. Lund, H. H.; Hallam, J. & Lee, W. (1997) Evolving robot morphology. Proceedings of the IEEE Fourth International Conference on Evolutionary Computation. IEEE Press.Google Scholar
  35. Maturana, H. and Varela, F. (1987) The Tree of Knowledge: The Biological Roots of Human Understanding. Boston, MA: Shambhala.Google Scholar
  36. Mondada, F. & Floreano, D. (1995) Evolution of neural control structures: Some experiments on mobile robots. Robotics and Autonomous Systems 16(2–4):183–196.CrossRefGoogle Scholar
  37. Newell, A. (1980) Physical Symbol Systems. Cognitive Science A: 135-183.Google Scholar
  38. Newell, A. & Simon, H. (1976) Computer science as empirical inquiry: Symbols and search. Communications of the ACM 19: 113–126.CrossRefGoogle Scholar
  39. Nolfi, S. (1997a) Using emergent modularity to develop control systems for mobile robots. Adaptive Behavior 5(3): 343–363.CrossRefGoogle Scholar
  40. Nolfi, S. (1997b) Evolving Non-Trivial Behavior on Autonomous Robots: Adaptation is More Powerful Than Decomposition and Integration. In: Gomi, T. (ed.) Evolutionary Robotics. From Intelligent Robots to Artificial Life. Kanata, Canada: AAI Books.Google Scholar
  41. Peschl, M. F. (1996) The Representational Relation Between Environmental Structures and Neural Systems: Autonomy and Environmental Dependency in Neural Knowledge Representation. Nonlinear Dynamics, Psychology and Life Sciences 1 (3).Google Scholar
  42. Pfeifer, R. (1995) Cognition. Perspectives from autonomous agents. Robotics and Autonomous Systems 15: 47–70.CrossRefGoogle Scholar
  43. Pfeifer, R. & Scheier, C. (1998) Understanding Intelligence. Cambridge, MA: MIT Press.Google Scholar
  44. Port, R. & van Gelder, T. (1995) Mind as Motion: Explorations in the Dynamics of Cognition. Cambridge, MA: MIT Press.Google Scholar
  45. Regier, T. (1992) The Acquisition of Lexical Semantics for Spatial Terms: A Connectionist Model of Perceptual Categorization. PhD Thesis / Tech. Rep. TR-92-062. Berkeley: Dept. of Computer Science, University of California at Berkeley.Google Scholar
  46. Roeder, K. & Treat, A. (1957) Ultrasonic reception by the tympanic organs of noctoid moths. Journal of Experimental Zoology 134:127–158.PubMedCrossRefGoogle Scholar
  47. Rutkowska, J. C. (1996) Reassessing Piaget’s Theory of Sensorimotor Intelligence: A View from Cognitive Science. In: Bremner, J. G. (ed.) Infant Development: Recent Advances. Hillsdale, NJ: Lawrence Erlbaum.Google Scholar
  48. Rylatt, M. & Czarnecki, C. (1998) Beyond Physical Grounding and Naive Time: Investigations into Short-Term Memory. In: Pfeifer, R., Blumberg, B., Meyer, J.-A. & Wilson, S. W (eds.) From Animals to Animats 5. Proceedings of the Fifth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 22–31.Google Scholar
  49. Schank, R. C. & Abelson, R. P. (1977) Scripts, Plans, Goals, and Understanding. Lawrence Erlbaum.Google Scholar
  50. Searle, J. (1980) Minds, brains and programs. Behavioral and Brain Sciences 3: 417–457.Google Scholar
  51. Sharkey, N. E. (1997) Neural networks for coordination and control: The portability of experiential representations. Robotics and Autonomous Systems 22(3–4): 345–359.CrossRefGoogle Scholar
  52. Sharkey, N. E. & Heemskerk, J. H. (1997) The Neural Mind and the Robot. In: Browne, A. J. (Ed.) Neural Perspectives on Cognition and Adaptive Robotics. Bristol, UK: IOP Press.Google Scholar
  53. Sharkey, N. E. & Jackson, S. A. (1994) Three Horns of the Representational Trilemma. In: Honavar, V. & Uhr, L. (eds.) Symbol Processing and Connectionist Models for Artificial Intelligence and Cognitive Modeling: Steps towards Integration. Academic Press, pp. 155–189.Google Scholar
  54. Sharkey, N. E. & Jackson, S. A. (1996) Grounding Computational Engines. Artificial Intelligence Review 10:65–82.CrossRefGoogle Scholar
  55. Sharkey, N. E. & Ziemke, T. (1998) A consideration of the biological and psychological foundations of autonomous robotics. Connection Science 10(3–4): 361–391.CrossRefGoogle Scholar
  56. Sherrington, C. S. (1906) The integrative action of the nervous system. New York: C. Scribner’s Sons.Google Scholar
  57. Tani, J. (1996) Does Dynamics Solve the Symbol Grounding Problem of Robots? An Experiment in Navigation Learning. Learning in Robots and Animals. Working Notes. AISB’96 workshop, Brighton, UK.Google Scholar
  58. van Gelder, T.J. (1995) What might cognition be if not computation? Journal of Philosophy 91: 345–381.CrossRefGoogle Scholar
  59. van Gelder, T.J. (1998) The Dynamical Hypothesis in Cognitive Science. Behavioral and Brain Sciences.Google Scholar
  60. Varela, E, Thompson, E. & Rosch, E. (1991) The Embodied Mind. Cognitive Science and Human Experience. Cambridge, MA: MIT Press.Google Scholar
  61. von Uexküll, J. (1928) Theoretische Biologie. Frankfurt/Main, Germany: Suhrkamp Verlag.Google Scholar
  62. Wilson, S. W. (1991) The Animat Path to AI. From Animals to Animats: Proceedings of the First International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press.Google Scholar
  63. Ziemke, T. (1996a) Towards Adaptive Behaviour System Integration using Connectionist Infinite State Automata. In: Maes, P., Mataric, M., Meyer, J.-A., Pollack J. & Wilson, S. (eds.) From Animals to Animats 4. Proceedings of the Fourth International Conference on Simulation of Adaptive Behavior. Cambridge, MA: MIT Press, pp. 145–154.Google Scholar
  64. Ziemke, T. (1996b) Towards Autonomous Robot Control via Self-Adapting Recurrent Networks. Artificial Neural Networks ICANN 96. Berlin/Heidelberg, Germany: Springer Verlag, pp. 611–616.Google Scholar
  65. Ziemke, T. (1996c) Towards Adaptive Perception in Autonomous Robots using Second-Order Recurrent Networks. Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT’ 96). Los Alamitos, CA: IEEE Computer Society Press, pp. 89–98.CrossRefGoogle Scholar
  66. Ziemke, T. (1997) The ‘Environmental Puppeteer’ Revisited: A Connectionist Perspective on ‘Autonomy’. Proceedings of the 6th European Workshop on Learning Robots (EWLR-6). Brighton, UK, August 1997.Google Scholar
  67. Ziemke, T. (1998) Adaptive Behavior in Autonomous Agents. Presence 7(6):564–587.CrossRefGoogle Scholar
  68. Ziemke, T. & Sharkey, N. E. (eds.) (1998) Biorobotics. Special issue of Connection Science 10(3–4).Google Scholar

Copyright information

© Kluwer Academic/Plenum Publishers 1999

Authors and Affiliations

  • Tom Ziemke
    • 1
  1. 1.Department of Computer ScienceUniversity of SkövdeSkövdeSweden

Personalised recommendations