Abstract
In the elephant paper, Brooks criticized the ungroundedness of traditional symbol systems and proposed physically grounded systems as an alternative. We want to make a contribution towards integrating the old with the new. We describe the GLAIR agent architecture that specifies an integration of explicit representation and reasoning mechanisms, embodied semantics through grounding symbols in perception and action, and implicit representations of special-purpose mechanisms of sensory processing, perception, and motor control. We present some agent components that we place in our architecture to build agents that exhibit situated activity and learning, and some applications. We believe that the Brooksian behavior generation approach goes a long way towards modeling elephant behavior, which we find most interesting, but that in order to generate more deliberative behavior we need something more.
The research reported in this paper was carried out while the first authors was a member of the SNePS researchg Group at the department of Computer Science, SUNY at Buffalo, and was supported in part by Equipment Grant No. EDUDUS-932022 from SUN Microsystems Computer Corporation, and in part by NASA under contract NAS 9-19004.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
P. Agre. The dynamic structure of everyday life. Technical Report 1085, MIT Artificial Intelligence Laboratory, MIT, 1988
P. E. Agre and D. Chapman. Pengi: An implementation of a theory of activity. In Proceedings of AAAI-87, Seattle WA, pp. 268–272, July 1987
J. Albus, A. Barbera, and R. Nagel. Theory and practice of hierarchical control. In 23rd International IEEE Computer Society Conference, pp. 18–38, 1981
J. R. Anderson. The Architecture of Cognition. Cambridge, MA: Harvard University Press, 1983
S. Anderson, D. Hart, and P. Cohen. Two ways to act. In ACM SIGART Bulletin, pp. 20–24. ACM publications, 1991
D. H. Ballard and C. M. Brown. Computer Vision. Prentice-Hall, Englewood Cliffs, NJ, 1982
C. Bandera, H. Hexmoor, and S. C. Shapiro. Foveal machine vision for robots using agent based gaze control final report. Technical Report SBIR-NAS 9–19004, Amherst Systems Inc., Buffalo, NY, September 1994
B. Berlin and P. Kay. Basic Color Terms: Their Universality and Evolution. University of California Press, Berkeley, CA, 1991 edition, 1969
R. Brooks. A robust layered control system for a mobile robot. Technical Report 864, MIT AI Labs, MIT, 1985
R. Brooks. Planning is just a way of avoiding figuring out what to do next. Technical Report 303, MIT AI Labs, 1987
R. A. Brooks. Elephants dont play chess. Robotics and Autonomous Systems, 6: 3–15, 1990
S. Card, T. Moran, and A. Newell. The Psychology of Human–Computer Interaction. Erlbaum, Hillsdale, NJ, 1983
D. Chapman. Vision, instruction, and action. Technical Report 1204, MIT Artificial Intelligence Laboratory, MIT, 1990
J. Connell. SSS: A hybrid architecture applied to robot navigation. In IEEE Conference on Robotics and Automation, pp. 2719–2724, 1992
J. Culbertson. The Minds of Robots. U. of Illinois Press, 1963
R. J. Firby. An investigation into reactive planning in complex domains. In Proceedings of AAAI–87, pp. 202–206, 1987
J. Fodor. The Modularity of Mind. MIT Press, 1983
E. Gat. Reliable goal–directed reactive control of autonomous mobile robots. Technical report, Dept. of Computer Science, Virginia Polytechnic Institute and State University, 1991
S. Harnad. The symbol grounding problem. Physica D, 42 (1–3): 335–346, 1990
S. Harnad. Electronic symposium on computation, cognition and the symbol grounding problem. Ftp archive at princeton. edu:/pub/harnad/sg. comp. arch, 1992
R. Hausser. Computation of Language: An Essay on Syntax, Semantics and Pragmatics in Natural Man–Machine Communication. Springer–Verlag, New York, NY, 1989
H. Hexmoor. An architecture for reactive sensor–based robots. In NASA God– dard conference on AI, Greenbelt, MD, 1989
H. Hexmoor. Representing and learning successful routine activities. Unpublished PhD Proposal, 1992
H. Hexmoor, G. Caicedo, F. Bidwell, and S. Shapiro. Air battle simulation: An agent with conscious and unconscious layers. In University at Buffalo Graduate Conference on Computer Science 93 (TR–93–14). Dept. of Computer Science, SUNY at Buffalo, New York, 1993
H. Hexmoor, J. Lammens, G. Caicedo, and S. C. Shapiro. Behavior based AI, cognitive processes, and emergent behaviors in autonomous agents. In G. Rzevski, J. Pastor, and R.Adey (eds.), Applications of AI in Engineering VIII, Vol. 2, Applications and Techniques, pp. 447–461. CMI/Elsevier, 1993. Reprint available TR–93–15, CS dept., SUNY/BufFalo
H. Hexmoor, J. Lammens, and S. Shapiro. Embodiment in GLAIR: A grounded layered architecture with integrated reasoning for autonomous agents. In D. D. Dankel (ed.), Proceedings of the 6th Florida AI Research Symposium, pp. 325–329. Florida AI Research Society, 1993
H. Hexmoor, J. Lammens, and S. C. Shapiro. An autonomous agent architecture for integrating unconscious and reasoned behaviors. In Proceedings of Computer Architectures for Machine Perception, New Orleans, LA, 1993. Preprint available as TR–93–36, CS dept., SUNY/BufFalo
H. Hexmoor and D. Nute. Methods for deciding what to do next and learning. Technical Report AI–1992–01, AI Programs, The University of Georgia, Athens, Georgia, 1992. Also available as TR–92–23, CS dept., SUNY/BufFalo
H. Hexmoor and S. C. Shapiro. Examining the expert reveals expertise. In Proceedings of the Third International Workshop on Human and Machine Cognition: Expertise in Context ( Seaside, FL ), 1993
L. Kaelbling. Goals as parallel program specifications. In Proceedings of AAAI–88. Morgan Kaufmann, 1988
L. Kaelbling and S. Rosenschein. Action and planning in embedded agents. In P. Maes (ed.), Designing Autonomous Agents, pp. 35–48. MIT Press, 1990
P. Kay and C. K. McDaniel. The linguistic significance of the meaning of Basic Color Terms. Language, 54 (3): 610–646, 1978
D. Kumar. An integrated model of acting and inference. In D. Kumar (ed.), Current Trends in SNPS–Semantic Network Processing System: Proceedings of the First Annual SNPS Workshop, pp. 55–65, Buffalo, NY, 1990. Springer– Verlag
D. Kumar. From Beliefs and Goals to Intentions and Actions: An Amalgamated Model of Inference and Acting. PhD thesis, Technical Report 94–04, Department of Computer Science, State University of New York at Buffalo, Buffalo, NY, 1994
D. Kumar. The SNPS BDI architecture. Journal of Decision Support Systems—Special Issue on Logic Modeling, 1994. Forthcoming
D. Kumar and S. C. Shapiro. Acting in service of inference (and vice versa). In D. D. Dankel II (ed.), Proceedings of the Seventh Florida Artificial Intelligence Research Symposium, pp. 207–211. the Florida AI Research Society, St. Petersburg, FL, May 1994
J. Laird, M. Huka, E. Yager, and C. Tucker. Robo–SOAR: An integration of external interaction, planning, and learning, using SOAR. In Robotics and Autonomous Systems, 1991
J. E. Laird, A. Newell, and P. S. Rosenbloom. SOAR: An architecture for general intelligence. Artificial Intelligence, 33: 1–64, 1987
G. Lakoff. Women, Fire, and Dangerous Things: What Categories Reveal about the Mind. University of Chicago Press, Chicago, IL, 1987
J. M. Lammens. A somewhat fuzzy color categorization model. Submitted to ICCV–95
J. M. Lammens. A Computational Model of Color Perception and Color Naming. PhD thesis, State University of New York at Buffalo, 1994. Also available as TR–94–26, CS dept., SUNY/Buffalo
P. Langley, K. McKusick, and J. Allen. A design for the ICARUS architecture. In ACM SIGART Bulletin, pp. 104–109. ACM publications, 1991
H. J. Levesque. Logic and the complexity of reasoning. Journal of Philosophical Logic, 17: 355–389, 1988
P. Maes. Action selection. In Proceedings of the Cognitive Science Society Conference, 1991
R. J. Makar. GLAIR: Mobile robot lab camera simulation. Masters project dept. of Computer Science, SUNY at Buffalo, NY, 1994
J. L. McClelland, D. E. Rumelhart, and G. E. Hinton. The appeal of parallel distributed processing. In D. Rumelhart, J. McClelland, and the PDP Research Group (eds.), Parallel Distributed Processing, chapter 1, pp. 3–44. MIT Press, Cambridge, MA MA, 1986
D. McDermott. Robot planning. Technical Report CS–861, Yale University, 1991
D. Payton. An architecture for reflexive autonomous vehicle control. In Proceedings of Robotics Automation, pp. 1838–1845. IEEE, 1986
J. Pollock. How to Build a Person. MIT Press, 1989
J. Pollock. New foundations for practical reasoning. In Minds and Machines, 1992
W. J. Rapaport. Syntactic semantics: Foundations of computational natural– language understanding. In J. H. Fetzer (ed.), Aspects of Artificial Intelligence, pp. 81–131. Kluwer Academic, New York, 1988
D. Regan and K. Beverly. Looming detectors in the human visual pathways. In Vision Research 18, pp. 209–212. 1978
J. K. Rosenblatt and D. Payton. A fine–grained alternative to the subsumption architecture for mobile robot control. In Proceedings of the International Joint Conference on Neural Networks, 1989
S. Russell. An architecture for bounded rationality. In ACM SIGART Bulletin, pp. 146–150. ACM publications, 1991
M. J. Schoppers. Universal plans for unpredictable environments. In Proceedings 10th IJCAI, pp. 1039–1046, 1987
S. C. Shapiro. Cables, paths, and subconscious reasoning in propositional semantic networks. In Principles of Semantic Networks. Morgan Kaufmann, 1990
S. C. Shapiro and W. J. Rapaport. SNPS considered as a fully intensional propositional semantic network. In N. Cercone and G. McCalla (eds.), The knowledge frontier: essays in the representation of knowledge, pp. 262–315. Springer Verlag, New York, 1987
S. C. Shapiro and W. J. Rapaport. The SNPS family. Computers Math. Applic., 23 (2–5): 243–275, 1992
S. C. Shapiro and the SNPS Implementation Group. SNPS 2. 1 Users Manual. Department of Computer Science, SUNY at Buffalo, 1994
W.–M. Shen. Learning from the Environment Based on Actions and Percepts. PhD thesis, Carnegie Mellon University, 1989
R. Simmons. An architecture for coordinating planning, sensing, and action. In Proceedings of the DARPA planning workshop, pp. 292–297, 1990
L. A. Suchman. Plans and Situated Actions: The Problem of Human Machine Communication. Cambridge University Press, 1988
P. H. Winston. Learning structural descriptions from examples. In R. J. Brachman and H. J. Levesque (eds.), Readings in Knowledge Representation, pp. 141–168. Morgan Kaufmann, San Mateo, CA, 1985 (orig. 1975 )
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 1995 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Lammens, J.M., Hexmoor, H.H., Shapiro, S.C. (1995). Of Elephants and Men. In: Steels, L. (eds) The Biology and Technology of Intelligent Autonomous Agents. NATO ASI Series, vol 144. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-79629-6_13
Download citation
DOI: https://doi.org/10.1007/978-3-642-79629-6_13
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-79631-9
Online ISBN: 978-3-642-79629-6
eBook Packages: Springer Book Archive