Abstract
In this paper we introduce the concept of knowledge granularity and study its influence on an agent's action selection process. Action selection is critical to an agent performing a task in a dynamic, unpredictable environment. Knowledge representation is central to the agent's action selection process. It is important to study what kind of knowledge the agent should represent and the preferred methods of representation. One interesting research issue in this area is the knowledge granularity problem: to what detail should an agent represent a certain kind of knowledge. In other words, how much memory should an agent allocate to represent a certain kind of knowledge. Here, we first study knowledge granularity and its influence on action selection in the context of an object search agent — a robot that searches for a target within an environment. Then we propose a guideline for selecting reasonable knowledge granularity for an agent in general.
This is a preview of subscription content, log in via an institution to check access.
Preview
Unable to display preview. Download preview PDF.
References
R. Bajcsy. Active perception vs. passive perception. In Third IEEE Workshop on Vision, pages 55–59, Bellaire, 1985.
R. Bajcsy. Perception with feedback. In Image Understanding Workshop, pages 279–288, 1988.
R. A. Brooks. Intelligence without representation. Artificial Intelligence, (47):139–160, 1991.
Connel. An Artificial Creature. PhD thesis, AI Lab, MIT, 1989.
I. Ferguson. Touring Machine: An Architecture for Dynamic, Rational, Mobile Agents. PhD thesis, University of Cambridge, UK, 1992.
T. D. Garvey. Perceptual strategies for purposive vision. Technical Report Technical Note 117, SRI International, 1976.
M. Georgeff and A. Lansky. Reactive reasoning and planning. In Proceedings of the Sixth National Conference on Artificial Intelligence, pages 677–682, Seattle, WA, 1987.
J. Muller and M. Pischel. Modelling interacting agents in dynamic environments. In Proceedings of the Eleventh European Conference on Artificial Intelligence, pages 709–713, Amsterdam, The Netherland, 1994.
S. Sen, S. Roychowdhury, and N. Arora. Effects of local information on group behavior. In Proceedings of Second International Conference on Multi-Agent Systems, pages 315–321, Kyoto, Japan, 1996.
T. Tyrrell. Computational Mechanisms for Action Selection. PhD thesis, Center for Cognitive Science, University of Edinburgh, England, 1993.
M. Wooldridge and N. Jenning. Intelligent agents: theory and practice. The Knowledge Engineering Review, 10(2):115–152, 1995.
Y. Ye and J. K. Tsotsos. Where to look next in 3d object search. In IEEE International Symposium for Computer Vision, Florida, U.S.A., November 1995.
Y. Ye and J. K. Tsotsos. Sensor planning in 3d object search: its formulation and complexity. In The 4th International Symposium on Artificial Intelligenceand Mathematics, Florida, U.S.A., January 3–5 1996.
Y. Ye and J. K. Tsotsos. Knowledge difference and its influence on a search agent. In First International Conference on AUTONOMOUS AGENTS, Marina del Rey, CA, January 1997.
Author information
Authors and Affiliations
Editor information
Rights and permissions
Copyright information
© 1998 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Ye, Y., Tsotsos, J.K. (1998). Knowledge granularity and action selection. In: Giunchiglia, F. (eds) Artificial Intelligence: Methodology, Systems, and Applications. AIMSA 1998. Lecture Notes in Computer Science, vol 1480. Springer, Berlin, Heidelberg. https://doi.org/10.1007/BFb0057468
Download citation
DOI: https://doi.org/10.1007/BFb0057468
Published:
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-64993-9
Online ISBN: 978-3-540-49793-6
eBook Packages: Springer Book Archive