A Unified Long-Term Memory System*

James H. Lawton	Roy M. Turner & Elise H. Turner

Air Force Research Laboratory	     Department of Computer Science
Rome Research Site	             University of Maine
Rome, NY 13441	                     Orono, ME 04469
lawton@ai.rl.af.mil	             {rmt,eht}@umcs.maine.edu



Abstract. Memory-based reasoning systems are a class of reasoners that derive
solutions to new problems based on past experiences. Such reasoners use a
long-term memory (LTM) to act as a knowledge base of these past experiences,
which may be represented by such things as specific events (i.e. cases), plans,
scripts, etc. This paper describes a Unified Long-Term Memory (ULTM)
system, which is a dynamic, conceptual memory that was designed to be a
general LTM capable of simultaneously supporting multiple intentional
reasoning systems. Through a unique mixture of content-independent and
domain-specific mechanisms, the ULTM is able to flexibly provide reasoners
accurate and timely storage and recall of episodic memory structures. In
addition, the ULTM provides support for recognizing opportunities to satisfy
suspended goals, allowing reasoning systems to better cope with the
unpredictability of dynamic real-world domains by helping them take advantage
of unexpected events.
References

1.	Francis, A.G. Jr. (1997). Memory-Based Opportunistic Reasoning, Ph.D. Thesis
proposal, Georgia Institute of Technology.
2.	Hammond, K. (1990). Case-Based Planning: A Framework for Planning from
Experience, The Journal of Cognitive Science, 14(3).
3.	Hammond, K. (1993). Opportunistic Memory, The Journal of Machine Learning,
10(3).
4.	Kellermann, K., Broetzmann, S., Lim, T.-S., and Kitao, K. (1989). The conversation
mop: Scenes in the steam of discourse, Discourse Processes, 12(1):27-61.
5.	Kolodner, J. (1981). Organization and Retrieval in a Conceptual Memory for Events,
Proceedings of the Seventh International Joint Conference on Artificial Intelligence.
6.	Kolodner, J. (1989). SeLecting the Best Case for a Case-Based Reasoner, Proceedings of
the Eleventh Conference of the Cognitive Science Society.
7.	Kolodner, J. (1993). Case-Based Reasoning, Morgan Kaufman, San Mateo.
8.	Patalano, A., Seifert, C., and Hammond, K. (1991). Predictive Encodings: Planning for
Opportunities, Proceedings of the Fifteenth Conference of the Cognitive Science Society.
9.	Schank, R. (1982). Dynamic Memory, Cambridge University Press, New York.
10.	Schank, R. and Osgood, R. (1990). A content theory of memory indexing,
Northwestern University, Institute for Learning Sciences Technical Report no. 2.
11.	Steele, G. (1990). Common Lisp: The Language (Second Edition), Digital Press, Bedford,
MA.
12.	Sycara, K. and Navinchandra, D. (1991). Index Transformation and Generation for Case
Retrieval, In Proceedings of the 1991 Case-Based Reasoning Workshop (DARPA),
Bareiss, E. (ed.), Morgan Kaufman, San Mateo, CA.
13.	Turner, E. (1990). Integrating Intention and Convention To Organize Problem Solving
Dialogues, Ph.D. Dissertation, Georgia Institute of Technology technical report GIT-ICS-
90/02.
14.	Turner, R. (1987). Issues in the design of advisory systems: The consumer-advisor
system, in Proceedings of the Eleventh Annual Conference of the Cognitive Science
Society, Detroit, MI.
15.	Turner, R. (1994). Adaptive Reasoning for Real-World Problems: A Schema-Based
Approach, Lawrence Erlbaum Associates, Hillsdale, NJ.
16.	Turner, R. (1995a). Context-Sensitive, Adaptive Reasoning for Intelligent AUV Control:
Orca Project Update, In Proceedings of the 9th International Symposium on Unmanned
Untethered Submersible Technology (AUV95), Durham, New Hampshire.
17.	Turner, R. (1995b). Intelligent Control of Autonomous Underwater Vehicles: The Orca
Project, Roy M. Turner. In Proceedings of the 1995 IEEE Conference on Systems, Man,
and Cybernetics, Vancouver, BC, Canada.
18.	Turner, R. (1997). Orca Documentation (for Version 2.1), CDPS Research Group in-
house report, University of Maine. http://cdps.umcs.maine.edu/Docs/orca-2.0/
