Integrating Conversational Case Retrieval
with Generative Planning

Hctor Muoz-Avila12, David W. Aha2, Leonard A. Breslow2,
Dana S. Nau1, and Rosina Weber3

1 Department of Computer Science, University of Maryland

College Park, MD 20742-3255
{lastname}@cs.umd.edu
2 Navy Center for Applied Research in Al, Naval Research Laboratory (Code 5510)

Washington, DC 20375
{lastname}@aic.nrl.navy.mil

3 Department of Computer Science, University of Wyoming,

Laramie, WY 82071



Abstract. Some problem-solving tasks are amenable to integrated case
retrieval and generative planning techniques. This is certainly true for
some decision support tasks, in which a user controls the problem-solving
process but cannot provide a complete domain theory. Unfortunately,
existing integrations are either non-interactive or require a complete domain 
theory and/or complete world state to produce acceptable plans,
preventing them from being easily used in these situations. We describe
a novel integrated algorithm, named SiN, that is interactive aud does
not require a complete domain theory or complete world state. SiN users
leverage a conversational case retriever to focus both partial world state
acquisition and plan generation. We highlight the benefits of SiN (e.g.,
quadratically fewer cases needed) in an experimental study using a new
travel planning domain.
References

1.	Aha, D. W., & Breslow, L. A. (1997). Refining conversational case libraries. Proceedings 
of the Second International Conference on CBR (pp. 267278). Providence, RI: Springer.
2.	Avesani, P., Perini, A., & Ricci, F. (1998). The twofold integration of CBR in decision 
support systems. In D. W. Aha & J. J. Daniels (Eds.), Case-Based Reasoning
Integrations: Papers from the 1998 Workshop (Technical Report WS-98-15). Menlo
Park, CA: AAAI Press.
3.	Bergmann R. & Wilke W. (1995). Building and refining abstract planning cases
by change of representation language. Journal of Artificial Intelligence Research,
3, 53118.
4.	Carrick, C., Yang, Q., Abi-Zeid, I., & Lamontagne, L. (1999). Activating CBR
systems through autonomous information gathering. Proceedings of the Third International 
Conference on Case-Based Reasoning (pp. 7488). Munich, Germany:
Springer.
5.	Golding, A., & Rosenhloom, P. 5. (1991). Improving rule-based systems through
case-based reasoning. In Proceedings of the Ninth National Conference on Artificial
Intelligence (pp. 2227). Anaheim, CA: AAAI Press.
6.	Hammond, K. (1989). Case-based planning: Viewing planning as a memory task.
Boston, MA: Academic Press.
7.	Leake, D., Kinley, A., & Wilson, D. (1997). A Case Study of Case-Based CBR.
Proceedings of the Second International Conference on Case-Based Reasoning (pp.
371382). Providence, RI: Springer.
8.	Mitchell, S. W. (1997). A hybrid architecture for real-time mixed-initiative planning 
and control. Proceedings of the Ninth Conference on Innovative Applications
of Al (pp. 10321037). Providence, RI: AAAI Press.
9.	Muoz-Avila, H., McFarlane, D., Aha, D. W., Ballas, J., Breslow, L. A., & Nau, D.
(1999). Using guidelines to constrain interactive case-based H TN planning. Proceedings 
of the Third International Conference on Case-Based Reasoning (pp. 288302).
Munich, Germany: Springer.
10.	Muoz-Avila, H., Weberskirch, F., & Roth-Berghofer, T. (1997). On the relation
between the context of a feature and the domain theory in case-based planning.
Proceedings of the Second International Conference on Case-Based Reasoning (pp.
337-348). Providence, RI: Springer.
11.	Nau, D., Cao, Y., Lotem, A., & Muoz-Avila, H. (1999). SHOP: Simple hierarchical
ordered planner. Proceedings of the Sixteenth International Joint Conference on
Artificial Intelligence (pp. 968973). Stockholm: AAAI Press.
12.	Veloso, M. M., & Carbonell, J. G. (1993). Derivational analogy in PRODIGY:
Automating case acquisition, storage, and utilization, Machine Learning, 10, 249
278.
13.	Veloso, M., Mulvehill, A. M., & Cox, M. T. (1997). Rationale-supported mixed-initiative 
case-based planning. Proceedings of the Ninth Conference on Innovative
Applications of Artificial Intelligence (pp. 10721077). Providence, RI: AAAI Press.
14.	Weber, R., Aha, D. W., Muoz-Avila, H., & Breslow, L. A. (2000). Active delivery
for lessons learned systems. To appear in Fifth European Workshop on Case-Based
Reasoning. Trento, Italy: Springer.
15.	Wilkins, D. F. (1998). Using the SIPE-2 planning system: A manualfor Version 5.0
(Working Document). Menlo Park, CA: Stanford Research International, Artificial
Intelligence Center.
