Design and Implementation of CITKA, a Context Based Tactical Knowledge Acquisition System

The CITKA system has been developed to facilitate the acquisition of the knowledge for military tactics; this is known to be one of the limiting factors in the development of computer generated forces. This acquisition is achieved via a query session between a subject matter expert (SME) and an intelligent system. Such a system has several advantages. The most important of these would be the drastic decrease in manpower effort to implement the tactical behaviors directly into whatever language is used by the modeling paradigm. Moreover, fewer errors can be expected, making the verification of the model less difficult. Also, a tool developed to carry out the query session and build the model could serve to maximize re-use of previously defined tactics. Context-based Reasoning has been selected as the paradigm because it lends itself very well to automating the knowledge acquisition process. This paper describes CITKA, a system that develops a model of tactical behaviors via a Q&A process with the SME. A prototype was built and is described in detail. Comparisons with manual knowledge base development are being researched. The metrics used are the number of person hours required to develop the model automatically vs. manually, and the proportion of the model that can be developed in this fashion. We use a non-trivial sea scenario mission as the benchmark for the comparisons.