Real-Time Decision Support for Course of Action/Enemy Course of Action (COA/ECOA) Analysis
Abstract
This report documents the research on course of action (COA) analysis in alignment with commander's intent. A military mission requires that a series of COAs be generated, developed, analyzed and executed. For each mission, thousands of COAs may be automatically generated but only those in alignment with Commander's Intent are worth investigating. The challenge is that given a specific pair of commander's intent and COA, there is always a semantic gap: the two not only differ syntactically, but also semantically. In this research, we have made two specific contributions towards developing a solution to this problem. First, we have discovered that the classic symbolic reasoning does not work in developing such a solution, as the semantics involved are always fuzzy and inexact. Second, under the assumptions that both the commander's intent and the COAs are represented in a low level in a semantic hierarchy (such that there is a syntax to represent them in terms of languages), we have developed a specific solution as a method to identify whether a specific pair of commander's intent and COA is in alignment and if not, how far they divert from each other. We have done proof-of-concept testing on a small, hand-crafted ontology.
Document Details
- Document Type
- Technical Report
- Publication Date
- Oct 01, 2005
- Accession Number
- ADA441062
Entities
People
- Zhongfei Zhang