Anticipatory Planning with agents using genetic algorithms and simulation /
The traditional Military Decision Making Process (MDMP) focuses on developing a few friendly Courses of Action (COAs) against the "most-likely and most-dangerous" enemy COAs. There is a well-known axiom that "No plan survives the first shot." This indicates that a branch has oc...
| Main Author: | |
|---|---|
| Format: | Thesis Book |
| Language: | English |
| Published: |
[Place of publication not identified] :
[publisher not identified] ;
2001.
|
| Subjects: | |
| Online Access: | http://proxy.library.tamu.edu/login?url=http://proquest.umi.com/pqdweb?did=728908321&sid=1&Fmt=2&clientId=2945&RQT=309&VName=PQD |
| Summary: | The traditional Military Decision Making Process (MDMP) focuses on developing a few friendly Courses of Action (COAs) against the "most-likely and most-dangerous" enemy COAs. There is a well-known axiom that "No plan survives the first shot." This indicates that a branch has occurred during execution that was not included in the plan, forcing the human planners into reactive mode. The military is capable of producing unprecedented amounts of battlefield information that could be used to better anticipate the flow of the battle. Military planners need a way to incorporate this continuous feed of battle information into the planning process so that they achieve and maintain "option dominance". A new approach to military operations, called Anticipatory Planning and Adaptive Execution, treats planning and execution as a tightly coupled, single process, and replaces reaction to events with anticipation of events. This research develops the methodology for automating the Anticipatory Planning process. A prototype Anticipatory Planning Support System (APSS) has been designed and implemented to provide human planners with an interactive visual development system using simulations to build Plan Descriptions. Nodes represent option points in the plan and Branches represent the transitions between them. As execution progresses the plan is continuously updated based on actual events. Execution Monitors are attached to Nodes, use forward simulation from the Actual State to derive Anticipated States, and compare them with the Planned State at the Nodes. The Execution Monitors recommend re-planning to the Planning Executive, which prioritizes planning to maintain a balance between anticipating as many future branches to the plan as possible and constraining the planning effort. The Planning Executive launches Planners that use a genetic algorithm and inference mechanisms to postulate and consider possible friendly and enemy actions, then produce significant, representative, Branches. For testing or training purposes, an external Stimulator uses a controlled Plan Description and a simulation to produce Actual States for use by the APSS. The primary goals of this implementation are to provide a common representation of the plan, facilitate the planning process, anticipate the flow of the battle, and provide a means for stimulating planning systems. |
|---|---|
| Item Description: | Vita. "Major Subject: Computer Science". |
| Physical Description: | xiii, 177 leaves : illustrations ; 28 cm. + 1 CD-ROM. Issued also on microfiche from University Microfilm Inc. |
| Bibliography: | Includes bibliographical references (leaves 160-175). |