AN ANALYSIS OF ARTIFICIAL INTELLIGENCE PERFORMANCE AND BEHAVIOR WITHIN THE MODEL OF EXPEDITIONARY ADVANCED BASE OPERATIONS
Loading...
Authors
Islas, Sean W.
Subjects
artificial intelligence
expeditionary advanced base operations
analysis
wargaming
expeditionary advanced base operations
analysis
wargaming
Advisors
Darken, Christian J.
Fitzpatrick, Christian R.
Date of Issue
2024-06
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The purpose of this thesis is an analysis of artificial intelligence (AI) applications in expeditionary advanced base operations (EABO), focusing on combat and logistical operations. Using Atlatl as the simulation engine, multiple autonomous agents were tested in a scenario modeling the challenges of a stand-in force conducting dispersed operations in an amphibious environment. Each AI was tested for its ability to conduct sustainment operations below the threshold of military action as well as defend against an amphibious assault when that threshold has been crossed. In the case of scripted agents, adjustments to behavior based on a combined arms approach to warfare proved to create a more survivable AI, while maintaining its level of lethality. In the case of agents built on neural networks, their performance was limited due to the size and scope of the problem and may require additional study to show significant results. This research is an explorative tool for the continuation of the development of EABO concepts, offering feedback on the concept of operations for continued refinement.
Type
Thesis
Description
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
Funding
Format
Citation
Distribution Statement
Distribution Statement A. Approved for public release: Distribution is unlimited.
Rights
This publication is a work of the U.S. Government as defined in Title 17, United States Code, Section 101. Copyright protection is not available for this work in the United States.