MULTI-AGENT FLIGHT PLANNING IN A THREE-DIMENSIONAL THREAT ENVIRONMENT USING CROSS-ENTROPY SEARCH
Loading...
Authors
Daniel, Christopher M.
Subjects
weapon engagement zone
WEZ
three-dimensional
3D
optimal substructure property
OSP
dynamic programming
DP
flight planning
mission planning
optimization
path-finding
cross-entropy
CE
A*
JMPS
multiagent
multi-agent
WEZ
three-dimensional
3D
optimal substructure property
OSP
dynamic programming
DP
flight planning
mission planning
optimization
path-finding
cross-entropy
CE
A*
JMPS
multiagent
multi-agent
Advisors
Peitso, Loren E.
Drusinsky, Doron
Date of Issue
2025-03
Date
Publisher
Monterey, CA; Naval Postgraduate School
Language
Abstract
The multi-agent cross-entropy (CE) search method effectively optimizes flight routes in dynamic, contested three-dimensional (3D) environments where multiple aircraft must cooperate. Traditional military flight planning relies on pilots using complex and cumbersome software that lacks a comprehensive view of the operating environment. Surface-to-air threat weapon engagement zones (WEZs) are critical considerations in route planning, as excessive exposure can lead to mission failure, aircraft loss, or personnel endangerment. This thesis introduces a multi-agent CE-based path-finding approach that efficiently generates coordinated flight routes while optimizing factors such as route length and altitude and its deviations. For single-aircraft scenarios, where the path-finding problem satisfies the optimal substructure property (OSP), fast and optimal dynamic programming (DP) algorithms such as A* can be applied. However, multi-agent coordination violates OSP, making DP methods unsuitable. This research demonstrates that the CE search method can effectively navigate this complex problem space, producing near-optimal flight routes that balance the collective needs and objectives of multiple aircraft. Additionally, a novel evaluation framework is presented to assess the quality of CE-generated routes relative to the unattainable optimal solution.
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.