Mission Planning Optimization for Infantry Operations

Abstract

Geospatial intelligence is readily available to tactical-level leaders for mission planning, but few analytical models exist or are directly available for exploitation by end-users. This capability gap results in a slower planning process that decreases in comprehensibility and precision as time and support available are constrained. We offer a capability to fill this gap in offensive operations by formulating four models for: helicopter landing zone detection, tactical pathfinding, battlespace geometry optimization, and course of action selection optimization. Methods leveraged include geospatial data analysis, unsupervised machine learning, multi-objective minimum-cost flow, and weighted-sum multi-objective optimization. In our experiment, we run our models to generate courses of action for an air assault at Camp Pendleton, California. By choice of landing zone, route, supporting machine gun position, and objective entry point, the model finds 785,664 possible decision combinations for this scenario. The model constrains to 220 courses of action by user preferences and doctrinal considerations. The decision-maker is presented with a preferred number of optimal courses of action after evaluating the set of branch plans with a multi-objective optimization. This research demonstrates the utility for analytic models to rapidly and precisely inform decision-making cycles at the tactical edge.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 2023
Accession Number
AD1213491

Entities

People

  • Ryan A. Helm

Organizations

  • Naval Postgraduate School

Tags

Readers

  • Enterprise Information Systems Architecture and Joint Command Capability Interoperability Support.
  • Military Science
  • Operations Research

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference
  • AI & ML - DoD AI Strategy
  • AI & ML - Machine Learning Algorithms