Simulated Laser Weapon System Decision Support to Combat Drone Swarms with Machine Learning is a Naval Postgraduate School thesis by Daniel M. Edwards.
This thesis showcases the application of machine learning to provide automated decision support for warfighters managing laser weapon systems in intricate tactical scenarios. The study leveraged the Swarm Commander modeling and simulation software environment from the NPS Modeling Virtual Environments and Simulation (MOVES) Institute to generate simulated datasets involving wargaming scenarios where a shipboard laser weapon system defended against drone swarm threats.
These simulated datasets were employed to train a machine learning algorithm to predict the optimal engagement strategy within a complex battlespace featuring diverse drone swarms. Several machine learning techniques were assessed, ultimately selecting the classification tree method as the preferred approach. The final algorithm exhibited an impressive 96% overall accuracy in correctly forecasting engagement outcomes, accounting for drone threat types, quantities, and laser weapon system attack strategies.
This research underscores three key findings: (1) the value of modeling and simulation in aiding the development of tactical machine learning applications, (2) the potential of machine learning to enhance support for future tactical operations, and (3) the broader potential of machine learning and automation to alleviate the cognitive burden on future warfighters faced with critical decisions in complex threat environments.
Publication Date– September 2021
Simulated Laser Weapon System Decision Support to Combat Drone Swarms with Machine Learning contains the following major sections:
- Literature Review
- Swarm Commander Tactics and Machine Learning Experimentation
- Results and Data Optimization
Approved for public release. Distribution is unlimited.
C-UAS Hub does not own this content and provides a link for users at the bottom of the page to access it in its original location. This allows the author(s) to track important article metrics related to their work. All credit goes to its rightful owner.
Author- Daniel M. Edwards
Post Image Credit: Adobe Stock by lucky pics