COTS AI/ML technology for data fusion and track management
Loading...
Authors
Garza, Victor
Wood, Brian
Gallup, Shelley
MacKinnon, Douglas
Subjects
artificial intelligence
AI
machine learning
ML
intelligence fusion
data analysis
human machine interaction
decision aids
AI
machine learning
ML
intelligence fusion
data analysis
human machine interaction
decision aids
Advisors
Date of Issue
2022
Date
2022
Publisher
Monterey, California: Naval Postgraduate School
Language
Abstract
The Navy, and specifically Naval Information Forces, lacks the ability to fully employ artificial intelligence/machine learning (AI/ML) effectively to assist with data fusion and provide quick and timely analysis of the common operating picture/common tactical picture (COP/CTP). Other industries use this rising technology to enhance their analysis fusion. To help bring the Navy up to date, we examined multiple data streams such as geospatial intelligence (GEOINT) and radar data sets to fuse this information quickly and with greater accuracy of managing positive identification of tracks to provide the most current intelligence directly to the commanders for their decisions. We performed an analysis of the ability to use AI/ML by using commercial off-the-shelf (COTS) software to automate filtering and demonstrate accuracy of multiple data streams into the Navy’s COP/CTP for specific use by Naval Information Forces. Multiple data sets were integrated and filtered with automation to provide quick and timely analysis, while increasing speed and accuracy of managing positive identification of tracks, and developing the COP. During our research, we created an ML pipeline that processes data from a simulation to train and test ML models that can be used in a Kalman filter (KF) system. We improved the KF by adding a learning component, called the ML-KF, which used sensor measurement errors to make more accurate predictions. The simulation system provided accurate data to train the learning component of our KF model, which means simulation can be a useful method for developing and testing ML models. These trained models may be able to be used in real-world situations in the future.
Type
Report
Description
NPS NRP Executive Summary
Series/Report No
Department
Organization
Identifiers
NPS Report Number
Sponsors
N8 - Integration of Capabilities & Resources
Funding
This research is supported by funding from the Naval Postgraduate School, Naval Research Program (PE 0605853N/2098). https://nps.edu/nrp
Chief of Naval Operations (CNO)
Chief of Naval Operations (CNO)
Format
Citation
Distribution Statement
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.