US Navy researches ML techniques to improve drone detection

5 December 2019 (Last Updated December 5th, 2019 12:42)

The Naval Surface Warfare Center Crane Division (NSWC Crane) is working on a research project to improve drone detection capability.

The Naval Surface Warfare Center Crane Division (NSWC Crane) is working on a research project to improve drone detection capability.

NSWC Crane partnered with Old Dominion University (ODU) to research drone detection technologies based on machine learning (ML).

Under a Cooperative Research and Development Agreement (CRADA), researchers will implement ML methods to detect and identify unmanned aerial systems based on their classification of radio frequency (RF) signals.

The objective of the collaborative work is to deliver a portable system that can support the warfighters in constrained and remote environments

The partnership will apply the latest technology to RF signals to deliver the capability.

The project team includes ODU Virginia Modeling, Analysis, and Simulation Center associate director Dr Sachin Shetty and his undergraduate student research assistant Michael Nilsen.

The duo developed ML techniques to enable adaptive detection of UAS systems. The method successfully completed evaluation at outdoor test ranges.

Dr Shetty said: “The benefits of using this machine learning technique is that no matter what types or models of drones made in the future, the technique can detect them. We didn’t want to create a technique that would be tied to a certain drone model and have to constantly change it.”

“Where the warfighters needs to use rapid drone detection technology, there is often no internet. They need a mobile, lightweight, and packable solution that works in a resource-constrained environment.

“Essentially, we are able to give the warfighter an RF classification toolbox on a device the size of a phone.”

Shetty added that algorithms were tested in multiple rural and urban environments.