NATO experts develop ARTEMIS for sUAS detection

A team at the NATO Communications and Information (NCI) Agency has built an experimental prototype to detect, identify and localise small UASs (sUASs) using low-cost COTS devices and machine learning.

Called the Advanced Recognition Tool using Electromagnetic Waves for Identifying Unmanned Aerial Systems (ARTEMIS), the prototype uses advanced techniques to detect RF signals and classify them.

ARTEMIS only needs to process 40 milliseconds of data to obtain a probability of correct classification above 90%, NATO claimed on 3 September.

The system continuously monitors the bandwidth where UAVs normally operate and automatically detects any RF emissions.

‘Once detected, a process entirely based on machine learning and pattern recognition will allow us to classify and identify the emission,’ said Franco Fois, NCI Agency senior scientist and ARTEMIS lead engineer.

If a signal is found to be from an sUAS, the system will also try to calculate the direction of arrival of the signal to localise the unmanned aircraft. The system can also narrow down the location of the operator on the ground.

The identification of the type of drone was a key driver of this work, since that information determines the threat response. Very high percentages of correct classification were achieved in experiments using up to 10 different sUAS types.

‘ARTEMIS serves to prove that it is possible, with low-cost equipment, to counter the threat posed by commercial drones,’ said Edison Cristofani, radar and signal processing engineer at the NCI Agency.

He added that the use of software-defined radios and virtual instrumentation in ARTEMIS is a  ‘game changer’.

As part of our promise to deliver comprehensive coverage to our Defence Insight and Premium News subscribers, our curated defence news content provides the latest industry updates, contract awards and programme milestones.