Machine Learning Algorithm Offers Real-Time Warnings of a Drone's Malicious Intent

Researchers at the Universities of Cambridge and Birmingham have developed a system for real-time detection of drone intent — rather than simply presence — which they hope can help prevent them from straying into restricted areas like airports.

The team's work is inspired by a 2018 event that shut-down Gatwick Airport, stranding thousands of passengers as flights were diverted and grounded over reports of an unauthorized drone — reports which, to this day, have yet to be substantiated.

"While we don’t fully know what happened at Gatwick, the incident highlighted the potential risk drones can pose to the public if they are misused, whether that’s done maliciously or completely innocently," explains co-author Bashar Ahmad, PhD. "It’s crucial for future drone surveillance systems to have predictive capabilities for revealing, as early as possible, a drone with malicious intent or anomalous behavior."

"There needs to be some sort of automated equivalent to air traffic control for drones," adds Simon Godsill, project lead and professor at Cambridge’s Department of Engineering. "But unlike large and fast-moving targets, like a passenger jet, drones are small, agile, and slow-moving, which makes them difficult to track. They can also easily be mistaken for birds, and vice versa."

The solution: An algorithm that is capable of using existing surveillance systems determine a drone's intent — instead of simply its location, velocity, or heading — and to figure out the likelihood of a drone reaching a particular waypoint, like an airport, at a particular time.

"In tests, our system was able to spot potential threats in seconds, but in a real scenario, those seconds or minutes can make the difference between an incident happening or not," claims first author Jiaming Liang, PhD. "It could give time to warn incoming flights about the threat so that no one gets hurt."

The team's work was presented at the Sensor Signal Processing for Defence (SSPD) Conference 2021, but has not yet been publicly released.