AIs Spot Drones with Help from a Fly Eye
Unauthorized drones in commercial airspace are causing more frequent problems around the world. As these remotely piloted flying machines become ever cheaper and more accessible, there is growing concern they will become increasingly disruptive. Now a group of researchers has developed a special detection system to help stop troublesome drones. They’ve come up with an algorithm designed by reverse engineering the visual system of the hoverfly. These flies, like some other kinds of buzzing insects, have extremely keen vision and fast reaction times. Such abilities stem from their compound eyes, which take in a lot of information simultaneously, and from the neurons that process that information — which are very good at separating relevant signals from meaningless noise. Fulton Schools Assistant Professor Ted Pavlic, associate director of research for ASU’s Biomimicry Center, says the achievement by these scientists is yet another valuable example of how much can potentially be learned from nature about signal processing.