Autonomous drones will drive away flocks of birds from airports

Caltech Institute engineers have developed an algorithm that allows drones to scare away birds without human intervention. In the future, the system will be introduced to airports around the world and will help save more than a billion dollars a year.

Usually, unmanned aerial vehicles are prohibited from being near airports. Man-operated unmanned aerial vehicles can be unreliable: if the operator becomes too aggressive and frightens the birds, the flock can fly apart and become even more uncontrollable. Therefore, a team of researchers from Caltech has developed an algorithm that trains drones to autonomously drive away flocks of birds from airport airspace.

Engineers said they were inspired by the incident of 2009 with the flight of US Airways-1549, which became known as the “Miracle on the Hudson.” At the exit from the airport, the plane hit a flock of geese and lost all engine power. The only reason he did not crash was because experienced pilots managed to make a water landing on the Hudson River. Subsequently, the commander of this flight Chesley Sullenberg will shoot a film with Tom Hanks.

Miracle on the Hudson

Sun Yu Chang, a professor in the field of aerospace engineering and lead author of the project, fears that the next time the story may not be so successful:

One hundred fifty-five passengers of flight 1549 were saved only thanks to the talent of the pilots. It made me think about what would happen if the commander of the plane’s crew made a different decision. Therefore, I began to look for ways to protect airspace from birds, using my skills in autonomy and robotics.

')

Now for repelling birds, airports use several strategies: changing the environment to make it less attractive to birds (lack of fields, trees, etc.), using trained falcons attacking flocks, and using manned UAVs. All these methods turn out to be weakly effective, and only slightly reduce the chance of an aircraft colliding with birds.

When you are trying to get the birds out of a certain airspace, you need to be very precise. If your drone is too far, it will not scare away the pack. And if he gets too close, you risk dispelling the pack and making it completely unmanageable. With a manned vehicle every time to find the exact zone is almost unreal.

In the implemented project of Sun Yu Chang ( PDF ), the cameras record how a pack is formed and determine its position. The computer system forms a further pattern of the pack's behavior, predicts its trajectories and gives commands to the drone. And he automatically chooses how to fly, so that the birds are guaranteed not to fall into the “protected” zone.

Each bird in the wedge responds to the behavior of its neighbors. An exactly positioned drone can force individuals on the edge to slightly change the direction of their movement - which affects the birds nearest to them, which affects the birds deeper in the flock, and so on, until it forces the whole group to do the necessary maneuver.

Work on the project Sun Yu Chang began in 2013, when he worked at the University of Illinois. Funding provided by the US National Science Foundation ( NSF Career ). At first, Chang wanted to build a homing robot with flapping wings - which would imitate the behavior of a falcon. So his team had a completely new type of drone, " Bat Bot ", resembling a bat. But as a result of the tests, it turned out that the standard quadcopter scares the birds no worse (and costs less).

Mosedron Song Yu Chang

So that the drone could automatically chase the birds, Chung and his colleagues built a mathematical model of the flock's work, describing how it keeps together and how it reacts to the danger of setting at a certain angle. Old algorithms designed for sheep herd were taken as a basis, only they were expanded for three dimensions, instead of two. Professor Chang’s previous research on spacecraft and drone swarms also turned out to be unexpectedly useful. From space, it may be information about new flocks found, and to protect a large airport will need to use at least a dozen drones.

The team successfully tested its algorithm using a ready-made multicopter near the field in Korea. They discovered that he himself could keep a flock of dozens of birds at a distance from the “protected zone”. Researchers still need to find a way to scale up the project before the technology can completely replace trained falcons and manual-controlled drones. But Sun Yu Chang says it’s worth it:

Birds cause military and civil aviation damage of $ 400 million per year in the United States, and $ 1.2 billion in the world. If we can reduce this damage by at least a few percent, the project will more than justify itself. Also during the work it turned out that vineyards are facing a similar problem. Crows eat the fruit before the harvest. Imagine a drone, autonomously rising above the field, and daring away any intruders from the territory. This is the future we are working on.