The battle between drones and anti-drone technology is heating up. As drones are now highly maneuverable, special technologies are being developed to neutralize them for reasons of security and even for military applications. And even the public has been known to take down drones by shooting at them.
Most drones just aren’t very good at avoiding incoming objects, especially if those objects are moving fast. Drones can often avoid static obstacles like buildings or trees, but even the most advanced drones struggle to react to dynamic objects and adjust their trajectories accordingly. This makes them vulnerable to being shot down or interfered with, but it also means they are not great at avoiding collisions with other drones or with people or aircraft.
But now a team from the University of Zurich has developed a drone which can dodge, swoop, and dive to avoid an incoming object. The drone is shown avoiding a soccer ball which the researchers throw at it from various angles, traveling at speeds of nearly 32 feet per second. It is able to avoid the football in a dynamic and autonomous manner, meaning it can react very quickly to nearby moving objects and avoid collisions.
And the drone doesn’t use an external position tracking system as you might imagine. It uses its own onboard sensors, using a technique called visual-inertial odometry to estimate the location of the incoming ball. It works by using a type of camera with extremely low latency, called an event camera, which tracks the movement of the ball and can relay this information to the drone’s motors to control its movements.
“We wanted to really push the boundaries and see what these robots are capable of,” Davide Falanga, researcher at the University of Zurich, said to The Verge. Even though these types of cameras are still rare due to their high price and early stage of development, the researchers believe they will eventually become available to the mainstream once they are more affordable: “Absolutely I think in the long run I think we’ll see more and more usage of these cameras,” Falanga said.
The research is published in the journal IEEE Robotics and Automation Letters [pdf link].
