Remember when IBM’s Deep Blue won against Gary Kasparov at chess in 1996, or Google’s AlphaGo crushed the top champion Lee Sedol at Go, a much more complex game, in 2016? These competitions where machines prevailed over human champions are key milestones in the history of artificial intelligence. Now a group of researchers from the University of Zurich and Intel has set a new milestone with the first autonomous system capable of beating human champions at a physical sport: drone racing.
The AI system, called Swift, won multiple races against three world-class champions in first-person view (FPV) drone racing, where pilots fly quadcopters at speeds exceeding 100 km/h, controlling them remotely while wearing a headset linked to an onboard camera.
Learning by interacting with the physical world
“Physical sports are more challenging for AI because they are less predictable than board or video games. We don’t have a perfect knowledge of the drone and environment models, so the AI needs to learn them by interacting with the physical world,” says Davide Scaramuzza, head of the Robotics and Perception Group at the University of Zurich — and newly minted drone racing team captain.
Until very recently, autonomous drones took twice as long as those piloted by humans to fly through a racetrack, unless they relied on an external position-tracking system to precisely control their trajectories. Swift, however, reacts in real time to the data collected by an onboard camera, like the one used by human racers. Its integrated inertial measurement unit measures acceleration and speed while an artificial neural network uses data from the camera to localize the drone in space and detect the gates along the racetrack. This information is fed to a control unit, also based on a deep neural network that chooses the best action to finish the circuit as fast as possible.
Training in an optimised simulation environment
Swift was trained in a simulated environment where it taught itself to…