Publications
Partners
- For more stories, visit the Tech and Trends homepage.
The history of computing is filled with milestones marked when a machine finally overcame a human at a game it was thought fiendishly difficult for artificial intelligence (AI) to win.
Think how 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.
Now a group of researchers from the University of Zurich and Intel has set a new mark - building 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. Davide Scaramuzza, head of the Robotics and Perception Group at the University of Zurich, explains why Swift’s victory is such a remarkable achievement.
He says:
Until recently, autonomous drones took twice as long as those piloted by humans to fly through a racetrack.
Swift, however, reacts in real-time to the data collected by an onboard camera, like the one used by human racers.
Racing against 2019 Drone Racing League champion Alex Vanover, the 2019 MultiGP Drone Racing champion Thomas Bitmatta, and three-times Swiss champion Marvin Schaepper, the AI achieved the fastest lap, with a half-second lead over the best lap by a human pilot.
Watch the video above for more.
