An autonomous quadrotor drone has bettered the performance of two human pilots in a drone race for the very first time, primarily thanks to a new algorithm.

According to an article on techxplore.com, the algorithm, produced by a team of researchers from the University of Zurich (UZH), was able to guide the drone through a perfect racing line of the circuit by offering it information on the optimum levels of trajectory that it should reach. 

Further real-time information was captured by external cameras which notified the algorithm of the drone’s exact location. Despite the human pilots receiving some extra time on the circuit prior to the duel, the algorithm reigned victorious by recording the faster lap times.   

“Our drone beat the fastest lap of two world-class human pilots on an experimental race track,” said Davide Scaramuzza, who is the head of the Robotics and Perception Group at UZH.

“The novelty of the algorithm is that it is the first to generate time-optimal trajectories that fully consider the drones’ limitations.”

Going forward, the team will look to use onboard cameras as opposed to external cameras. 

“This algorithm can have huge applications in package delivery with drones, inspection, search and rescue, and more,” said Scaramuzza.