Drone pilot Ken Loo was brought in by the team at NASA to race against the artificial intelligence-powered drone. Loo averaged 11.1 seconds for the drone loop while the autonomous drone averaged 13.9 seconds.
But the course was tricky. “This is definitely the densest track I’ve ever flown,” says Loo in a statement released by NASA. “One of my faults as a pilot is I get tired easily. When I get mentally fatigued, I start to get lost, even if I’ve flown the course 10 times.”
Indeed, the AI drone was steadier, says NASA.
“We pitted our algorithms against a human, who flies a lot more by feel,” says Rob Reid, the project’s task manager, in the written statement. “You can actually see that the A.I. flies the drone smoothly around the course, whereas human pilots tend to accelerate aggressively, so their path is jerkier.”
The NASA researchers who built the robot drone work at NASA’s Jet Propulsion Laboratory in Pasadena, Calif. Google paid for two years of autonomous drone research at NASA and the race was the culmination of that.
Of course, developing autonomous drone technology is good for more than just racing. Such drones will be able to check on inventory in warehouses, help search and rescue operations in a disaster and potentially help robots navigate a space station.
The NASA team built three drones (with fly names: Batman, Joker and Nightwing) and programmed them with algorithms, so that the drones would be able to fly quickly without running into objects.
“One day you might see them racing professionally!” says Reid.