Artificial intelligence can beat us at chess, Go, the game current Jeopardy, and a rising number of completely totally different occupations throughout the workplace. But how does it fare in opposition to human pilots within the case of inauspicious them on the exhilarating new sport of drone racing? Researchers at NASA’s Jet Propulsion Laboratory in Pasadena, California, not too way back decided to hunt out out — by pitting a expert human drone pilot in opposition to racing drones managed by cutting-edge A.I. machine intelligence.

Held on October 12, the Google-funded race involved a timed trial between A.I. drones named Batman, Joker, and Nightwing, powered by Google’s Tango know-how. Against them — serving as a result of the guide of non-Google, non-NASA humanity — was world-class drone pilot Ken Loo.

“We pitted our algorithms against a human, who flies a lot more by feel,” Rob Reid, of the Jet Propulsion Lab, talked about in a assertion. “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.”


Loo described the obstacle course as, “definitely the densest track I’ve ever flown.” He was in a place to achieve the higher speeds all through the race and pulled off additional spectacular acrobatics. Ultimately, he averaged 11.1 seconds for his official laps. However, he moreover admitted to getting “mentally fatigued” by the demanding course and flew a lot much less consistently than the computer-controlled drones, which averaged 13.9 seconds.

In totally different phrases, humanity received right here out of the opponents as messier, nonetheless additional inventive, whereas the A.I.-powered bot exhibited machine-like precision and consistency.

The outcomes of the October 22 race put folks throughout the worthwhile place for now, although the A.I. drones nonetheless carried out impressively correctly. In reality, NASA seems unwilling to cede victory to us fleshy folks for prolonged, since Reid insists that, “Our autonomous drones can fly much faster. One day you might see them racing professionally!”

Looking forward, NASA hopes that the camera-based localization and mapping utilized sciences involved throughout the evaluation may be used for a variety of functions — just like checking inventory in warehouses, performing search and rescue missions at disaster web sites, and even serving to robots navigate by home stations.

Like what you read? Follow us on Facebook, Follow us on Twitter, Follow us on Instagram and Subscribe by means of FeedBurner.

Enter your e-mail sort out:

Delivered by FeedBurner