Published On: Mon, Nov 27th, 2017

Human commander beats AI in worker race


Anything we can do, AI can do better. Eventually.

On Oct 12, NASA put on a possess demonstration, pitting an AI-piloted racing worker opposite world-renowned worker commander Ken Loo.

Researchers during NASA’s Jet Propulsion Laboratory, who have spent a final dual years operative on worker liberty (which was saved by Google), built 3 tradition drones versed with cameras for prophesy and algorithms that would assistance them fly during high speeds while still avoiding obstacles.

The drones, named Batman, Joker, and Nightwing, used algorithms that were integrated with Google’s Tango technology, that helps AI map out 3D spaces.

These drones could fly adult to 80mph in a true line, though on this quite close course, were usually means to strike 40mph.

In a press release, NASA explained a pros and cons of both a unconstrained drones and a tellurian pilot. While a AI-powered drones were means to fly some-more consistently, they were also some-more discreet and, during times, ran into problems with suit fuzz during aloft speeds. On a other hand, Loo was means to learn a march after a few laps and fly with most some-more lively than a unconstrained drones, though is receptive to fatigue.

“This is really a densest lane I’ve ever flown,” Loo pronounced in a release. “One of my faults as a commander is we get sleepy easily. When we get mentally fatigued, we start to get lost, even if I’ve flown a march 10 times.”

Long story short, a AI and a tellurian started out with identical path times, though Loo eventually won out and finished adult with a faster normal path time than a AI.

The implications here are big: unconstrained drones might eventually be used for surveillance, puncture response, or register in warehouses.

About the Author

Leave a comment

XHTML: You can use these html tags: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>