Engadget cited aerospace research by the University of Cincinnati in a story examining work by the Air Force Research Lab to create an autonomous drone that can defeat a human pilot in aerial combat.
From Engadget:
The US Air Force has long been exploring the way artificial intelligence (AI) can assist in its operations - back in 2016 we saw combat AI beat some of the Air Force's top tactical experts, for example. Now, researchers are working on an autonomous drone designed to take down a piloted plane in air-to-air combat, with a showdown slated for July 2021.
UC's artificial intelligence project was an international revelation in 2016 as it demonstrated for the first time the vast potential for artificial intelligence to outwit human reflexes in a dogfight. UC's AI dubbed ALPHA was able to outflank retired U.S. Air Force Col. Gene Lee in simulation after simulation at the Air Force Research Lab at Wright-Patterson Air Force Base.
Lee called ALPHA "the most aggressive, responsive, dynamic and credible AI I've seen to date."
UC College of Engineering and Applied Science graduate Nick Ernest, who developed ALPHA, used the project to launch a Cincinnati startup company called Psibernetix. Ernest last year sold his company to the French arms manufacturer Thales.
The system Ernest developed used a type of machine learning called fuzzy logic in which the AI's decisions could be mathematically verified and validated, according to Thales.
Thales' senior vice president of avionics Gil Michielin called the system "a game-changer."
Ernest was a student of UC aerospace engineering professor Kelly Cohen, the interim department head. Cohen and his students continue to push the boundaries of autonomous systems in his UAV Master Lab.
