The AI algorithm, called ARTUu, was in charge of tactical navigation and sensor employment during a simulated missile strike as part of a reconnaissance mission. The algorithm used the aircraft’s radar in detecting enemy launchers, while the pilot was responsible for finding hostile aircraft.
The pilot transitioned the sensor control to the AI algorithm after liftoff. During the flight, the algorithm operated the sensor using learned insights from more than 500,000 computer simulated training iterations.
“ARTUu’s groundbreaking flight culminates our three-year journey to becoming a digital force,” said Will Roper, assistant secretary of the Air Force for acquisition, technology and logistics and a three-time Wash100 Award recipient, “Putting AI safely in command of a U.S. military system for the first time ushers in a new age of human-machine teaming and algorithmic competition. Failing to realize AI’s full potential will mean ceding decision advantage to our adversaries.”
Researchers at Air Combat Command’s U-2 Federal Laboratory developed and trained the AI algorithm to carry out in-flight tasks.