OPINION | This article contains opinion. This site is licensed to publish this content.
The US Air Force conducted the first successful dogfight between an AI-controlled experimental aircraft and a manned fighter jet.
The AI-jet, an F-16 variant called the X-62A VISTA, engaged in close-range aerial engagements with an F-16, demonstrating machine learning-based autonomy for flight-critical systems.
“The potential for autonomous air-to-air combat has been imaginable for decades, but the reality has remained a distant dream up until now,” Secretary of the Air Force Frank Kendall stated. “In 2023, the X-62A broke one of the most significant barriers in combat aviation. This is a transformational moment, all made possible by breakthrough accomplishments of the X-62A ACE team.”
Over 21 test flights involving more than 100,000 lines of software changes, the AI was able to dogfight without pilots needing to disengage the autonomous system.
This represented a breakthrough in enabling autonomous air combat.
“We have to be able to trust these algorithms to use them in a real-world setting,” Lt. Col. Ryan Hefron said.
“The first-ever use of machine-learning-based autonomy in flight-critical systems will serve as a foundation for future aerospace AI advances that are both safer and more reliable in both commercial and defense applications,” the Air Force wrote.
Continued testing will advance the use of machine learning for both commercial and military aviation applications.
“It’s very easy to look at the X-62A ACE program and see it as under autonomous control, it can dogfight, but that misses the point,” said Bill Gray, the Test Pilot School’s chief test pilot. “Dogfighting was the problem to solve so we could start testing autonomous artificial intelligence systems in the air. Every lesson we’re learning applies to every task you could give to an autonomous system.”
The program involves collaboration between government, academic and industry partners to solve challenges around developing and trusting autonomous flight systems.
