In a groundbreaking achievement, the US Air Force has publicly confirmed the first successful dogfight between a fighter jet piloted by artificial intelligence (AI) and a human-controlled aircraft. The dogfight was conducted as part of the Air Combat Evolution (ACE) program, marking a transformative moment in aerial warfare.
The US Air Force has publicly confirmed the first successful dogfight between a fighter jet piloted by artificial intelligence (AI) and a human-controlled aircraft. Conducted as part of the Air Combat Evolution (ACE) program, the dogfight represents a significant milestone in the advancement of AI technology.
The dogfight pitted a manned F-16 against the X-62A VISTA (Variable In-flight Simulator Test Aircraft), an experimental variant of the F-16 equipped with live AI agents. The agents were installed in the X-62A less than a year before the successful dogfight test.
"The potential for autonomous air-to-air combat has been imaginable for decades, but the reality has remained a distant dream up until now," said Secretary of the Air Force Frank Kendall. "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."
As an initial part of the test, flight safety was established using defensive maneuvers before progressing into "offensive high-aspect nose-to-nose engagements where the dogfighting aircraft got as close as 2,000 feet at 1,200 miles per hour."
Test pilots were on board the X-62A during the dogfight but didn't have to switch off the AI system. They had the ability to disengage the AI, but they didn't need to activate the safety switch at any time during the dogfights.
"We have to be able to trust these algorithms to use them in a real-world setting," said Lt. Col. Ryan Hefron, ACE program manager for DARPA.
The Air Force explained that traditional autonomous control of aircraft has been executed for decades, but machine learning has historically been prohibited due to high risk and a lack of independent control. Across 21 test flights, teams involved with the test made more than 100,000 lines of flight-critical software changes.
DARPA and the U.S. Air Force Test Pilot School will continue to advance testing with machine learning, with the X-62A VISTA serving a variety of research customers and providing academic lessons for future tests and programs.
"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 Air Force noted that the ACE program involves collaboration between a variety of partners from government, private industry, and academia. The Air Force Test Center, Air Force Research Laboratory, DARPA, and the Air Force Test Pilot School are among the government partners, while academic partners include Johns Hopkins University and MIT's Computer Science and Artificial Intelligence Laboratory.
Industry partners in the ACE program include Calspan Corp., Cubic Corp., EpiSci, Lockheed Martin Skunk Works, and Shield AI.
The Air Force has further stated that the X-62A VISTA will be used to evaluate the performance of different AI algorithms in combat scenarios and to explore the limits of autonomous control. The program is expected to provide valuable insights for the development of future autonomous aerial combat systems.
In conclusion, the successful dogfight between an AI-piloted fighter jet and a human-controlled aircraft represents a major breakthrough in aerial combat. The test results demonstrate the potential of AI to revolutionize traditional aerial warfare and open up new possibilities for the future of military engagement.
