Last year, an American X-62A VISTA aircraft was successfully flown by artificial intelligence (AI) for the first time in a simulated dogfight with a human pilot of an F-16 fighter jet, according to the Air Force's Air Force Research Laboratory (AFRL). did. ) was recently revealed.
A “groundbreaking achievement in aerospace machine learning” was credited to the U.S. Air Force Test Pilot School (USAF TPS) and the Defense Advanced Research Projects Agency (DARPA). This breakthrough was part of DARPA's Air Combat Evolution (ACE) program. The first test was followed by a number of similar dogfights.
Click here to follow our WhatsApp channel
“The possibility of autonomous air-to-air combat has been imaginable for decades, but reality has remained a distant dream until now. In 2023, the X-62A will be one of the most important obstacles in combat aviation. “This is a transformative moment made possible by the breakthrough work of the X-62A ACE team,” AFRL said in a statement.
This release marks less than a year since the teams involved “installed a live AI agent on the X-62A's systems” and “the first AI-on-human visual range engagement known as air combat.” It became clear that we had proven it. . He did not say when the experiment took place, but said it was at Edwards Air Force Base in California.
The X-62A has a safety pilot on board who can disable the AI, but the release added that the test pilot “was not required to activate the safety switch” at any point during the dogfight with a manned F-16. .
The dogfight involved “aggressive high-aspect nose-to-aircraft combat,” with AI-controlled manned aircraft approaching as close as 2,000 feet at 1,200 miles per hour, AFRL said.
The X-62A utilized “non-deterministic artificial intelligence” to engage in these dogfights.
AFRL's release states that “the first use of machine learning-based autonomy in flight-critical systems” will lay the foundation for future aerospace AI development that will be safer and more reliable for both commercial and defense applications. It says that it will be.
AFRL also said that while air combat is the primary test scenario, it is not the ultimate goal.
Bill Gray, chief test pilot for the U.S. Air Force TPS, explained in an AFRL release: “It's very easy to look at the X-62A ACE program and think it's under autonomous control and capable of air combat, but that's missing the point. To start testing autonomous artificial intelligence systems in the air , there is a problem to be solved.”
Gray added, “All the lessons we've learned apply to any task we can give an autonomous system.”
