The U.S. Air Force Test Pilot School and the Defense Advanced Research Projects Agency recently showcased the effectiveness of artificial intelligence algorithms in controlling the X-62A Variable In-Flight Stability Test Aircraft as part of DARPA’s Air Combat Evolution program. This groundbreaking demonstration took place at Edwards Air Force Base in California, where the AI-controlled X-62A VISTA aircraft went head-to-head against a manned F-16 plane in within-visual-range combat scenarios, commonly referred to as dogfighting.
During the test, key military personnel emphasized that the focus was not solely on the aircraft’s ability to engage in dogfighting but rather on harnessing autonomous artificial intelligence systems in the air. Bill Gray, the school’s chief test pilot, highlighted the significance of tackling dogfighting as a problem to advance the testing of autonomous AI systems across various tasks.
The X-62A ACE program marks a significant milestone as the first-ever implementation of machine learning-based autonomy in flight-critical platforms. Col. James Valpiani, the commandant of the Test Pilot School, commended the X-62A’s exceptional capabilities not only for research purposes but also for shaping the future generation of test leaders.
In addition to the Air Force, DARPA’s ACE program has enlisted partnerships with several prestigious organizations, including Johns Hopkins University, MIT’s Computer Science and Artificial Intelligence Laboratory, Calspan, Cubic, EpiSci, Lockheed Martin’s Skunk Works arm, and Shield AI. These collaborations underscore the collective effort to push the boundaries of AI technology within the realm of aviation.
This successful demonstration sets the stage for further exploration into the integration of autonomous AI systems in flight operations, paving the way for innovative advancements in military aviation technology.
