The Defense Advanced Research Projects Agency completed the first flight tests of artificial intelligence algorithms on a Lockheed Martin-built modified F-16 fighter jet, dubbed X-62A Variable In-flight Simulator Test Aircraft, in December.
The AI algorithms developed through DARPA’s Air Combat Evolution program were uploaded into VISTA at the Air Force Test Pilot School at Edwards Air Force Base in California, and demonstrated their capability to control a fighter aircraft during multiple flights, DARPA said Monday.
DARPA participants EpiSci, Shield AI, PhysicsAI and the Johns Hopkins Applied Physics Laboratory also gathered live-flight data during the series of tests, which included the Air Force Research Laboratory.
“We conducted multiple sorties [takeoffs and landings] with numerous test points performed on each sortie to test the algorithms under varying starting conditions, against various simulated adversaries, and with simulated weapons capabilities,” said Air Force Lt. Col. Ryan “Hal” Hefron, ACE program manager at DARPA.
“We didn’t run into any major issues but did encounter some differences compared to simulation-based results, which is to be expected when transitioning from virtual to live. This highlights the importance of not only flight testing advanced autonomous capabilities but doing so on testbeds like VISTA, which allowed us to rapidly learn lessons and iterate at a much faster rate than with other air vehicles,” added Hefron.
DARPA said the System for Autonomous Control of Simulation was integrated into VISTA as part of an upgrade to accommodate testing of F-16 AI agents developed under the ACE program.
Lockheed said its Skunk Works arm developed VISTA in collaboration with Calspan for the Air Force’s Test Pilot School. The open systems architecture-based aircraft comes with Calspan’s updated VISTA Simulation System and Lockheed’s Model Following Algorithm in addition to SACS.
Register now for the Potomac Officers Club’s 4th Annual Artificial Intelligence Summit, where DOD and GovCon leaders will share insight into recent AI advancements as well as outlook on cutting-edge development approaches for 2023 and beyond.