A Heron Systems-developed artificial intelligence ‘pilot’ on an F-16 Viper jet came out undefeated against a human Air Force fighter pilot in five rounds of simulated air combat as part of the Defense Advanced Research Projects Agency’s AlphaDogfight Trials, The Drive reported Thursday.
The three-day virtual tournament is part of the Air Combat Evolution program, which seeks to explore how AI and machine learning can support various aspects of aerial combat.
Lockheed Martin, Perspecta Labs, Aurora Flight Sciences, SoarTech, PhysicsAI, Georgia Tech Research Institute and EpiSys Science took part in the event to test their platforms against five different types of hostile threats developed by Johns Hopkins University Applied Physics Laboratory.
"Even though [dogfights are] probably less likely in the future, the need for an ability to handle that sort of situation won’t go away," Air Force Col. Daniel “Animal” Javorsek, program manager for ACE at DARPA, said of the AlphaDogfight effort and ACE in an interview with the Air Force Magazine. "We continue to use it as a gateway into these more demanding scenarios like suppression of enemy air defenses or offensive counter-air."
The ACE program’s initial phase is slated to conclude in 2021 and will include test flights of experimental AI-based systems to assess autonomous capabilities on jet-powered and propeller-driven unmanned aircraft. DARPA plans to transition those platforms onto larger types of aircraft through two subsequent phases.