An AI-controlled virtual F-16 has defeated a human F-16 pilot 5-0 in a virtual dogfight hosted by the Defense Advanced Research Projects Agency (DARPA).

Heron Systems’ AI ‘Falco’, beat a senior F-16 pilot wearing a VR helmet in the five round virtual challenge. Falco’s triumph marks a major milestone in the development of artificial intelligence and the use of the technology in aerial combat. Falco joins the likes of IBM’s Deep Blue computer beating chess world champion Garry Kasparov in 1997, and Google DeepMind’s AlphaGo defeating Go world champion Lee Sedol in 2016.

Heron Systems, pilot Falco defeated other AI adversaries from Lockheed Martin, Perspecta Labs, PhysicsAI, SoarTech, Aurora Flight Sciences, EpiSys Science and the Georgia Tech Research Institute for the chance to face-off against an experience human pilot in the simulator.

AI “comes of age”

Col Dan Javorsek, programme manager at Darpa’s Strategic Technology Office said: “We’ve gotten an opportunity to watch AI come of age [against] a very credible adversary in the human pilot.”

“The AlphaDogfight Trials is all about increasing trust in AI. If the champion AI earns the respect of an F-16 pilot, we’ll have come one step closer to achieving effective human-machine teaming in air combat.”

The human pilot, who went by the name ‘Banger’, said he could not match the twisting techniques used by Falco in human-to-human air combat. AI pilots have a significant advantage as they are not affected by the extreme G forces that occur when manoeuvring at high speeds. “Standard things we do as fighter pilots are not working,” he said during a livestream of the event.

But DARPA said there is still some way to go before AI fighter pilots are ready to take to the skies as the virtual dogfight was limited to a guns-forward scenario such as a WW2 dogfight, rather than modern aerial combat.

ACE programme aims to incorporate autonomous systems into warfare

The AlphaDogfight is part of the agency’s Air Combat Evolution (ACE) programme which aims to increase trust in combat autonomy as the US envisions a future where autonomous systems become more prevalent in warfare.

DARPA said: “In a future air domain contested by adversaries, a single human pilot can increase lethality by effectively orchestrating multiple autonomous unmanned platforms from within a manned aircraft.

Human role will shift from single platform operator to mission commander

“This shifts the human role from single platform operator to mission commander. In particular, ACE aims to deliver a capability that enables a pilot to attend to a broader, more global air command mission while their aircraft and teamed unmanned systems are engaged in individual tactics.”

Heron Systems AI used a reinforced learning approach where software undergoes a task numerous times and learns by trial and error. The dogfight did not simulate beyond the line of sight engagements using missiles, but the tests showed that AI could handle itself in a close combat situation. This would be important in the future which could see swarms of drones facing off against each other.

DARPA said it intends to take its AI to Nellis Air Force Base where other pilots will be able to take on the AI.

Subscribe to the FINN weekly newsletter