In a series of flight combat simulations, the A.I. successfully dodged Lee, and shot him down every time. In a statement, Lee called it “the most aggressive, responsive, dynamic and credible A.I. I’ve seen to date.”
Having said that, Lee is experienced when it comes to aerial combat is a remarkable understatement. He is an adversary tactics instructor who has trained thousands of U.S. Air Force pilots. He is also a former Air Battle Manager who has been fighting against AI opponents in air combat simulations since the 1980s. He’s controlled or flown in thousands of air-to-air intercepts as mission commander or pilot. Yet, not even once he was successful in winning against ALPHA. Certainly, it did not even when the researchers intentionally handicapped ALPHA’s aircraft, hampering it in terms of speed, turning, missile capability, and sensor use. “I was surprised at how aware and reactive it was. It seemed to be aware of my intentions and reacting instantly to my changes in flight and my missile deployment. It knew how to defeat the shot I was taking. It moved instantly between defensive and offensive actions as needed,” Lee said. He added that with most AIs, “an experienced pilot can beat up on it (the AI) if you know what you’re doing. “Sure, you might have gotten shot down once in a while by an AI program when you, as a pilot, were trying something new, but, until now, an AI opponent simply could not keep up with anything like the real pressure and pace of combat-like scenarios”. The A.I., dubbed ALPHA, was developed by Psibernetix, a company founded by University of Cincinnati doctoral graduate Nick Ernest, in collaboration with the Air Force Research Laboratory. According to the developers, ALPHA was specifically designed for use with Unmanned Combat Aerial Vehicles (UCAVs) in simulated air-combat missions for research purposes. Currently, Alpha is viewed as a research tool for manned and unmanned teaming in a simulation environment. The secret to ALPHA’s superhuman flying skills is a decision-making system called a genetic fuzzy tree system, which is a subtype of fuzzy logic algorithms. The system approaches complex problems much like a human would by breaking the bigger task into smaller subtasks, which include high-level tactics, firing, evasion, and defensiveness, says Nick Ernest, who founded the company Psibernetix to develop ALPHA. It can calculate strategies based on its opponent’s movements 250 times faster than a person can blink – a speed that gives it an undeniable advantage in an arena where a mix of advanced skills in aerospace physics and intuition are required. When Lee flies against ALPHA in hours-long sessions that mimic real missions, he says, “I go home feeling washed out. I’m tired, drained and mentally exhausted. This may be artificial intelligence, but it represents a real challenge.” Details on Alpha are published in the most-recent issue of the Journal of Defense Management.
