Newly Developed Artificial Intelligence Defeats Human Tactical Experts in Aerial Combat Simulation
A newly developed Artificial Intelligence from the University of Cincinnati has been proclaimed the victor after being put to an aerial combat simulation against human tactical experts.
The new AI, dubbed as ALPHA, has already outperformed the baseline computer program previously used by the Air Force Research Lab for research, defeating other AI opponents in its early iterations.
In October 2015, Retired U.S. Air Force Colonel Gene Lee has given the chance to face off ALPHA in a simulated aerial combat. Despite extensive aerial combat experience and considerable fighter aircraft expertise, Lee was completely beaten by ALPHA, without even scoring a kill. Lee described ALPHA as "the most aggressive, responsive, dynamic and credible AI" he had seen up to date.
"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," commented Lee in a statement.
Since then, other aerial tactical experts challenged ALPHA. However, ALPHA defeated every single one of them. Even when the aircraft controlled by ALPHA was deliberately handicapped in terms of speed, turning, missile capability and sensors, the new AI managed to defeat human pilots.
According to a paper published in the Journal of Defense Management, ALPHA has the ability to take in the entirety of sensor data, organize it, create a complete mapping of a combat scenario and make or change combat decisions for a flight of four fighter aircraft in less than a millisecond, widely surpassing human capabilities.
Researchers believe that ALPHA will be the new face of air combat. ALPHA is equipped with an onboard battle management system capable of processing situational awareness, determining reactions, selecting tactics and managing weapon use, making it possible for the AI to simultaneously evade dozens of hostile missiles, take accurate shots at multiple targets, coordinate actions of squad mates, and record and learn from observations of enemy tactics and capabilities.
"ALPHA would be an extremely easy AI to cooperate with and have as a teammate. ALPHA could continuously determine the optimal ways to perform tasks commanded by its manned wingman, as well as provide tactical and situational advice to the rest of its flight," said Kelly Cohen, an aerospace professor at University of Cincinnati, in a press release.