Artificial intelligence (or AI) that has been developed by a University of Cincinnati doctoral graduate was recently assessed by subject matter expert and retired United States Air Force Colonel Gene Lee in a high-fidelity air combat simulator. Lee holds extensive aerial combat experience as an instructor and Air Battle Manager with a considerable amount of fighter aircraft expertise.
The AI, known as ALPHA, won the simulated scenario and Lee states the technology is the most aggressive, responsive, dynamic and credible AI he’s seen to date. Complete details on ALPHA, which is a significant breakthrough in the application of what’s known as genetic-fuzzy systems have been published in the most recent issue of the Journal of Defense Management. This application is specifically designed for use with Unmanned Combat Aerial Vehicles (or UCAVs) in simulated air-combat missions for the purpose of research.
ALPHA is currently being viewed as a research tool for both manned and unmanned teaming in a simulation environment. Previously, ALPHA has outperformed a baseline computer program that was used in the past by the Air Force Research Lab during research. It was only after early iterations of ALPHA bested other computer program opponents that Lee then took to manual controls against a mere mature version of ALPHA created last October. Lee was not able to kill a single target when fighting up against ALPHA, but was also shot out of the air every time he engaged in the simulator.
Since then, ALPHA has continued to defeat other experts as well, and is even able to win out against these human experts when its aircraft is deliberately given a handicapped in terms of speed, turning, missile capability and even sensors. Lee, for instance, has been flying against simulators since the 1980s and says his first encounter with ALPHA surprised him due to its ability to be so aware and reactive. It appeared the technology was aware of his intensions and reacted instantly to any changes in his flight and missile deployment. He says it knew how to defeat every shot he was taking, moving instantly between defensive and offensive actions as required.
Most AIs can be beat by an experienced pilot if they know what they are doing. In most cases, AIs simply are not able to keep up with the pressure and fast pace of combat-like scenarios. Lee has trained with thousands of U.S. Air Force pilots and has flown in several fighter aircrafts and even graduated from the U.S. Fighter Weapons School and says he still goes home feeling washed out, tired and drained when competing against ALPHA.
The goal of researchers involved is to continue to develop ALPHA, pushing its capabilities and continue to perform additional testing against other trained pilots. Fidelity is going to be increased which will come in the form of even more realistic aerodynamic and sensor models.
In the long term, teaming artificial intelligence with U.S. air capabilities will represent a revolutionary leap. Air combat as it is performed today by human pilots is a highly dynamic application of aerospace physics, skill, art and intuition to maneuver a fighter aircraft and missiles against adversaries, all moving at very high speeds. Today’s fighters fly at speeds that exceed 1,500 miles per hour while flying at altitudes of above 40,000 feet. Microseconds matter and the cost for a mistake are extremely high.
ALPHA aims to lessen the likelihood of mistakes since its operations already occur significantly faster than do those of other language-based consumer product programming. ALPHA actually can 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. To better explain just how fast that is, ALPHA is so fast that it can consider and coordinate the best tactical plan and precise responses within a dynamic environment over 250 times faster than ALPHA’s human opponents could blink.