The pilotless fighter jet of the future could be a step closer, after a recent successful experiment by the US Air Force and the University of Cincinnati.
The experiment pitted a retired Air Force air combat instructor against a fuzzy logic artificial intelligence computer program called ALPHA. The result? ALPHA won every time. The human pilot was unable to score a kill against ALPHA after repeated attempts, and was shot down every time, after protracted battles in a flight simulator. The mission featured two human-controlled blue fighters versus four red. ALPHA’s red fighters had shorter-range missiles and a reduced missile payload compared to the blue opposing forces.
The Journal of Defence Management report said the pilot was easily able to defeat the baseline fuzzy logic system used by the Air Force research laboratory. But after being defeated by ALPHA he described it as as ‘the most aggressive, responsive, dynamic and credible AI (he’d) seen-to-date.’
‘It seemed to be aware of my intentions and reacting instantly to my changes in flight and my missile deployment,’ he told the university’s UC magazine.
Discussing the experiment, the journal report said manned-unmanned autonomous teaming (MMAT) in an air combat environment would represent a revolutionary leap in capability of airpower in the near future, comparable to the introduction of unmanned aerial vehicles in the 1990s.
‘The human mind is an extremely powerful machine that will likely always have unbeatable performance in certain areas. However, the speeds at which ALPHA can intelligently operate serve as a distinct advantage within the context of air-to-air combat,’ the journal said.
‘Combining these strengths in a mixed manned and unmanned fighter squadron could prove to be an extremely effective fighting force. ALPHA-controlled aircraft would happily volunteer to take risky tactics and have the manned craft perform safer support roles.’