An Artificial Intelligence program developed by a doctoral graduate at University of Cincinnati recently defeated Retired US Air Force Colonel and Air Combat Expert Gene Lee. The impressive thing about this bout was that the AI was operating on the famous $35 computer Raspberry Pi. The AI is called ALPHA. The bout was performed in a simulated environment. Gene Lee said, ALPHA is “the most aggressive, responsive, dynamic and credible AI I’ve seen to date.”
ALPHA already has a good past. ALPHA had outperformed the computer programs used by the Air Force Research Lab for research. ALPHA is being considered as future research tool for more improved air combat simulator AI.
Gene Lee who has a great experience of working with simulators and AIs said, “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.”
Even though ALPHA is complex and powerful AI it only needs a low budget computer not supercomputers to perform its action. This paves a way for more advance and low cost AIs to be used in military operations.
According to a lead engineer at Air Force Research Laboratory, “ALPHA shows incredible potential, with a combination of high performance and low computational cost that is a critical enabling capability for complex coordinated operations by teams of unmanned aircraft.”
The AI algorithm that the creators developed is entirely based on If and Else statements of computer programming language. According to them, owing to the simplicity of the algorithm the program can be validated and verified easily. An air combat expert can also be used to improve and impart the expertise into the algorithm.
More information about the simulation battle can be found here. Details about ALPHA can be found in the document here.