Artificial Intelligence Outflies A Fighter Pilot
Unmanned aircraft capabilities took a big leap forward when an expert fighter pilot found he was no match for ALPHA. The artificial intelligence system was developed by Psibernetix, founded by a University of Cincinnati graduate. Gene Lee, a retired Air Force colonel taking part in the research, told UC Magazine this week that ALPHA is unprecedented. “I was surprised at how aware and reactive it was,” he said. An expert in aerial combat who has flown simulated scenarios for years, Lee found that when he went up against the program in the sim, he couldn’t put a scratch on his target. “It seemed to be aware of my intentions and reacting instantly to my changes in flight and my missile deployment,” he said.
Lee’s simulator flights were part of recent research trials by Psibernetix to test its newest version of the system. Its findings were published (PDF) in the current issue of the Journal of Defense Management. Company founder and CEO Nicholas Ernest developed ALPHA with what he calls a “Genetic Fuzzy Tree” system that allows the program to make the quick, complex decisions required for aerial combat. “The goal is to continue developing ALPHA, to push and extend its capabilities, and perform additional testing against other trained pilots,” Ernest told the magazine. “Fidelity also needs to be increased, which will come in the form of even more realistic aerodynamic and sensor models.”