Tactical AI beats US Air Force colonel in dogfighting simulation

Whether it’s Deep Blue beating Garry Kasparov at chess, Watson defeating Ken Jennings at Jeopardy!, or Google DeepMind’s AlphaGO besting Lee Sedo at Go, artificial intelligence can’t be underestimated when it comes to taking on the champions and winning.

Well, chalk another win up for AI!

That’s because a new AI system called ALPHA — developed by recent University of Cincinnati doctoral graduate Nick Ernest, now CEO of Psibernetix — recently defeated retired United States Air Force Colonel Gene Lee in an air combat simulator. Not only did Colonel Lee, who has extensive aerial combat experience as an instructor, fail to kill ALPHA’s aircraft during combat, he was also repeatedly shot out of the air by the bot.

According to Lee, ALPHA is “the most aggressive, responsive, dynamic and credible AI I’ve seen to date.”

“ALPHA is an incredibly difficult opponent to face,” Psibernetix CEO Nick Ernest tells Digital Trends. “Even flying against other pilots when ALPHA has severe handicaps to a number of its systems — including speed, turning, missile capability and sensors — it is able to win. There is additional work to be done to both increase ALPHA’s capabilities and improve its model fidelity, but these results represent a significant breakthrough.”

But haven’t there been hard combat video game simulators for years? What is it that makes ALPHA any different to any of the other popular combat sim video games out there?

“Typically, video games have extremely simplified underlying simulation mechanics,” Ernest notes. “These immense simplifications greatly reduce the scope of the problem. AFSIM, the environment ALPHA flies in for this study, is a high-fidelity simulator, which can realistically represent a modern air combat environment with appropriately behaving models for aircraft, sensors, and weapons. Rather than relying on cheating by giving the AI an unfair advantage with its capabilities, we create virtual opponents that present real challenges through legitimate means.”

As for the future, Earnest says he sees tools like ALPHA playing out as next-gen autopilots in real aircraft: possibly as part of manned/unmanned teams in the theater of air combat. “This isn’t just about reaction times; the raw quantity of information flying around is staggering,” he says. “Calculations need to be performed constantly on this massive flow of data, and AI systems are perfectly suited for that job.”

Move over Maverick. In 2016, it turns out you’re no longer the Top Gun!

from Planet GS via John Jason Fallows on Inoreader http://ift.tt/299KjEB
Luke Dormehl