An artificial intelligence (AI) system has beaten a US military pilot in a five-round challenge to demonstrate whether autonomous computer systems could be capable of flying fighter jets.
America’s Defence Advanced Research Projects Agency (DARPA) ran its final AlphaDogfight trial this week as part of a programme to see whether autonomous systems could defeat adversary aircraft in a simulated dogfight.
It’s a precursor to DARPA’s air combat evolution (ACE) programme, which will eventually fly live aircraft using AI algorithms to demonstrate that the technology will work in the real world.
The win came about during the finale of the US military’s AlphaDogfight challenge, put on by the Defense Advanced Research Project Agency (DARPA), in which big-name military contractors including Lockheed Martin competed for the crown.
The winning company, Heron Systems, emerged as a victor with its fighter jet AI by defeating a human fighter pilot — call-sign “Banger” — who was sitting inside a simulator wearing a VR headset five rounds to zero.
For Lockheed Martin, it took several servers running trial-and-error dogfights around the clock to come up with its final AI, a piece of software capable of being run on a single graphics card.
“You don’t have to teach a human [that] it shouldn’t crash into the ground… They have basic instincts that the algorithm doesn’t have,” in terms of training. “That means dying a lot. Hitting the ground, a lot,” said Ritholtz.
The use of artificial intelligence (AI) in diverse domains of military activity, from intelligence to training and logistics, is being explored by various defence forces and manufacturers as the battlefield becomes increasingly technology-driven.
Now, it seems, even the old school dogfights — aerial battle between fighter aircraft — are set to be revolutionised by AI algorithms.
The AIs weren’t allowed to learn from their experiences during the actual trials, which Bell said was “a little bit unfair.”
“The standard things that we do as fighter pilots aren’t working,” he said. It didn’t matter in the end. He hadn’t learned fast enough and was defeated.
The simulation also presented a Second World War-style scenario for the planes, where the aerial battle was based on the idea that the fighter aircraft had only forward-facing guns to attack each other with.
Modern dogfights can be much more complex, especially when they include missiles, which were not used during the simulations.
US Air Force Lieutenant Colonel Dan Javorsek, who is DARPA’s ACE programme manager, was cautious about the limitations of the simulation in proving the AI’s superiority to a human pilot.
“I think what we’re seeing today is the beginning of something I’m going to call human-machine symbiosis… Let’s think about the human sitting in the cockpit, being flown by one of these AI algorithms as truly being one weapon system, where the human is focusing on what the human does best [like higher order strategic thinking] and the AI is doing what the AI does best,” Grayson said.