Powered by MOMENTUM MEDIA
defence connect logo

‘I’m the captain now’: Pilots follow artificial intelligence instruction for attack mission

OPL’s human-piloted L-29s flying as surrogate advanced UAS as they prepare to execute the virtual electronic attack mission. Photo: Collin Clemons.

Lockheed Martin has successfully conducted an electronic attack using piloted aircraft being instructed by artificial intelligence.

Lockheed Martin has successfully conducted an electronic attack using piloted aircraft being instructed by artificial intelligence.

The American defence prime performed the Enhanced Collaborative High-Frequency Orientation System test in conjunction with the University of Iowa’s Operator Performance Laboratory.

Two piloted L-29 jet-powered trainer aircraft, following instructions from the AI agents in the form of heading, altitude, and speed cues, performed jamming support in a simulated air-to-ground mission.

==============
==============

Joe Villani, Lockheed Martin demo and prototype vice-president, said the testing shows how autonomous uncrewed aerial systems can operate in coordination with crewed tactical platforms in future combat operations as a unified team.

“ECHOS is a terrific example of using artificial intelligence and UAS to further enable the DOD vision of Joint All Domain Operations, providing new capabilities to identify targets and deliver effects,” he said.

The AI agents could also reduce pilot workload by providing data for rapid decision making and increased mission effectiveness. Having a human in the loop also provides the option for pilots to stop following AI cues if at any point they felt unsafe or the AI instruction is outside acceptable operating conditions.

“This was an awesome experience and the event went smoothly,” OPL founder and director Tom ‘Mach’ Schnell said.

“It was an exceptional example of industry and academia working together on a cutting-edge project. We’re excited to take this to the next level.”

The AI agents were trained using advanced deep multi-agent reinforcement learning techniques, incentivising emergent collaborative tactics and best possible tactics for the mission completion.

By the end of 2023, the Skunk Works and OPL team will test AI in an end-to-end suppression and destruction of enemy air defences mission.

You need to be a member to post comments. Become a member for free today!