Lockheed Martin has demonstrated the ability of artificial intelligence (AI) to assist in electronic warfare missions.
The company recently announced that trained AI agents successfully commanded two piloted L-29 aircraft to perform jamming support in a simulated air-to-ground mission.
During the demonstration, the L-29s acted as autonomous uncrewed aerial system surrogates and followed instructions from the AI agents for their flight altitude and speed.
The AI agents also reportedly allowed the surrogates to disrupt a radar that was tracking friendly combat jets.
“The successful execution of the electronic attack task by AI agents shows how autonomous uncrewed aerial systems can operate in coordination with crewed tactical platforms in future combat operations, creating a powerful, unified team to address complex threats,” Lockheed Martin stated.
The L-29 pilots had the option to stop following AI cues if at any point they felt unsafe or the agents went outside acceptable operating conditions.
Supporting Joint All Domain Operations
The test, conducted in conjunction with the University of Iowa’s Operator Performance Laboratory, was meant to demonstrate how AI can enable rapid decision making and increase mission effectiveness.
It also showcased reduced pilot workload while maintaining efficiency in performing pre-programmed missions.
According to Lockheed Vice President Joe Villani, the activity was a “terrific example” of using AI and unmanned systems to enable improved Joint All Domain Operations by accurately identifying targets and delivering effects.
To achieve this, the company said it trained the AI agents using advanced multi-agent reinforcement learning techniques to ensure the best possible tactics for any mission.
“This demonstration focused on sim-to-real transfer to train an AI agent in a simulated environment, fly it on real aircraft and test the behavior,” Lockheed explained. “The tests successfully demonstrated that AI agents can be trusted to deliver high performance and reliable behaviors.”