Lockheed shows off AI able to conduct aircraft interception

Lockheed Martin Skunk Works has demonstrated the use of artificial intelligence (AI) in air-to-air intercept scenarios, in collaboration with the University of Iowa’s Operator Performance Laboratory (OPL), according to a press release.

In these tests, AI directly flew and conducted tactical exercises using OPL’s L-29 Delfin jets, managing heading, speed, and altitude commands.

The AI system executed simulated-to-real transfer test objectives against a virtual adversary in both offensive and defensive risk postures.

Eight test cases were conducted per flight to challenge the AI in various scenarios, including standard head-to-head fights, off-aspect encounters, missile support, and missile defeat situations. The team observed effective sim-to-real transfer of learned behaviours, noting that the AI performed intentionally and decisively in its actions.

“This was the first live exercise of the new flight interface; it’s thrilling to see the separate components successfully integrate on the L-29 to demonstrate new capabilities. The complete system performed even better in live flight than in simulation,” said Dr. Tom “Mach” Schnell, OPL professor at Iowa Technology Institute.

Matthew “Gabe” Beard, Lockheed Martin Skunk Works autonomy/AI and machine learning engineering manager, stated, “Live flight tests are a crucial aspect of advancing our expertise in AI and autonomy. These flights are powerful demonstrations of our ability to quickly and affordably develop and test operationally relevant AI capabilities.”

These flight tests are part of a broader initiative to rapidly develop and test AI-driven autonomy for air-to-air missions. Additional flight tests are planned for this year, aiming to introduce more aircraft into offensive counter air and battle management scenarios.