Lockheed Martin, University of Iowa Demonstrate AI in Air-to-Air Intercepts

Lockheed Martin Skunk Works and the University of Iowa's Operator Performance Laboratory (OPL) demonstrated AI-piloted air-to-air intercepts using an L-29 Delfin jet.

The partnership led to flight demonstrations in which Artificial Intelligence (AI) directly piloted and conducted tactical exercises with a full-scale, live aircraft – specifically, one of OPL's L-29 Delfin jets – by issuing commands related to heading, speed, and altitude. The exercises included simulated-to-real transfer test objectives against virtual adversaries, encompassing both offensive and defensive maneuvers.

During the tests, eight scenarios were executed per flight to challenge the AI agent in various situations, ranging from standard head-to-head engagements to off-aspect encounters, missile support, and missile defeat scenarios. The AI demonstrated intentional and decisive behavior, with a transfer of learned behaviors from simulation to real-world application.

"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," stated Dr. Tom "Mach" Schnell, an OPL professor at Iowa Technology Institute.

These flight tests form part of a larger initiative aimed at the rapid development and testing of AI-driven autonomy for air-to-air missions. Additional flight tests are planned for this year, which will further enhance the complexity by incorporating more aircraft into offensive counter air and battle management scenarios.

Lockheed Martin aims to continually elevate AI mission performance in operationally representative simulated environments, ensuring compatibility and quick transition with future platforms using open mission systems standards. The company’s AI and machine learning solutions aim to augment human performance by processing, fusing, and analyzing vast amounts of data to provide actionable intelligence and a strategic advantage.

The company said it strictly adheres to the U.S. Department of Defense's guidelines on the ethical and safe use of autonomous systems, ensuring humans remain on-the-loop with final decision-making authority in AI and machine learning systems.