Lockheed Martin Skunk Works and the US Air Force Test Pilot School (TPS) have demonstrated how onboard sensors and AI can complement each other to execute aerial intercepts during a series of flight tests.
The test featured the X-62 Variable In-flight Simulation Test Aircraft (VISTA) equipped with Lockheed’s Legion Pod sensor, while a T-38 aircraft served as the live target.
The sensor streamed targeting data directly to an AI agent, which autonomously maneuvered the fighter into a tactical intercept position.
Across eight sorties, the X-62 VISTA reportedly completed 27 AI-controlled intercepts.
“Our autonomous agents consumed classified infrared search and track feeds and executed combat‑critical maneuvers in real time,” said Ron Fehlen, vice president and general manager of Lockheed Martin Skunk Works.
“This achievement marks a decisive advance toward delivering AI‑augmented air dominance for the United States.”
Easing Pilot Workload
Rather than relying on simulated target data, the AI agent made its decisions using real-time inputs from the aircraft’s onboard sensors, bringing the flight tests closer to the conditions pilots could encounter in future combat.
By offloading complex tasks to AI, pilots can focus more on tactical decision-making and rapidly changing battlefield conditions.
Lockheed said its “Supermassive” framework enabled engineers to integrate the AI agents with the X-62 VISTA and complete ground testing in just three months.
“Our ability to provide reliable sensor data is critical, but the real advantage comes when that data can connect seamlessly with AI to take action,” said Stacy Kubicek, vice president and general manager of Lockheed Martin Sensors and Global Sustainment.
“This project demonstrates how sensing and autonomous AI can come together as a force multiplier to make faster, more informed action in complex environments.”
