Skunk Works advances sensor-powered AI for fighter intercepts

Lockheed Martin Skunk Works, the U.S. Air Force Test Pilot School and industry partners have demonstrated sensor-driven autonomy on a fighter aircraft, using real-time sensor data to guide artificial intelligence decision-making in the air. Over eight flights, the X-62A Variable In-Flight Simulation Test Aircraft executed 27 AI-controlled air intercepts against a live target at Edwards Air Force Base, California.

The team’s objective was to prove that the X-62A and its autonomy architecture can use operational sensor inputs to inform AI behavior from development and simulation through training and flight. In a closed-loop test, the aircraft carried a Lockheed Martin Legion Pod that tracked a live T‑38 and relayed secure data to an onboard AI agent, which then flew the aircraft into an intercept position. The approach shifts testing from simulated targets to real-time, on-board sensor streams intended to reflect the conditions pilots will face in contested environments.

Lockheed Martin said its “Supermassive” AI agent-generation capability accelerated the effort, enabling full agent integration with the X‑62A and ground testing in three months. The collaboration also broadens the Test Pilot School’s AI and autonomy portfolio to include mission-critical onboard systems, with the aim of offloading complex tasks to AI so pilots can concentrate on higher-level tactical decisions.

“Our ongoing partnership with TPS is driving important progress with this latest flight test series demonstrating that our AI can effectively and reliably close the sensor‑to‑action loop aboard an operational combat aircraft,” said Ron Fehlen, vice president and general manager, Lockheed Martin Skunk Works. “Our autonomous agents consumed classified infrared search and track feeds and executed combat‑critical maneuvers in real time. This achievement marks a decisive advance toward delivering AI‑augmented air dominance for the United States.”

“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, 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.”

Building on the demonstrated framework, a Mission Systems Upgrade for the X‑62A is planned to enable integration of combat systems, sensors and airborne AI agents within a next‑generation mesh network. Skunk Works, which has long served as a key integrator on the aircraft with open software and hardware architectures to enable pathfinding flight tests, said the team will continue executing technology roadmaps in coordination with operators to advance U.S. leadership in AI and autonomy.