AviationNews – Lockheed Martin Skunk Works and the U.S. Air Force Test Pilot School have successfully demonstrated sensor-driven artificial intelligence on a fighter jet, marking a major leap forward for airborne autonomy. During live flight trials at Edwards Air Force Base, California, an AI agent processed real-time targeting feeds from an onboard operational sensor to execute multiple autonomous air intercepts against a live target.
The landmark test campaign featured the X-62 Variable In-flight Simulation Test Aircraft (VISTA), a highly customized F-16 derivative designed to test advanced flight controls and autonomous software. Across eight dedicated test sorties, the X-62 VISTA completed 27 AI-controlled intercepts against a live T-38 Talon target jet. Using Lockheed Martin’s Legion Pod, an advanced infrared search and track (IRST) system, the aircraft tracked the adversary and routed classified data directly to the AI agent. Notably, engineers utilized Skunk Works’ Supermassive AI agent generation platform, completing the full integration and ground testing process in just three months.
Technically, the flights validate a complete closed-loop combat cycle, moving autonomous aviation from synthetic simulation directly into real-world operational environments. The Legion Pod passively detects and tracks heat signatures without emitting radar signals, feeding precise angular data directly into the AI flight algorithm. The autonomous system then calculates tactical intercept geometries and pilots the aircraft into ideal attack positions without human intervention. Delegating these rapid, complex tactical calculations to algorithms reduces cockpit workload, giving human pilots greater situational bandwidth to command overall mission strategy.
“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,” stated Ron Fehlen, vice president and general manager at 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.”
Looking ahead, Lockheed Martin plans to incorporate an extensive Mission Systems Upgrade onto the X-62 VISTA platform. This architectural enhancement will allow the jet to test deeper integration between AI software, multi-domain sensor networks, and advanced combat payloads. As air arms worldwide transition toward uncrewed collaborative combat aircraft (CCA), mastering closed-loop autonomous decision-making will remain vital to securing future tactical air superiority.
This successful trial confirms that artificial intelligence can reliably process live sensor inputs to navigate dynamic aerial combat scenarios. By successfully merging real-time infrared tracking with autonomous flight controls, Skunk Works and the U.S. Air Force have established a crucial baseline for crewed-uncrewed teaming. These flight tests accelerate the operational deployment of next-generation autonomous fighter platforms across future battlefields.
