X-62A Achieves 27 Autonomous Intercepts Using Live Sensor Data in Major AI Milestone

X-62A completes first fully autonomous air intercepts via live sensors

The new AI software was developed by Lockheed Martin's Skunk Works Autonomous air combat reached a major milestone in the skies over Edwards Air Force Base, California, as the X-62A VISTA test aircraft carried out full AI air intercept missions using live sensor data rather than simulated feeds. How new technology, especially military technology, is tested can often be confusing if all you have to go on are occasional, not-very-in-depth news articles. It's easy to feel skeptical after reading, for example, that a laser weapon test shooting down a target drone involved the flight trajectory of the drone being preprogrammed into its tracking system. While that may seem like cheating, engineering tests are designed to isolate and fix one problem at a time, requiring all other variables to be tightly controlled. In the laser example, engineers may have been evaluating the laser's focusing mechanism, so they needed to make sure the laser's tracking mechanism wasn't complicating matters. The same principle applies to developing autonomous flight systems for combat aircraft. Having a plane fly a full mission on its own is a lot more complicated than just going from point A to point B. Not only are highly complex aerodynamics at play, combined with the computer needing to work out how to complete its tasks, there's also how to handle a huge influx of real-time data from a suite of onboard sensors and off-board platforms. Worse than that, real-world sensor data is often so ambiguous, incomplete, and riddled with noise that the only way to describe it is borderline chaotic. For this reason, the X-62A and similar experimental aircraft typically rely on digital simulations of various sensor input to simplify flight testing. A target aircraft might only exist as a simulated data file, as may radar signals, ground station input, or obstacles. That's also the reason all the test flights have a human safety pilot aboard - to comply with US Air Force protocols and to ensure that there's someone on hand if manual control is required. During the recent HAVE HEAT test series, however, the X-62A ingested live, noisy target-tracking data from an optical sensor in its Legion Pod IRST (Infrared Search and Track) system. The AI interpreted this data to perform 27 tactical air intercepts against a live T-38 Talon "threat" aircraft across eight flights. In doing so, the aircraft successfully managed to close the problematic sensor-to-action loop as it shifted from automated navigation to dynamic, autonomous combat maneuvering. It managed this using an "Supermassive" AI agent framework developed by Lockheed Martin's famous yet oh-so secret Skunk Works. According to the company, ground testing and full integration of the software on the X-62A took only three months. Additionally, the Legion Pod allowed the X-62A to carry out its interceptions without active radar. Instead, it was able to maintain stealth by passively tracking the Talon's heat signature while remaining electronically silent. "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."

X-62A nails 27 autonomous intercepts with live sensor tracking

Artificial intelligence has taken another step from the lab to the cockpit. Lockheed Martin and the U.S. Air Force Test Pilot School have completed a series of flight tests in which an AI agent flew a fighter aircraft using live sensor data to locate and intercept another aircraft. The campaign marks one of the clearest demonstrations yet of a closed-loop airborne autonomy system. Instead of relying on simulated inputs, the AI processed data from an operational sensor aboard the aircraft before making tactical decisions during flight. Engineers completed 27 autonomous intercepts across eight sorties using the X-62A Variable In-flight Simulation Test Aircraft, better known as VISTA. The tests centered on a sensor package known as the Legion Pod, which tracked a live T-38 aircraft during flight. Its infrared search and track data fed directly into an onboard AI agent that controlled the X-62A and guided it into tactical intercept positions. That approach differs from many previous AI demonstrations, which often relied on simulated targets or pre-generated datasets. Using live sensor feeds exposes autonomous software to the same type of information military pilots encounter during real missions. Lockheed Martin also said its engineers completed AI integration, software validation and ground testing in roughly three months. The company credited its "Supermassive" AI development framework for speeding up the process, allowing teams to move new autonomous agents from development to flight testing much faster than traditional methods. Ron Fehlen, vice president and general manager of Lockheed Martin Skunk Works, said the flights proved the company's AI could process classified infrared search and track information before carrying out combat-relevant maneuvers in real time. He described the milestone as an important step toward AI-assisted air combat capabilities for the U.S. military. The flight campaign also expands the U.S. Air Force Test Pilot School's growing work on autonomous aviation. The school has increasingly used the X-62A as a flying laboratory for evaluating AI technologies before they move closer to operational aircraft. Stacy Kubicek, vice president and general manager of Lockheed Martin Sensors and Global Sustainment, said accurate sensing remains essential, but greater value comes when those sensors connect directly to autonomous systems that can respond immediately. The companies argue that handing selected tasks to AI could reduce pilot workload during complex missions. That would allow aircrews to spend more attention on tactical decision-making while autonomous software handles time-sensitive actions. The latest experiments also lay the groundwork for future upgrades planned for the X-62A. Lockheed Martin says the aircraft's upcoming Mission Systems Upgrade will support tighter integration between onboard sensors, combat systems and multiple AI agents operating across next-generation military networks. Skunk Works has supported the X-62A program for decades and developed its open software and hardware architecture. That design lets engineers quickly integrate new technologies without redesigning the aircraft from scratch. Although the demonstrations remain part of a test program, they offer another indication of how the U.S. military plans to incorporate AI into future air combat. Instead of replacing pilots, the technology aims to act as a mission partner that can process information faster and execute complex maneuvers when every second matters.

Lockheed Martin Skunk Works Demonstrates Sensor-Driven Ai Autonomy on X-62 Vista Fighter Aircraft

Lockheed Martin Skunk Works, the U.S. Air Force Test Pilot School (TPS) and industry partners demonstrated sensor-driven autonomy on a fighter aircraft. An artificial intelligence (AI) agent used targeting information from an operational sensor to execute successful air intercepts against a live target. Across eight flights, the X-62 Variable In-flight Simulation Test Aircraft (VISTA) executed 27 AI-controlled intercepts. The objective was to demonstrate that the X-62 and its integrated autonomy architecture can successfully use real sensor data to inform AI behavior, validating the full test cycle from development and simulation through training and flight execution. X-62 equipped with the Lockheed Martin Legion Pod tracks a live T-38 jet and feeds secure data to an AI agent that autonomously pilots the fighter into a tactical intercept position. Moves AI testing from simulated target data to real-time, on-board sensor streams, mirroring the data environment pilots will face in future high-stakes engagements. Skunk Works' "Supermassive" AI agent generation capability dramatically improves speed and agility. Full integration and ground test of the agents with the X-62 occurred in just three months. Connects the cutting-edge of the U.S. Air Force test community with industry expertise, expanding the TPS's AI and autonomy test portfolio to include mission-critical onboard systems. By delegating complex tasks to AI, pilots gain bandwidth to focus on tactical information that increases their effectiveness and survivability. Skunk Works has been a key partner and integrator on X-62 for decades, providing open software and hardware architectures that enable pathfinding flight tests. Leveraging the proven framework from this experiment, the X-62's Mission Systems Upgrade will enable the aircraft to demonstrate seamless integration of combat systems, sensors and airborne AI agents within a next-generation mesh network.