Lockheed Martin Skunk Works successfully demonstrated autonomous AI controlling a fighter aircraft using live sensor data in eight flight tests, executing 27 intercepts against a real target.
The breakthrough moves AI combat testing from simulation to operational conditions, validating that AI can reliably process real infrared targeting feeds and execute tactical maneuvers in real time—a significant step toward AI-augmented air dominance and enhanced pilot survivability in future air combat.
What happened
Lockheed Martin Skunk Works, working with the U.S. Air Force Test Pilot School, flew the X-62 VISTA aircraft on eight test flights where an AI agent used real sensor data from the onboard Legion Pod to autonomously execute 27 air intercepts against a live T-38 target jet.
Why it matters
The test marks the first time AI controlling a fighter aircraft has closed the loop from real-time sensor input to autonomous tactical action in live flight—moving beyond simulation to operational conditions. This demonstrates that AI can handle classified infrared targeting feeds and execute combat maneuvers reliably, a critical step toward AI-augmented air combat systems that could enhance pilot effectiveness and survivability by offloading complex tasks.
What to watch
Skunk Works plans to use this proven framework to advance the X-62's Mission Systems Upgrade, which will integrate combat systems, sensors, and airborne AI agents into a next-generation mesh network; full integration and ground testing of the AI agents occurred in just three months.
Lockheed Martin Skunk Works announced a landmark autonomous flight test program conducted in partnership with the U.S. Air Force Test Pilot School (TPS) on the X-62 Variable In-flight Simulation Test Aircraft (VISTA). The core achievement was the successful execution of 27 AI-controlled air intercepts across eight flights, in which an autonomous AI agent ingested real targeting sensor data and maneuvered the fighter aircraft to intercept a live T-38 target jet.
The experimental setup placed an AI agent in the control loop, fed by classified infrared search and track data from the onboard Lockheed Martin Legion Pod. Rather than relying on simulated or pre-recorded target information, the system operated on real-time sensor streams—the actual data environment that pilots will face in future high-stakes engagements. Ron Fehlen, vice president and general manager of Lockheed Martin Skunk Works, stated: "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."
The compressed development timeline underscored the maturity of the autonomy platform: full integration and ground testing of the AI agents with the X-62 was completed in just three months. Stacy Kubicek, vice president and general manager of Lockheed Martin Sensors and Global Sustainment, highlighted the integration challenge: "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. This project demonstrates how sensing and autonomous AI can come together as a force multiplier to make faster, more informed action in complex environments."
Looking ahead, Skunk Works intends to leverage this validated framework to support the X-62's Mission Systems Upgrade, which will enable seamless integration of combat systems, sensors, and airborne AI agents within a next-generation mesh network. The partnership demonstrates a coordinated push by the defense industry and the U.S. Air Force test community to mature autonomy for mission-critical onboard systems, with the stated aim of ensuring American leadership in AI and autonomy for air combat.
This test represents a watershed moment in military AI development: the transition from controlled laboratory environments to real-world sensor-to-action loops aboard an operational combat aircraft. The X-62 VISTA has long served as Lockheed Martin's flying testbed for advanced concepts, and the partnership with the Air Force Test Pilot School provided the rigorous validation framework necessary to move autonomous systems from theory to live flight. The use of classified infrared targeting data—the actual sensor environment pilots will encounter in operational scenarios—distinguishes this work from earlier simulated trials and signals confidence in the AI's reliability and security under real combat conditions.
The speed of integration—three months from full ground testing to eight successful flight trials—underscores the maturity of Skunk Works' autonomy architecture. By delegating tactical maneuvering tasks to AI while pilots retain focus on higher-order decision-making and survivability, the system appears designed to amplify human effectiveness rather than replace it. The planned Mission Systems Upgrade, which aims to weave combat systems, sensors, and multiple AI agents into a mesh network, suggests the long-term vision is not isolated autonomous systems but coordinated networks operating across distributed platforms.
AI-summarized, only the topics you pick — one digest a day via Email, Slack, or Discord.
Free · takes 30 seconds · unsubscribe anytime
Ask AI anything about this article. Q&As are published on this page for other readers too.
Bank of America released a report concluding that artificial intelligence is unlikely to significantly displac…
IBM and Together AI have signed a $240 million agreement to build and operate an Nvidia-powered AI inference c…
Running a 122-billion-parameter model on three RTX 3090 GPUs with a 256K-token context, the author's AI agent…
Industry analysts and energy companies see artificial intelligence as a tool to increase oil extraction and re…
Healthcare investors are treating sector exposure as an indirect bet against artificial intelligence, with som…
NVIDIA and partners released multiple open-source AI models optimized for local execution throughout August, i…
The AI news that matters, in one minute each morning.
Sign up free