By identifying deviations from expected patterns, the system reduces the number of scans required to detect irregularities. This advancement has implications for security, disaster response, environmental monitoring, and operational safety.
The technology allows ISR systems to identify subtle changes not visible from a single angle by using stored visual memories trained into neural networks. In demonstrations, a small uncrewed air system (UAS) flew through a simulated jungle, successfully identifying physical changes even from previously unseen perspectives.
Machine learning algorithms compare new visual data against past observations to detect hidden threats, wildfires, pollution, and equipment faults. This enables earlier warnings, better situational awareness, and more informed decision-making.
“Our work with Arquimea is on a pivotal research and development initiative, driving advancements in artificial intelligence and machine learning, which supports Spain’s involvement in the development of these cutting-edge technologies,” said Emanuele Serafini, Lockheed Martin’s West Europe vice president.
The system supports trustworthy AI by allowing platforms to manage unfamiliar scenarios, going beyond simple image comparisons. It also has future applications in autonomous navigation and search systems.
“Skunk Works is dedicated to enabling crewed-uncrewed teaming to optimize operational flexibility, abbreviate data-to-decision timelines and improve pilot safety,” added OJ Sanchez, vice president and general manager of Skunk Works. “We continue to invest in collaborative enablers to keep our customers ahead of emerging threats.”
Looking ahead, Lockheed Martin and Arquimea will continue to develop the technology in 2025, expanding its use to enhance sensors and autonomous decision-making across a broader range of systems.
Source: Lockheed Martin (press release).
