Lockheed Martin has successfully demonstrated its AI-powered SensorMAX sonar system during the multinational RIMPAC 2026 exercise, showcasing a capability designed to accelerate underwater threat detection through rapid artificial intelligence model updates and real-time acoustic analysis.
The demonstration took place off the coast of Hawaii, where two MH-60R Seahawk helicopters equipped with the system conducted anti-submarine warfare (ASW) missions using networks of sonobuoys. Acting as underwater acoustic sensors, the sonobuoys collected subsurface sound data and transmitted it directly to SensorMAX for continuous processing.
SensorMAX monitored the incoming acoustic information in real time, assisting helicopter crews with identifying potential submarine contacts. Its operator interface supported the simultaneous management of up to eight sonobuoy surveillance feeds, representing a significant increase in monitoring capacity compared to legacy systems.
A central element of the demonstration was SensorMAX’s ability to adapt to previously unknown acoustic signatures during an ongoing mission. When unfamiliar underwater sounds were detected, the data was transmitted to ground operators, who labelled the new signature and retrained the AI classifier in less than five minutes. A compact software update was then securely transmitted back to the helicopters via an encrypted over-the-air data link, enabling the updated model to be used immediately without interrupting operations.
The demonstration highlighted a continuous operational cycle in which acoustic data is collected, analysed, retrained and redistributed throughout the mission, allowing AI models to evolve as new information becomes available.
According to Lockheed Martin, SensorMAX is designed as a lightweight, platform-agnostic AI system capable of processing data from multiple sensor types beyond underwater acoustics, including electromagnetic and gravitational sensors. Its modular architecture allows the same core algorithms to be deployed across air, maritime and land platforms, while its classifier models, each smaller than one megabyte, can be distributed rapidly across operational networks.
The company also noted that secure over-the-air software delivery is supported through its collaboration with FUSE Inc., allowing updated AI models and mission software to reach deployed aircraft without disrupting ongoing missions.
“Today’s battlespace requires the defence industry to accelerate capability delivery and seamlessly integrate commercial technology; at RIMPAC 2026 our mission‑focused engineers demonstrated exactly how we are meeting that challenge,” said Devon Rodgers, vice president and general manager, Undersea Mission Systems. “Lockheed Martin is investing its own resources to mature AI capabilities, blending commercial innovation with our engineering expertise so the Navy has the technology it needs for tomorrow’s battles.”