Lockheed Martin and the US Navy have successfully demonstrated a rapidly retrainable artificial intelligence and machine learning (AI/ML) sonar system for antisubmarine warfare (ASW).
The demonstrations took place during the Rim of the Pacific (RIMPAC) Exercise 2026, held from 24 June to 31 July.
Go deeper with GlobalData
Discover B2B Marketing That Performs
Combine business intelligence and editorial excellence to reach engaged professionals across 36 leading media platforms.
During the exercise, Lockheed Martin’s SensorMAX processed and analysed subsurface acoustic data collected from a network of sonobuoys deployed by MH-60R helicopters.
According to the company, the system assists aircrews by continuously monitoring underwater sound signatures and can update its acoustic models mid-mission through over-the-air transmission.
Two MH-60R helicopters equipped with SensorMAX participated in anti-submarine warfare scenarios involving undersea threats at the trials.
The helicopters deployed sonobuoys, which served as underwater microphones, transmitting acoustic information directly to the system.
This allowed the aircrew to manage real-time surveillance feeds from up to eight sonobuoys simultaneously, a capacity that, according to Lockheed Martin, doubles that of previous systems.
When the system encountered new or unexpected acoustic signatures, operators on the ground were able to label and use the data to retrain the AI model.
The updated model was then securely transmitted back to the helicopters using an encrypted data link.
Lockheed Martin stated that this closed-loop process, comprising data capture, labelling, retraining, and redeployment, could be completed in under five minutes per iteration.
This rapid model-updating workflow is designed to deliver continuously enhanced situational awareness, enabling crews to identify and track threats more quickly than with traditional sonar analysis methods.
Furthermore, the company highlighted SensorMAX’s platform-agnostic and portable design, noting that it can accommodate data from both commercial and defence sensors and operate in airborne, maritime, or land-based settings.
The successful RIMPAC exercise shows that integrating AI-enabled acoustic experts with traditional anti-submarine platforms such as the MH-60R can improve detection and tracking of underwater threats.
Lockheed Martin Undersea Mission Systems, vice president and general manager Devon Rodgers said: “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.
“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.”
