Unmanned Surface Vehicles
Discover cutting-edge solutions from leading global suppliers
SEA.AI has integrated and field-tested its machine-vision technology across multiple crewed and uncrewed vessel platforms during REPMUS 2026, NATO’s premier exercise for maritime uncrewed systems.
The deployment marked the company’s broadest multi-platform integration in a defense context to date, evaluating how camera-based detection can strengthen situational awareness for both human crews and autonomous systems. Rather than serving as an accessory for a single autonomy platform, the machine-vision system functioned as a common perception layer capable of supporting diverse vessels, mission profiles, and operators.
While traditional maritime sensors remain vital, they carry inherent operational vulnerabilities. Active radar emits signals that can be detected, tracked, or jammed in contested waters, while satellite navigation is increasingly susceptible to GNSS spoofing, a growing issue in regions such as the Baltic and Black Seas. Because the Automatic Identification System (AIS) relies on GNSS-derived position and timing data, it inherits similar vulnerabilities.
A passive machine-vision system addresses these limitations by offering an independent data stream based on direct visual analysis. By continuously monitoring camera feeds, the system detects hazards that lack active transmitters or strong radar signatures, such as small or unlit craft, floating debris, and individuals in the water.
Marcus Warrelmann, CEO of SEA.AI, said, “Maritime is ready to adopt machine vision as a key sensor, just as other industries have. Eight years of development and more than 1,300 vessels in civilian use back that up. In naval operations, and especially on unmanned platforms, machine vision has a real role to play, closing the perception gap that radar and AIS leave open. REPMUS, across numerous platforms, is where we show that shift taking place in defence too.”
Developed initially for offshore sailing, where high speeds and remote waters require early detection of unflagged hazards, the core technology relies on detection models trained since 2018 on real-world maritime imagery gathered across ocean racing, recreational boating, and commercial shipping. At REPMUS 2026, held in Tróia and Sesimbra, Portugal, bringing together 36 nations, this detection core processed live camera feeds into actionable contextual intelligence, identifying and classifying objects on and above the water.
Miguel Pedro, Portugal Country Manager and Product Owner at SEA.AI, said, “Years of training with real-world maritime data are what give our detection system its strength. Radar and AIS remain important, but they do not provide the complete picture on their own. Machine vision adds another layer, helping vessels detect objects that other sensors, and sometimes even the human eye, can miss.”
Throughout the exercise, SEA.AI collaborated with several Uncrewed Surface Vehicle (USV) manufacturers and naval partners to demonstrate multi-platform integration without requiring individual developers to create custom perception systems from scratch.
Maritime Robotics integrated SEA.AI’s machine vision into its autonomous surface vessels to evaluate optical situational awareness alongside existing navigation suites.
Vegard Evjen Hovstein, CEO of Maritime Robotics, said, “Good autonomy starts with good situational awareness. A USV needs to detect and understand its surroundings just as reliably as it controls its course. Integrating SEA.AI’s machine vision gives us an additional optical layer to evaluate alongside our existing systems, and REPMUS provides the ideal setting to demonstrate how sensors and platforms from different partners can work together.”
UK–New Zealand manufacturer SYOS Aerospace equipped its SM300 USVs with the technology, continuing a partnership established in 2024 to provide independent visual perception as the platform operates in increasingly complex environments.
The Portuguese Navy also fielded the capability on its internally designed and assembled USV Shiver. Pedro Pereira, Project Lead for USV Shiver at the Portuguese Navy, noted, “We got this partnership going with SEA.AI to test the product during the exercise, and the main reason we chose it specifically is that it has AI embedded in the camera system, giving us an extra layer of detection for vessels and objects at sea that helps unload the operator from the overflow of information they have to process today — it’s like getting the warning before the warning is real. We’re getting positive detections that are very useful for our panoramic view and vessel identification, and it’s another layer that confirms radar detection. We’re happy with the performance and are considering integrating it into our future projects.”
Additionally, Polar Mist Technologies demonstrated the integration of the SEA.AI Sentry payload onto its payload-agnostic, GPS-independent USV platform. “From the start, we have designed our systems for an affordable mass,” said Gustaf von Grothusen, CEO of Polar Mist Technologies. “At the same time, the military should have configuration options: equip the unmanned fleet according to what threats they see and what they need to accomplish, while still maintaining control of cost. With this SEA.AI Sentry integration we have demonstrated exactly that freedom in live trials here at REPMUS and added a world class day-and-night ISR capability on the fly. Our militaries can today configure a fleet, make it maximally capable per tax dollar, and deploy.”
By applying a unified vision layer across varied hull designs, autonomy software, and operational roles, the trial demonstrated how standardized perception can streamline interoperability, reduce duplicate development efforts across allied nations, and provide operators with a consistent picture of their surroundings.
Captain Caldeira de Carvalho, CEOM Director, added, “REPMUS is designed to test capabilities in realistic conditions and to explore how technologies from different partners can operate together. Integrating a common perception system across several platforms provided useful evidence of its maturity and interoperability.”
