Maritime AI specialist SEA.AI successfully demonstrated a shared, cross-platform machine-vision perception layer across multiple crewed and uncrewed vessels during the Portuguese Navy-led REPMUS 2026 exercise. By integrating its passive optical technology with platforms from partners like Maritime Robotics, SYOS Aerospace, Polar Mist Technologies, and the Portuguese Navy, the company showcased how camera-based detection closes critical sensor gaps left by vulnerable radar, AIS, and GPS systems. The deployment marks SEA.AI’s broadest defense integration to date, proving the maturity and interoperability of autonomous optical safety tools in realistic operational environments.
Lisbon and Troia | October 1, 2026 – Maritime artificial intelligence specialist SEA.AI executed its broadest multi-platform defense integration to date at the Portuguese Navy-led REPMUS 2026 exercise. Running from August 31 to September 25 across Tróia and Sesimbra, Portugal, the 16th annual exercise for maritime uncrewed systems brought together delegations and assets from 36 nations.
Rather than treating machine vision as an isolated accessory for a single platform, SEA.AI demonstrated a shared, cross-platform “perception layer” designed to close critical information gaps for both crewed ships and uncrewed surface vessels (USVs).
The Strategic Rationale: Closing the Sensor Gap
While radar, AIS (Automatic Identification System), and satellite navigation remain foundational to marine navigation, modern defense environments expose distinct vulnerabilities in each. Active radar emissions can be tracked or jammed in contested zones, while satellite navigation and AIS face growing threats like GNSS spoofing, which can feed false position and timing data to uncrewed craft without immediate detection.
To address this, SEA.AI leverages an independent, passive optical system built on eight years of maritime data collection spanning offshore racing, commercial shipping, and recreational boating.
Emphasizing the industry transition, Marcus Warrelmann, CEO of SEA.AI, noted “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.”
Adding context to how the algorithm processes real-world variables, Miguel Pedro, Portugal Country Manager and Product Owner at SEA.AI, explained “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.”
Multi-Platform Integration: Industry Leaders Weigh In
During the live trials at REPMUS 2026, SEA.AI’s machine-vision core successfully translated live camera feeds into actionable data across diverse hulls, autonomy frameworks, and partner architectures. Industry leaders shared their perspectives on how optical AI is reshaping uncrewed operations:
Integrating the vision layer onto coastal and open-ocean uncrewed surface vessels (USVs), Vegard Evjen Hovstein, CEO of Maritime Robotics, emphasized the fundamental requirement for reliable navigation:
“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.”
Designed and assembled entirely in-house by Navy engineers, the Shiver USV integrated the AI-embedded camera system specifically to mitigate operator fatigue and streamline data processing. Pedro Pereira, Project Lead for USV Shiver (The Portuguese Navy), detailed the operational impact:
“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.”
Integrating SEA.AI into its payload-agnostic, GPS-independent USV architecture, Gustaf von Grothusen, CEO of Polar Mist Technologies, focused on strategic cost-efficiency and configuration flexibility:
“From the start, we have designed our systems for an affordable mass. 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.”
SYOS Aerospace: Building on a strategic partnership established in 2024, the UK-New Zealand manufacturer equipped its SM300 uncrewed surface vessels with SEA.AI’s system. This integration provided the craft with an independent optical channel to maintain robust situational awareness as they pushed into increasingly demanding and unpredictable marine environments.
Validating Interoperability under Operational Pressure
A central objective of REPMUS is testing whether technologies built by different international manufacturers and defense entities can seamlessly interoperate under realistic field conditions. By providing a uniform perception layer across multiple distinct USV designs, SEA.AI successfully proved that common software architecture can eliminate redundant development while standardizing environmental awareness for operators.
Summarizing the overarching success of the deployment, Captain Caldeira de Carvalho, CEOM Director, stated “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.”
About SEA.AI
SEA.AI pioneered maritime machine vision in 2018. Its systems combine optical and thermal sensors with artificial intelligence to detect what conventional sensors. such as radar and AIS, often miss, including persons overboard, marine mammals, unlit vessels, small craft, containers, semi-submerged logs, and other floating hazards, day and night, in real time.
Operators see what was previously invisible, gaining more information, more time to react, and the certainty to act. The technology is built on more than eight years of real-world data gathered at sea and is used across recreational, commercial, and security operations, both at sea and from fixed installations. More than 1,300 systems are in service worldwide, protecting people, vessels, and marine life.
About REPMUS
REPMUS (Robotic Experimentation and Prototyping with Maritime Unmanned Systems) is the Portuguese Navy’s annual exercise dedicated to testing maritime drones, autonomy, and multi-domain unmanned systems, held in collaboration with NATO and international partners. Now in its 16th edition, REPMUS 2026 ran from August 31 to September 25 in Tróia and Sesimbra, spanning more than 400 square nautical miles (over 1,370 square kilometers) of exercise areas.
The 2026 edition brought together more than 3,700 participants from 36 nations, over 130 R&D companies, 13 universities, and five NATO entities linked to maritime operations and unmanned systems. It tested more than 280 maritime unmanned systems supported by 14 ships across surface, subsurface, aerial, and land domains. REPMUS was organized by the Portuguese Navy together with the Faculty of Engineering of the University of Porto, the NATO Centre for Maritime Research and Experimentation (CMRE), the NATO Joint Capability Group Maritime Unmanned Systems, and the European Defence Agency.
Source: SEA.AI