Abstract
Autonomous Surface Vehicles (ASVs) are bound to play a fundamental role in the maintenance of offshore wind farms. Robust navigation for inspection vehicles should take into account the operation of docking within a harbouring structure, which is a critical and still unexplored maneuver. This work proposes an end-to-end docking approach for ASVs, based on Reinforcement Learning (RL), which teaches an agent to tackle collision- free navigation towards a target pose that allows the berthing of the vessel. The developed research presents a methodology that introduces the concept of illegal actions to facilitate the vessel's exploration during the learning process. This method improves the adopted Actor-Critic (AC) framework by accelerating the agent's optimization by approximately 38.02%. A set of comprehensive experiments demonstrate the accuracy and robustness of the presented method in scenarios with simulated environmental constraints (Beaufort Scale and Douglas Sea Scale), and a diversity of docking structures. Validation with two different real ASVs in both controlled and real environments demonstrates the ability of this method to enable safe docking maneuvers without prior knowledge of the scenario.

Abstract
Exploiting stronger winds at offshore farms leads to a cyclical need for maintenance due to the harsh maritime conditions. While autonomous vehicles are the prone solution for O&M procedures, sub-sea phenomena induce severe data degradation that hinders the vessel's 3D perception. This article demonstrates a hybrid underwater imaging system that is capable of retrieving tri-dimensional information: dense and textured Photogrammetric Stereo (PS) point clouds and multiple accurate sets of points through Light Stripe Ranging (LSR), that are combined into a single dense and accurate representation. Two novel fusion algorithms are introduced in this manuscript. A Joint Masked Regression (JMR) methodology propagates sparse LSR information towards the PS point cloud, exploiting homogeneous regions around each beam projection. Regression curves then correlate depth readings from both inputs to correct the stereo-based information. On the other hand, the learning-based solution (RHEA) follows an early-fusion approach where features are conjointly learned from a coupled representation of both 3D inputs. A synthetic-to-real training scheme is employed to bypass domain-adaptation stages, enabling direct deployment in underwater contexts. Evaluation is conducted through extensive trials in simulation, controlled underwater environments, and within a real application at the ATLANTIS Coastal Testbed. Both methods estimate improved output point clouds, with RHEA achieving an average RMSE of 0.0097 m -a 52.45% improvement when compared to the PS input. Performance with real underwater information proves that RHEA is robust in dealing with degraded input information; JMR is more affected by missing information, excelling when the LSR data provides a complete representation of the scenario, and struggling otherwise.

Abstract
Fishing for deep-sea species occurs on continental slopes, ridges, and seamounts. Fishing operations using fishing gears that contact the bottom (e.g., trawls and bottom longlines) may have significant impacts on Vulnerable Marine Ecosystems (VMEs). VMEs refer to marine ecosystems with a population or community of sensitive taxa or habitats that are likely to experience substantial alteration from short-term to chronic disturbance and that are unlikely to recover during the timeframe in which the disturbance occurs. The VME concept, introduced in the United Nations General Assembly Resolution 61/105, has been worldwide applied to the management of deep-sea fisheries. However, the effective identification and management of VMEs is highly constrained by the scarcity of data on VME indicator taxa. This data deficiency is usually surpassed by the use of VME predictive modelling. Video footage is a non-destructive method commonly used for exploring and investigating areas of seabed and for characterising and identifying habitat types. Remotely Operated Vehicles (ROVs) are one of the tools for seabed mapping. ROVs range in size from small observation-class to large work-class vehicles. Their sizes determine the payload, manoeuvrability, depth rating and ultimately uses of the vehicle. For epifaunal imaging, ROVs can be used in two modes: qualitative inspections and quantitative assessments. This paper presents the development of an innovative system composed of a compact support research vessel and a hybrid autonomous underwater vehicle capable of accurate georeferenced high-resolution imaging and profiling of the seabed for a detailed survey of the seabed for biodiversity studies. The experimental results obtained by the developed system in field work in real VME survey at 600m depth are presented.

Abstract
The increasing development of Unmanned Surface Vehicles (USVs) for various applications in open and shallow waters has increased demand for more advanced USVs with improved safety and navigation systems. This article introduces a collision avoidance system for USVs that complies with the International Regulations for Preventing Collisions at Sea (COLREG) rules, particularly rules 13 to 18 from Part B - Steering and Sailing. The system utilizes a three-block architecture for risk assessment, situation identification, and path replanning. Practical testing and validation were conducted using the Stonefish simulator, demonstrating the system's effectiveness in ensuring compliance with COLREG rules and facilitating safe navigation of USVs.

Abstract
This paper presents the results of field trials performed with the EVA autonomous underwater vehicle in the protection of critical infrastructures. The trials were conducted in the context of the REPMUS23 naval exercise organized by the Portuguese Navy. EVA was successfully deployed in a mission of detailed inspection of a submarine cable and in the detection and localization of a possible hostile attack with explosive charges. Multibeam sonar and structured laser light systems were also used to locate and obtain a detailed model of the TURTLE robotic lander deployed on the sea bottom.

Abstract
This paper underscores the critical role of evolving tools for underwater search and rescue. Successful submarine crew rescue hinges on detecting, locating, and obtaining detailed information about the submerged vessel. Robotic systems, particularly ROVs and AUVs, emerge as invaluable tools, offering swift deployment times compared to manned submersibles. This study presents findings from Submarine Escape and Rescue (SMER) field trials conducted during the REPMUS 2023 naval military exercise off the west coast of Portugal, showcasing the effectiveness of these tools in real-world emergency situations. An initial multibeam sonar search from the surface with the Mar Porfundo ship was performed, followed by a close detailed inspection and visual survey with the EVA AUV of a target military submarine (NRP Arp (a) over tildeo) stationed on the sea bottom.