Abstract
One way to mitigate the high costs of doing science or business at sea is to create technological infrastructures possessing all the skills and resources needed for successful maritime operations, and make those capabilities and skills available to the external entities requiring them. By doing so, the individual economic and scientific agents can be spared the enormous effort of creating and maintaining their own, particular set of equivalent capabilities, thus drastically lowering their initial operating costs. In addition to cost savings, operating based on fully-fledged, shared infrastructures not only allows the use of more advanced scientific equipment and highly skilled personnel, but it also enables the business teams (be it industry or research) to focus on their goals, rather than on equipment, logistics, and support. This paper will describe the TEC4SEA infrastructure, created precisely to operate as described. This infrastructure has been under implementation in the last few years, and has now entered its operational phase. This paper will describe it, present its current portfolio of services, and discuss the most relevant assets and facilities that have been recently acquired, so that the research and industrial communities requiring the use of such assets can fully evaluate their adequacy for their own purposes and projects.

Abstract
There are several compelling reasons for exploring the ocean, for instance, the potential for accessing valuable resources, such as energy and minerals; establishing sovereignty; and addressing environmental issues. As a result, the scientific community has increasingly focused on the use of autonomous underwater vehicles (AUVs) for ocean exploration. Recent research has demonstrated that buoyancy change modules can greatly enhance the energy efficiency of these vehicles. However, the literature is scarce regarding the dynamic models of the vertical motion of buoyancy change modules. It is therefore difficult to develop adequate depth controllers, as this is a very complex task to perform in situ. The focus of this paper is to develop simplified linear models for a buoyancy change module that was previously designed by the authors. These models are experimentally identified and used to fine-tune depth controllers. Experimental results demonstrate that the controllers perform well, achieving a virtual zero steady-state error with satisfactory dynamic characteristics.

Abstract
This paper describes a robotic system to detect and estimate the volume of sediments in underwater wall corners, in scenarios with zero visibility. All detection and positioning is based on data from a scanning sonar. The main idea is to scan the walls and the bottom of the structure to detect the corner, and then use data obtained in the direction of the corner to estimate the presence of sediment accumulation and its volume. Our approach implements an image segmentation to extract range from the surfaces of interest. The resulting data is then employed for relative localization and estimate of the sediment accumulation. The paper provides information about the methodologies developed and data from practical experiments.

Abstract
Some structures in the harbour environment need to be inspected regularly. However, these scenarios present a major challenge for the accurate estimation of a vehicle's position and subsequent recognition of similar images. In these scenarios, visibility can be poor, making place recognition a difficult task as the visual appearance of a local feature can be compromised. Under these operating conditions, imaging sonars are a promising solution. The quality of the captured images is affected by some factors but they do not suffer from haze, which is an advantage. Therefore, a purely acoustic approach for unsupervised recognition of similar images based on forward-looking sonar (FLS) data is proposed to solve the perception problems in harbour facilities. To simplify the variation of environment parameters and sensor configurations, and given the need for online data for these applications, a harbour scenario was recreated using the Stonefish simulator. Therefore, experiments were conducted with preconfigured user trajectories to simulate inspections in the vicinity of structures. The place recognition approach performs better than the results obtained from optical images. The proposed method provides a good compromise in terms of distinctiveness, achieving 87.5% recall considering appropriate constraints and assumptions for this task given its impact on navigation success. That is, it is based on a similarity threshold of 0.3 and 12 consistent features to consider only effective loops. The behaviour of FLS is the same regardless of the environment conditions and thus this work opens new horizons for the use of these sensors as a great aid for underwater perception, namely, to avoid degradation of navigation performance in muddy conditions.

Abstract
Nowadays, semantic segmentation is used increasingly often in exploration by underwater robots. For example, it is used in autonomous navigation so that the robot can recognise the elements of its environment during the mission to avoid collisions. Other applications include the search for archaeological artefacts, the inspection of underwater structures or in species monitoring. Therefore, it is necessary to improve the performance in these tasks as much as possible. To this end, we compare some methods for image quality improvement and data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementation and the SUIM dataset with eight common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The result for the individual classes shows that there are five classes with an IoU value close to 60% and only one class with an IoU value less than 30%, which is a more reliable result and is easier to use in real contexts.

Abstract
Nowadays, the semantic segmentation of the images of the underwater world is crucial, as these results can be used in various applications such as manipulation or one of the most important in the semantic mapping of the environment. In this way, the structure of the scene observed by the robot can be recovered, and at the same time, the robot can identify the class of objects seen and choose the next action during the mission. However, semantic segmentation using cameras in underwater environments is a non-trivial task, as it depends on the quality of the acquired images (which change over time due to various factors), the diversification of objects and structures that can be inspected during the mission, and the quality of the training performed prior to the evaluation, as poor training means an incorrect estimation of the object class or a poor delineation of the object. Therefore, in this paper, a comparative study of suitable modern semantic segmentation algorithms is conducted to determine whether they can be used in underwater scenarios. Nowadays, it is very important to equip the robot with the ability to inspect port facilities, as this scenario is of particular interest due to the large variety of objects and artificial structures, and to know and recognise most of them. For this purpose, the most suitable dataset available online was selected, which is the closest to the intended context. Therefore, several parameters and different conditions were considered to perform a complete evaluation, and some limitations and improvements are described. The SegNet model shows the best overall accuracy, reaching more than 80%, but some classes such as robots and plants degrade the quality of the performance (considering the mean accuracy and the mean IoU metric).