Abstract
The automation of typically intelligent and decision-making processes in the maritime industry leads to fewer accidents and more cost-effective operations. However, there are still lots of challenges to solve until fully autonomous systems can be employed. Artificial Intelligence (AI) has played a major role in this paradigm shift and shows great potential for solving some of these challenges, such as the docking process of an autonomous vessel. This work proposes a lightweight volumetric Convolutional Neural Network (vCNN) capable of recognizing different docking-based structures using 3D data in real-time. A synthetic-to-real domain adaptation approach is also proposed to accelerate the training process of the vCNN. This approach makes it possible to greatly decrease the cost of data acquisition and the need for advanced computational resources. Extensive experiments demonstrate an accuracy of over 90% in the recognition of different docking structures, using low resolution sensors. The inference time of the system was about 120ms on average. Results obtained using a real Autonomous Surface Vehicle (ASV) demonstrated that the vCNN trained with the synthetic-to-real domain adaptation approach is suitable for maritime mobile robots. This novel AI recognition method, combined with the utilization of 3D data, contributes to an increased robustness of the docking process regarding environmental constraints, such as rain and fog, as well as insufficient lighting in nighttime operations.

Abstract
Understanding the surrounding 3D scene is of the utmost importance for many robotic applications. The rapid evolution of machine learning techniques has enabled impressive results when depth is extracted from a single image. High-latency networks are required to achieve these performances, rendering them unusable for time-constrained applications. This article introduces a lightweight Convolutional Neural Network (CNN) for depth estimation, NEON, designed for balancing both accuracy and inference times. Instead of solely focusing on visual features, the proposed methodology exploits the Motion-Parallax effect to combine the apparent motion of pixels with texture. This research demonstrates that motion perception provides crucial insight about the magnitude of movement for each pixel, which also encodes cues about depth since large displacements usually occur when objects are closer to the imaging sensor. NEON's performance is compared to relevant networks in terms of Root Mean Squared Error (RMSE), the percentage of correctly predicted pixels (delta(1)) and inference times, using the KITTI dataset. Experiments prove that NEON is significantly more efficient than the current top ranked network, estimating predictions 12 times faster; while achieving an average RMSE of 3.118 m and a delta(1) of 94.5%. Ablation studies demonstrate the relevance of tailoring the network to use motion perception principles in estimating depth from image sequences, considering that the effectiveness and quality of the estimated depth map is similar to more computational demanding state-of-the-art networks. Therefore, this research proposes a network that can be integrated in robotic applications, where computational resources and processing-times are important constraints, enabling tasks such as obstacle avoidance, object recognition and robotic grasping.

Abstract
The ATLANTIS project aims to establish a pioneer pilot infrastructure that will allow the demonstration of key enabling robotic technologies for inspection and maintenance of offshore wind farms. The pilot will be implemented in Viana do Castelo, Portugal, and will allow for testing, validation and demonstration of technologies with a range of technology readiness level, in near-real/real environments.The demonstration of robotic technologies can promote the transition from traditional inspection and maintenance methodologies towards automated robotic strategies, that remove or reduce the need of human-in-the-loop, reducing costs and improving the safety of interventions. Eight scenarios, split into four showcases, will be used to determine the required developments for robotic integration and demonstrate the applicability in the inspection and maintenance processes. The scenarios considered were identified by end-users as key areas for robotics.

Abstract
Recently, research concerning the navigation of Autonomous Surface Vehicles (ASVs) has been increasing. However, a big scale implementation of these vessels is still held back by a plethora of challenges such as multi-object tracking. This article presents the development of a tracking model through transfer learning techniques, based on referenced object trackers for urban scenarios. The work consisted in training a neural network through deep learning techniques, including data association and comparison of three different optimisers, Adadelta, Adam and SGD, determining the best hyper-parameters to maximise the training efficiency. The developed model achieved decent performance at tracking large vessels in the ocean, being successful even in harsh lighting conditions and lack of image focus.

Abstract
The worldwide context has fostered the innovation geared to the blue growth. However, the aquatic environment imposes many restrictions to mobile robots, as their perceptual capacity becomes severely limited. DIIUS aims to strengthen the perception of distributed robotic systems to improve the current procedures for inspection of aquatic structures (constructions and/or vessels).The perception of large working areas from multiples robots raises a number of unresolved inference problems and calls for new interaction patterns between multiple disciplines, both at the conceptual and technical level. To address this important challenge, the DIIUS project seeks to reinforce the current state-of-art in several scientific domains that fit into artificial intelligence, computer vision, and robotics. Through case studies focused on 3D mapping of aquatic structures (ex., maritime constructions and adduction tunnels), the project investigates new spatio-temporal data association techniques, including the correlation of sensors from heterogeneous robot formations operating in environments with communications constraints.

Abstract