Abstract
Autonomous Mobile Robots (AMR) are seeing an increased introduction in distinct areas of daily life. Recently, their use has expanded to intralogistics, where forklift type AMR are applied in many situations handling pallets and loading/unloading them into trucks. One of the these vehicles requirements, is that they are able to correctly identify the location and status of pallets, so that the forklifts AMR can insert the forks in the right place. Recently, some commercial sensors have appeared in the market for this purpose. Given these considerations, this paper presents a comparison of the performance of two different approaches for pallet detection: using a commercial off-the-shelf (COTS) sensor and a custom developed application based on Artificial Intelligence algorithms applied to an RGB-D camera, where both the RGB and depth data are used to estimate the position of the pallet pockets.

Abstract
The calibration of sensors stationed along a cable in marine observatories is a time-consuming and expensive operation that involves taking the mooring out of the water periodically. In this paper, we present a method that allows an underwater vehicle to approach a mooring, in order to take reference measurements along the cable for in-situ sensor calibration. We use the vehicle's Mechanically Scanned Imaging Sonar (MSIS) to identify the cable's reflection within the sonar image. After pre-processing the image to remove noise, enhance contour lines, and perform smoothing, we employ three detection steps: 1) selection of regions of interest that fit the cable's reflection pattern, 2) template matching, and 3) a track-before-detect scheme that utilized the vehicle's motion. The later involves building a lattice of template matching responses for a sequence of sonar images, and using the Viterbi algorithm to find the most probable sequence of cable locations that fits the maximum speed assumed for the surveying vessel. Performance is explored in pool and sea trials, and involves an MSIS onboard an underwater vehicle scanning its surrounding to identify a steel-core cable. The results show a sub-meter accuracy in the multi-reverberant pool environment and in the sea trial. For reproducibility, we share our implementation code.

Abstract
The underwater domain presents a myriad of challenges for perception systems that must be overcome to achieve accurate object detection and recognition. To augment the performance and safety of existing solutions for intricate O&M (Operations and Maintenance) procedures, AUVs must perceive the surroundings and locate potential objects of interest based on the perceived information. A depth gradient methodology is employed to survey the seabed using a multibeam sonar to perform a coarse reconstruction of the scenario that it later used to locate and identify foreign objects. This could include rocks, debris, wreckage, or other objects that may pose potential exploratory interest. First results show that the proposed method was able to detect 100 % of the objects present in the scenario with an average chamfer distance error of 0.0238m between models and respective reconstruction. © 2024 IEEE.

Abstract
Marine aquaculture, particularly in the Mediterranean region, faces the challenge of minimizing growth dispersion, which has a direct impact on the production cycle, market value and sustainability of the sector. Conventional grading methods are resource intensive and potentially detrimental to fish health. The current study presented an innovative approach in predicting fish weight dispersion in European seabass (Dicentrarchus labrax) aquaculture. Seabass is one of the two major fish species cultivated on the Mediterranean coast, with a fattening cycle of 18-24 months. During this period, several grading operations are carried out to minimize growth dispersion. The intricate feed-fish-water system, characterized by complex interactions among feeding regimes, fish behavior, individual metabolism and environmental factors, is the focus of the study. The comprehensive, five-step methodology addresses this complexity. The process begins with a Discrete Event System (DES) model that simulates the feed-fish-water dynamics, taking into account individual fish metabolism. This is followed by the development of a surrogate machine learning (ML) regressor model, which is trained on DES simulation data to efficiently predict growth distribution. The model is then calibrated and customized for specific fish stocks and production tanks. The preliminary results from 21 tanks in two trials with European seabass (D. labrax) showed the effectiveness of the method. The results from the simulation models achieved a R2 of 99.9 % and a Mean Absolute Percentage Error (MAPE) of 1.1 % for the prediction of mean final weight and a R2 of 90.3 % with a MAPE of 8.1 % for the standard deviation of final weight. In summary, this study represents a significant advance in the planning and management of seabass aquaculture. Given the lack of effective prediction tools in the aquaculture industry, the proposed methodology has the potential to reduce risks and inefficiencies, thus possibly optimizing aquaculture practices by increasing sustainability and profitability.

Abstract
This paper advocates for the integration of system identification in graduate-level control system courses using accessible theoretical tools. Emphasising real-world applications, particularly in Remotely Operated Vehicle (ROV), the study proposes ROV as educational platforms for teaching control principles. As a concrete example, the paper presents a graduation course project focusing on designing a depth control system for an ROV, where students derive the model from experimental data. This practical application not only enhances the students skills in system identification but also prepares them for challenges in controlling complex systems in both academic and industrial settings.

Abstract
This paper introduces an advanced acoustic imaging system leveraging multibeam water column data at various frequencies to detect and classify marine litter. This study encompasses (i) the acquisition of test tank data for diverse types of marine litter at multiple acoustic frequencies; (ii) the creation of a comprehensive acoustic image dataset with meticulous labelling and formatting; (iii) the implementation of sophisticated classification algorithms, namely support vector machine (SVM) and convolutional neural network (CNN), alongside cutting-edge detection algorithms based on transfer learning, including single-shot multibox detector (SSD) and You Only Look once (YOLO), specifically YOLOv8. The findings reveal discrimination between different classes of marine litter across the implemented algorithms for both detection and classification. Furthermore, cross-frequency studies were conducted to assess model generalisation, evaluating the performance of models trained on one acoustic frequency when tested with acoustic images based on different frequencies. This approach underscores the potential of multibeam data in the detection and classification of marine litter in the water column, paving the way for developing novel research methods in real-life environments.