Abstract
Effective navigation in mobile robotics relies on precise environmental mapping, including the detection of complex objects as geometric primitives. This work introduces a deep learning model that determines the pose, type, and dimensions of 2D primitives using a mobile robot equipped with a noisy LiDAR sensor. Simulated experiments conducted in Webots involved randomly placed primitives, with the robot capturing point clouds which were used to progressively build a map of the environment. Two mapping techniques were considered, a deterministic and probabilistic (Bayesian) mapping, and different levels of noise for the LiDAR were compared. The maps were used as input to a YOLOv5 network that detected the position and type of the primitives. A cropped image of each primitive was then fed to a Convolutional Neural Network (CNN) that determined the dimensions and orientation of a given primitive. Results show that the primitive classification achieved an accuracy of 95% in low noise, dropping to 85% under higher noise conditions, while the prediction of the shapes' dimensions had error rates from 5% to 12%, as the noise increased. The probabilistic mapping approach improved accuracy by 10-15% compared to deterministic methods, showcasing robustness to noise levels up to 0.1. Therefore, these findings highlight the effectiveness of probabilistic mapping in enhancing detection accuracy for mobile robot perception in noisy environments.

Abstract
Laser-based additive manufacturing (LAM) offers the ability to produce near-net-shape metal parts with unparalleled energy efficiency and flexibility in both geometry and material selection. Despite advantages, these processes are inherently, as they are characterized by multiphysics interactions, multiscale phenomena, and highly dynamic behaviors, making their modeling and optimization particularly challenging. Artificial intelligence (AI) has emerged as a promising tool for enhancing the monitoring and control of additive manufacturing. This paper presents a systematic review of AI applications for real-time control of laser-based manufacturing processes, analyzing 16 relevant articles sourced from Scopus, IEEE Xplore, and Web of Science databases. The primary objective of this work is to contribute to the advancement of autonomous manufacturing systems capable of self-monitoring and self-correction, ensuring optimal part quality, enhanced efficiency, and reduced human intervention. Our findings indicate that 62.5 % of the 16 analyzed studies have deployed AI-driven controllers in real-world scenarios, with over 56 % using AI for control strategies, such as Reinforcement Learning. Furthermore, 62.5 % of the studies employed AI for process modeling or monitoring, which was integral to the development or data pipelines of the controllers. By defining a groundwork for future developments, this review not only highlights current advancements but also hints future innovations that will likely include AI-based controllers.

Abstract
Precision agriculture seeks to optimize crop yields while minimizing resource use. A key challenge is achieving uniform pesticide spraying to prevent crop damage and environmental contamination. Water-sensitive paper (WSP) is a common tool used for assessing spray quality, as it visually registers droplet impacts through color change. This work introduces a smartphone-based solution for capturing WSP images within vegetation, offering a tool for farmers to assess spray quality in real-world conditions. To achieve this, two approaches were explored: classical computer vision techniques and machine learning (ML) models (YOLOv8, Mask-RCNN, and Cellpose). Addressing the challenges of limited real-world data and the complexity of manual annotation, a programmatically generated synthetic dataset was employed to enable sim-to-real transfer learning. For the task of WSP segmentation within vegetation, YOLOv8 achieved an average Intersection over Union of 97.76%. In the droplet detection task, which involves identifying individual droplets on WSP, Cellpose achieved the highest precision of 96.18%, in the presence of overlapping droplets. While classical computer vision techniques provided a reliable baseline, they struggled with complex cases. Additionally, ML models, particularly Cellpose, demonstrated accurate droplet detection even without fine-tuning.

Abstract
The article will present the development of the tool FEUPAutom, used at the Faculty of Engineering of the University of Porto (FEUP) in the automation engineering Technological & Scientific area. In FEUP, the pressure to deliver well trained engineers is steadily high in the last two decades, thus producing a well-known situation of massification in Higher Education Institutions, namely in engineering degrees. In the school year of 2013/14, the course where the tool was used had about 270 students, despite quite low retention rates. The article also includes a brief characterization of the engineering program, course and expected outcomes in full alignment with the ideas promoted by the EUR-ACE referential for the accreditation of engineering programs and also in strong consonance with the ideas defended by the Bologna process. The course includes lab work and a part of those uses Problem Based Learning (PBL) methodology. In the last decade, the professors of the mentioned course have tried to limit the usage of real world industrial equipments because of budget concerns, always without hindering the learning process. Adequate simulation tools were sought on the market but not found, mainly because the needs of a full blown engineer are frequently not the same as those of an early engineering student. At that point, the decision was made to develop an in-house tool, adequate for students. Industrial-grade equipment was not totally set aside, only reserved for latter stages and the actual usage strategy allowed the number of equipments to be halved. The article will go on briefly describing the FEUPAutom tool and new strategies available for lab classes and PBL. As control groups would be unethical, students' quiz data from the two last editions of the course are used to evaluate learning (self-assessed). Grading strategy and coordination with the university's LMS is also addressed. Final grades of the course and satisfaction are also discussed. The students' assessment is that the FEUPAutom tool is very useful for the learning process and easier to use than the available industrial counterpart. Continuous improvement efforts have tried to push students to adequate PBL work only possible with the tool, with some results hinting deep learning in the technical area at stake. Some final thoughts, lessons learned and future work are also present in the article.

Abstract
Abstract This work introduces Gen-JEMA, a generative approach based on joint embedding with multimodal alignment (JEMA), to enhance feature extraction in the embedding space and improve the explainability of its predictions. Gen-JEMA addresses these challenges by leveraging multimodal data, including multi-view images and metadata such as process parameters, to learn transferable semantic representations. Gen-JEMA enables more explainable and enriched predictions by learning a decoder from the embedding. This novel co-learning framework, tailored for directed energy deposition (DED), integrates multiple data sources to learn a unified data representation and predict melt pool images from the primary sensor. The proposed approach enables real-time process monitoring using only the primary modality, simplifying hardware requirements and reducing computational overhead. The effectiveness of Gen-JEMA for DED process monitoring was evaluated, focusing on its generalization to downstream tasks such as melt pool geometry prediction and the generation of external melt pool representations using off-axis sensor data. To generate these external representations, autoencoder (AE) and variational autoencoder (VAE) architectures were optimized using Bayesian optimization. The AE outperformed other approaches achieving a 38% improvement in melt pool geometry prediction compared to the baseline and 88% in data generation compared with the VAE. The proposed framework establishes the foundation for integrating multisensor data with metadata through a generative approach, enabling various downstream tasks within the DED domain and achieving a small embedding, allowing efficient process control based on model predictions and embeddings.

Abstract
Problem-Based Learning (PBL) has been used in several domains for almost two decades as a more efficient way to develop student's new skills. This approach lends itself well to teaching Industrial Communication Systems, allowing the students to acquire skills that enable them to solve a large set of concrete problems in an industrial context. Based on the authors experience in the Integrated Master in Electrical and Computer Engineering at the University of Porto in Portugal, we have developed a new hardware and software based platform for teaching industrial communications that is affordable and portable and amenable to PBL. This platform is the basis of a new course developed as a module in the MEDIS European project (MEDIS: A Methodology for the Formation of Highly Qualified Engineers at Masters Level in the Design and Development of Advanced Industrial Informatics Systems). This paper describes the course itself, the tools used and includes a brief discussion on the feedback received from early adopters among MEDIS participating universities.