Abstract
Robot Learning is one of the most important areas in Robotics and its relevance has only been increasing. The Robot Operating System (ROS) has been one of the most used architectures in Robotics but learning it is not a simple task. Additionally, ROS 1 is reaching its end-of-life and a lot of users are yet to make the transition to ROS 2. Reinforcement Learning (RL) and Robotics are rarely taught together, creating greater demand for tools to teach all these components. This paper aims to develop a learning kit that can be used to teach Robot Learning to students with different levels of expertise in Robotics. This kit works with the Flatland simulator using open-source free software, namely the OpenAI Gym and Stable-Baselines3 packages, and contains tutorials that introduce the user to the simulation environment as well as how to use RL to train the robot to perform different tasks. User tests were conducted to better understand how the kit performs, showing very positive feedback, with most participants agreeing that the kit provided a productive learning experience.

Abstract
The concept of Industry 4.0 promises to transversally revolutionise industries. Simulation, as one of the main pillars of Industry 4.0, allows improvements in the organisational and production processes of companies. This research work develops a decision support tool based on system dynamics, that address the problem of car dealership sales forecast and evolution depending on the commercial strategies adopted. This decision support tool considers main variables that are expected to influence car sales in Portugal. To develop this tool several interviews were conducted with the people responsible for the commercial sector of different dealerships while considering existing literature on the subject. This allowed us to parameterize a system dynamics model with the most influential sales factors. The developed tool is expected to contribute to car dealerships to evaluate their commercial policies and define adjustments to these to improve profitability.

Abstract

Abstract
AbstractWith the rapid growth of Deep Learning models and neural networks, the medical data available for training – which is already significantly less than other types of data – is becoming scarce. For that purpose, Generative Adversarial Networks (GANs) have received increased attention due to their ability to synthesize new realistic images. Our preliminary work shows promising results for brain MRI images; however, there is a need to distribute the workload, which can be supported by High-Performance Computing (HPC) environments. In this paper, we generate 256×256 MRI images of the brain in a distributed setting. We obtained an FIDRadImageNetof 10.67 for the DCGAN and 23.54 for the WGAN-GP, which are consistent with results reported in several works published in this scope. This allows us to conclude that distributing the GAN generation process is a viable option to overcome the computational constraints imposed by these models and, therefore, facilitate the generation of new data for training purposes.

Abstract
In an era characterized by extensive use of and reliance on information and communications technology (ICT), cyber-physical power systems (CPPSs) have emerged as a critical integral of modern power infrastructures, providing vital energy sources to consumers, communities, and industries worldwide. The integration of ICT in these systems, while beneficial, introduces a rapidly evolving range of cybersecurity challenges that significantly threaten their confidentiality, integrity, and availability. To address this, our article offers a comprehensive and timely survey of the current landscape of cyber vulnerabilities in CPPS, reflecting the latest developments in the field up to the present. This includes an in-depth analysis of the diverse types of cyber threats to CPPS and their potential consequences, underscoring the necessity for a broad, multidisciplinary approach. Our review is distinguished by its thoroughness and timeliness, covering recent research to offer one of the most current overviews of cybersecurity in CPPSs. We adopt a holistic perspective, integrating technical, societal, environmental, and policy implications, thereby providing a more comprehensive understanding of cybersecurity in CPPSs. We delve into the complexities of cyberattacks, exploring sophisticated, targeted attacks alongside common threats, and emphasize the dynamic nature of cyber threats, providing insights into their evolution and future trends. Additionally, our review highlights critical yet often overlooked challenges, such as system visibility and standardization in security protocols, arguing their significance in enhancing CPPS resilience. Furthermore, our work gives special attention to the aspects of restoration and recovery postcyberattack, an area less emphasized in the existing literature. Through this comprehensive overview of the current state and evolving challenges of CPPS security, our article serves as an indispensable resource for research, practice, and policymaking dedicated to safeguarding the safety, reliability, and resilience of ICT-empowered energy systems.

Abstract
Climate change, limited natural resources, and the increase in the world's population impose society to produce food more sustainably, with lower energy and water consumption. The use of robots in agriculture is one of the most promising solutions to change the paradigm of agricultural practices. Agricultural robots should be seen as a way to make jobs easier and lighter, and also a way for people who do not have agricultural skills to produce their food. The PixelCropRobot is a low-cost, open-source robot that can perform the processes of monitoring and watering plants in small gardens. This work proposes a mission supervisor for PixelCropRobot, and general agricultural robots, and presents a prototype of user interface to this mission supervision. The communication between the mission supervisor and the other components of the system is done using ROS2 and MQTT, and mission file standardized. The mission supervisor receives a prescription map, with information about the respective mission, and decomposes them into simple tasks. An A* algorithm then defines the priority of each mission that depends on factors like water requirements, and distance travelled. This concept of mission supervisor was deployed into the PixelCropRobot and was validated in real conditions, showing a enormous potential to be extended to other agricultural robots.