Abstract
This paper explores the use of Robotics and decentralized Multi-Agent Reinforcement Learning (MARL) for side-by-side navigation in Intelligent Wheelchairs (IW). Evolving from a previous work approach using traditional single-agent methodologies, it adopts a Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm to provide control input and enable a pair of IW to be deployed as decentralized computing agents in real-world environments, discarding the need to rely on communication between each other. In this study, the Flatland 2D simulator, in conjunction with the Robot Operating System (ROS), is used as a realistic environment to train and test the navigation algorithm. An overhaul of the reward function is introduced, which now provides individual rewards for each agent and revised reward incentives. Additionally, the logic for identifying side-by-side navigation was improved, to encourage dynamic alignment control. The preliminary results outline a promising research direction, with the IWs learning to navigate in various realistic hallways testing scenarios. The outcome also suggests that while the MADDPG approach holds potential over single-agent techniques for the decentralized IW robotics application, further investigation are needed for real-world deployment.

Abstract
Faced with the current unsustainability and recognizing the importance of engineering (and technology) in the Capitalocene, it is important to develop educational approaches that facilitate the awareness and training of engineering students to the sustainable future’s construction. The main objective of the study is the evaluation of the educational approach developed (educational board game). It was used an action-research methodology and a quasi-experimental method. These results show that the developed game can be an important contribution in the engineers training to change the role of engineering to an ethical and responsible construction of a sustainable and fair future. © 2024 Taylor & Francis Group, LLC.

Abstract
Total arthroplasty is one of the most common knee surgeries and, due to the ageing of the population, the number of procedures performed each year is expected to increase. With almost a quarter of patients dissatisfied, systems for computer assistance in orthopaedic surgery have been on the rise, appearing to have better outcomes than conventional techniques by reproducing a planned alignment with a similar learning curve. The search for inexpensive solutions to improve these prototypes is extremely relevant since most systems in the market involve expensive robots. The development of a simulation for an extended reality system, specifically spatial augmented reality, with a projector and a depth camera to project the desired total knee arthroplasty bone cuts onto a simulated knee joint has been proposed. It was created with Gazebo and communicates with the Robotic Operating System (ROS) framework so that it can easily be transposed to the real world. An evaluation of the simulator was performed regarding the projection's accuracy. The performance of the simulator was fitting for surgery, with the highest mean position error between the desired bone cut and the simulated bone cut of 1.11 +/- 0.86 mm (minimum = 0.00 mm, maximum = 2.60 mm) for the tibia cut. These values could be further improved with the implementation of a feature-matching algorithm and a dynamic projection.

Abstract

Abstract

Abstract
The trend for an increasingly ubiquitous and cyber-physical world has been leveraging the use and importance of microcontrollers (mu C) to unprecedented levels. Therefore, microcontroller programming (mu CP) becomes a paramount skill for electrical and computer engineering students. However, mu CP poses significant challenges for undergraduate students, given the need to master low-level programming languages and several algorithmic strategies that are not usual in generic programming. Moreover, mu CP can be time-consuming and complex even when using high-level languages. This article samples the current state of mu CP education in Portugal and unveils the potential support of natural language processing (NLP) tools (such as chatGPT). Our analysis of mu CP curricular units from seven representative Portuguese engineering schools highlights a predominant use of AVR 8-bit mu C and project-based learning. While NLP tools emerge as strong candidates as students' mu C companion, their application and impact on the learning process and outcomes deserve to be understood. This study compares the most prominent NLP tools, analyzing their benefits and drawbacks for mu CP education, building on both hands-on tests and literature reviews. By providing automatic code generation and explanation of concepts, NLP tools can assist students in their learning process, allowing them to focus on software design and real-world tasks that the mu C is designed to handle, rather than on low-level coding. We also analyzed the specific impact of chatGTP in the context of a mu CP course at ISEP, confirming most of our expectations, but with a few curiosities. Overall, this work establishes the foundations for future research on the effective integration of NLP tools in mu CP courses.