Abstract
Accurate localization in autonomous robots enables effective decision-making within their operating environment. Various methods have been developed to address this challenge, encompassing traditional techniques, fiducial marker utilization, and machine learning approaches. This work proposes a deep-learning solution employing Convolutional Neural Networks (CNN) to tackle the localization problem, specifically in the context of the RobotAtFactory 4.0 competition. The proposed approach leverages transfer learning from the pre-trained VGG16 model to capitalize on its existing knowledge. To validate the effectiveness of the approach, a simulated scenario was employed. The experimental results demonstrated an error within the millimeter scale and rapid response times in milliseconds. Notably, the presented approach offers several advantages, including a consistent model size regardless of the number of training images utilized and the elimination of the need to know the absolute positions of the fiducial markers.

Abstract
This research addresses the significant challenge of automating the annotation of medical images, with a focus on capsule endoscopy videos. The study introduces a novel approach that synergistically combines Deep Learning and Content-Based Image Retrieval (CBIR) techniques to streamline the annotation process. Two pre-trained Convolutional Neural Networks (CNNs), MobileNet and VGG16, were employed to extract and compare visual features from medical images. The methodology underwent rigorous validation using various performance metrics such as accuracy, AUC, precision, and recall. The MobileNet model demonstrated exceptional performance with a test accuracy of 98.4%, an AUC of 99.9%, a precision of 98.2%, and a recall of 98.6%. On the other hand, the VGG16 model achieved a test accuracy of 95.4%, an AUC of 99.2%, a precision of 97.3%, and a recall of 93.5%. These results indicate the high efficacy of the proposed method in the automated annotation of medical images, establishing it as a promising tool for medical applications. The study also highlights potential avenues for future research, including expanding the image retrieval scope to encompass entire endoscopy video databases.

Abstract
Exploring a rich administrative matched employer -employee longitudinal dataset over the 2002-2020 period and a task -based approach, this study investigates to what extent the recent paradigm shift in the electricity sector has affected the structure of employment and wages in the Portuguese case. Our results show that the liberalization in the sector led to the entry of new players and firms' downsizing of the workforce, most notably in occupations involving routine cognitive tasks and non -routine manual tasks. In two decades, the employment share of occupations involving non -routine cognitive tasks (abstract or interactive) doubled, from 29.7% in 2002 to 58.1% in 2020. Regarding wage premiums, the results reveal a clear positive trend in real hourly wages for all types of occupations in the sector. However, we observe a lower wage growth acceleration for workers employed in routine (cognitive or manual) occupations, when compared with similar workers employed in non -routine occupations (cognitive or manual). Our findings are partly consistent with the skill -biased and routine -biased technological change hypotheses in the sense that we observe, respectively, a skill up -grading translated into an increase in employment share in non -routine cognitive occupations and a substantial decline in employment share in routine cognitive occupations.

Abstract
Autonomous vehicles and robotic manipulators are two examples of mechanically distinct systems. Whether these areas are indoors or outside, the environment in which such vehicles will be employed will play a crucial role in how their locomotion systems develop. The speed and stability of wheeled traditional mobility on ordinary flooring are superior. Leg traction is an efficient method for navigating uneven floors, but it takes more time and uses more energy. The foundation of the hybrid configuration is the creation of a leg that enables the interchange and fusion of the two previously described locomotion methods. One advantage of the hybrid arrangement is that the robot may now be deployed in a wider variety of environments. The goal of this paper is to showcase the creation of a leg for a hybrid locomotive robot. The leg can be printed and constructed at a reasonably low-cost thanks to the design of the numerous 3D modules, which will be made accessible later. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

Abstract
Diagnosis of health disorders relies heavily on detecting biological data and accurately observing pathological changes. A significant challenge lies in detecting targeted biological signals and developing reliable sensing technology for clinically relevant results. The combination of data analytics with the sensing abilities of Optical Fiber Tweezers (OFT) provides a high-capability, multifunctional biosensing approach for biophotonic tools. In this work, we introduced phase as a new domain to obtain light patterns in OFT back-scattering signals. By applying a multivariate data analysis procedure, we extract phase spectral information for discriminating micro and nano (bio)particles. A newly proposed method-Hilbert Phase Slope-presented high suitability for differentiation problems, providing features able to discriminate with statistical significance two optically trapped human tumoral cells (MKN45 gastric cell line) and two classes of non-trapped cancer-derived extracellular nanovesicles - an important outcome in view of the current challenges of label-free bio-detection for multifunctional single-molecule analytic tools.

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.