Abstract
Diabetes, a chronic condition affecting millions of people, requires ongoing medical care and treatment, which can place a significant financial burden on society, directly and indirectly. In this paper we propose a vision-robotics system for the automatic assessment of the diabetic foot, one the exams used for the disease management. We present and discuss various computer vision techniques that can support the core operation of the system. U-Net and Segnet, two popular convolutional network architectures for image segmentation are applied in the current case. Hardcoded and machine learning pipelines are explained and compared using different metrics and scenarios. The obtained results show the advantages of the machine learning approach but also point to the importance of hard coded rules, especially when well know areas, such as the human foot, are the systems’ target. Overall, the system achieved very good results, paving the way to a fully automated clinical system.

Abstract
Logistics chains are being increasingly developed due to several factors, among which the exponential growth of e-commerce. Crossdocking is a logistics strategy used by several companies from varied economic sectors, applied in warehouses and distribution centres. In this context, it is the objective of the “CrossLog – Automatic Mixed-Palletizing for Crossdocking Logistics Centers” Project, to investigate and study an automated and collaborative crossdocking system, capable of moving and managing the flow of products within the warehouse in the fastest and safest way. In its scope, this paper describes the concept and architecture envisioned for the crossdocking system developed in the scope of the CrossLog Project. One of its main distinguishing characteristics is the use of Autonomous Mobile Robots for performing much of the operations traditionally performed by human operators in today’s logistics centres.

Abstract
Quadruped robots are gaining attention in the research community because of their superior mobility and versatility in a wide range of applications. However, they are restricted to procedures that do not need precise object interaction. With the addition of a robotic arm, they can overcome these drawbacks and be used in a new set of tasks. Combining a legged robot's dextrous movement with a robotic arm's maneuverability allows the emergence of a highly flexible system, but with the disadvantage of higher complexity of motion planning and control methods. This paper gives an overview of the existing quadruped systems capable of manipulation, with a particular interest in systems with high movement flexibility. The main topics discussed are the motion planning approaches and the selected kinematic configuration. This review concludes that the most followed research path is to add a robotic arm on the quadrupedal base and that the motion planning approach used depends on the desired application. For simple tasks, the arm can be seen as an independent system, which is simpler to implement. For more complex jobs the coupling effects between the arm and quadruped robot must be considered.

Abstract
Quadruped robots have gained significant attention in the robotics world due to their capability to traverse unstructured terrains, making them advantageous in search and rescue and surveillance operations. However, their utility is substantially restricted in situations where object manipulation is necessary. A potential solution is to integrate a robotic arm, although this can be challenging since the arm’s addition may unbalance the whole system, affecting the quadruped locomotion. To address this issue, the robotic arm must be adapted to the quadruped robot, which is not viable with commercially available products. This paper details the design and development of a robotic arm that has been specifically built to integrate with a quadruped robot to use in a variety of agricultural and industrial applications. The design of the arm, including its physical model and kinematic configuration, is presented. To assess the effectiveness of the prototype, a simulation was conducted with a motion-planning algorithm based on the arm’s inverse kinematics. The simulation results confirm the system’s stability and the functionality of the robotic arm’s movement.

Abstract
Welding is a challenging, risky, and time-consuming profession. Recently, there has been a documented shortage of trained welders, and as a result, the market is pushing for an increase in the rate at which new professionals are trained. To address this growing demand, training institutions are exploring alternative methods to train future professionals. The emergence of virtual reality technologies has led to initiatives to explore their potential for welding training. Multiple studies have suggested that virtual reality training delivers comparable, or even superior, results when compared to more conventional approaches, with shorter training times and reduced costs in consumables. This paper conducts a comprehensive review of the current state of the field of welding simulators. This involves exploring the different types of welding simulators available and evaluating their effectiveness and efficiency in meeting the learning objectives of welding training. The aim is to identify gaps in the literature, suggest future research directions, and promote the development of more effective and efficient welding simulators in the future. The research also seeks to develop a categorical system for evaluating and comparing welding simulators. This system will enable a more systematic and objective analysis of the features and characteristics of each simulator, identifying the essential characteristics that should be included in each level of classification.

Abstract
The extraction of geometric information from the environment may be of interest to localisation and mapping algorithms. Existent literature on extracting geometric features from 2D laser data focuses mainly on detecting lines. Regarding corners, most methodologies use the intersection of line segment features. This paper presents a feature extraction algorithm for corner-like points in the 2D laser scan. The proposed methodol-ogy defines arrival and departure neighbourhoods around each scan point and performs local line fitting evaluated in multiple distance-based scales. Then, a set of indicators based on line fitting error, the angle between arrival and departure lines, and consecutive observation of the same keypoint across different scales determine the existence of a corner-like feature. The experiments evaluated the corner-like features regarding their relative position and observability, achieving standard deviations on the relative position lower than the sensor noise and visibility ratios higher than 75% with very low false positives rates. © 2024 IEEE.