Advanced Robotics and Mechatronics

Surface electromyography (sEMG) signals are the sum of action potentials emitted by many motor units; they contain the information of muscle contraction patterns and intensity, so they can be used as a simple and reliable source for grasping mode recognition. This paper introduces the InRes-ACNet (inception–attention–ACmix-ResNet50) model, a novel deep-learning approach based on ResNet50, incorporating multi-scale modules and self-attention mechanisms. The proposed model aims to improve gesture recognition performance by enhancing its ability to extract channel feature information within sparse sEMG signals. The InRes-ACNet model is evaluated on the NinaPro DB1 and NinaPro DB5 datasets; the recognition accuracy for these datasets can reach 87.94% and 87.04%, respectively, and recognition accuracy can reach 88.37% in the grasping mode prediction of an electromyography manipulator. The results show that the fusion of multi-scale modules and self-attention mechanisms endows a strong ability for the task of gesture recognition based on sparse sEMG signals. Full article

The COVID-19 outbreak demonstrated the viability of various remote working solutions, telepresence robots (TPRs) being one of them. High-quality video transmission is one of the cornerstones of using such solutions, as most of the information about the environment is acquired through vision. This study aims to compare the camera capabilities of four models of popular telepresence robots using compact reduced LogMAR and Snellen optometry charts as well as text displayed on a projector screen. The symbols from the images are extracted using the Google Vision OCR (Optical Character Recognition) software, and the results of the recognition are compared with the symbols on the charts. Double 3 TPR provides the best quality images of optometric charts, but the OCR results of measurements of the image on the projector do not show the clear advantage of one single model over the others. The results demonstrated by Temi 2 and Double 3 TPRs are generally better than the others, suggesting that these TPRs are more feasible to be used in teaching and learning scenarios. Full article

This work proposes an Augmented Reality (AR) application designed for HoloLens 2 which allows human operators, without particular experience or knowledge of robotics, to easily interact with collaborative robots. Building on the application presented in a previous work of the authors, the novel contributions are focused on a bi-directional interaction that manages the exchange of data from the robot to the human operator and, in the meantime, the flow of commands in the opposite direction. More in detail, the application includes the reading of the robot state, in terms of joint positions, velocities and torques, the visualization of the workspace and the generation and manipulation of the end-effector trajectory by directly moving a set of way-points displayed in the AR environment. Finally, the trajectory feasibility is verified and notified to the user by taking into account the workspace limits. A usability study of the AR platform has been conducted involving 45 participants with different ages and expertise in robot programming and Extended Reality (XR) platforms, comparing two programming methods: a classical kinesthetic teaching interface, provided by the Franka Emika Panda cobot, and the presented AR platform. Participants have reported the effectiveness of the proposed platform, experiencing less physical demand and higher intuitiveness and usability. Full article

Drone simulations offer a safe environment for collecting data and testing algorithms. However, the depth camera sensor in the simulation provides exact depth values without error, which can result in variations in algorithm behavior, especially in the case of SLAM, when transitioning to real-world environments. The aerodynamic model in the simulation also differs from reality, leading to larger errors in drag force calculations at high speeds. This disparity between simulation and real-world conditions poses challenges when attempting to transfer high-speed drone algorithms developed in the simulated environment to actual operational settings. In this paper, we propose a more realistic simulation by implementing a novel depth camera noise model and an improved aerodynamic drag force model. Through experimental validation, we demonstrate the suitability of our models for simulating real-depth cameras and air drag forces. Our depth camera noise model can replicate the values of a real depth camera sensor with a coefficient of determination ($R^2$) value of 0.62, and our air drag force model improves accuracy by 51% compared to the Airsim simulation air drag force model in outdoor flying experiments at 10 m/s. Full article

The use of high-precision positioning systems in modern navigation applications is crucial since location data is one of the most important pieces of information in Industry 4.0, especially for robots operating outdoors. In the modernization process of global navigation satellite system (GNSS) positioning, precise point positioning (PPP) has demonstrated its effectiveness in comparison to traditional differential positioning methods over the past thirty years. However, various challenges hinder the integration of PPP techniques into Internet of Things (IoT) systems for robot localization, with accuracy being a primary concern. This accuracy is impacted by factors such as satellite availability and signal disruptions in outdoor environments, resulting in less precise determination of satellite observations. Effectively addressing various GNSS errors is crucial when collecting PPP observations. The paper investigates the trade-off between kinematic PPP accuracy and cost effectiveness, through the examination of various influencing factors, including the choice of GNSS system (single or mixed), observation type (single or dual frequency), and satellite geometry. This research investigates kinematic PPP accuracy variation on a 10.4 km observed track based on different factors, using the GNSS system (single or mixed), and observation type (single or dual frequency). It can be concluded that mixed (GPS/GLONASS) dual frequency offers a 3D position accuracy of 9 cm, while mixed single frequency offers a 3D position accuracy of 13 cm. In industry, the results enable manufacturers to select suitable robot localization solutions according to the outdoor working environment (number of available satellites), economical constraint (single or dual frequency), and 3D position accuracy. Full article