Explore the vast range of titles available.

Robotic devices have become increasingly important in upper-limb rehabilitation, as they assist therapists, improve treatment efficiency, and enable personalised therapy. However, the lack of standardised protocols and integrative tools limits their widespread adoption and effectiveness. To address these challenges, a robotic framework was developed for upper-limb rehabilitation in patients with acquired brain injury (ABI). The framework is designed to be adaptable to various ROS-compatible collaborative robots with admittance control and potentially adaptable to other types of control, and also integrates kinematic and electrophysiological (EMG) metrics to monitor patient performance and progress. It combines data acquisition through EMG and robot motion sensors, gamification elements to enhance engagement, and configurable robot control modes within a unified software platform. A pilot evaluation with eight healthy subjects performing upper limb movements on an ROS-compatible robot from the UR family demonstrated the feasibility of the framework’s components, including robot control, EMG acquisition and synchronization, gamified interaction, and synchronised data collection. User performance through all levels remained below the controller limits of force and velocity thresholds even in the most resistive damping. These results support the potential of the proposed framework as a flexible, extensible, and integrative tool for upper-limb rehabilitation, providing a foundation for future clinical studies and multi-platform implementations.

Artificial intelligence (AI) is currently transforming diverse fields (Qasmi & Fatima, 2024; Alyabroodi et al., 2023), by enabling the personalization of the user experience or expected outcomes, by monitoring and detecting pathological conditions, among other benefits. The use of non-invasive biomedical signals can enhance the performance of AI applications by providing complimentary objective information about the traits of a person that can be otherwise difficult to evaluate or by delivering physiological information that can contribute to the advancement of biomedical signal processing to improve medical attention (Tseng et al., 2023; Kumar et al., 2024).Several applications of AI on non-invasive physiological signals for neuroscience are explored in this collection. In the pioneer field of neuro-humanities, Blanco-Ríos et al. (2024) propose a real-time system for emotion recognition using EEG signals and Extra-Trees, which achieved a very high accuracy with the goal of enhancing learning experience in the field of humanities. Health applications are also explored, such as in Fernandez Rojas et al. (2024) where the accuracy of deep learning models is compared with fNIRS (functional near-infrared spectroscopy) and baseline models for the assessment of pain. The best model (CNN-LSTM) could be used as a possible method for effective pain assessment, which could lead to a more precise tool for clinicians for the care for patients with communication limitations. Other novel studies in this collection are focused on the research of brain-computer interfaces (BCI). Juan et al. (2024) combined spectro-temporal and spectro-spatial feature extraction methods and deep learning models (CNN) to enhance the decoding accuracy of motor imagery from EEG signals during pedaling tasks, obtaining an accuracy of up to 80% despite higher instability. In a similar topic, Dillen et al. (2024) evaluated the usability of a BCI that relied on motor imagery detection and augmented reality for different motor tasks. This was achieved through an assessing protocol that consisted in validating technical robustness, evaluating the control system and comparing it with a non-BCI alternative, including user evaluations. These contributions are important for assuring BCIs are practical and effective in different scenarios.Regarding wearable devices, biomedical signals need to be compressed and reconstructed for their transmission while reducing noise. Zhang et al. (2024) present an improvement in electrocardiographic (ECG) signal reconstruction based on weighted nuclear norm minimization (WNNM) and denoising-based approximate message passing algorithms (AMP). Within the same topic of signal quality, Cisotto et al. (2024) present an innovative deep learning model called hvEEGNet, which is based on a hierarchical variational autoencoder and trained with a new loss function. It is designed for the reconstruction of multi-channel EEG signals. Unlike previous works, the model is capable of performing high-fidelity reconstruction of multi-channel EEG datasets, with high consistency across subjects.The presented articles in this editorial topic provide insights into the recent applications of artificial intelligence and biomedical signals, mainly with a neuroscience perspective. These studies show some of the future trends that may be developed to improve personal experience and accuracy, especially in the healthcare services. Conflict of InterestThe authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.Author ContributionsINA drafted the first version of the manuscript. AU and EI contributed to the critical discussion and revision of its contents. All authors revised the final version of the document.

In this work, we evaluate the relationship between human manipulability indices obtained from motion sensing cameras and a variety of muscular factors extracted from surface electromyography (sEMG) signals from the upper limb during specific movements that include the shoulder, elbow and wrist joints. The results show specific links between upper limb movements and manipulability, revealing that extreme poses show less manipulability, i.e., when the arms are fully extended or fully flexed. However, there is not a clear correlation between the sEMG signals’ average activity and manipulability factors, which suggests that muscular activity is, at least, only indirectly related to human pose singularities. A possible means to infer these correlations, if any, would be the use of advanced deep learning techniques. We also analyze a set of EMG metrics that give insights into how muscular effort is distributed during the exercises. This set of metrics could be used to obtain good indicators for the quantitative evaluation of sequences of movements according to the milestones of a rehabilitation therapy or to plan more ergonomic and bearable movement phases in a working task.

Robotic developments in the field of rehabilitation and assistance have seen a significant increase in the last few years [...].Robotic developments in the field of rehabilitation and assistance have seen a significant increase in the last few years [...].

Human Muscular Manipulability is a metric that measures the comfort of an specific pose and it can be used for a variety of applications related to healthcare. For this reason, we introduce KIMHu: a Kinematic, Imaging and electroMyography dataset for Human muscular manipulability index prediction. The dataset is comprised of images, depth maps, skeleton tracking data, electromyography recordings and 3 different Human Muscular Manipulability indexes of 20 participants performing different physical exercises with their arm. The methodology followed to acquire and process the data is also presented for future replication. A specific analysis framework for Human Muscular Manipulability is proposed in order to provide benchmarking tools based on this dataset.

In this paper, we present ARMIA: a sensorized arm wearable that includes a combination of inertial and sEMG sensors to interact with serious games in telerehabilitation setups. This device reduces the cost of robotic assistance technologies to be affordable for end-users at home and at rehabilitation centers. Hardware and acquisition software specifications are described together with potential applications of ARMIA in real-life rehabilitation scenarios. A detailed comparison with similar medical technologies is provided, with a specific focus on wearable devices and virtual and augmented reality approaches. The potential advantages of the proposed device are also described showing that ARMIA could provide similar, if not better, the effectivity of physical therapy as well as giving the possibility of home-based rehabilitation.

In this paper, we propose a daily living situation where objects in a kitchen can be grasped and stored in specific containers using a virtual robot arm operated by different myoelectric control modes. The main goal of this study is to prove the feasibility of providing virtual environments controlled through surface electromyography that can be used for the future training of people using prosthetics or with upper limb motor impairments. We propose that simple control algorithms can be a more natural and robust way to interact with prostheses and assistive robotics in general than complex multipurpose machine learning approaches. Additionally, we discuss the advantages and disadvantages of adding intelligence to the setup to automatically assist grasping activities. The results show very good performance across all participants who share similar opinions regarding the execution of each of the proposed control modes.

The main goal of this study is to evaluate how to optimally select the best vibrotactile pattern to be used in a closed loop control of upper limb myoelectric prostheses as a feedback of the exerted force. To that end, we assessed both the selection of actuation patterns and the effects of the selection of frequency and amplitude parameters to discriminate between different feedback levels. A single vibrotactile actuator has been used to deliver the vibrations to subjects participating in the experiments. The results show no difference between pattern shapes in terms of feedback perception. Similarly, changes in amplitude level do not reflect significant improvement compared to changes in frequency. However, decreasing the number of feedback levels increases the accuracy of feedback perception and subject-specific variations are high for particular participants, showing that a fine-tuning of the parameters is necessary in a real-time application to upper limb prosthetics. In future works, the effects of training, location, and number of actuators will be assessed. This optimized selection will be tested in a real-time proportional myocontrol of a prosthetic hand.

This paper presents a methodology to detect the intention to make a reaching movement with the arm in healthy subjects before the movement actually starts. This is done by measuring brain activity through electroencephalographic (EEG) signals that are registered by electrodes placed over the scalp. The preparation and performance of an arm movement generate a phenomenon called event-related desynchronization (ERD) in the mu and beta frequency bands. A novel methodology to characterize this cognitive process based on three sums of power spectral frequencies involved in ERD is presented. The main objective of this paper is to set the benchmark for classifiers and to choose the most convenient. The best results are obtained using an SVM classifier with around 72% accuracy. This classifier will be used in further research to generate the control commands to move a robotic exoskeleton that helps people suffering from motor disabilities to perform the movement. The final aim is that this brain-controlled robotic exoskeleton improves the current rehabilitation processes of disabled people.

This Special Issue is focused on breakthrough developments in the field of assistive and rehabilitation robotics. The selected contributions include current scientific progress from biomedical signal processing and cover applications to myoelectric prostheses, lower-limb and upper-limb exoskeletons and assistive robotics.