Myoelectric control of robotic lower limb prostheses: a review of electromyography interfaces, control paradigms, challenges and future directions

Refining a Multidisciplinary "Vasculoplastic" Approach to Limb Salvage: An Institutional Review Examining 300 Lower Extremity Free Flaps

BACKGROUND

The use of free tissue transfer (FTT) is effective for treatment of chronic nonhealing lower extremity (LE) wounds, requiring collaboration across plastic, vascular, podiatric, orthopedic, and infectious disease disciplines for comprehensive treatment plans to optimize limb salvage. The authors describe their vasculopathic approach with 300 LE FTTs, comparing outcomes between the first 200 LE FTTs and the most recent 100 procedures performed.

METHODS

A single-institution, retrospective review of 300 LE FTTs from July of 2011 to January of 2023 was performed. Patients were compared between the first 200 (group 1; July of 2011 through February of 2020) and last 100 flaps (group 2; February of 2020 through January of 2023) performed. Patient characteristics, preoperative management, intraoperative details, and outcomes were collected.

RESULTS

Group 2 patients had significantly higher rates of diabetes (67.0% versus 48.5%; P = 0.002), peripheral vascular disease (56.0% versus 24.5%; P < 0.001), history of venous thromboembolism (13.0% versus 6.0%; P = 0.039), venous reflux (81.9% versus 67.8%; P = 0.028), and preoperative venous thromboses on venous testing (25.5% versus 10.5%; P = 0.003) compared with group 1. Group 2 patients underwent more pre-FTT endovascular interventions (23.0% versus 16.5%; P = 0.039) and vascular bypasses (4.0% versus 0.0%; P = 0.012). Immediate flap success and amputation rates were similar between the groups, but group 2 had higher rates of partial flap necrosis (7% versus 3%; P = 0.012).

CONCLUSION

The adoption of a vasculoplastic approach allows LE FTT to remain successful and achieve long-term limb salvage despite a highly comorbid population.

CLINICAL QUESTION/LEVEL OF EVIDENCE

Therapeutic, IV.

Designing for practicality: a personalized and adaptive framework for real-time EMG-based hand motor decoding

Objective.Despite remarkable advances in electromyography (EMG)-based hand motor decoding, developing a practical and reliable decoder for robotic prosthetic hands remains unsolved. This study highlights inter-individual, inter-session, and intra-session variabilities of EMG signals as practical challenges and introduces a novel personalized and adaptive motor decoding framework, designed to mitigate their impact and improve hand motor decoding.Approach.A dataset was collected from twelve participants (8 male, 4 female), incorporating EMG signals from three forearm muscles during 20 repetitions of 9 distinct hand motions. This data was used to conduct a number of tests for analyzing variabilities of EMG signals, followed by the evaluation of the proposed framework using various classifier models, including multi-layer perceptron, support vector machine, convolutional neural network, and Kolmogorov-Arnold network, as well as different feature extraction methods, some of which were suggested in previous studies.Main Results.For feature extraction, a window size of 100 ms proved optimal, balancing the trade-off between time and accuracy. Focusing on EMG signal variabilities, this study highlights the impact of intra-session variability on classification accuracy, alongside inter-individual and inter-session variabilities. For all models, accuracy declines from an initial average of92.33±6.17%to80.56±9.57%after only 17 repetitions without adaptation. However, the framework, which is designed based on unsupervised adaptation, enhances this degradation to88.88±8.72%, achieving statistically significant improvements, regardless of the classifier structure and feature extraction method used.Significance.Considering the variabilities of EMG signals, the proposed framework is modular and integrates components such as a motion classifier and a feature extractor, which can be selected based on suggestions from prior studies. These are extended by additional elements, including a finite-state machine to identify hand rest and action states and manage state transitions, and a Softmax module designed to ensure the consistency of performed motions and minimize the likelihood of misclassification.

Outdoor Overground Gait Biomechanics and Energetics in Individuals With Transtibial Amputation Walking With a Prescribed Passive Prosthesis and a Bionic Myoelectric Prosthesis

The metabolic cost of walking for individuals with transtibial amputation is generally greater compared with able-bodied individuals. One aim of powered prostheses is to reduce metabolic deficits by replicating biological ankle function. Individuals with transtibial amputation can activate their residual limb muscles to volitionally control bionic ankle prostheses for walking; however, it is unknown how myoelectric control performs outside the laboratory. We recruited 6 individuals with transtibial amputation to walk an outdoor course with the Open Source Leg prosthesis under continuous proportional myoelectric control and compared it with their passive device. There were no significant differences (P = .142) in cost of transport between prostheses. Participants significantly increased residual limb vastus lateralis (P = .042) and rectus femoris (P = .029) muscle activity during early and midstance phase of walking with the powered prosthesis compared with their passive device. All but one participant preferred walking with myoelectric control compared with their passive prosthesis. The additional mass of the powered ankle prosthesis coupled with increased residual quadriceps activity could explain why the energy cost of walking was not lower compared with a passive prosthesis. This study demonstrates participants can volitionally control a bionic ankle prosthesis to navigate real-world environments.

Advancing Myoelectric Prostheses: Efficacy of Gold-Plated 3D-Printed Thermoplastic Dry Electrodes

In the evolving landscape of assistive technologies, significant advancements are being made in the functionality of intelligent myoelectric prostheses, positioning them as a legitimate option for amputees and persons with congenital limb differences. Concurrently, 3D printing is transitioning from its traditional role as a prototyping tool to a viable, cost-effective method for manufacturing. Against this backdrop, it becomes feasible to assess the capabilities of 3D printing in fabricating intricate components, such as electrodes, which are critical for the effective operation of these prostheses. This study explores the efficacy of 3D-printed electrodes by producing and evaluating three variants of graphite-doped thermoplastic electrodes, subsequently enhanced with a layer of gold-plating. These innovative electrodes were benchmarked against five conventional electromyography (EMG) electrodes to compare their performance and characteristics. Testing with ten participants revealed that two of the three thermoplastic materials examined, PLA and TPU, exhibited real potential for electromyography applications. Notably, the application of gold-plating to these thermoplastics significantly enhanced signal quality, achieving parity with the performance of traditional metal electrodes in certain cases. This investigation underscores the promising future of doped thermoplastic 3D-printed electrodes in medical applications. By enabling the production of electrodes that combine a conductive core with an insulating exterior, this technology paves the way for the creation of highly complex electrode designs. Moreover, the ability to rapidly prototype and iterate designs through 3D printing is set to revolutionize the development of electrode arrays, offering new avenues for innovation in prosthetic technology and beyond.

Leveraging Extended Windows in End-to-End Deep Learning for Improved Continuous Myoelectric Locomotion Prediction

Current surface electromyography (sEMG) methods for locomotion mode prediction face limitations in anticipatory capability due to computation delays and constrained window lengths typically below 500 ms-a practice historically tied to stationarity requirements of handcrafted feature extraction. This study investigates whether end-to-end convolutional neural networks (CNNs) processing raw sEMG signals can overcome these constraints through extended window lengths (250 ms to 1500 ms). We systematically evaluate six window lengths paired with three prediction horizons (model forecasts 50 ms to 150 ms ahead) in a continuous locomotion task involving eight modes and 16 transitions. The optimal configuration (1000 ms window with 150 ms horizon) achieved subject-average accuracies of 96.93% (steady states) and 97.50% (transient states), maintaining 95.03% and 85.53% respectively in real-time simulations. With a net averaged anticipation time of 147.9 ms after 2.1 ms computation latency, this approach demonstrates that windows covering 74% of the gait cycle can synergize with deep learning to balance the inherent trade-off between extracting richer information and maintaining system responsiveness to changes in activity.

Electromyographic typing gesture classification dataset for neurotechnological human-machine interfaces

Neurotechnological interfaces have the potential to create new forms of human-machine interactions, by allowing devices to interact directly with neurological signals instead of via intermediates such as keystrokes. Surface electromyography (sEMG) has been used extensively in myoelectric control systems, which use bioelectric activity recorded from muscles during contractions to classify actions. This technology has been used primarily for rehabilitation applications. In order to support the development of myoelectric interfaces for a broader range of human-machine interactions, we present an sEMG dataset obtained during key presses in a typing task. This fine-grained classification dataset consists of 16-channel bilateral sEMG recordings and key logs, collected from 19 individuals in two sessions on different days. We report baseline results on intra-session, inter-session and inter-subject evaluations. Our baseline results show that within-session accuracy is relatively high, even with simple learning models. However, the results on between-session and between-participant are much lower, showing that generalizing between sessions and individuals is an open challenge.

An assistive robot that enables people with amyotrophia to perform sequences of everyday activities

Mobile manipulation aids aim at enabling people with motor impairments to physically interact with their environment. To facilitate the operation of such systems, a variety of components, such as suitable user interfaces and intuitive control of the system, play a crucial role. In this article, we validate our highly integrated assistive robot EDAN, operated by an interface based on bioelectrical signals, combined with shared control and a whole-body coordination of the entire system, through a case study involving people with motor impairments to accomplish real-world activities. Three individuals with amyotrophia were able to perform a range of everyday tasks, including pouring a drink, opening and driving through a door, and opening a drawer. Rather than considering these tasks in isolation, our study focuses on the continuous execution of long sequences of realistic everyday tasks.

Simultaneous and Proportional Control Based on an Enhanced Musculoskeletal Model

Recently, the musculoskeletal model (MM) has been widely studied for decoding movement intent from electromyography (EMG) signals. However, the decoding performance of the MM is impaired for the coordinated movements of multiple degrees of freedom (DoFs) due to the crosstalk between signals of multiple muscles. To address this problem, this study proposed an enhanced MM for 3-DoF motion prediction by taking the "divide and conquer" (DC) strategy and integrating the non-negative matrix factorization (NMF) algorithm, which is named as DC-NMF-MM. The control signals of wrist flexion/extension and MCP flexion/extension were obtained from four independent muscles, and the control signals of wrist pronation/supination were obtained from eight-channel surface EMG signals. Eight non-disabled subjects were recruited for offline and online experiment. For offline experiment, another two MMs were established and taken as the control groups for validation of the proposed DC-NMF-MM, including the MM totally taking the NMF algorithm (T-NMF-MM) and that partly taking the NMF algorithm (P-NMF-MM) for predicting the wrist pronation/supination only. The Pearson's correlation coefficient and the normalized root mean square error were employed to compare the prediction performance of three models. The results showed that the proposed method performs better than the other two models. Moreover, artificial neural network and linear regression model were established to compare with the proposed model and the results showed that DC-NMF-MM is more accurate in predicting joint Angle. For online experiment, a general 3-DOF musculoskeletal model based on DC-NMF-MM was established and the completion time, the number of overshoots, and the path efficiency were taken as evaluation indexes. The results further demonstrated the feasibility of the proposed method to achieve 3-DoF motion control. The proposed enhanced MM provides a prerequisite for the realization of clinical hand myoelectric control.

Hand gestures classification of sEMG signals based on BiLSTM-metaheuristic optimization and hybrid U-Net-MobileNetV2 encoder architecture

Surface electromyography (sEMG) data has been extensively utilized in deep learning algorithms for hand movement classification. This paper aims to introduce a novel method for hand gesture classification using sEMG data, addressing accuracy challenges seen in previous studies. We propose a U-Net architecture incorporating a MobileNetV2 encoder, enhanced by a novel Bidirectional Long Short-Term Memory (BiLSTM) and metaheuristic optimization for spatial feature extraction in hand gesture and motion recognition. Bayesian optimization is employed as the metaheuristic approach to optimize the BiLSTM model's architecture. To address the non-stationarity of sEMG signals, we employ a windowing strategy for signal augmentation within deep learning architectures. The MobileNetV2 encoder and U-Net architecture extract relevant features from sEMG spectrogram images. Edge computing integration is leveraged to further enhance innovation by enabling real-time processing and decision-making closer to the data source. Six standard databases were utilized, achieving an average accuracy of 90.23% with our proposed model, showcasing a 3-4% average accuracy improvement and a 10% variance reduction. Notably, Mendeley Data, BioPatRec DB3, and BioPatRec DB1 surpassed advanced models in their respective domains with classification accuracies of 88.71%, 90.2%, and 88.6%, respectively. Experimental results underscore the significant enhancement in generalizability and gesture recognition robustness. This approach offers a fresh perspective on prosthetic management and human-machine interaction, emphasizing its efficacy in improving accuracy and reducing variance for enhanced prosthetic control and interaction with machines through edge computing integration.

Multimodal data-based human motion intention prediction using adaptive hybrid deep learning network for movement challenged person

Recently, social demands for a good quality of life have increased among the elderly and disabled people. So, biomedical engineers and robotic researchers aimed to fuse these techniques in a novel rehabilitation system. Moreover, these models utilized the biomedical signals acquired from the human body's particular organ, cells, or tissues. The human motion intention prediction mechanism plays an essential role in various applications, such as assistive and rehabilitation robots, that execute specific tasks among elders and physically impaired individuals. However, more complications are increased in the human-machine-based interaction techniques, creating more scope for personalized assistance for the human motion intention prediction system. Therefore, in this paper, an Adaptive Hybrid Network (AHN) is implemented for effective human motion intention prediction. Initially, multimodal data like electroencephalogram (EEG)/Electromyography (EMG) signals and sensor measures data are collected from the available data resource. The gathered EEG/EMG signals are then converted into spectrogram images and sent to AH-CNN-LSTM, which is the integration of an Adaptive Hybrid Convolution Neural Network (AH-CNN) with a Long Short-Term Memory (LSTM) network. Similarly, the data details of sensor measures are directly subjected to AH-CNN-Res-LSTM, which is the combination of Adaptive Hybrid CNN with Residual Network and LSTM (Res-LSTM) to get the predictive result. Further, to enhance the prediction, the parameters in both the AH-CNN-LSTM and AH-CNN-Res-LSTM techniques are optimized using the Improved Yellow Saddle Goatfish Algorithm (IYSGA). The efficiency of the implemented model is computed by conducting the comparison experiment of the proposed technique with other standard models. The performance outcome of the developed method outperformed the other traditional methods.

Improving Electromyography Electrode Placement Accuracy in Transtibial Amputees: A Comparative Study of Ultrasound and Palpation Methods

In the past decade, significant focus has been on electromyography (EMG) control of prostheses in transtibial amputees (TTAs). Reliable signal acquisition requires accurate EMG electrode placement. Conventional electrode placement methods are challenging due to altered post-surgical anatomy. This study investigated the application of ultrasound imaging for placement of EMG electrodes in TTAs. Four residual limb muscles, Tibialis Anterior (TA), Peroneus Longus (PL), Gastrocnemius Medial (GM), and Gastrocnemius Lateral (GL), were examined in 9 unilateral TTAs. Ultrasound was used to identify each muscle belly's thickest part and fiber orientation. A Certified Prosthetist Orthotist (CPO) then performed palpation to identify muscle bellies, blinded to ultrasound findings. Distances between ultrasound- and palpation-identified spots were measured. EMG data were contrasted between methods in terms of root mean square (RMS) amplitude and signal-to-noise ratio (SNR). The results indicated that Ultrasound-guided placement produced slightly higher, though non-significant, signal amplitudes (p = 0.06) and significantly higher SNR (p = 0.04). Moreover, palpation misidentified muscles in four cases. In 72.2% of cases, the distance between ultrasound- and palpation-identified spots was more than 10 mm. The mean distance was the greatest for PL and GL. Relying on palpation to identify PL and TA in TTAs may provide irrelevant EMG due to erroneous placement. Using ultrasound imaging can avoid this and, in addition to accurate muscle identification, may improve signal amplitude and SNR. In conclusion, ultrasound imaging is a valuable tool for enhancing the accuracy of EMG electrode placement in TTAs, which may lead to better prosthetic control outcomes.

Research on Multimodal Control Method for Prosthetic Hands Based on Visuo-Tactile and Arm Motion Measurement

The realization of hand function reengineering using a manipulator is a research hotspot in the field of robotics. In this paper, we propose a multimodal perception and control method for a robotic hand to assist the disabled. The movement of the human hand can be divided into two parts: the coordination of the posture of the fingers, and the coordination of the timing of grasping and releasing objects. Therefore, we first used a pinhole camera to construct a visual device suitable for finger mounting, and preclassified the shape of the object based on YOLOv8; then, a filtering process using multi-frame synthesized point cloud data from miniature 2D Lidar, and DBSCAN algorithm clustering objects and the DTW algorithm, was proposed to further identify the cross-sectional shape and size of the grasped part of the object and realize control of the robot's grasping gesture; finally, a multimodal perception and control method for prosthetic hands was proposed. To control the grasping attitude, a fusion algorithm based on information of upper limb motion state, hand position, and lesser toe haptics was proposed to realize control of the robotic grasping process with a human in the ring. The device designed in this paper does not contact the human skin, does not produce discomfort, and the completion rate of the grasping process experiment reached 91.63%, which indicates that the proposed control method has feasibility and applicability.

Beyond Flexible: Unveiling the Next Era of Flexible Electronic Systems

Flexible electronics are integral in numerous domains such as wearables, healthcare, physiological monitoring, human-machine interface, and environmental sensing, owing to their inherent flexibility, stretchability, lightweight construction, and low profile. These systems seamlessly conform to curvilinear surfaces, including skin, organs, plants, robots, and marine species, facilitating optimal contact. This capability enables flexible electronic systems to enhance or even supplant the utilization of cumbersome instrumentation across a broad range of monitoring and actuation tasks. Consequently, significant progress has been realized in the development of flexible electronic systems. This study begins by examining the key components of standalone flexible electronic systems-sensors, front-end circuitry, data management, power management and actuators. The next section explores different integration strategies for flexible electronic systems as well as their recent advancements. Flexible hybrid electronics, which is currently the most widely used strategy, is first reviewed to assess their characteristics and applications. Subsequently, transformational electronics, which achieves compact and high-density system integration by leveraging heterogeneous integration of bare-die components, is highlighted as the next era of flexible electronic systems. Finally, the study concludes by suggesting future research directions and outlining critical considerations and challenges for developing and miniaturizing fully integrated standalone flexible electronic systems.

Enhancing prosthetic hand control: A synergistic multi-channel electroencephalogram

Electromyogram (EMG) has been a fundamental approach for prosthetic hand control. However it is limited by the functionality of residual muscles and muscle fatigue. Currently, exploring temporal shifts in brain networks and accurately classifying noninvasive electroencephalogram (EEG) for prosthetic hand control remains challenging. In this manuscript, it is hypothesized that the coordinated and synchronized temporal patterns within the brain network, termed as brain synergy, contain valuable information to decode hand movements. 32-channel EEGs were acquired from 10 healthy participants during hand grasp and open. Synergistic spatial distribution pattern and power spectra of brain activity were investigated using independent component analysis of EEG. Out of 32 EEG channels, 15 channels spanning the frontal, central and parietal regions were strategically selected based on the synergy of spatial distribution pattern and power spectrum of independent components. Time-domain and synergistic features were extracted from the selected 15 EEG channels. These features were employed to train a Bayesian optimizer-based support vector machine (SVM). The optimized SVM classifier could achieve an average testing accuracy of 94.39 .84% using synergistic features. The paired t-test showed that synergistic features yielded significantly higher area under curve values (p < .05) compared to time-domain features in classifying hand movements. The output of the classifier was employed for the control of the prosthetic hand. This synergistic approach for analyzing temporal activities in motor control and control of prosthetic hands have potential contributions to future research. It addresses the limitations of EMG-based approaches and emphasizes the effectiveness of synergy-based control for prostheses.

Phasor-Based Myoelectric Synergy Features: A Fast Hand-Crafted Feature Extraction Scheme for Boosting Performance in Gait Phase Recognition

Gait phase recognition systems based on surface electromyographic signals (EMGs) are crucial for developing advanced myoelectric control schemes that enhance the interaction between humans and lower limb assistive devices. However, machine learning models used in this context, such as Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM), typically experience performance degradation when modeling the gait cycle with more than just stance and swing phases. This study introduces a generalized phasor-based feature extraction approach (PHASOR) that captures spatial myoelectric features to improve the performance of LDA and SVM in gait phase recognition. A publicly available dataset of 40 subjects was used to evaluate PHASOR against state-of-the-art feature sets in a five-phase gait recognition problem. Additionally, fully data-driven deep learning architectures, such as Rocket and Mini-Rocket, were included for comparison. The separability index (SI) and mean semi-principal axis (MSA) analyses showed mean SI and MSA metrics of 7.7 and 0.5, respectively, indicating the proposed approach's ability to effectively decode gait phases through EMG activity. The SVM classifier demonstrated the highest accuracy of 82% using a five-fold leave-one-trial-out testing approach, outperforming Rocket and Mini-Rocket. This study confirms that in gait phase recognition based on EMG signals, novel and efficient muscle synergy information feature extraction schemes, such as PHASOR, can compete with deep learning approaches that require greater processing time for feature extraction and classification.

Analysis of human ambulation as a chaotic time-series: with nonlinear dynamics tools

The aim of the present study is to investigate the complexity and stability of human ambulation and the implications on robotic prostheses control systems. Fourteen healthy individuals participate in two experiments, the first group run at three different speeds. The second group ascended and descended stairs of a five-level building block at a self-selected speed. All participants completed the experiment with seven inertial measurement units wrapped around the lower body segments and waist. The data were analyzed to determine the fractal dimension, spectral entropy, and the Lyapunov exponent (LyE). Two methods were used to calculate the long-term LyE, first LyE calculated using the full size of data sets. And the embedding dimensions were calculated using Average Mutual Information (AMI) and the False Nearest Neighbor (FNN) algorithm was used to find the time delay. Besides, a second approach was developed to find long-term LyE where the time delay was based on the average period of the gait cycle using adaptive event-based window. The average values of spectral entropy are 0.538 and 0.575 for stairs ambulation and running, respectively. The degree of uncertainty and complexity increases with the ambulation speed. The short term LyEs for tibia orientation have the minimum range of variation when it comes to stairs ascent and descent. Using two-way analysis of variance we demonstrated the effect of the ambulation speed and type of ambulation on spectral entropy. Moreover, it was shown that the fractal dimension only changed significantly with ambulation speed.

EMG-based prediction of step direction for a better control of lower limb wearable devices

BACKGROUND AND OBJECTIVES

Lower-limb wearable devices can significantly improve the quality of life of subjects suffering from debilitating conditions, such as amputations, neurodegenerative disorders, and stroke-related impairments. Current control approaches, limited to forward walking, fall short of replicating the complexity of human locomotion in complex environments, such as uneven terrains or crowded places. Here we propose a high-level controller based on two Support Vector Machines exploiting four surface electromyography (EMG) signals of the thigh muscles to detect the onset (Toe-off intention decoder) and the direction (Directional EMG decoder) of the upcoming step.

METHODS AND MATERIALS

We validated a preliminary version of the approach by acquiring EMG signals from ten healthy subjects, performing steps in four directions (forward, backward, right, and left), in three different settings (ground-level walking, stairs, and ramps), and in both steady-state and static conditions. Both the Toe-off intention and Directional EMG decoders have been tested with a 5-fold cross-validation repeated five times, using linear and radial-basis-function kernels, and by changing the classification output timing, from 200 ms before to 50 ms after the toe-off.

RESULTS

The Toe-off intention decoder reached a median accuracy of 83.34 % (interquartile range (IQR): 6.48) and specificity of 92.72 % (IQR: 3.62) in its radial-basis-function version, while the Directional EMG decoder's median accuracy ranged between 73.92 % (IQR: 5.8), 200 ms before the toe-off, to 92.91 % (IQR: 4.11), 50 ms after the toe-off, with the radial-basis-function kernel implementation. For both the Toe-off intention and Directional EMG decoders the radial-basis-function version achieved better performances than the linear one (Wilcoxon signed rank test, p < 0.05).

CONCLUSIONS AND SIGNIFICANCE

The combination of the two decoders proved to be a promising solution to detect the step initiation and classify its direction, paving the way for wearable devices with a broader range of movements and more degrees of freedom, ultimately promoting usability in uncontrolled settings and better reactions to external perturbations. Additionally, the encumbrance of the setup is limited to the thigh of the leg of interest, which simplifies the implementation in compact devices, concurrently limiting the sensors worn by the subject.

Walking Ankle Biomechanics of Individuals With Transtibial Amputations Using a Prescribed Prosthesis and a Portable Bionic Prosthesis Under Myoelectric Control

Individuals with transtibial amputation can activate residual limb muscles to volitionally control robotic ankle prostheses for walking and postural control. Most continuous myoelectric ankle prostheses have used a tethered, pneumatic device. The Open Source Leg allows for myoelectric control on an untethered electromechanically actuated ankle. To evaluate continuous proportional myoelectric control on the Open Source Ankle, we recruited five individuals with transtibial amputation. Participants walked over ground with an experimental powered prosthesis and their prescribed passive prosthesis before and after multiple powered device practice sessions. Participants averaged five hours of total walking time. After the final testing session, participants indicated their prosthesis preference via questionnaire. Participants tended to increase peak ankle power after practice (powered 0.80 ± 1.02 W/kg and passive 0.39 ± 0.31 W/kg). Additionally, participants tended to generate greater ankle work with the powered prosthesis compared to their passive device ( 0.13 ± .15 J/kg increase). Although work and peak power generation were not statistically different between the two prostheses, participants preferred walking with the prosthesis under myoelectric control compared to the passive prosthesis. These results indicate individuals with transtibial amputation learned to walk with an untethered powered prosthesis under continuous myoelectric control. Four out 5 participants generated larger magnitudes in peak power compared to their passive prosthesis after practice sessions. An additional important finding was participants chose to walk with peak ankle powers about half of what the powered prosthesis was capable of based on mechanical testing.

Emerging Medical Technologies and Their Use in Bionic Repair and Human Augmentation

As both the proportion of older people and the length of life increases globally, a rise in age-related degenerative diseases, disability, and prolonged dependency is projected. However, more sophisticated biomedical materials, as well as an improved understanding of human disease, is forecast to revolutionize the diagnosis and treatment of conditions ranging from osteoarthritis to Alzheimer's disease as well as impact disease prevention. Another, albeit quieter, revolution is also taking place within society: human augmentation. In this context, humans seek to improve themselves, metamorphosing through self-discipline or more recently, through use of emerging medical technologies, with the goal of transcending aging and mortality. In this review, and in the pursuit of improved medical care following aging, disease, disability, or injury, we first highlight cutting-edge and emerging materials-based neuroprosthetic technologies designed to restore limb or organ function. We highlight the potential for these technologies to be utilized to augment human performance beyond the range of natural performance. We discuss and explore the growing social movement of human augmentation and the idea that it is possible and desirable to use emerging technologies to push the boundaries of what it means to be a healthy human into the realm of superhuman performance and intelligence. This potential future capability is contrasted with limitations in the right-to-repair legislation, which may create challenges for patients. Now is the time for continued discussion of the ethical strategies for research, implementation, and long-term device sustainability or repair.

Integrating Upper-Limb Prostheses with the Human Body: Technology Advances, Readiness, and Roles in Human-Prosthesis Interaction

Significant advances in bionic prosthetics have occurred in the past two decades. The field's rapid expansion has yielded many exciting technologies that can enhance the physical, functional, and cognitive integration of a prosthetic limb with a human. We review advances in the engineering of prosthetic devices and their interfaces with the human nervous system, as well as various surgical techniques for altering human neuromusculoskeletal systems for seamless human-prosthesis integration. We discuss significant advancements in research and clinical translation, focusing on upper limbprosthetics since they heavily rely on user intent for daily operation, although many discussed technologies have been extended to lower limb prostheses as well. In addition, our review emphasizes the roles of advanced prosthetics technologies in complex interactions with humans and the technology readiness levels (TRLs) of individual research advances. Finally, we discuss current gaps and controversies in the field and point out future research directions, guided by TRLs.

Walking Mode-depending Improvements of Locomotion Detection through Rejection Based Post-Processing

The limited availability of information regarding user intent and the surrounding locomotion environment poses obstacles to achieving intuitive prosthetic control. Despite utilizing machine learning algorithms based on external muscle activity and movement sensors to infer user intention, the stringent reliability requirements for leg prostheses control have not been met. This study seeks to enhance the accuracy of locomotion mode detection by incorporating information in the postprocessing phase following Linear Discriminant Analysis classification of locomotion modes. A locomotion dataset comprising data from 15 able-bodied participants, including electromyography, inertial measurement units, and insole pressure sensors during both level walking and stair/ramp ambulation, was employed. To address uncertainties in classification, a threshold-based rejection postprocessing method was implemented, eliminating classifications falling below the threshold. The rejection threshold significantly improved overall locomotion detection accuracy, with transition locomotion showing more pronounced improvement compared to steady-state locomotion. A subanalysis that specifically examined transition locomotion emphasized that biomechanically similar transitions, such as moving from a slight ramp slope to level walking, demonstrated more significant improvement compared to dissimilar transitions like stair to level walking. These findings underscore the significance of leveraging additional information with postprocessing to refine uncertain locomotion classification for better control for prosthetic users.

Intuitive and versatile bionic legs: a perspective on volitional control

Active lower limb prostheses show large potential to offer energetic, balance, and versatility improvements to users when compared to passive and semi-active devices. Still, their control remains a major development challenge, with many different approaches existing. This perspective aims at illustrating a future leg prosthesis control approach to improve the everyday life of prosthesis users, while providing a research road map for getting there. Reviewing research on the needs and challenges faced by prosthesis users, we argue for the development of versatile control architectures for lower limb prosthetic devices that grant the wearer full volitional control at all times. To this end, existing control approaches for active lower limb prostheses are divided based on their consideration of volitional user input. The presented methods are discussed in regard to their suitability for universal everyday control involving user volition. Novel combinations of established methods are proposed. This involves the combination of feed-forward motor control signals with simulated feedback loops in prosthesis control, as well as online optimization techniques to individualize the system parameters. To provide more context, developments related to volitional control design are touched on.

Study on Gesture Recognition Method with Two-Stream Residual Network Fusing sEMG Signals and Acceleration Signals

Currently, surface EMG signals have a wide range of applications in human-computer interaction systems. However, selecting features for gesture recognition models based on traditional machine learning can be challenging and may not yield satisfactory results. Considering the strong nonlinear generalization ability of neural networks, this paper proposes a two-stream residual network model with an attention mechanism for gesture recognition. One branch processes surface EMG signals, while the other processes hand acceleration signals. Segmented networks are utilized to fully extract the physiological and kinematic features of the hand. To enhance the model's capacity to learn crucial information, we introduce an attention mechanism after global average pooling. This mechanism strengthens relevant features and weakens irrelevant ones. Finally, the deep features obtained from the two branches of learning are fused to further improve the accuracy of multi-gesture recognition. The experiments conducted on the NinaPro DB2 public dataset resulted in a recognition accuracy of 88.25% for 49 gestures. This demonstrates that our network model can effectively capture gesture features, enhancing accuracy and robustness across various gestures. This approach to multi-source information fusion is expected to provide more accurate and real-time commands for exoskeleton robots and myoelectric prosthetic control systems, thereby enhancing the user experience and the naturalness of robot operation.

Multi-layer CNN-LSTM network with self-attention mechanism for robust estimation of nonlinear uncertain systems

Introduction

With the help of robot technology, intelligent rehabilitation of patients with lower limb motor dysfunction caused by stroke can be realized. A key factor constraining the clinical application of rehabilitation robots is how to realize pattern recognition of human movement intentions by using the surface electromyography (sEMG) sensors to ensure unhindered human-robot interaction.

Methods

A multilayer CNN-LSTM prediction network incorporating the self-attention mechanism (SAM) is proposed, in this paper, which can extract and learn the periodic and trend characteristics of the sEMG signals, and realize the accurate autoregressive prediction of the human motion information. Firstly, the multilayer CNN-LSTM network utilizes the CNN layer for initial feature extraction of data, and the LSTM network is used to improve the enhancement of the historical time-series features. Then, the SAM is used to improve the global feature extraction performance and parallel computation speed of the network.

Results

In comparison with existing test is carried out using actual data from five healthy subjects as well as a clinical hemiplegic patient to verify the superiority and practicality of the proposed algorithm. The results show that most of the model's prediction R > 0.9 for different motion states of healthy subjects; in the experiments oriented to the motion characteristics of patient subjects, the angle prediction results of R > 0.99 for the untrained data on the affected side, which proves that our proposed model also has a better effect on the angle prediction of the affected side.

Discussion

The main contribution of this paper is to realize continuous motion estimation of ankle joint for healthy and hemiplegic individuals under non-ideal conditions (weak sEMG signals, muscle fatigue, high muscle tension, etc.), which improves the pattern recognition accuracy and robustness of the sEMG sensor-based system.

Lower-Limb Myoelectric Calibration Postures for Transtibial Prostheses

The use of an agonist-antagonist muscle pair for myoelectric control of a transtibial prosthesis requires normalizing the myoelectric signals and identifying their co-contraction signature. Extensive literature has explored the relationship between body posture and lower-limb muscle activation level using surface electromyography (EMG), but it is unknown how these relationships hold after amputation. Using a virtual tracking task, this study compares the effect of three different calibration postures (seated, standing, dynamic) on user tracking ability while in two tracking postures (seated, standing) for 18 able-bodied (AB) subjects and 9 subjects with transtibial (TT) amputation. As expected, AB subjects produced statistically significant differences in muscle activation for gastrocnemius (GAS) when seated vs. standing during calibration (p = 8.8e-4), but not for tibialis anterior (TA) (p = 0.76). TT subjects, however, showed no significant differences in GAS or TA between seated and standing (p = 0.90, 0.60 respectively). It was also determined that normalizing EMG by the global maximum signal observed (standard in biomechanic analysis) is undesirable for myoelectric control. For best general results with this framework, calibration in both seated and dynamic postures is recommended, taking the normalization information from the seated posture and the narrowest co-contraction slopes from the two.

Shaping high-performance wearable robots for human motor and sensory reconstruction and enhancement

Most wearable robots such as exoskeletons and prostheses can operate with dexterity, while wearers do not perceive them as part of their bodies. In this perspective, we contend that integrating environmental, physiological, and physical information through multi-modal fusion, incorporating human-in-the-loop control, utilizing neuromuscular interface, employing flexible electronics, and acquiring and processing human-robot information with biomechatronic chips, should all be leveraged towards building the next generation of wearable robots. These technologies could improve the embodiment of wearable robots. With optimizations in mechanical structure and clinical training, the next generation of wearable robots should better facilitate human motor and sensory reconstruction and enhancement.

Robust myoelectric pattern recognition methods for reducing users' calibration burden: challenges and future

Myoelectric pattern recognition (MPR) has evolved into a sophisticated technology widely employed in controlling myoelectric interface (MI) devices like prosthetic and orthotic robots. Current MIs not only enable multi-degree-of-freedom control of prosthetic limbs but also demonstrate substantial potential in consumer electronics. However, the non-stationary random characteristics of myoelectric signals poses challenges, leading to performance degradation in practical scenarios such as electrode shifting and switching new users. Conventional MIs often necessitate meticulous calibration, imposing a significant burden on users. To address user frustration during the calibration process, researchers have focused on identifying MPR methods that alleviate this burden. This article categorizes common scenarios that incur calibration burdens as based on data distribution shift and based on dynamic data categories. Then further investigated and summarized the popular robust MPR algorithms used to reduce the user's calibration burden. We categorize these algorithms as based on data manipulate, feature manipulation and, model structure. And describes the scenarios to which each method is applicable and the conditions required for calibration. Finally, this review is concluded with the advantages of robust MPR and the remaining challenges and future opportunities.

Modified motor unit properties in residual muscle following transtibial amputation

Objective.Neural signals in residual muscles of amputated limbs are frequently decoded to control powered prostheses. Yet myoelectric controllers assume muscle activities of residual muscles are similar to that of intact muscles. This study sought to understand potential changes to motor unit (MU) properties after limb amputation.Approach.Six people with unilateral transtibial amputation were recruited. Surface electromyogram (EMG) of residual and intacttibialis anterior(TA) andgastrocnemius(GA) muscles were recorded while subjects traced profiles targeting up to 20% and 35% of maximum activation for each muscle (isometric for intact limbs). EMG was decomposed into groups of MU spike trains. MU recruitment thresholds, action potential amplitudes (MU size), and firing rates were correlated to model Henneman's size principle, the onion-skin phenomenon, and rate-size associations. Organization (correlation) and modulation (rates of change) of relations were compared between intact and residual muscles.Main results.The residual TA exhibited significantly lower correlation and flatter slopes in the size principle and onion-skin, and each outcome covaried between the MU relations. The residual GA was unaffected for most subjects. Subjects trained prior with myoelectric prostheses had minimally affected slopes in the TA. Rate-size association correlations were preserved, but both residual muscles exhibited flatter decay rates.Significance.We showed peripheral neuromuscular damage also leads to spinal-level functional reorganizations. Our findings suggest models of MU recruitment and discharge patterns for residual muscle EMG generation need reparameterization to account for disturbances observed. In the future, tracking MU pool adaptations may also provide a biomarker of neuromuscular control to aid training with myoelectric prostheses.

Toward the Development of User-Centered Neurointegrated Lower Limb Prostheses

The last few years witnessed radical improvements in lower-limb prostheses. Researchers have presented innovative solutions to overcome the limits of the first generation of prostheses, refining specific aspects which could be implemented in future prostheses designs. Each aspect of lower-limb prostheses has been upgraded, but despite these advances, a number of deficiencies remain and the most capable limb prostheses fall far short of the capabilities of the healthy limb. This article describes the current state of prosthesis technology; identifies a number of deficiencies across the spectrum of lower limb prosthetic components with respect to users' needs; and discusses research opportunities in design and control that would substantially improve functionality concerning each deficiency. In doing so, the authors present a roadmap of patients related issues that should be addressed in order to fulfill the vision of a next-generation, neurally-integrated, highly-functional lower limb prosthesis.

First-in-human demonstration of floating EMG sensors and stimulators wirelessly powered and operated by volume conduction

BACKGROUND

Recently we reported the design and evaluation of floating semi-implantable devices that receive power from and bidirectionally communicate with an external system using coupling by volume conduction. The approach, of which the semi-implantable devices are proof-of-concept prototypes, may overcome some limitations presented by existing neuroprostheses, especially those related to implant size and deployment, as the implants avoid bulky components and can be developed as threadlike devices. Here, it is reported the first-in-human acute demonstration of these devices for electromyography (EMG) sensing and electrical stimulation.

METHODS

A proof-of-concept device, consisting of implantable thin-film electrodes and a nonimplantable miniature electronic circuit connected to them, was deployed in the upper or lower limb of six healthy participants. Two external electrodes were strapped around the limb and were connected to the external system which delivered high frequency current bursts. Within these bursts, 13 commands were modulated to communicate with the implant.

RESULTS

Four devices were deployed in the biceps brachii and the gastrocnemius medialis muscles, and the external system was able to power and communicate with them. Limitations regarding insertion and communication speed are reported. Sensing and stimulation parameters were configured from the external system. In one participant, electrical stimulation and EMG acquisition assays were performed, demonstrating the feasibility of the approach to power and communicate with the floating device.

CONCLUSIONS

This is the first-in-human demonstration of EMG sensors and electrical stimulators powered and operated by volume conduction. These proof-of-concept devices can be miniaturized using current microelectronic technologies, enabling fully implantable networked neuroprosthetics.

Ankle Torque Estimation With Motor Unit Discharges in Residual Muscles Following Lower-Limb Amputation

There has been increased interest in using residual muscle activity for neural control of powered lower-limb prostheses. However, only surface electromyography (EMG)-based decoders have been investigated. This study aims to investigate the potential of using motor unit (MU)-based decoding methods as an alternative to EMG-based intent recognition for ankle torque estimation. Eight people without amputation (NON) and seven people with amputation (AMP) participated in the experiments. Subjects conducted isometric dorsi- and plantarflexion with their intact limb by tracing desired muscle activity of the tibialis anterior (TA) and gastrocnemius (GA) while ankle torque was recorded. To match phantom limb and intact limb activity, AMP mirrored muscle activation with their residual TA and GA. We compared neuromuscular decoders (linear regression) for ankle joint torque estimation based on 1) EMG amplitude (aEMG), 2) MU firing frequencies representing neural drive (ND), and 3) MU firings convolved with modeled twitch forces (MUDrive). In addition, sensitivity analysis and dimensionality reduction of optimization were performed on the MUDrive method to further improve its practical value. Our results suggest MUDrive significantly outperforms (lower root-mean-square error) EMG and ND methods in muscles of NON, as well as both intact and residual muscles of AMP. Reducing the number of optimized MUDrive parameters degraded performance. Even so, optimization computational time was reduced and MUDrive still outperformed aEMG. Our outcomes indicate integrating MU discharges with modeled biomechanical outputs may provide a more accurate torque control signal than direct EMG control of assistive, lower-limb devices, such as exoskeletons and powered prostheses.

A Wearable Co-Located Neural-Mechanical Signal Sensing Device for Simultaneous Bimodal Muscular Activity Detection

The co-located and concurrent measurement of both muscular neural activity and muscular deformation is considered necessary in many applications, such as medical robotics, assistive exoskeletons and muscle function evaluations. Nevertheless, conventional muscle-related signal perception systems either detect only one of these modalities, or are made with rigid and bulky components that cannot provide conformal and flexible interface. Herein, a flexible, easy-to-fabricate, bimodal muscular activity sensing device, which collects neural and mechanical signal at the same muscle location, is reported. The sensing patch includes a screen-printed sEMG sensor, and a pressure-based muscular deformation sensor (PMD sensor) based on a highly sensitive, co-planar iontronic pressure sensing unit. Both sensors are integrated on a super-thin (25 μm) substrate. The sEMG sensor shows a high signal-to-noise ratio of 37.1 dB, and the PMD sensor sensor exhibits a high sensitivity of 70.9 kPa -1. The responses of the sensor to three types of muscle activities (isotonic, isometric, and passive stretching) were analyzed and validated by ultrasound imaging. Bimodal signals during dynamic walking experiments with different level-ground walking speeds were also investigated. The application of the bimodal sensor was verified in gait phase estimation, and results show that the assembly of both modalities significantly reduce (p < 0.05) the average estimation error across all subjects and all walking speeds to 3.82%. Demonstrations show the potential of this sensing device for informative evaluation of muscular activities, and its abilities in human-robot interaction.

Neural prosthesis control restores near-normative neuromechanics in standing postural control

Current lower-limb prostheses do not provide active assistance in postural control tasks to maintain the user's balance, particularly in situations of perturbation. In this study, we aimed to address this missing function by enabling neural control of robotic lower-limb prostheses. Specifically, electromyographic (EMG) signals (amplified neural control signals) recorded from antagonistic residual ankle muscles were used to drive a robotic prosthetic ankle directly and continuously. Participants with transtibial amputation were recruited and trained in using the EMG-driven robotic ankle. We studied how using the EMG-controlled ankle affected the participants' anticipatory and compensatory postural control strategies and stability under expected perturbations compared with using their daily passive devices. We investigated the similarity of neuromuscular coordination (by analyzing motor modules) of the participants, using either device in a postural sway task, to that of able-bodied controls. Results showed that, compared with their passive prosthesis, the EMG-controlled prosthesis enabled participants to use near-normative postural control strategies, as evidenced by improved between-limb symmetry in intact-prosthetic center-of-pressure and joint angle excursions. Participants substantially improved postural stability, as evidenced by a reduction in steps or falls using the EMG-controlled prosthetic ankle. Furthermore, after relearning to use residual ankle muscles to drive the robotic ankle in postural control, nearly all participants' motor module structure shifted toward that observed in individuals without limb amputations. Here, we have demonstrated the potential benefit of direct EMG control of robotic lower limb prostheses to restore normative postural control strategies (both neural and biomechanical) toward enhancing standing postural stability in amputee users.

Volitional EMG Control Enables Stair Climbing with a Robotic Powered Knee Prosthesis

Existing controllers for robotic powered prostheses regulate the prosthesis speed, timing, and energy generation using predefined position or torque trajectories. This approach enables climbing stairs step-over-step. However, it does not provide amputees with direct volitional control of the robotic prosthesis, a functionality necessary to restore full mobility to the user. Here we show that proportional electromyographic (EMG) control of the prosthesis knee torque enables volitional control of a powered knee prosthesis during stair climbing. The proposed EMG controller continuously regulates knee torque based on activation of the residual hamstrings, measured using a single EMG electrode located within the socket. The EMG signal is mapped to a desired knee flexion/extension torque based on the prosthesis knee position, the residual limb position, and the interaction with the ground. As a result, the proposed EMG controller enabled an above-knee amputee to climb stairs at different speeds, while carrying additional loads, and even backwards. By enabling direct, volitional control of powered robotic knee prostheses, the proposed EMG controller has the potential to improve amputee mobility in the real world.

A Scientometric Analysis and Visualization of Prosthetic Foot Research Work: 2000 to 2022

This study aims to highlight recent research work on topics around prosthetic feet through a scientometric analysis and historical review. The most cited publications from the Clarivate Analytics Web of Science Core Collection database were identified and analyzed from 1 January 2000 to 31 October 2022. Original articles, reviews with full manuscripts, conference proceedings, early access documents, and meeting abstracts were included. A scientometric visualization analysis of the bibliometric information related to the publications, including the countries, institutions, journals, references, and keywords, was conducted. A total of 1827 publications met the search criteria in this study. The related publications grouped by year show an overall trend of increase during the two decades from 2000 to 2022. The United States is ranked first in terms of overall influence in this field (n = 774). The Northwestern University has published the most papers on prosthetic feet (n = 84). Prosthetics and Orthotics International has published the largest number of studies on prosthetic feet (n = 151). During recent years, a number of studies with citation bursts and burst keywords (e.g., diabetes, gait, pain, and sensor) have provided clues on the hotspots of prosthetic feet and prosthetic foot trends. The findings of this study are based on a comprehensive analysis of the literature and highlight the research topics on prosthetic feet that have been primarily explored. The data provide guidance to clinicians and researchers to further studies in this field.

Synergy-Driven Musculoskeletal Modeling to Estimate Muscle Excitations and Joint Moments at Different Walking Speeds in Individuals with Transtibial Amputation

The main requirement for an amputee is to regain the function of the lost limb. In order to fully benefit from powered prosthetic legs, the user must rely on the dynamic control of the device. Progress in high-level control for powered prosthetic legs is currently challenged by the inability of current control schemes to generalize to large repertoires of movements as well as adapting to external mechanical demands. This ultimately leads the user to adopt compensatory movements, lack of comfort, higher energy requirements during walking and standing. This study uses a feedforward model of muscle activation and force generation that applies mathematical formulations of muscle synergies to generate synthetic activation profiles underlying walking across different speeds. Estimated activation profiles are used to drive forward subject-specific numerical models of the lower extremity musculoskeletal system. The model was validated on one individual with uni-lateral transtibial amputation and its predictions were compared to experimental torques from inverse dynamic calculations. Results showed that a generic muscle synergy driven personalized musculoskeletal model can fit the ankle torques of the intact limb of a person with transtibial amputation (RMSD = 0.1329±0.02). The estimated moments might be suitable as the control signal to drive powered prostheses to ultimately improve physical interaction between the user and a powered prostheses during dynamic motor tasks.

Continuous Phase Estimation in a Variety of Locomotion Modes Using Adaptive Dynamic Movement Primitives

Accurate gait phase estimation algorithms can be used to synchronize the action of wearable robots to the volitional user movements in real time. Current-day gait phase estimation methods are designed mostly for rhythmic tasks and evaluated in highly controlled walking environments (namely, steady-state walking). Here, we implemented adaptive Dynamic Movement Primitives (aDMP) for continuous real-time phase estimation in the most common locomotion activities of daily living, which are level-ground walking, stair negotiation, and ramp negotiation. The proposed method uses the thigh roll angle and foot-contact information and was tested in real time with five subjects. The estimated phase resulted in an average root-mean-square error of 3.98% ± 1.33% and a final estimation error of 0.60% ± 0.55% with respect to the linear phase. The results of this study constitute a viable groundwork for future phase-based control strategies for lower-limb wearable robots, such as robotic prostheses or exoskeletons.

Angle-programmed tendril-like trajectories enable a multifunctional gripper with ultradelicacy, ultrastrength, and ultraprecision

Achieving multicapability in a single soft gripper for handling ultrasoft, ultrathin, and ultraheavy objects is challenging due to the tradeoff between compliance, strength, and precision. Here, combining experiments, theory, and simulation, we report utilizing angle-programmed tendril-like grasping trajectories for an ultragentle yet ultrastrong and ultraprecise gripper. The single gripper can delicately grasp fragile liquids with minimal contact pressure (0.05 kPa), lift objects 16,000 times its own weight, and precisely grasp ultrathin, flexible objects like 4-μm-thick sheets and 2-μm-diameter microfibers on flat surfaces, all with a high success rate. Its scalable and material-independent design allows for biodegradable noninvasive grippers made from natural leaves. Explicitly controlled trajectories facilitate its integration with robotic arms and prostheses for challenging tasks, including picking grapes, opening zippers, folding clothes, and turning pages. This work showcases soft grippers excelling in extreme scenarios with potential applications in agriculture, food processing, prosthesis, biomedicine, minimally invasive surgeries, and deep-sea exploration.

Facial electromyogram-based facial gesture recognition for hands-free control of an AR/VR environment: optimal gesture set selection and validation of feasibility as an assistive technology

The rapid expansion of virtual reality (VR) and augmented reality (AR) into various applications has increased the demand for hands-free input interfaces when traditional control methods are inapplicable (e.g., for paralyzed individuals who cannot move their hands). Facial electromyogram (fEMG), bioelectric signals generated from facial muscles, could solve this problem. Discriminating facial gestures using fEMG is possible because fEMG signals vary with these gestures. Thus, these signals can be used to generate discrete hands-free control commands. This study implemented an fEMG-based facial gesture recognition system for generating discrete commands to control an AR or VR environment. The fEMG signals around the eyes were recorded, assuming that the fEMG electrodes were embedded into the VR head-mounted display (HMD). Sixteen discrete facial gestures were classified using linear discriminant analysis (LDA) with Riemannian geometry features. Because the fEMG electrodes were far from the facial muscles associated with the facial gestures, some similar facial gestures were indistinguishable from each other. Therefore, this study determined the best facial gesture combinations with the highest classification accuracy for 3-15 commands. An analysis of the fEMG data acquired from 15 participants showed that the optimal facial gesture combinations increased the accuracy by 4.7%p compared with randomly selected facial gesture combinations. Moreover, this study is the first to investigate the feasibility of implementing a subject-independent facial gesture recognition system that does not require individual user training sessions. Lastly, our online hands-free control system was successfully applied to a media player to demonstrate the applicability of the proposed system.

Supplementary Information

The online version contains supplementary material available at 10.1007/s13534-023-00277-9.

Robust neural decoding for dexterous control of robotic hand kinematics

BACKGROUND

Manual dexterity is a fundamental motor skill that allows us to perform complex daily tasks. Neuromuscular injuries, however, can lead to the loss of hand dexterity. Although numerous advanced assistive robotic hands have been developed, we still lack dexterous and continuous control of multiple degrees of freedom in real-time. In this study, we developed an efficient and robust neural decoding approach that can continuously decode intended finger dynamic movements for real-time control of a prosthetic hand.

METHODS

High-density electromyogram (HD-EMG) signals were obtained from the extrinsic finger flexor and extensor muscles, while participants performed either single-finger or multi-finger flexion-extension movements. We implemented a deep learning-based neural network approach to learn the mapping from HD-EMG features to finger-specific population motoneuron firing frequency (i.e., neural-drive signals). The neural-drive signals reflected motor commands specific to individual fingers. The predicted neural-drive signals were then used to continuously control the fingers (index, middle, and ring) of a prosthetic hand in real-time.

RESULTS

Our developed neural-drive decoder could consistently and accurately predict joint angles with significantly lower prediction errors across single-finger and multi-finger tasks, compared with a deep learning model directly trained on finger force signals and the conventional EMG-amplitude estimate. The decoder performance was stable over time and was robust to variations of the EMG signals. The decoder also demonstrated a substantially better finger separation with minimal predicted error of joint angle in the unintended fingers.

CONCLUSIONS

This neural decoding technique offers a novel and efficient neural-machine interface that can consistently predict robotic finger kinematics with high accuracy, which can enable dexterous control of assistive robotic hands.

Recent trends and challenges of surface electromyography in prosthetic applications

Surface electromyography (sEMG) meets extensive applications in the field of prosthesis in the current period. The effectiveness of sEMG in prosthesis applications has been verified by numerous revolutionary developments and extensive research attempts. A large volume of research and literature works have explored and validated the vast use of these signals in prostheses as an assistive technology. The objective of this paper is to conduct a systematic review and offer a detailed overview of the work record in the prosthesis and myoelectric interfaces framework. This review utilized a systematic search strategy to identify published articles discussing the state-of-the-art applications of sEMG in prostheses (including upper limb prosthesis and lower limb prostheses). Relevant studies were identified using electronic databases such as PubMed, IEEE Explore, SCOPUS, ScienceDirect, Google Scholar and Web of Science. Out of 3791 studies retrieved from the databases, 188 articles were found to be potentially relevant (after screening of abstracts and application of inclusion-exclusion criteria) and included in this review. This review presents an investigative analysis of sEMG-based prosthetic applications to assist the readers in making further advancements in this field. It also discusses the fundamental advantages and disadvantages of using sEMG in prosthetic applications. It also includes some important guidelines to follow in order to improve the performance of sEMG-based prosthesis. The findings of this study support the widespread use of sEMG in prosthetics. It is concluded that sEMG-based prosthesis technology, still in its sprouting phase, requires significant explorations for further development. Supplementary investigations are necessary in the direction of making a seamless mechanism of biomechatronics for sEMG-based prosthesis by cohesive efforts of robotic researchers and biomedical engineers.

Electromyography-Based Control of Lower Limb Prostheses: A Systematic Review

Most amputations occur in lower limbs and despite improvements in prosthetic technology, no commercially available prosthetic leg uses electromyography (EMG) information as an input for control. Efforts to integrate EMG signals as part of the control strategy have increased in the last decade. In this systematic review, we summarize the research in the field of lower limb prosthetic control using EMG. Four different online databases were searched until June 2022: Web of Science, Scopus, PubMed, and Science Direct. We included articles that reported systems for controlling a prosthetic leg (with an ankle and/or knee actuator) by decoding gait intent using EMG signals alone or in combination with other sensors. A total of 1,331 papers were initially assessed and 121 were finally included in this systematic review. The literature showed that despite the burgeoning interest in research, controlling a leg prosthesis using EMG signals remains challenging. Specifically, regarding EMG signal quality and stability, electrode placement, prosthetic hardware, and control algorithms, all of which need to be more robust for everyday use. In the studies that were investigated, large variations were found between the control methodologies, type of research participant, recording protocols, assessments, and prosthetic hardware.

Database of lower limb kinematics and electromyography during gait-related activities in able-bodied subjects

This data descriptor describes the Roessingh Research & Development-MyLeg database for activity prediction (MyPredict), containing three data sets. These data sets contain data from 55 able-bodied subjects, mean age 24 ± 2 years, measured in 85 measurement sessions. Measurement sessions consisted of trials containing sitting, standing, overground walking, stair ascent, stair descent, ramp ascent, ramp descent, walking on uneven terrain and walking in simulated confined spaces. Subjects were measured using eight inertial measurement units in combination with different types of sEMG. Recorded kinematics consisted of joint angles, sensor accelerations, angular velocity, orientation and virtual marker positions. sEMG was recorded using bipolar sEMG, multi-array sEMG or a combination of both. All data showed excellent correlation with other online available data sets. The data reported in this descriptor forms a solid basis for research into myoelectric pattern recognition, myoelectric control development and electromyography to be used in data-driven applications.

Artificial intelligence meets medical robotics

Artificial intelligence (AI) applications in medical robots are bringing a new era to medicine. Advanced medical robots can perform diagnostic and surgical procedures, aid rehabilitation, and provide symbiotic prosthetics to replace limbs. The technology used in these devices, including computer vision, medical image analysis, haptics, navigation, precise manipulation, and machine learning (ML) , could allow autonomous robots to carry out diagnostic imaging, remote surgery, surgical subtasks, or even entire surgical procedures. Moreover, AI in rehabilitation devices and advanced prosthetics can provide individualized support, as well as improved functionality and mobility (see the figure). The combination of extraordinary advances in robotics, medicine, materials science, and computing could bring safer, more efficient, and more widely available patient care in the future. -Gemma K. Alderton.

High-density Surface and Intramuscular EMG Data from the Tibialis Anterior During Dynamic Contractions

Valid approaches for interfacing with and deciphering neural commands related to movement are critical to understanding muscular coordination and developing viable prostheses and wearable robotics. While electromyography (EMG) has been an established approach for mapping neural input to mechanical output, there is a lack of adaptability to dynamic environments due to a lack of data from dynamic movements. This report presents data consisting of simultaneously recorded high density surface EMG, intramuscular EMG, and joint dynamics from the tibialis anterior during static and dynamic muscle contractions. The dataset comes from seven subjects performing three to five trials each of different types of muscle contractions, both static (isometric) and dynamic (isotonic and isokinetic). Each subject was seated in an isokinetic dynamometer such that ankle movement was isolated and instrumented with four fine wire electrodes and a 126-electrode surface EMG grid. This data set can be used to (i) validate methods for extracting neural signals from surface EMG, (ii) develop models for predicting torque output, or (iii) develop classifiers for movement intent.

The use of nonnormalized surface EMG and feature inputs for LSTM-based powered ankle prosthesis control algorithm development

Advancements in instrumentation support improved powered ankle prostheses hardware development. However, control algorithms have limitations regarding number and type of sensors utilized and achieving autonomous adaptation, which is key to a natural ambulation. Surface electromyogram (sEMG) sensors are promising. With a minimized number of sEMG inputs an economic control algorithm can be developed, whereas limiting the use of lower leg muscles will provide a practical algorithm for both ankle disarticulation and transtibial amputation. To determine appropriate sensor combinations, a systematic assessment of the predictive success of variations of multiple sEMG inputs in estimating ankle position and moment has to conducted. More importantly, tackling the use of nonnormalized sEMG data in such algorithm development to overcome processing complexities in real-time is essential, but lacking. We used healthy population level walking data to (1) develop sagittal ankle position and moment predicting algorithms using nonnormalized sEMG, and (2) rank all muscle combinations based on success to determine economic and practical algorithms. Eight lower extremity muscles were studied as sEMG inputs to a long-short-term memory (LSTM) neural network architecture: tibialis anterior (TA), soleus (SO), medial gastrocnemius (MG), peroneus longus (PL), rectus femoris (RF), vastus medialis (VM), biceps femoris (BF) and gluteus maximus (GMax). Five features extracted from nonnormalized sEMG amplitudes were used: integrated EMG (IEMG), mean absolute value (MAV), Willison amplitude (WAMP), root mean square (RMS) and waveform length (WL). Muscle and feature combination variations were ranked using Pearson's correlation coefficient (r > 0.90 indicates successful correlations), the root-mean-square error and one-dimensional statistical parametric mapping between the original data and LSTM response. The results showed that IEMG+WL yields the best feature combination performance. The best performing variation was MG + RF + VM (rposition = 0.9099 and rmoment = 0.9707) whereas, PL (rposition = 0.9001, rmoment = 0.9703) and GMax+VM (rposition = 0.9010, rmoment = 0.9718) were distinguished as the economic and practical variations, respectively. The study established for the first time the use of nonnormalized sEMG in control algorithm development for level walking.

Probability-Based Rejection of Decoding Output Improves the Accuracy of Locomotion Detection During Gait

Prosthetic users need reliable control over their assistive devices to regain autonomy and independence, particularly for locomotion tasks. Despite the potential for myoelectric signals to reflect the users' intentions more accurately than external sensors, current motorized prosthetic legs fail to utilize these signals, thus hindering natural control. A reason for this challenge could be the insufficient accuracy of locomotion detection when using muscle signals in activities outside the laboratory, which may be due to factors such as suboptimal signal recording conditions or inaccurate control algorithms.This study aims to improve the accuracy of detecting locomotion during gait by utilizing classification post-processing techniques such as Linear Discriminant Analysis with rejection thresholds. We utilized a pre-recorded dataset of electromyography, inertial measurement unit sensor, and pressure sensor recordings from 21 able-bodied participants to evaluate our approach. The data was recorded while participants were ambulating between various surfaces, including level ground walking, stairs, and ramps. The results of this study show an average improvement of 3% in accuracy in comparison with using no post-processing (p-value < 0.05). Participants with lower classification accuracy profited more from the algorithm and showed greater improvement, up to 8% in certain cases. This research highlights the potential of classification post-processing methods to enhance the accuracy of locomotion detection for improved prosthetic control algorithms when using electromyogram signals.Clinical Relevance- Decoding of locomotion intent can be improved using post-processing techniques thus resulting in a more reliable control of lower limb prostheses.

Prediction of Joint Angles Based on Human Lower Limb Surface Electromyography

Wearable exoskeletons can help people with mobility impairments by improving their rehabilitation. As electromyography (EMG) signals occur before movement, they can be used as input signals for the exoskeletons to predict the body's movement intention. In this paper, the OpenSim software is used to determine the muscle sites to be measured, i.e., rectus femoris, vastus lateralis, semitendinosus, biceps femoris, lateral gastrocnemius, and tibial anterior. The surface electromyography (sEMG) signals and inertial data are collected from the lower limbs while the human body is walking, going upstairs, and going uphill. The sEMG noise is reduced by a wavelet-threshold-based complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) reduction algorithm, and the time-domain features are extracted from the noise-reduced sEMG signals. Knee and hip angles during motion are calculated using quaternions through coordinate transformations. The random forest (RF) regression algorithm optimized by cuckoo search (CS), shortened as CS-RF, is used to establish the prediction model of lower limb joint angles by sEMG signals. Finally, root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) are used as evaluation metrics to compare the prediction performance of the RF, support vector machine (SVM), back propagation (BP) neural network, and CS-RF. The evaluation results of CS-RF are superior to other algorithms under the three motion scenarios, with optimal metric values of 1.9167, 1.3893, and 0.9815, respectively.

Surface electromyogram, kinematic, and kinetic dataset of lower limb walking for movement intent recognition

Surface electromyogram (sEMG) offers a rich set of motor information for decoding limb motion intention that serves as a control input to Intelligent human-machine synergy systems (IHMSS). Despite growing interest in IHMSS, the current publicly available datasets are limited and can hardly meet the growing demands of researchers. This study presents a novel lower limb motion dataset (designated as SIAT-LLMD), comprising sEMG, kinematic, and kinetic data with corresponding labels acquired from 40 healthy humans during 16 movements. The kinematic and kinetic data were collected using a motion capture system and six-dimensional force platforms and processed using OpenSim software. The sEMG data were recorded using nine wireless sensors placed on the subjects' thigh and calf muscles on the left limb. Besides, SIAT-LLMD provides labels to classify the different movements and different gait phases. Analysis of the dataset verified the synchronization and reproducibility, and codes for effective data processing are provided. The proposed dataset can serve as a new resource for exploring novel algorithms and models for characterizing lower limb movements.