A Novel TCN-LSTM Hybrid Model for sEMG-Based Continuous Estimation of Wrist Joint Angles

Surface electromyography (sEMG) offers a novel method in human-machine interactions (HMIs) since it is a distinct physiological electrical signal that conceals human movement intention and muscle information. Unfortunately, the nonlinear and non-smooth features of sEMG signals often make joint angle estimation difficult. This paper proposes a joint angle prediction model for the continuous estimation of wrist motion angle changes based on sEMG signals. The proposed model combines a temporal convolutional network (TCN) with a long short-term memory (LSTM) network, where the TCN can sense local information and mine the deeper information of the sEMG signals, while LSTM, with its excellent temporal memory capability, can make up for the lack of the ability of the TCN to capture the long-term dependence of the sEMG signals, resulting in a better prediction. We validated the proposed method in the publicly available Ninapro DB1 dataset by selecting the first eight subjects and picking three types of wrist-dependent movements: wrist flexion (WF), wrist ulnar deviation (WUD), and wrist extension and closed hand (WECH). Finally, the proposed TCN-LSTM model was compared with the TCN and LSTM models. The proposed TCN-LSTM outperformed the TCN and LSTM models in terms of the root mean square error (RMSE) and average coefficient of determination (R2). The TCN-LSTM model achieved an average RMSE of 0.064, representing a 41% reduction compared to the TCN model and a 52% reduction compared to the LSTM model. The TCN-LSTM also achieved an average R2 of 0.93, indicating an 11% improvement over the TCN model and an 18% improvement over the LSTM model.

Knee Angle Estimation from Surface EMG during Walking Using Attention-Based Deep Recurrent Neural Networks: Feasibility and Initial Demonstration in Cerebral Palsy

Accurately estimating knee joint angle during walking from surface electromyography (sEMG) signals can enable more natural control of wearable robotics like exoskeletons. However, challenges exist due to variability across individuals and sessions. This study evaluates an attention-based deep recurrent neural network combining gated recurrent units (GRUs) and an attention mechanism (AM) for knee angle estimation. Three experiments were conducted. First, the GRU-AM model was tested on four healthy adolescents, demonstrating improved estimation compared to GRU alone. A sensitivity analysis revealed that the key contributing muscles were the knee flexor and extensors, highlighting the ability of the AM to focus on the most salient inputs. Second, transfer learning was shown by pretraining the model on an open source dataset before additional training and testing on the four adolescents. Third, the model was progressively adapted over three sessions for one child with cerebral palsy (CP). The GRU-AM model demonstrated robust knee angle estimation across participants with healthy participants (mean RMSE 7 degrees) and participants with CP (RMSE 37 degrees). Further, estimation accuracy improved by 14 degrees on average across successive sessions of walking in the child with CP. These results demonstrate the feasibility of using attention-based deep networks for joint angle estimation in adolescents and clinical populations and support their further development for deployment in wearable robotics.

Continuous Kalman Estimation Method for Finger Kinematics Tracking from Surface Electromyography

Deciphering hand motion intention from surface electromyography (sEMG) encounters challenges posed by the requisites of multiple degrees of freedom (DOFs) and adaptability. Unlike discrete action classification grounded in pattern recognition, the pursuit of continuous kinematics estimation is appreciated for its inherent naturalness and intuitiveness. However, prevailing estimation techniques contend with accuracy limitations and substantial computational demands. Kalman estimation technology, celebrated for its ease of implementation and real-time adaptability, finds extensive application across diverse domains. This study introduces a continuous Kalman estimation method, leveraging a system model with sEMG and joint angles as inputs and outputs. Facilitated by model parameter training methods, the approach deduces multiple DOF finger kinematics simultaneously. The method's efficacy is validated using a publicly accessible database, yielding a correlation coefficient (CC) of 0.73. With over 45,000 windows for training Kalman model parameters, the average computation time remains under 0.01 s. This pilot study amplifies its potential for further exploration and application within the realm of continuous finger motion estimation technology.

Graph-Driven Simultaneous and Proportional Estimation of Wrist Angle and Grasp Force via High-Density EMG

Myoelectric prostheses are generally unable to accurately control the position and force simultaneously, prohibiting natural and intuitive human-machine interaction. This issue is attributed to the limitations of myoelectric interfaces in effectively decoding multi-degree-of-freedom (multi-DoF) kinematic and kinetic information. We thus propose a novel multi-task, spatial-temporal model driven by graphical high-density electromyography (HD-EMG) for simultaneous and proportional control of wrist angle and grasp force. Twelve subjects were recruited to perform three multi-DoF movements, including wrist pronation/supination, wrist flexion/extension, and wrist abduction/adduction while varying grasp force. Experimental results demonstrated that the proposed model outperformed five baseline models, with the normalized root mean square error of 13.2% and 9.7% and the correlation coefficient of 89.6% and 91.9% for wrist angle and grasp force estimation, respectively. In addition, the proposed model still maintained comparable accuracy even with a significant reduction in the number of HD-EMG electrodes. To the best of our knowledge, this is the first study to achieve simultaneous and proportional wrist angle and grasp force control via HD-EMG and has the potential to empower prostheses users to perform a broader range of tasks with greater precision and control, ultimately enhancing their independence and quality of life.

Continuous Motion Intention Prediction Using sEMG for Upper-Limb Rehabilitation: A Systematic Review of Model-Based and Model-Free Approaches

Upper limb functional impairments persisting after stroke significantly affect patients' quality of life. Precise adjustment of robotic assistance levels based on patients' motion intentions using sEMG signals is crucial for active rehabilitation. This paper systematically reviews studies on continuous prediction of upper limb single joints and multi-joint combinations motion intention using Model-Based (MB) and Model-Free (MF) approaches over the past decade, based on 186 relevant studies screened from six major electronic databases. The findings indicate ongoing challenges in terms of subject composition, algorithm robustness and generalization, and algorithm feasibility for practical applications. Moreover, it suggests integrating the strengths of both MB and MF approaches to improve existing algorithms. Therefore, future research should further explore personalized MB-MF combination methods incorporating deep learning, attention mechanisms, muscle synergy features, motor unit features, and closed-loop feedback to achieve precise, real-time, and long-duration prediction of multi-joint complex movements, while further refining the transfer learning strategy for rapid algorithm deployment across days and subjects. Overall, this review summarizes the current research status, significant findings, and challenges, aiming to inspire future research on predicting upper limb motion intentions based on sEMG.

A rotary transformer cross-subject model for continuous estimation of finger joints kinematics and a transfer learning approach for new subjects

Introduction

Surface Electromyographic (sEMG) signals are widely utilized for estimating finger kinematics continuously in human-machine interfaces (HMI), and deep learning approaches are crucial in constructing the models. At present, most models are extracted on specific subjects and do not have cross-subject generalizability. Considering the erratic nature of sEMG signals, a model trained on a specific subject cannot be directly applied to other subjects. Therefore, in this study, we proposed a cross-subject model based on the Rotary Transformer (RoFormer) to extract features of multiple subjects for continuous estimation kinematics and extend it to new subjects by adversarial transfer learning (ATL) approach.

Methods

We utilized the new subject's training data and an ATL approach to calibrate the cross-subject model. To improve the performance of the classic transformer network, we compare the impact of different position embeddings on model performance, including learnable absolute position embedding, Sinusoidal absolute position embedding, and Rotary Position Embedding (RoPE), and eventually selected RoPE. We conducted experiments on 10 randomly selected subjects from the NinaproDB2 dataset, using Pearson correlation coefficient (CC), normalized root mean square error (NRMSE), and coefficient of determination (R2) as performance metrics.

Results

The proposed model was compared with four other models including LSTM, TCN, Transformer, and CNN-Attention. The results demonstrated that both in cross-subject and subject-specific cases the performance of RoFormer was significantly better than the other four models. Additionally, the ATL approach improves the generalization performance of the cross-subject model better than the fine-tuning (FT) transfer learning approach.

Discussion

The findings indicate that the proposed RoFormer-based method with an ATL approach has the potential for practical applications in robot hand control and other HMI settings. The model's superior performance suggests its suitability for continuous estimation of finger kinematics across different subjects, addressing the limitations of subject-specific models.

Single-Channel sEMG-Based Estimation of Knee Joint Angle Using a Decomposition Algorithm With a State-Space Model

Accurate human motion estimation is crucial for effective and safe human-robot interaction when using robotic devices for rehabilitation or performance enhancement. Although surface electromyography (sEMG) signals have been widely used to estimate human movements, conventional sEMG-based methods, which need sEMG signals measured from multiple relevant muscles, are usually subject to some limitations, including interference between sEMG sensors and wearable robots/environment, complicated calibration, as well as discomfort during long-term routine use. Few methods have been proposed to deal with these limitations by using single-channel sEMG (i.e., reducing the sEMG sensors as much as possible). The main challenge for developing single-channel sEMG-based estimation methods is that high estimation accuracy is difficult to be guaranteed. To address this problem, we proposed an sEMG-driven state-space model combined with an sEMG decomposition algorithm to improve the accuracy of knee joint movement estimation based on single-channel sEMG signals measured from gastrocnemius. The effectiveness of the method was evaluated via both single- and multi-speed walking experiments with seven and four healthy subjects, respectively. The results showed that the normal root-mean-squared error of the estimated knee joint angle using the method could be limited to 15%. Moreover, this method is robust with respect to variations in walking speeds. The estimation performance of this method was basically comparable to that of state-of-the-art studies using multi-channel sEMG.

Multi-scale EMG classification with spatial-temporal attention for prosthetic hands

A classification framework for hand gestures using Electromyography (EMG) signals in prosthetic hands is presented. Leveraging the multi-scale characteristics and temporal nature of EMG signals, a Convolutional Neural Network (CNN) is used to extract multi-scale features and classify them with spatial-temporal attention. A multi-scale coarse-grained layer introduced into the input of one-dimensional CNN (1D-CNN) facilitates multi-scale feature extraction. The multi-scale features are fed into the attention layer and subsequently given to the fully connected layer to perform classification. The proposed model achieves classification accuracies of 93.4%, 92.8%, 91.3%, and 94.1% for Ninapro DB1, DB2, DB5, and DB7 respectively, thereby enhancing the confidence of prosthetic hand users.

Attention-Based Deep Recurrent Neural Network to Estimate Knee Angle During Walking from Lower-Limb EMG

Accurate prediction of joint angle during walking from surface electromyography (sEMG) offers the potential to infer movement intention and therefore represents a potentially useful approach for adaptive control of wearable robotics. Here, we present the use of a recurrent neural network (RNN) with gated recurrent units (GRUs) and an attention mechanism to estimate knee angle during overground walking from sEMG and its initial offline validation in healthy adolescents. Our results show that the attention mechanism improved estimation accuracy by focusing on the most relevant parts of the input dataset within each time window, particularly muscles active during knee excursion. Sensitivity analysis revealed knee extensor and flexor muscles to be most salient in accurately estimating joint angle. Additionally, we demonstrate the ability of the GRU-RNN approach to accurately estimate knee angle during overground walking in a child with cerebral palsy (CP) in the presence of exoskeleton knee extension assistance. Collectively, our findings establish the initial feasibility of using this approach to estimate user movement from sEMG, which is particularly important for developing robotic exoskeletons for children with neuromuscular disorders such as CP.

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.

Bio-robotics research for non-invasive myoelectric neural interfaces for upper-limb prosthetic control: a 10-year perspective review

A decade ago, a group of researchers from academia and industry identified a dichotomy between the industrial and academic state-of-the-art in upper-limb prosthesis control, a widely used bio-robotics application. They proposed that four key technical challenges, if addressed, could bridge this gap and translate academic research into clinically and commercially viable products. These challenges are unintuitive control schemes, lack of sensory feedback, poor robustness and single sensor modality. Here, we provide a perspective review on the research effort that occurred in the last decade, aiming at addressing these challenges. In addition, we discuss three research areas essential to the recent development in upper-limb prosthetic control research but were not envisioned in the review 10 years ago: deep learning methods, surface electromyogram decomposition and open-source databases. To conclude the review, we provide an outlook into the near future of the research and development in upper-limb prosthetic control and beyond.