Extraction of Nonlinear Synergies for Proportional and Simultaneous Estimation of Finger Kinematics.

OBJECTIVE: Proportional and simultaneous est-imation of finger kinematics from surface EMG based on the assumption that there exists a correlation between muscle activations and finger kinematics in low dimensional space. METHODS: We employ Manifold Relevance Determination (MRD), a multi-view learning model with a nonparametric Bayesian approach, to extract the nonlinear muscle and kinematics synergies and the relationship between them by studying muscle activations (input-space) together with the finger kinematics (output-space). RESULTS: This study finds that there exist muscle synergies which are associated with kinematic synergies. The acquired nonlinear synergies and the association between them has further been utilized for the estimation of finger kinematics from muscle activation inputs, and the proposed approach has outperformed other commonly used linear and nonlinear regression approaches with an average correlation coefficient of 0.91±0.03. CONCLUSION: There exists an association between muscle and kinematic synergies which can be used for the proportional and simultaneous estimation of finger kinematics from the muscle activation inputs. SIGNIFICANCE: The findings of this study not only presents a viable approach for accurate and intuitive myoelectric control but also provides a new perspective on the muscle synergies in the motor control community.

Modeling dynamic high-DOF finger postures from surface EMG using nonlinear synergies in latent space representation.

Accurate proportional myoelectric control of the hand is important in replicating dexterous manipulation in robot prostheses and orthoses. However, this is still difficult to achieve due to the complex and high degree-of-freedom (DOF) nature present in the governing musculoskeletal system. To address this problem, we suggest using a low dimensional encoding based on nonlinear synergies to represent both the high-DOF finger joint kinematics and the coordination of muscle activities taken from surface electromyographic (EMG) signals. Generating smooth multi-finger movements using EMG inputs is then done by using a shared Gaussian Process latent variable model that learns a dynamical model between both the kinematic and EMG data represented in a shared latent space. The experimental results show that the method is able to synthesize continuous movements of a full five-finger hand model, with total dimensions as large as 69 (although highly redundant and correlated). Finally, by comparing the estimation performances when the number of EMG latent dimensions are varied, we show that these synergistic features can capture the variance, shared and specific to the observed kinematics.

Continuous and simultaneous estimation of finger kinematics using inputs from an EMG-to-muscle activation model.

BACKGROUND: Surface electromyography (EMG) signals are often used in many robot and rehabilitation applications because these reflect motor intentions of users very well. However, very few studies have focused on the accurate and proportional control of the human hand using EMG signals. Many have focused on discrete gesture classification and some have encountered inherent problems such as electro-mechanical delays (EMD). Here, we present a new method for estimating simultaneous and multiple finger kinematics from multi-channel surface EMG signals. METHOD: In this study, surface EMG signals from the forearm and finger kinematic data were extracted from ten able-bodied subjects while they were tasked to do individual and simultaneous multiple finger flexion and extension movements in free space. Instead of using traditional time-domain features of EMG, an EMG-to-Muscle Activation model that parameterizes EMD was used and shown to give better estimation performance. A fast feed forward artificial neural network (ANN) and a nonparametric Gaussian Process (GP) regressor were both used and evaluated to estimate complex finger kinematics, with the latter rarely used in the other related literature. RESULTS: The estimation accuracies, in terms of mean correlation coefficient, were 0.85 ± 0.07, 0.78 ± 0.06 and 0.73 ± 0.04 for the metacarpophalangeal (MCP), proximal interphalangeal (PIP) and the distal interphalangeal (DIP) finger joint DOFs, respectively. The mean root-mean-square error in each individual DOF ranged from 5 to 15%. We show that estimation improved using the proposed muscle activation inputs compared to other features, and that using GP regression gave better estimation results when using fewer training samples. CONCLUSION: The proposed method provides a viable means of capturing the general trend of finger movements and shows a good way of estimating finger joint kinematics using a muscle activation model that parameterizes EMD. The results from this study demonstrates a potential control strategy based on EMG that can be applied for simultaneous and continuous control of multiple DOF(s) devices such as robotic hand/finger prostheses or exoskeletons.

Estimation of continuous multi-DOF finger joint kinematics from surface EMG using a multi-output Gaussian Process.

Surface electromyographic (EMG) signals have often been used in estimating upper and lower limb dynamics and kinematics for the purpose of controlling robotic devices such as robot prosthesis and finger exoskeletons. However, in estimating multiple and a high number of degrees-of-freedom (DOF) kinematics from EMG, output DOFs are usually estimated independently. In this study, we estimate finger joint kinematics from EMG signals using a multi-output convolved Gaussian Process (Multi-output Full GP) that considers dependencies between outputs. We show that estimation of finger joints from muscle activation inputs can be improved by using a regression model that considers inherent coupling or correlation within the hand and finger joints. We also provide a comparison of estimation performance between different regression methods, such as Artificial Neural Networks (ANN) which is used by many of the related studies. We show that using a multi-output GP gives improved estimation compared to multi-output ANN and even dedicated or independent regression models.

Control of an optimal finger exoskeleton based on continuous joint angle estimation from EMG signals.

Patients suffering from loss of hand functions caused by stroke and other spinal cord injuries have driven a surge in the development of wearable assistive devices in recent years. In this paper, we present a system made up of a low-profile, optimally designed finger exoskeleton continuously controlled by a user's surface electromyographic (sEMG) signals. The mechanical design is based on an optimal four-bar linkage that can model the finger's irregular trajectory due to the finger's varying lengths and changing instantaneous center. The desired joint angle positions are given by the predictive output of an artificial neural network with an EMG-to-Muscle Activation model that parameterizes electromechanical delay (EMD). After confirming good prediction accuracy of multiple finger joint angles we evaluated an index finger exoskeleton by obtaining a subject's EMG signals from the left forearm and using the signal to actuate a finger on the right hand with the exoskeleton. Our results show that our sEMG-based control strategy worked well in controlling the exoskeleton, obtaining the intended positions of the device, and that the subject felt the appropriate motion support from the device.

Continuous estimation of finger joint angles using muscle activation inputs from surface EMG signals.

Prediction of dynamic hand finger movements has many clinical and engineering applications in the control of human interface devices such as those used in virtual reality control, robot prosthesis and rehabilitation aids. Surface electromyography (sEMG) signals have often been used in the mentioned applications because these reflect the motor intention of users very well. In this study, we present a method to estimate the finger joint angles of a hand from sEMG signals that considers electromechanical delay (EMD), which is inherent when EMG signals are captured alongside motion data. We use the muscle activation obtained from the sEMG signals as input to a neural network. In this muscle activation model, the EMD is parameterized and automatically obtained through optimization. With this method, we can predict the finger joint angles with sEMG signals in both periodic and nonperiodic free movements of the flexion and extension movement of the fingers. Our results show correlation as high as 0.92 between the actual and predicted metacarpophalangeal (MCP) joint angles for periodic finger flexion movements, and as high as 0.85 for nonperiodic movements, which are more dynamic and natural.