Kinematics, Speed, and Anthropometry-Based Ankle Joint Torque Estimation: A Deep Learning Regression Approach

Abstract

Powered Assistive Devices (PADs) have been proposed to enable repetitive, user-oriented gait rehabilitation. They may include torque controllers that typically require reference joint torque trajectories to determine the most suitable level of assistance. However, a robust approach able to automatically estimate user-oriented reference joint torque trajectories, namely ankle torque, while considering the effects of varying walking speed, body mass, and height on the gait dynamics, is needed. This study evaluates the accuracy and generalization ability of two Deep Learning (DL) regressors (Long-Short Term Memory and Convolutional Neural Network (CNN)) to generate user-oriented reference ankle torque trajectories by innovatively customizing them according to the walking speed (ranging from 1.0 to 4.0 km/h) and users’ body height and mass (ranging from 1.51 to 1.83 m and 52.0 to 83.7 kg, respectively). Furthermore, this study hypothesizes that DL regressors can estimate joint torque without resourcing electromyography signals. CNN was the most robust algorithm (Normalized Root Mean Square Error: 0.70 ± 0.06; Spearman Correlation: 0.89 ± 0.03; Coefficient of Determination: 0.91 ± 0.03). No statistically significant differences were found in CNN accuracy (p-value > 0.05) whether electromyography signals are included as inputs or not, enabling a less obtrusive and accurate setup for torque estimation.

A Review on Locomotion Mode Recognition and Prediction When Using Active Orthoses and Exoskeletons

“…Considering this information and the used gait speeds, only the study [ 33 ] seems to address the typical walking speeds of these patients. There is evidence that waking speed affects the lower limb biomechanics [ 50 , 51 ]. Consequently, the LM decoding tools’ performance may be jeopardized if walking speeds different from those used during the algorithms’ training process (commonly involving healthy subjects walking at higher self-selected speeds than patients) are employed [ 52 , 53 , 54 ].…”

Assist-As-Needed Control Strategy of Bilateral Upper Limb Rehabilitation Robot Based on GMM

“…The identification of the remaining ability of patients is more complex [5,7,10], without further identifying whether the patients are in a state of needing assistance when completing the task, which has great limitations. Nonetheless, because of the advantages of the GMM algorithm in data modeling [15], and how GMM has been successfully applied in robot demonstration learning [16][17][18], this paper proposes an AAN control strategy based on GMM in order to solve the problem of whether patients need assistance when completing tasks. Firstly, a new end-effector bilateral mirror upper limb rehabilitation robot was designed for patients with upper limb motor dysfunction, differentiating it from other upper limb rehabilitation robots [18,21] that can only be provided by the virtual environment, which cannot accurately express the real intention of the patient.…”

“…GMM is a type of probability density function that requires less data to obtain good results and does not require any prior knowledge, compared with other commonly used techniques, such as a neural network [15] providing faster regression [16], which is widely used in data modeling. The model can parameterize a set of data points and its underlying functions into a weighted sum of the Gaussian component density, each of which has its own mean and covariance.…”

PMSM Speed Control Based on Particle Swarm Optimization and Deep Deterministic Policy Gradient under Load Disturbance

“…Supervised learning deals mainly with classification and regression problems. It requires well-labelled dataset, such as a convolutional neural network [27], long shortterm memory [28], and random forest [29]. In addition, in the literature [30], a two-layer recursive neural network was used to approximate a motor model, and the network was considered to be a motor speed predictor.…”