Wearable Exoskeleton Research Articles

Effects of overground gait training assisted by a wearable exoskeleton in patients with Parkinson’s disease

BackgroundIn the recent past, wearable devices have been used for gait rehabilitation in patients with Parkinson’s disease. The objective of this paper is to analyze the outcome of a wearable hip orthosis whose assistance adapts in real time to the patient’s gait kinematics via adaptive oscillators. In particular, this study focuses on a metric characterizing natural gait variability, i.e., the level of long-range autocorrelations (LRA) in series of stride durations.MethodsEight patients with Parkinson’s disease (Hoehn and Yahr stages 1-2.5) performed overground gait training three times per week for four consecutive weeks, assisted by a wearable hip orthosis. Gait was assessed based on performance metrics such as the hip range of motion, speed, stride length and duration, and the level of LRA in inter-stride time series assessed using the Adaptive Fractal Analysis. These metrics were measured before, directly after, and 1 month after training.ResultsAfter training, patients increased their hip range of motion, their gait speed and stride length, and decreased their stride duration. These improvements were maintained 1 month after training. Regarding long-range autocorrelations, the population’s behavior was standardized towards a metric closer to the one of healthy individuals after training, but with no retention after 1 month.ConclusionThis study showed that an overground gait training with adaptive robotic assistance has the potential to improve key gait metrics that are typically affected by Parkinson’s disease and that lead to higher prevalence of fall.Trial registration: ClinicalTrials.gov Identifer NCT04314973. Registered on 11 April 2020.

SEMG-Based End-to-End Continues Prediction of Human Knee Joint Angles Using the Tightly Coupled Convolutional Transformer Model.

Wearable exoskeleton robots can promote the rehabilitation of patients with physical dysfunction. And improving human-computer interaction performance is a significant challenge for exoskeleton robots. The traditional feature extraction process based on surface Electromyography(sEMG) is complex and requires manual intervention, making real-time performance difficult to guarantee. In this study, we propose an end-to-end method to predict human knee joint angles based on sEMG signals using a tightly coupled convolutional transformer (TCCT) model. We first collected sEMG signals from 5 healthy subjects. Then, the envelope was extracted from the noise-removed sEMG signal and used as the input to the model. Finally, we developed the TCCT model to predict the knee joint angle after 100 ms. For the prediction performance, we used the Root Mean Square Error(RMSE), Pearson Correlation Coefficient(CC), and Adjustment R2 as metrics to evaluate the error between the actual knee angle and the predicted knee angle. The results show that the model can predict the human knee angle quickly and accurately. The mean RMSE, Adjustment R2, and (CC) values of the model are 3.79°, 0.96, and 0.98, respectively, which are better than traditional deep learning models such as Informer (4.14, 0.95, 0.98), CNN (5.56, 0.89, 0.96) and CNN-BiLSTM (3.97, 0.95, 0.98). In addition, the prediction time of our proposed model is only 11.67±0.67 ms, which is less than 100 ms. Therefore, the real-time and accuracy of the model can meet the continuous prediction of human knee joint angle in practice.

Wearable Exoskeleton Robotic Device for Upper Limb by Using 3d Printer

Dyskinesia of upper limb caused by stroke, sports injury, or traffic accident limits the ability to perform the activities of daily livings. This systems caused by numbness of face, arm and legs. It affects the person one side of the body recently the use of hand exoskeleton for assistance and motor rehabilitation has become increasingly widespread. Most of the 3D exoskeleton are customized, replication and maintenance as a low cost. We are used to predict the stroke patient based on arm band, STM 32 controller and gyro sensor to increasing the repetition movement and enhance their function. This device can use out of the hospital environment.

Wearable Exoskeleton Robotic Device for Upper Limb by Using 3d Printer

Dyskinesia of upper limb caused by stroke, sports injury, or traffic accident limits the ability to perform the activities of daily livings. This systems caused by numbness of face, arm and legs. It affects the person one side of the body recently the use of hand exoskeleton for assistance and motor rehabilitation has become increasingly widespread. Most of the 3D exoskeleton are customized, replication and maintenance as a low cost. We are used to predict the stroke patient based on arm band, STM 32 controller and gyro sensor to increasing the repetition movement and enhance their function. This device can use out of the hospital environment.

A Pilot Study of an Innovative Hand Exoskeleton: Nuada Glove.

The human hand is a crucial anatomical structure, and its complexity enables humans to grasp tools essential for daily life activities.Consequently, hand disabilities have a negativeand profoundimpact on people'sautonomy in performing everyday tasks.The Nuada Glove (Nuada,Braga, Portugal) is a wearable exoskeleton robotic device designed to assist individuals with hand impairments or weakness inregaining hand function, particularly in grasping movements.This pilot studyaims to evaluateits impact on improving hand function in first-time users with hand disabilities and to assess its usability.A total of 63 participants with hand disabilities were asked to complete a series of exercises that simulated various human grasping motions, initially without any assistanceand then with the Nuada Glove. Of the participants,98% exhibited measurable improvement in hand function in at least one exercise.This pilot study, conducted in a controlled environment, clearly demonstrated thebenefits of the Nuada Glove and its ease of use.Future studies should expand from this one to assess the use of the Nuada Glove in a real-world environment with continuous use.

A qualitative study to elicit user requirements for lower limb wearable exoskeletons for gait rehabilitation in spinal cord injury

ObjectiveWe aim to determine a comprehensive set of requirements, perceptions, and expectations that people with spinal cord injury (SCI) and the clinicians in charge of their rehabilitation have regarding the use of wearable robots (WR) for gait rehabilitation.BackgroundThere are concerns due to the limited user acceptance of WR for gait rehabilitation. Developers need to emphasize understanding the needs and constraints of all stakeholders involved, including the real-life dynamics of rehabilitation centers.Methods15 people with SCI, 9 without experience with WR and 6 with experience with these technologies, and 10 clinicians from 3 rehabilitation centers in Spain were interviewed. A directed content analysis approach was used.Results78 codes grouped into 9 categories (physical results, usability, psychology-related codes, technical characteristics, activities, acquisition issues, context of use, development of the technologies and clinical rehabilitation context) were expressed by at least 20% of the users interviewed, of whom 16 were not found in the literature. The agreement percentage between each group and subgroup included in the study, calculated as the number of codes that more than 20% of both groups expressed, divided over the total amount of codes any of those two groups agreed on (≥ 20%), showed limited agreement between patients and clinicians (50.00%) and between both types of patients (55.77%). The limited accessibility and availability of lower limb exoskeletons for gait rehabilitation arose in most of the interviews.ConclusionsThe limited agreement percentage between patients and clinicians indicates that including both types of users in the design process of these technologies is important, given that their requirements are complementary. Engaging users with prior technology experience is recommended, as they often exhibit strong internal consensus and articulate well-defined requirements. This study adds up the knowledge available in the literature and the new codes found in our data, which enlighten important aspects that ought to be addressed in the field to develop technologies that respond to users’ needs, are usable and feasible to implement in their intended contexts.ApplicationThe set of criteria summarized in our study will be useful to guide the design, development, and evaluation of WR for gait rehabilitation to meet user’s needs and allow them to be implemented in their intended context of use.

Multivariate CNN Model for Human Locomotion Activity Recognition with a Wearable Exoskeleton Robot.

This study introduces a novel convolutional neural network (CNN) architecture, encompassing both single and multi-head designs, developed to identify a user's locomotion activity while using a wearable lower limb robot. Our research involved 500 healthy adult participants in an activities of daily living (ADL) space, conducted from 1 September to 30 November 2022. We collected prospective data to identify five locomotion activities (level ground walking, stair ascent/descent, and ramp ascent/descent) across three terrains: flat ground, staircase, and ramp. To evaluate the predictive capabilities of the proposed CNN architectures, we compared its performance with three other models: one CNN and two hybrid models (CNN-LSTM and LSTM-CNN). Experiments were conducted using multivariate signals of various types obtained from electromyograms (EMGs) and the wearable robot. Our results reveal that the deeper CNN architecture significantly surpasses the performance of the three competing models. The proposed model, leveraging encoder data such as hip angles and velocities, along with postural signals such as roll, pitch, and yaw from the wearable lower limb robot, achieved superior performance with an inference speed of 1.14 s. Specifically, the F-measure performance of the proposed model reached 96.17%, compared to 90.68% for DDLMI, 94.41% for DeepConvLSTM, and 95.57% for LSTM-CNN, respectively.

A Wearable Device for Upper Limb Rehabilitation and Assistance Based on Fluid Actuators and Myoelectric Control

Wearable exoskeleton solutions for upper limb rehabilitation or assistance, particularly for the hand area, have become increasingly attractive to researchers, proving to be effective over time in treating hand movement impairments following various neurological diseases. Our aim in the present work is to design a wearable exoskeleton device for active hand rehabilitation/assist control based on myoelectric signal (EMG) capture from forearm muscles, which is easy to wear by the user, comfortable, lightweight, and relatively inexpensive to make. The actuators use two different lengths to increase biocompatibility with the anatomy of the hand, and PneuNets fluid actuators are used. Their design to meet force and bending requirements was based on finite element numerical simulations, and the actuators were designed based on a clear design methodology to achieve the best possible quality. Tests on healthy subjects show that the EMG-based control strategy meets the needs of rehabilitation/assistive hand therapy, finding a comfortable and easy-to-use device. Future directions will focus on developing the device to meet rehabilitation needs for the entire upper limb and integrating the device into virtual reality (VR) through immersive devices.

Magnetoactive microlattice metamaterials with highly tunable stiffness and fast response rate

Active metamaterials with shapes or mechanical properties that can be controlled remotely are promising candidates for soft robots, flexible electronics, and medical applications. However, current active metamaterials often have long response times and short ranges of linear working strains. Here, we demonstrate magnetoactive microlattice metamaterials constructed from 3D-printed, ultra-flexible polymer shells filled with magnetorheological (MR) fluid. Under compressive stress, the magnetorheological fluid develops hydrostatic pressure, allowing for a linear compression strain of more than 30% without buckling. We further show that under a relatively low magnetic field strength (approximately 60 mT), the microlattices can become approximately 200% stiffer than those in a relaxed state, and the energy absorption increases ~16 times. Furthermore, our microlattices showed an ultra-low response time with “field on” and “field off” times of ~200 ms and ~50 ms, respectively. The ability to continuously tune the mechanical properties of these materials in real time make it possible to modulate stress‒strain behavior on demand. Our study provides a new route toward large-scale, highly tunable, and remotely controllable metamaterials with potential applications in wearable exoskeletons, tactile sensors, and medical supports.

Fractional-Order Prescribed Performance Sliding-Mode Control With Time-Delay Estimation for Wearable Exoskeletons

Wearable exoskeletons can help people with spinal cord injuries regain mobility. For the control of wearable exoskeletons, transient performance and steady-state performance are the important indices to be considered. In this paper, a model-free fractional-order prescribed performance sliding mode control scheme is proposed for the joint angle tracking control. Time delay control is developed based on the ultra-local model of the wearable exoskeleton to form the model-free feature. Afterward, a novel exponential-type barrier Lyapunov function is designed to ensure the prescribed transient performance on the tracking errors. Then, a fractional-order sliding mode surface is introduced, based on the exponential-type barrier Lyapunov function and fractional-order sliding mode surface, a fixed-time sliding mode controller is designed to further enhance the control performance. Benefiting from the above methods, the proposed controller is model-free and has fixed-time convergence with prescribed performance. In addition, the adjustable range of the parameters is enlarged by the fractional-order sliding mode surface. Stability is analyzed based on the Lyapunov theory. Finally, experiments are implemented in the wearable exoskeleton experimental platform, experiment results demonstrate the effectiveness of the proposed scheme.

RETRACTED: A Newly-Designed Wearable Robotic Hand Exoskeleton Controlled by EMG Signals and ROS Embedded Systems

One of the most difficult parts of stroke therapy is hand mobility recovery. Indeed, stroke is a serious medical disorder that can seriously impair hand and locomotor movement. To improve hand function in stroke patients, new medical technologies, such as various wearable devices and rehabilitation therapies, are being developed. In this study, a new design of electromyography (EMG)-controlled 3D-printed hand exoskeleton is presented. The exoskeleton was created to help stroke victims with their gripping abilities. Computer-aided design software was used to create the device’s 3D architecture, which was then printed using a polylactic acid filament. For online classifications, the performance of two classifiers—the support vector machine (SVM) and the K-near neighbor (KNN)—was compared. The Robot Operating System (ROS) connects all the various system nodes and generates the decision for the hand exoskeleton. The selected classifiers had high accuracy, reaching up to 98% for online classification performed with healthy subjects. These findings imply that the new wearable exoskeleton, which could be controlled in accordance with the subjects’ motion intentions, could aid in hand rehabilitation for a wider motion range and greater dexterity.

A Deep Learning Control Strategy of IMU-Based Joint Angle Estimation for Hip Power-Assisted Swimming Exoskeleton

Wearable exoskeleton techniques are becoming mature and wildly used in many areas. However, the biggest challenge lies in that the control system should recognize and follow the wearer’s motion correctly and quickly. In this study, we propose a deep learning control strategy utilizing inertial measurement units (IMU) for hip power-assisted swimming exoskeleton. The control strategy includes two steps: Step 1, the swimming stroke is recognized by a deep convolutional neural and bidirectional long short-term memory network (DCNN-BiLSTM); Step 2, the hip joint angles are estimated with BiLSTM network belonging to the recognized motion to predict the hip trajectory. The dataset of motion recognition and estimation of four swimming strokes are collected by placing IMUs on swimmers’ back and thighs. We conduct offline and online testing of control strategy for accuracy and robustness validation. During offline testing, we achieve an accuracy more than 96% of motion recognition and root mean square error (RMSE) less than 1.2° of hip joint angle estimation, outperforming 2.76% of accuracy and 0.09° of RMSE compared with those of ELM or CNN-GRU. During online testing, the pre-trained networks are transplanted into a Raspberry Pi 4B and achieve 8.47ms for conducting one motion recognition and 6.72ms for one hip joint angle estimation on average, which are far less than 300ms of delayed sensations between the action of exoskeleton and human, while keeping a satisfying recognition accuracy as well. The experiment results show that the accuracy and robustness of proposed control strategy are stable and feasible for the application to exoskeletons.

Exoskeleton For Specially Abled

This is a paper about a wearable exoskeleton that addresses the lack of assistive devices for people with walking difficulties. The research revolves around the major problem in which the inpatient suffer for their dependency on a caretaker for basic tasks such as toiletries and fetching water or food or even for basic cores for themselves. People with disabilities suffer from many social and mental pressures due to exclusion from society just for being different from normal human beings. Hence, the usage and purpose of robotic technology trims down this segregation and promote vocational incorporation.

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.

Subject specific optimal control of powered knee exoskeleton to assist human lifting tasks under controlled environment

AbstractWearable robots, sometimes known as exoskeletons, are incredible devices for improving human strength, reducing fatigue, and restoring impaired mobility. The control of powered exoskeletons, on the other hand, is still a challenge. This necessitates the development of a technique to simulate exoskeleton–wearer interaction. This study uses a two-dimensional human skeletal model with a powered knee exoskeleton to predict the optimal lifting motion and assistive torque. For lifting motion prediction, an inverse dynamics optimization formulation is utilized. In addition, the electromechanical dynamics of the exoskeleton DC motor are modeled in the lifting optimization formulation. The design variables are human joint angle profiles and exoskeleton motor current profiles. The human joint torque square is minimized subject to physical and lifting task constraints. Then, the lifting optimization problem is solved by the gradient-based sparse nonlinear optimizer (SNOPT). Furthermore, the optimal exoskeleton torque is implemented through a two-phase control strategy to provide optimal assistance in lifting. Experimental validations of the optimal control with 6 Nm and 16 Nm maximum assistive torque are presented. Both 6 Nm and 16 Nm maximum optimal assistance of the exoskeletons reduce the mean values of vastus lateralis, biceps femoris, and latissimus dorsi muscle activations compared to the lifting without the exoskeleton. However, the mean value of the vastus medialis activation is increased by a small amount for the exoskeleton case, although its peak value is reduced. Finally, the experimental results demonstrate that the proposed lifting optimization formulation and control strategy are promising for powered knee exoskeleton for lifting tasks.

The Influence of Gait Phase on Predicting Lower-Limb Joint Angles

Machine learning has seen a rapid increase in applications that harness wearable signals to improve human mobility. Previous work has used machine learning predictors as a means of continuously estimating locomotor intent. Although previous studies perform gait phase classification and joint-level angular prediction, there are currently no studies that compare joint-level prediction performance at various phases of gait. As such, the purpose of this offline study was to analyze how machine learning and deep learning models perform at predicting future joint angles during various phases of gait. EMG, IMU, and joint kinematics collected during level-ground walking from thirty participants and data was separated into six distinct gait phases. Random forest, long short-term memory (LSTM), and bidirectional LSTM was used to predict lower-limb joint angles during the phases of gait. Results indicate that bidirectional LSTM is the most robust performer across the gait cycle, with a mean prediction RMSE of 1.42-5.71 degrees. Our study shows how deep learning methods, such as bidirectional LSTM, can accurately estimate joint angles throughout the gait cycle. Furthermore, we propose future work of deploying models which accurately predict future joint angles throughout the gait cycle for users to sufficiently operate a wearable exoskeleton during locomotion.

Predicting the metabolic cost of exoskeleton-assisted squatting using foot pressure features and machine learning.

Introduction: Recent studies found that wearable exoskeletons can reduce physical effort and fatigue during squatting. In particular, subject-specific assistance helped to significantly reduce physical effort, shown by reduced metabolic cost, using human-in-the-loop optimization of the exoskeleton parameters. However, measuring metabolic cost using respiratory data has limitations, such as long estimation times, presence of noise, and user discomfort. A recent study suggests that foot contact forces can address those challenges and be used as an alternative metric to the metabolic cost to personalize wearable robot assistance during walking. Methods: In this study, we propose that foot center of pressure (CoP) features can be used to estimate the metabolic cost of squatting using a machine learning method. Five subjects' foot pressure and metabolic cost data were collected as they performed squats with an ankle exoskeleton at different assistance conditions in our prior study. In this study, we extracted statistical features from the CoP squat trajectories and fed them as input to a random forest model, with the metabolic cost as the output. Results: The model predicted the metabolic cost with a mean error of 0.55W/kg on unseen test data, with a high correlation (r = 0.89, p < 0.01) between the true and predicted cost. The features of the CoP trajectory in the medial-lateral direction of the foot (xCoP), which relate to ankle eversion-inversion, were found to be important and highly correlated with metabolic cost. Conclusion: Our findings indicate that increased ankle eversion (outward roll of the ankle), which reflects a suboptimal squatting strategy, results in higher metabolic cost. Higher ankle eversion has been linked with the etiology of chronic lower limb injuries. Hence, a CoP-based cost function in human-in-the-loop optimization could offer several advantages, such as reduced estimation time, injury risk mitigation, and better user comfort.

Effects and Safety of Wearable Exoskeleton for Robot-Assisted Gait Training: A Retrospective Preliminary Study.

Wearable devices for robot-assisted gait training (RAGT) provide overground gait training for the rehabilitation of neurological injuries. We aimed to evaluate the effectiveness and safety of RAGT in patients with a neurologic deficit. Twenty-eight patients receiving more than ten sessions of overground RAGT using a joint-torque-assisting wearable exoskeletal robot were retrospectively analyzed in this study. Nineteen patients with brain injury, seven patients with spinal cord injury and two patients with peripheral nerve injury were included. Clinical outcomes, such as the Medical Research Council scale for muscle strength, Berg balance scale, functional ambulation category, trunk control tests, and Fugl-Meyer motor assessment of the lower extremities, were recorded before and after RAGT. Parameters for RAGT and adverse events were also recorded. The Medical Research Council scale scores for muscle strength (36.6 to 37.8), Berg balance scale (24.9 to 32.2), and functional ambulation category (1.8 to 2.7) significantly improved after overground RAGT (p < 0.05). The familiarization process was completed within six sessions of RAGT. Only two mild adverse events were reported. Overground RAGT using wearable devices can improve muscle strength, balance, and gait function. It is safe in patients with neurologic injury.

Reconfigurable Soft Pneumatic Actuators Using Extensible Fabric-Based Skins.

The development of the field of soft robotics has led to the exploration of novel techniques to manufacture soft actuators, which provide distinct advantages for wearable assistive robotics. One subset of these soft pneumatic actuators is conventionally developed from silicone, fabrics, and thermoplastic polyurethane (TPU). Each of these materials in isolation possesses limitations of low-stress capacity, low-design complexity, and high-input pressure requirements, respectively. Combining these materials can overcome some limitations and maintain their desirable properties. In this article, we explore one such composite design scheme using a combination of silicone polymer-based bladder and reconfigurable fabric skin made from an anisotropic extensible fabric. The silicone polymer bladder acts as the hermetic seal, while this skin acts as the constraint. Bending and torsional actuators were designed utilizing the anisotropy of these fabrics. The torsional actuator designs can achieve over 540° of twist, significantly larger than previously reported in the literature, owing to the lower mechanical impedance of the extensible fabrics. Actuators with 360° of bending were also fabricated using this method. In addition, the lack of TPU-backed or inextensible fabrics reduces the actuator's stiffness, leading to lower actuation pressures. Skin-based designs also confer the advantage of modularity, reconfigurability, and the ability to achieve complex motions by tuning the properties of the bladder and the skin. For applications with high-force requirements, such as wearable exoskeletons, we demonstrate the utility of multilayer design schemes. A multilayer bending actuator generated 190 N of force at 100 kPa and was shown to be a candidate for wearable assistive devices. In addition, torsional designs were shown to have utility in practical scenarios such as screwing on a bottle cap and turning knobs. Thus, we present a novel fabric-skin-based design concept that is highly versatile and customizable for various application requirements.

Safety evaluation of human–robot collaboration for industrial exoskeleton

Wearable exoskeletons are a type of collaborative robots that are widely used in human–robot collaboration, and their safety in the collaboration process has received significant attention. An industrial exoskeleton was the research object of this study. First, the influencing factors found in the relevant literature were analyzed and summarized. Subsequently, a group decision-making method was used to formulate preliminarily evaluation indicators. These indicators were then evaluated using the Delphi method. Based on the finalized evaluation indices, a physical safety evaluation index system for industrial exoskeleton human–robot collaboration was constructed, and an evaluation index model was established to evaluate the physical safety. Simultaneously, a questionnaire on the perceived safety was used to evaluate the perceptions of human operators on the safety of industrial exoskeleton human–robot collaboration. These two types of safety, the physical and perceived safety, were combined in an industrial exoskeleton human–robot collaboration safety evaluation. Three different industrial exoskeletons were used in the case study for this research. Their safety was evaluated using the model proposed in this study, which enabled human operators to quickly and effectively select an industrial exoskeleton through comparative analysis.