Introduction Wearable exoskeletons are emerging technologies for providing movement assistance and rehabilitation for people with motor disorders. In this study, we focus on the specific gait pathology dropfoot, which is common after a stroke. Dropfoot makes it difficult to achieve foot clearance during swing and heel contact at early stance and often necessitates compensatory movements. Methods We developed a soft ankle exoskeleton consisting of actuation and transmission systems to assist two degrees of freedom simultaneously: dorsiflexion and eversion, then performed several proof-of-concept experiments on non-disabled persons. The actuation system consists of two motors worn on a waist belt. The transmission system provides assistive force to the medial and lateral sides of the forefoot via Bowden cables. The coupling design enables variable assistance of dorsiflexion and inversion at the same time, and a force-free controller is proposed to compensate for device resistance. We first evaluated the performance of the exoskeleton in three seated movement tests: assisting dorsiflexion and eversion, controlling plantarflexion, and compensating for device resistance, then during walking tests. In all proof-of-concept experiments, dropfoot tendency was simulated by fastening a weight to the shoe over the lateral forefoot. Results In the first two seated tests, errors between the target and the achieved ankle joint angles in two planes were low; errors of <1.5 degrees were achieved in assisting dorsiflexion and/or controlling plantarflexion and of <1.4 degrees in assisting ankle eversion. The force-free controller in test three significantly compensated for the device resistance during ankle joint plantarflexion. In the gait tests, the exoskeleton was able to normalize ankle joint and foot segment kinematics, specifically foot inclination angle and ankle inversion angle at initial contact and ankle angle and clearance height during swing. Discussion Our findings support the feasibility of the new ankle exoskeleton design in assisting two degrees of freedom at the ankle simultaneously and show its potential to assist people with dropfoot and excessive inversion.

Accurate and timely movement intention detection can facilitate exoskeleton control during transitions between different locomotion modes. Detecting movement intentions in real environments remains a challenge due to unavoidable environmental uncertainties. False movement intention detection may also induce risks of falling and general danger for exoskeleton users. To this end, in this study, we developed a method for detecting human movement intentions in real environments. The proposed method is capable of online self-correcting by implementing a decision fusion layer. Gaze data from an eye tracker and inertial measurement unit (IMU) signals were fused at the feature extraction level and used to predict movement intentions using 2 different methods. Images from the scene camera embedded on the eye tracker were used to identify terrains using a convolutional neural network. The decision fusion was made based on the predicted movement intentions and identified terrains. Four able-bodied participants wearing the eye tracker and 7 IMU sensors took part in the experiments to complete the tasks of level ground walking, ramp ascending, ramp descending, stairs ascending, and stair descending. The recorded experimental data were used to test the feasibility of the proposed method. An overall accuracy of 93.4% was achieved when both feature fusion and decision fusion were used. Fusing gaze data with IMU signals improved the prediction accuracy.

Integrating mobile eye-tracking and motion capture emerges as a promising approach in studying visual-motor coordination, due to its capability of expressing gaze data within the same laboratory-centered coordinate system as body movement data. In this paper, we proposed an integrated eye-tracking and motion capture system, which can record and analyze temporally and spatially synchronized gaze and motion data during dynamic movement. The accuracy of gaze measurement were evaluated on five participants while they were instructed to view fixed vision targets at different distances while standing still or walking towards the targets. Similar accuracy could be achieved in both static and dynamic conditions. To demonstrate the usability of the integrated system, several walking tasks were performed in three different pathways. Results revealed that participants tended to focus their gaze on the upcoming path, especially on the downward path, possibly for better navigation and planning. In a more complex pathway, coupled with more gaze time on the pathway, participants were also found having the longest step time and shortest step length, which led to the lowest walking speed. It was believed that the integration of eye-tracking and motion capture is a feasible and promising methodology quantifying visual-motor coordination in locomotion.

There is an increasing demand for accurately predicting human movement intentions. To be effective, predictions must be performed as early as possible in the preceding step, though precisely how early has been studied relatively little; how and when a person's movement patterns in a transition step deviate from those in the preceding step must be clearly defined. In this study, we collected motion kinematics, kinetics and electromyography data from 9 able-bodied participants during 7 locomotion modes. Twelve types of steps between the 7 locomotion modes were studied, including 5 continuous steps (taking another step in the same locomotion mode) and 7 transitions steps (taking a step from one locomotion mode into another). For each joint degree of freedom, joint angles, angular velocities, moments, and moment rates were compared between continuous steps and transition steps, and the relative timing during the transition step at which these parameters diverged from those of a continuous step, which we refer to as transition starting times, were identified using multiple analyses of variance. Muscle synergies were also extracted for each step, and we studied in which locomotion modes these synergies were common (task-shared) and in which modes they were specific (task-specific). The transition starting times varied among different transitions and joint degrees of freedom. Most transitions started in the swing phase of the transition step. These findings can be applied to determine the critical timing at which a powered assistive device must adapt its control to enable safe and comfortable support to a user.

Detecting human movement intentions is fundamental to neural control of robotic exoskeletons, as it is essential for achieving seamless transitions between different locomotion modes. In this study, we enhanced a muscle synergy-inspired method of locomotion mode identification by fusing the electromyography data with two types of data from wearable sensors (inertial measurement units), namely linear acceleration and angular velocity. From the finite state machine perspective, the enhanced method was used to systematically identify 2 static modes, 7 dynamic modes, and 27 transitions among them. In addition to the five broadly studied modes (level ground walking, ramps ascent/descent, stairs ascent/descent), we identified the transition between different walking speeds and modes of ramp walking at different inclination angles. Seven combinations of sensor fusion were conducted, on experimental data from 8 able-bodied adult subjects, and their classification accuracy and prediction time were compared. Prediction based on a fusion of electromyography and gyroscope (angular velocity) data predicted transitions earlier and with higher accuracy. All transitions and modes were identified with a total average classification accuracy of 94.5% with fused sensor data. For nearly all transitions, we were able to predict the next locomotion mode 300-500ms prior to the step into that mode.

People walk on different types of terrain daily; for instance, level-ground walking, ramp and stair ascent and descent, and stepping over obstacles are common activities in daily life. Movement patterns change as people move from one terrain to another. The prediction of transitions between locomotion modes is important for developing assistive devices, such as exoskeletons, as the optimal assistive strategies may differ for different locomotion modes. The prediction of locomotion mode transitions is often accompanied by gait-event detection that provides important information during locomotion about critical events, such as foot contact (FC) and toe off (TO). In this study, we introduce a method to integrate locomotion mode prediction and gait-event identification into one machine learning framework, comprised of two multilayer perceptrons (MLP). Input features to the framework were from fused data from wearable sensors-specifically, electromyography sensors and inertial measurement units. The first MLP successfully identified FC and TO, FC events were identified accurately, and a small number of misclassifications only occurred near TO events. A small time difference (2.5 ms and -5.3 ms for FC and TO, respectively) was found between predicted and true gait events. The second MLP correctly identified walking, ramp ascent, and ramp descent transitions with the best aggregate accuracy of 96.3%, 90.1%, and 90.6%, respectively, with sufficient prediction time prior to the critical events. The models in this study demonstrate high accuracy in predicting transitions between different locomotion modes in the same side's mid- to late stance of the stride prior to the step into the new mode using data from EMG and IMU sensors. Our results may help assistive devices achieve smooth and seamless transitions in different locomotion modes for those with motor disorders.

Exoskeletons are increasingly used in rehabilitation and daily life in patients with motor disorders after neurological injuries. In this paper, a realistic human knee exoskeleton model based on a physical system was generated, a human–machine system was created in a musculoskeletal modeling software, and human–machine interactions based on different assistive strategies were simulated. The developed human–machine system makes it possible to compute torques, muscle impulse, contact forces, and interactive forces involved in simulated movements. Assistive strategies modeled as a rotational actuator, a simple pendulum model, and a damped pendulum model were applied to the knee exoskeleton during simulated normal and fast gait. We found that the rotational actuator–based assistive controller could reduce the user's required physiological knee extensor torque and muscle impulse by a small amount, which suggests that joint rotational direction should be considered when developing an assistive strategy. Compared to the simple pendulum model, the damped pendulum model based controller made little difference during swing, but further decreased the user's required knee flexor torque during late stance. The trade-off that we identified between interaction forces and physiological torque, of which muscle impulse is the main contributor, should be considered when designing controllers for a physical exoskeleton system. Detailed information at joint and muscle levels provided in this human–machine system can contribute to the controller design optimization of assistive exoskeletons for rehabilitation and movement assistance.

There is an increasing demand for accurate prediction of joint moments using wearable sensors for robotic exoskeletons to achieve precise control and for rehabilitation care to remotely monitor users’ condition. In this study, we used electromyography (EMG) signals to first identify muscle synergies, then used them to train of a long short-term memory network to predict knee joint moments during walking. Kinematics, ground reaction forces, and EMG from 10 muscles on the right limb were collected from 6 able-bodied subjects during normal gait. Between 4 and 6 muscle synergies were extracted from the EMG signals, generating two outputs - the muscle synergies weight matrix and the time-dependent muscle synergies action signals. The muscle synergies action signals and measured knee joint moments from inverse dynamics were then used as inputs to train the joint moment prediction model using a long short-term memory network. For testing, between4 and 7 EMG signals were used to estimate the muscle synergies action signals with the extracted muscle synergies weights matrix. The estimated muscle synergies action signals were then used to predict knee joint moments. Knee joint moments were also predicted directly from all 10 EMGs, then from 4-7EMG signals using another long short-term memory network. Prediction accuracy from the synergies-trained network vs. the EMG-trained network were compared, using the same number of EMG signals in each. Prediction error with respect to moments measured via inverse dynamics was computed for both networks. Knee moments predicted with as few as 4 EMGswas at least as accurate as moments predicted from all 10 EMGswhen muscle synergies were exploited. Predicted knee moments from muscle synergies achieved an average of 4.63% root mean square error from 4 EMG signals, which was lower than error when predicted directly from 4 EMG signals (5.63%).

Lower extremity powered exoskeletons help people with movement disorders to perform daily activities and are used increasingly in gait retraining and rehabilitation. Studies of powered exoskeletons often focus on technological aspects such as actuators, control methods, energy and effects on gait. Limited research has been conducted on how different mechanical design parameters can affect the user. In this paper, we study the effects of weight distributions of knee exoskeleton components on simulated muscle activities during three functional movements. Four knee exoskeleton CAD models were developed based on actual motor and gear reducer products. Different placements of the motor and gearbox resulted in different weight distributions. One unilateral knee exoskeleton prototype was fabricated and tested on 5 healthy subjects. Simulation results were compared to observed electromyography signals. Muscle activities varied among weight distributions and movements, wherein no one physical design was optimal for all movements. We describe how a powered exoskeleton's core components can be expected to affect a user's ability and performance. Exoskeleton physical design should ideally take the user's activity goals and ability into consideration.

 People walk on different terrains daily, for instance, level-ground walking, ramp and stair ascent and descent, and stepping over obstacles are common activities in daily life. Movementspatterns change as people move from one terrain to another. Prediction of transitions between locomotion modes is important for developing assistive devices such as exoskeletons, as optimal assistive strategies may differ for different locomotion modes. Prediction of locomotion mode transitions is often accompanied by gait event detection that provides important information during locomotion about critical events, such as foot contact (FC) and toe off (TO). In this study, we introduce a method to integrate locomotion mode prediction and gait event identification into one machine learning framework, comprised of two multilayer perceptrons (MLP). Input features to the framework were from fused data from wearable sensors, specifically, electromyography sensors and inertial measurement units. The first MLP successfully identified FC and TO; FC events were identified accurately, and a small number of misclassifications only occurred near TO events. A small time difference (2.5 ms and -5.3 ms for FC and TO respectively) was found between predicted and true gait events. The second MLP correctly identified walking, ramp ascent, and ramp descent transitions with the best aggregate accuracy of 96.3%, 90.1%, and 90.6%, respectively, with sufficient prediction time prior to the critical events. The models in this study demonstrate high accuracy in predicting transitions between different locomotion modes in the same side’s mid-to late stance of the stride prior to the step into the new model using data from EMG and IMUs sensors. Our results may help assistive devices achieve smooth and seamless transitions in different locomotion modes for the person with motor disorders.