Figure - available from: Applied Bionics and Biomechanics
This content is subject to copyright. Terms and conditions apply.
![Sensor positions [10, 17, 19, 48–61]. (a) Typical attachment positions of multiple sensors. (b) Type and location of the sensors applied in the papers (IMU: inertial measurement unit; FSR: force sensitive resistor; sEMG: surface electromyography, EEG: electroencephalography; MPJ: metatarsophalangeal joint).](publication/359508306/figure/fig5/AS:1138604676001837@1648475917759/Sensor-positions-10-17-19-48-61-a-Typical-attachment-positions-of-multiple.jpg)
Sensor positions [10, 17, 19, 48–61]. (a) Typical attachment positions of multiple sensors. (b) Type and location of the sensors applied in the papers (IMU: inertial measurement unit; FSR: force sensitive resistor; sEMG: surface electromyography, EEG: electroencephalography; MPJ: metatarsophalangeal joint).
Source publication
![Sensor positions [10, 17, 19, 48–61]. (a) Typical attachment positions...](publication/359508306/figure/fig5/AS:1138604676001837@1648475917759/Sensor-positions-10-17-19-48-61-a-Typical-attachment-positions-of-multiple_Q320.jpg)
In recent decades, although the research on gait recognition of lower limb exoskeleton robot has been widely developed, there are still limitations in rehabilitation training and clinical practice. The emergence of interactive information fusion technology provides a new research idea for the solution of this problem, and it is also the development...
Citations
... Additionally, other aspects, such as identification, detection, and conversion tasks, play essential roles in personalization, safety, and system integration. Generally, deep learning algorithms have been shown to outperform conventional methods on several benchmark computer vision datasets for tasks such as gait recognition for lower limb exoskeletons based on interactive information fusion and predicting trajectory for exoskeleton control methods [47], [48]. By examining these tasks, we can gain valuable insights into the advancements and trends in the field of exoskeleton control using Deep Neural Networks. ...
Recent advancements in robotics have pushed the development of active exoskeletons and orthoses for assistive, augmentative, and rehabilitative purposes. Deep Learning approaches, particularly in motion analysis and prediction, hold promise for enhanced control of lower limb exoskeletons, offering the potential for improved outcomes in assistive and rehabilitative interventions. This review paper explores recent advancements in deep learning approaches for controlling lower limb exoskeletons. The study encompasses papers published from 2018 to the present, focusing on various aspects of deep learning models, including recognition, prediction, and other related tasks. The paper includes 103 papers covering various tasks and parameters like the gait phase, kinematics, and kinetics of the lower limb exoskeleton. Each aspect is thoroughly examined, highlighting the parameters utilized in the respective models. Moreover, the results obtained from these approaches are evaluated and compared against classical control strategies, shedding light on their effectiveness and potential benefits. The review also addresses the limitations of current deep learning techniques in lower limb exoskeleton control and outlines potential avenues for future research and improvement. By consolidating the latest findings and advancements in this field, this review paper provides valuable insights into the application of deep learning in the control of lower limb exoskeletons, paving the way for enhanced rehabilitation and assistive technologies in the future.
... The ULLE applies movement intention recognition, intelligent gait relearning, redundant sensor fusion technology, and bionic wearable exoskeleton design to improve the comfort and training experience of patients. Additionally, the intelligent relearning feature of the ULLE is superior as it promotes active use of the brain in controlling the unaffected limb to lead the interactive movement of both limbs, thereby achieving individualized bilateral combined functional training (BCFT) [24]. The ULLE ideally connects the CNS and PNS to provide a closed-loop control for complete neurorehabilitation in patients with hemiplegia (Fig. 2). ...
Background
Stroke remains the leading cause of both mortality and disability globally. Recovery of limb function in patients with stroke is usually poor and requires an extended period. Consequently, rehabilitation technology in stroke has gained attention. A unilateral lower limb exoskeleton (ULLE), which has an intelligent relearning feature that promotes active engagement of the patient’s brain in controlling of encouraging a patient to actively use their brain to control the unaffected limb to lead the interactive movement of both limbs, thereby achieving individualized bilateral combined functional training, was recently developed to be used in patients with hemiplegia after stroke or traumatic brain injury. However, data on the efficacy and safety of ULLE in patients with stroke are scarce. We aimed to assess the effectiveness and safety of the LiteStepper® ULLE in gait training of patients with post-stroke hemiplegia.
Methods
This study was a multicenter, optimal, open, loaded, randomized controlled trial. Overall, 92 patients in their post-stroke phase from Hangzhou First People’s Hospital, The Second Affiliated Hospital Zhejiang University School of Medicine, The First Hospital of Jiaxing, and The Fifth Affiliated Hospital of Zhengzhou University were enrolled in this study. The experimental group (EG) adopted the LiteStepper® ULLE based on a once-daily 21-day routine rehabilitation. The conventional group (CG) only underwent the once-daily 21-day routine rehabilitation.
Results
The efficacy analysis outcomes (Berg balance scale, Functional Ambulation Category scale, 6-minute walking distance, and Barthel Index) between EG and CG had significant differences (P < 0.05) (analyzed using full analysis and per protocol sets). EG showed better improvements than CG (lower limit value [EG-CG] > 2). Safety analysis showed that only one adverse event related to the device occurred during the study, which verified the safety of using the ULLE for gait training in patients after stroke.
Conclusions
The LiteStepper®ULLE is effective and safe for gait training in patients after stroke.
Trial registration
ClinicalTrials.gov identifier: NCT05360017
... Nowadays, the development of medical technologies and the improvements of living conditions bring convenience and improves quality of life, but the situation of population aging is not optimistic. In the aging process, the gradual decline of lower limb motor function and the mobility inconvenience caused by other diseases have largely affected the life of the elderly [1,2]. In addition, the contradiction between the increasing number of patients with limb injuries caused by stroke and traffic accidents and the current shortage of medical resources (the gap of professional medical nursing personnel has reached millions) is increasingly prominent. ...
Robot knee exoskeletons can not only help the rehabilitation training function of the elderly and disabled patients, but also enhance the performance of healthy people in normal walking and weigh-bearing walking by providing sufficient torques. In recent years, the exoskeletons of knee joints have been extensively explored. The review is to summarize the existing research results of mechanical structure design and actuation technologies, propose the future development trend, and promote the further development of the powered knee exoskeletons, related theories, and engineering applications. In this study, the mechanical structures of knee exoskeletons are first illustrated. Their mechanical structures are classified into two types: simple mechanical structures with one purely rotary DOF and biological geometry-based multi-DOF structures. Subsequently, the actuation design of wearable knee exoskeletons includes conventional driving actuators, pneumatic muscle actuators, variable stiffness actuators, and other actuators are compared and the driving compliance and the difficulty in the accurate control are analyzed. Furthermore, other crucial technologies such as motion intention recognition, control strategy and performance evaluation methods of most knee assistive devices are reviewed. Finally, the key technologies of structural design and actuation design in the research of knee exoskeletons are summarized and future research hotspots are proposed.
... However, the proposed system only detected six types of movements, requiring more effort. In [41], multiple gait recognition systems have been reviewed using lower limb exoskeletons. Multiple levels of data fusion, different features, a variety of pre-processing methods, and diverse classification models have been adopted. ...
Unhealthy lifestyle causes several chronic diseases in humans. Many products are introduced to avoid such illnesses and provide e-learning-based healthcare services. However, the main focus is still on providing comfortable and reliable solutions. Inertial measurement units (IMU) are considered as the most independent and non-intrusive way to monitor and analyze human health via motion patterns detection. Deep learning is also taken as an excellent tool to detect motion patterns from IMU data. In this paper, a deep-learning-based human motion detection approach for smart healthcare learning tool has been proposed. A novel hybrid descriptors-based pre-classification and multi-features analysis algorithm is proposed to classify the human motion for healthcare e-learning. For pre-processing, a quaternion-based filter is utilized to filter the IMU signals. An experiment is performed over the acceleration signals by using minimum and average gravity removal techniques. Next, signal segmentation of multiple time intervals has been applied to segment data and ultimately compare the results to decide which type provides better performance. Then, pre-classification is done using motion pattern identification in the form of active and passive patterns. During the features analysis phase, features have been extracted based on both active and passive motion patterns. Further, an orthogonal fuzzy neighborhood discriminant analysis technique has been used to reduce the dimensionality of the extracted feature vector. Finally, a deep learner known as long-short term memory has been applied to classify the actions of both active and passive motion features for healthcare e-learning systems. For this purpose, we utilized two datasets: REALDISP and wearable computing. The experimental results show that our proposed system for smart healthcare learning outperformed other state-of-the-art systems. The proposed implemented system provided 87.35% accuracy for REALDISP and 85.18% accuracy for wearable computing datasets. Furthermore, the classified motion patterns are provided to a smart healthcare advisor in order to provide live feedback about human health for immediate action.
... EMG signals are the superposition of action potential sequences of motor units generated during muscle contraction, which can reflect the intensity of muscle contraction. Therefore, EMG signals have been widely used in the recognition and prediction of human motion intentions [17]. ...
An exoskeleton is a kind of intelligent wearable device with bioelectronics and biomechanics. To realize its effective assistance to the human body, an exoskeleton needs to recognize the real time movement pattern of the human body in order to make corresponding movements at the right time. However, it is of great difficulty for an exoskeleton to fully identify human motion patterns, which are mainly manifested as incomplete acquisition of lower limb motion information, poor feature extraction ability, and complicated steps. Aiming at the above consideration, the motion mechanisms of human lower limbs have been analyzed in this paper, and a set of wearable bioelectronics devices are introduced based on an electromyography (EMG) sensor and inertial measurement unit (IMU), which help to obtain biological and kinematic information of the lower limb. Then, the Dual Stream convolutional neural network (CNN)-ReliefF was presented to extract features from the fusion sensors’ data, which were input into four different classifiers to obtain the recognition accuracy of human motion patterns. Compared with a single sensor (EMG or IMU) and single stream CNN or manual designed feature extraction methods, the feature extraction based on Dual Stream CNN-ReliefF shows better performance in terms of visualization performance and recognition accuracy. This method was used to extract features from EMG and IMU data of six subjects and input these features into four different classifiers. The motion pattern recognition accuracy of each subject under the four classifiers is above 97%, with the highest average recognition accuracy reaching 99.12%. It can be concluded that the wearable bioelectronics device and Dual Stream CNN-ReliefF feature extraction method proposed in this paper enhanced an exoskeleton’s ability to capture human movement patterns, thus providing optimal assistance to the human body at the appropriate time. Therefore, it can provide a novel approach for improving the human-machine interaction of exoskeletons.
Effectively controlling active power-assist lower-limb exoskeletons in a human-in-the-loop manner poses a substantial challenge, demanding an approach that ensures wearer autonomy while seamlessly adapting to diverse wearer needs. This paper introduces a novel hierarchical control scheme comprising five integral components: intention recognition layer, dynamics feedforward layer, force distribution layer, feedback compensation layer, as well as sensors and actuators. The intention recognition layer predicts the wearer’s movement and enables wearer-dominant movement through integrated force and position sensors. The force distribution layer effectively resolves the statically indeterminate problem in the context of double-foot support, showcasing flexible control modes. The dynamics feedforward layer mitigates the effect of the exoskeleton itself on movement. Meanwhile, the feedback compensation layer provides reliable closed-loop control. This approach mitigates abrupt changes in joint torques during frequent transitions between swing and stance phases by decomposed dynamics. Validating this innovative hierarchical control scheme on a hydraulic exoskeleton platform through a series of experiments, the results demonstrate its capability to deliver assistance in various modes such as stepping, squatting, and jumping while adapting seamlessly to different terrains.
Human motion intention (HMI) has increasingly gained concerns in lower limb exoskeletons (LLEs). Human motion intention recognition (HMIR) is the precondition of realizing active compliance control in LLEs. Accurate and efficient recognition of the HMI will benefit the LLEs achieving natural and effective human-robot interaction (HRI) and improving the wearing comfort level. A systematic review on HMIR is of great significance in developing LLEs. However, there is no literature comprehensively describing the development roadmap of the human lower limb motion intention recognition (HLLMIR) in the LLEs so far. In order to have a comprehensive understanding of the HLLMIR and explore the current research status and development trend of LLEs, this paper provides a systematic review of the HLLMIR research for LLEs. Firstly, the HMI mechanism and understanding are fully illustrated, and the HMIR tasks pertaining to lower limb motions (LLMs) are elaborated on. Next, the intention-related sensing signals with different sources are dissected in detail, including bioelectric signals of electroencephalography (EEG) and electromyogram (EMG), biomechanical signals, and multisource signals fusion. The HMIR methods for the LLEs are thoroughly addressed and analyzed, the methods are categorized as model-based like musculoskeletal model, and model-free method involving Heuristic rule-based, conventional machine learning (ML)-based, and deep learning (DL)-based. Finally, an overall discussion on the recognition tasks, sensing signals, recognition methods, and performance assessments is given, and thus the research challenges of the HLLMIR are summarized and prospected.
