Sensors

Research

20 pages, 5299 KiB

Open AccessArticle

Trajectory Planning and Simulation Study of Redundant Robotic Arm for Upper Limb Rehabilitation Based on Back Propagation Neural Network and Genetic Algorithm

by Xiaohan Qie, Cunfeng Kang, Guanchen Zong and Shujun Chen

Sensors 2022, 22(11), 4071; https://doi.org/10.3390/s22114071 - 27 May 2022

Cited by 22 | Viewed by 2661

Abstract

In this study, a Back Propagation (BP) neural network algorithm based on Genetic Algorithm (GA) optimization is proposed to plan and optimize the trajectory of a redundant robotic arm for the upper limb rehabilitation of patients. The feasibility of the trajectory was verified [...] Read more.

In this study, a Back Propagation (BP) neural network algorithm based on Genetic Algorithm (GA) optimization is proposed to plan and optimize the trajectory of a redundant robotic arm for the upper limb rehabilitation of patients. The feasibility of the trajectory was verified by numerical simulations. First, the collected dataset was used to train the BP neural network optimized by the GA. Subsequently, the critical points designated by the rehabilitation physician for the upper limb rehabilitation were used as interpolation points for cubic B−spline interpolation to plan the motion trajectory. The GA optimized the planned trajectory with the goal of time minimization, and the feasibility of the optimized trajectory was analyzed with MATLAB simulations. The planned trajectory was smooth and continuous. There was no abrupt change in location or speed. Finally, simulations revealed that the optimized trajectory reduced the motion time and increased the motion speed between two adjacent critical points which improved the rehabilitation effect and can be applied to patients with different needs, which has high application value. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

11 pages, 1210 KiB

Open AccessArticle

Feasibility of Overground Gait Training Using a Joint-Torque-Assisting Wearable Exoskeletal Robot in Children with Static Brain Injury

by Juntaek Hong, Jongweon Lee, Taeyoung Choi, Wooin Choi, Taeyong Kim, Kyuwan Kwak, Seongjun Kim, Kyeongyeol Kim and Daehyun Kim

Sensors 2022, 22(10), 3870; https://doi.org/10.3390/s22103870 - 19 May 2022

Cited by 7 | Viewed by 2805

Abstract

Pediatric gait disorders are often chronic and accompanied by various complications, which challenge rehabilitation efforts. Here, we retrospectively analyzed the feasibility of overground robot-assisted gait training (RAGT) using a joint-torque-assisting wearable exoskeletal robot. In this study, 17 children with spastic cerebral palsy, cerebellar [...] Read more.

Pediatric gait disorders are often chronic and accompanied by various complications, which challenge rehabilitation efforts. Here, we retrospectively analyzed the feasibility of overground robot-assisted gait training (RAGT) using a joint-torque-assisting wearable exoskeletal robot. In this study, 17 children with spastic cerebral palsy, cerebellar ataxia, and chronic traumatic brain injury received RAGT sessions. The Gross Motor Function Measure (GMFM), 6-min walk test (6 MWT), and 10-m walk test (10 MWT) were performed before and after intervention. The oxygen rate difference between resting and training was performed to evaluate the intensity of training in randomly selected sessions, while the Quebec User Evaluation of Satisfaction with assistive Technology 2.0 assessment was performed to evaluate its acceptability. A total of four of five items in the GMFM, gait speed on the 10 MWT, and total distance on the 6 MWT showed statistically significant improvement (p < 0.05). The oxygen rate was significantly higher during the training versus resting state. Altogether, six out of eight domains showed satisfaction scores more than four out of five points. In conclusion, overground training using a joint-torque-assisting wearable exoskeletal robot showed improvement in gross motor and gait functions after the intervention, induced intensive gait training, and achieved high satisfaction scores in children with static brain injury. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

20 pages, 3320 KiB

Open AccessArticle

The Middleware for an Exoskeleton Assisting Upper Limb Movement

by Przemyslaw Strzelczyk, Krzysztof Tomczewski and Krzysztof Wrobel

Sensors 2022, 22(8), 2986; https://doi.org/10.3390/s22082986 - 13 Apr 2022

Cited by 2 | Viewed by 1748

Abstract

This article presents the possibilities of newly developed middleware dedicated for distributed and modular control systems. The software enables the exchange of information locally, within one control module, and globally, between many modules. The executed information exchange system speed tests confirmed the correct [...] Read more.

This article presents the possibilities of newly developed middleware dedicated for distributed and modular control systems. The software enables the exchange of information locally, within one control module, and globally, between many modules. The executed information exchange system speed tests confirmed the correct operation of the software. The middleware was used in the control system of the active upper-limb exoskeleton. The upper-limb rehabilitation exoskeleton structure with six degrees of mechanical freedom is presented. The tests were performed using the prototype with three joints. The drives’ models of individual joints were developed and simulated. As a result, the courses of the motion trajectory were shown for different kinds of pressure on the force sensors, and different methods of signal filtering. The tests confirmed a correct operation of middleware and drives control system. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

18 pages, 827 KiB

Open AccessArticle

Performance of Deep Learning Models in Forecasting Gait Trajectories of Children with Neurological Disorders

by Rania Kolaghassi, Mohamad Kenan Al-Hares, Gianluca Marcelli and Konstantinos Sirlantzis

Sensors 2022, 22(8), 2969; https://doi.org/10.3390/s22082969 - 13 Apr 2022

Cited by 12 | Viewed by 3001

Abstract

Forecasted gait trajectories of children could be used as feedforward input to control lower limb robotic devices, such as exoskeletons and actuated orthotic devices (e.g., Powered Ankle Foot Orthosis—PAFO). Several studies have forecasted healthy gait trajectories, but, to the best of our knowledge, [...] Read more.

Forecasted gait trajectories of children could be used as feedforward input to control lower limb robotic devices, such as exoskeletons and actuated orthotic devices (e.g., Powered Ankle Foot Orthosis—PAFO). Several studies have forecasted healthy gait trajectories, but, to the best of our knowledge, none have forecasted gait trajectories of children with pathological gait yet. These exhibit higher inter- and intra-subject variability compared to typically developing gait of healthy subjects. Pathological trajectories represent the typical gait patterns that rehabilitative exoskeletons and actuated orthoses would target. In this study, we implemented two deep learning models, a Long-Term Short Memory (LSTM) and a Convolutional Neural Network (CNN), to forecast hip, knee, and ankle trajectories in terms of corresponding Euler angles in the pitch, roll, and yaw form for children with neurological disorders, up to 200 ms in the future. The deep learning models implemented in our study are trained on data (available online) from children with neurological disorders collected by Gillette Children’s Speciality Healthcare over the years 1994–2017. The children’s ages range from 4 to 19 years old and the majority of them had cerebral palsy (73%), while the rest were a combination of neurological, developmental, orthopaedic, and genetic disorders (27%). Data were recorded with a motion capture system (VICON) with a sampling frequency of 120 Hz while walking for 15 m. We investigated a total of 35 combinations of input and output time-frames, with window sizes for input vectors ranging from 50–1000 ms, and output vectors from 8.33–200 ms. Results show that LSTMs outperform CNNs, and the gap in performance becomes greater the larger the input and output window sizes are. The maximum difference between the Mean Absolute Errors (MAEs) of the CNN and LSTM networks was 0.91 degrees. Results also show that the input size has no significant influence on mean prediction errors when the output window is 50 ms or smaller. For output window sizes greater than 50 ms, the larger the input window, the lower the error. Overall, we obtained MAEs ranging from 0.095–2.531 degrees for the LSTM network, and from 0.129–2.840 degrees for the CNN. This study establishes the feasibility of forecasting pathological gait trajectories of children which could be integrated with exoskeleton control systems and experimentally explores the characteristics of such intelligent systems under varying input and output window time-frames. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

9 pages, 868 KiB

Open AccessArticle

The Effect of a Horse-Riding Simulator with Virtual Reality on Gross Motor Function and Body Composition of Children with Cerebral Palsy: Preliminary Study

by Yong Gi Jung, Hyun Jung Chang, Eun Sol Jo and Da Hye Kim

Sensors 2022, 22(8), 2903; https://doi.org/10.3390/s22082903 - 10 Apr 2022

Cited by 14 | Viewed by 3780

Abstract

This study aimed to evaluate the effect of a horse-riding simulator (HRS) with virtual reality (VR) on gross motor function, balance control, and body composition in children with spastic cerebral palsy (CP). Seventeen preschool and school-aged children with spastic CP were included; 10 [...] Read more.

This study aimed to evaluate the effect of a horse-riding simulator (HRS) with virtual reality (VR) on gross motor function, balance control, and body composition in children with spastic cerebral palsy (CP). Seventeen preschool and school-aged children with spastic CP were included; 10 children in the intervention group (HRS group) received 30 min of HRS with VR training twice a week for a total of 16 sessions in addition to conventional physiotherapy. Seven children in the control group were instructed to perform home-based aerobic exercises twice a week for 8 weeks in addition to conventional physiotherapy. Gross motor function measure (GMFM) and body composition were evaluated before the first session and after the last session. Before and after the 2-month intervention, Pediatric Balance Scale and Timed Up and Go test were evaluated for the HRS group. GMFM scores and body composition changed significantly in the HRS group (p < 0.05). However, no significant differences were observed in the control group. Changes in the GMFM total scores, GMFM dimension D scores, and skeletal muscle mass significantly differed between the HRS and control groups (p < 0.05). HRS with VR may be an effective adjunctive therapeutic approach for the rehabilitation of children with CP. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

21 pages, 3897 KiB

Open AccessArticle

Development of a Prototype Overground Pelvic Obliquity Support Robot for Rehabilitation of Hemiplegia Gait

by Seunghoon Hwang, Seungchan Lee, Dongbin Shin, Inhyuk Baek, Seoyeon Ham and Wansoo Kim

Sensors 2022, 22(7), 2462; https://doi.org/10.3390/s22072462 - 23 Mar 2022

Cited by 4 | Viewed by 2851

Abstract

In this work, we present the overground prototype gait-rehabilitation robot for using motion assistance and training for paralyzed patients. In contrast to the existing gait-rehabilitation robots, which focus on the sagittal plane motion of the hip and knee, we aim to develop a [...] Read more.

In this work, we present the overground prototype gait-rehabilitation robot for using motion assistance and training for paralyzed patients. In contrast to the existing gait-rehabilitation robots, which focus on the sagittal plane motion of the hip and knee, we aim to develop a mobile-based pelvic support gait-rehabilitation system that includes a pelvic obliquity support mechanism and a lower-limb exoskeleton. To achieve this, a scissor mechanism is proposed to generate the paralyzed patient’s pelvic obliquity motion and weight support. Moreover, the lower limb exoskeleton robot is integrated with the developed system to provide the patient’s gait by correcting mechanical aids. We used computer-aided analysis to verify the performance of the prototype hardware itself. Through these methods, it was shown that our motor can sufficiently lift 100 kg of user weight through the scissor mechanism, and that the mobile driving wheel motor can operate at a speed of 1.6 m/s of human walking, showing that it can be used for gait rehabilitation of patients in need of a lower speed. In addition, we verified that the system drives the model by generating pelvic motion, and we verified the position controller of the integrated system, which supports the multi-degree motion by creating hip/knee/pelvic motion with a human dummy mannequin and systems. We believe that the proposed system can help address the complex rehabilitation motion assistance and training of paralyzed patients. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

15 pages, 4698 KiB

Open AccessEditor’s ChoiceArticle

Quantitative Evaluation System of Upper Limb Motor Function of Stroke Patients Based on Desktop Rehabilitation Robot

by Mingliang Zhang, Jing Chen, Zongquan Ling, Bochao Zhang, Yanxin Yan, Daxi Xiong and Liquan Guo

Sensors 2022, 22(3), 1170; https://doi.org/10.3390/s22031170 - 3 Feb 2022

Cited by 16 | Viewed by 3943

Abstract

Rehabilitation training and movement evaluation after stroke have become a research hotspot as stroke has become a very common and harmful disease. However, traditional rehabilitation training and evaluation are mainly conducted under the guidance of rehabilitation doctors. The evaluation process is time-consuming and [...] Read more.

Rehabilitation training and movement evaluation after stroke have become a research hotspot as stroke has become a very common and harmful disease. However, traditional rehabilitation training and evaluation are mainly conducted under the guidance of rehabilitation doctors. The evaluation process is time-consuming and the evaluation results are greatly influenced by doctors. In this study, a desktop upper limb rehabilitation robot was designed and a quantitative evaluation system of upper limb motor function for stroke patients was proposed. The kinematics and dynamics data of stroke patients during active training were collected by sensors. Combined with the scores of patients’ upper limb motor function by rehabilitation doctors using the Wolf Motor Function Test (WMFT) scale, three different quantitative evaluation models of upper limb motor function based on Back Propagation Neural Network (BPNN), K-Nearest Neighbors (KNN), and Support Vector Regression (SVR) algorithms were established. To verify the effectiveness of the quantitative evaluation system, 10 healthy subjects and 21 stroke patients were recruited for experiments. The experimental results show that the BPNN model has the best evaluation performance among the three quantitative evaluation models. The scoring accuracy of the BPNN model reached up to 87.1%. Moreover, there was a significant correlation between the models′ scores and the doctors′ scores. The proposed system can help doctors to quantitatively evaluate the upper limb motor function of stroke patients and accurately master the rehabilitation progress of patients. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

12 pages, 1031 KiB

Open AccessArticle

Kinematic Assessment to Measure Change in Impairment during Active and Active-Assisted Type of Robotic Rehabilitation for Patients with Stroke

by Donghwan Hwang, Joon-Ho Shin and Suncheol Kwon

Sensors 2021, 21(21), 7055; https://doi.org/10.3390/s21217055 - 25 Oct 2021

Cited by 7 | Viewed by 2549

Abstract

Analysis of kinematic features related to clinical assessment scales may qualitatively improve the evaluation of upper extremity movements of stroke patients. We aimed to investigate kinematic features that could correlate the change in the Fugl-Meyer Assessment (FMA) score of stroke survivors through upper [...] Read more.

Analysis of kinematic features related to clinical assessment scales may qualitatively improve the evaluation of upper extremity movements of stroke patients. We aimed to investigate kinematic features that could correlate the change in the Fugl-Meyer Assessment (FMA) score of stroke survivors through upper extremity robotic rehabilitation. We also analyzed whether changes in kinematic features by active and active-assisted robotic rehabilitation correlated differently with changes in FMA scores. Fifteen stroke patients participated in the upper extremity robotic rehabilitation program, and nine kinematic features were calculated from reach tasks for assessment. Simple and multiple linear regression analyses were used to characterize correlations. Features representing movement speed were associated with changes in FMA scores for the group that used an active rehabilitation robot. In contrast, in the group that used an active-assisted rehabilitation robot, features representing movement smoothness were associated with changes in the FMA score. These estimates can be an important basis for kinematic analysis to complement clinical scales. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

9 pages, 597 KiB

Open AccessArticle

Virtual Reality-Incorporated Horse Riding Simulator to Improve Motor Function and Balance in Children with Cerebral Palsy: A Pilot Study

by Hyun Jung Chang, Yong Gi Jung, Young Sook Park, Se Hwi O, Da Hye Kim and Chang Woo Kim

Sensors 2021, 21(19), 6394; https://doi.org/10.3390/s21196394 - 24 Sep 2021

Cited by 5 | Viewed by 3708

Abstract

The horse riding simulator (HRS) reportedly has a beneficial effect on motor function and balance in children with cerebral palsy (CP). However, by itself, the HRS is not a sufficient source of challenge and motivation for children. To address this issue, we combined [...] Read more.

The horse riding simulator (HRS) reportedly has a beneficial effect on motor function and balance in children with cerebral palsy (CP). However, by itself, the HRS is not a sufficient source of challenge and motivation for children. To address this issue, we combined the HRS with virtual reality (VR) to promote somatosensory stimulation and motivation. Sixteen children (ages: 5–17 years) with CP and presenting Gross Motor Function Classification System (GMFCS) levels I–IV were enrolled in the study. Using a head-mounted display and controllers, interventions were carried out over 30-min periods (two rides lasting 12 min each, along with a six-min rest period) twice a week over a period of eight weeks (16 sessions in aggregate). The Pediatric Balance Scale (PBS), Gross Motor Function measure (GMFM)-88, and GMFM-66 scores of each participant were measured before and after the interventions. Statistically significant improvements were observed in the PBS, GMFM-66, the total GMFM-88 scores, and those corresponding to dimensions D and E of GMFM-88 after the intervention (p < 0.05). This study demonstrates that VR-incorporated HRS is effective in improving motor function and balance in children with CP and that its incorporation in conventional PT programs could yield beneficial results. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

10 pages, 791 KiB

Open AccessArticle

Cardiorespiratory Responses to 10 Weeks of Exoskeleton-Assisted Overground Walking Training in Chronic Nonambulatory Patients with Spinal Cord Injury

by Jae Hyeon Park, Hyeon Seong Kim, Seong Ho Jang, Dong Jin Hyun, Sang In Park, JuYoung Yoon, Hyunseop Lim and Mi Jung Kim

Sensors 2021, 21(15), 5022; https://doi.org/10.3390/s21155022 - 24 Jul 2021

Cited by 7 | Viewed by 2445

Abstract

Exercise intensity of exoskeleton-assisted walking in patients with spinal cord injury (SCI) has been reported as moderate. However, the cardiorespiratory responses to long-term exoskeleton-assisted walking have not been sufficiently investigated. We investigated the cardiorespiratory responses to 10 weeks of exoskeleton-assisted walking training in [...] Read more.

Exercise intensity of exoskeleton-assisted walking in patients with spinal cord injury (SCI) has been reported as moderate. However, the cardiorespiratory responses to long-term exoskeleton-assisted walking have not been sufficiently investigated. We investigated the cardiorespiratory responses to 10 weeks of exoskeleton-assisted walking training in patients with SCI. Chronic nonambulatory patients with SCI were recruited from an outpatient clinic. Walking training with an exoskeleton was conducted three times per week for 10 weeks. Oxygen consumption and heart rate (HR) were measured during a 6-min walking test at pre-, mid-, and post-training. Exercise intensity was determined according to the metabolic equivalent of tasks (METs) for SCI and HR relative to the HR reserve (%HRR). Walking efficiency was calculated as oxygen consumption divided by walking speed. The exercise intensity according to the METs (both peak and average) corresponded to moderate physical activity and did not change after training. The %HRR demonstrated a moderate (peak %HRR) and light (average %HRR) exercise intensity level, and the average %HRR significantly decreased at post-training compared with mid-training (31.6 ± 8.9% to 24.3 ± 7.3%, p = 0.013). Walking efficiency progressively improved after training. Walking with an exoskeleton for 10 weeks may affect the cardiorespiratory system in chronic patients with SCI. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

14 pages, 572 KiB

Open AccessArticle

Wearable Robotic Gait Training in Persons with Multiple Sclerosis: A Satisfaction Study

by Diego Fernández-Vázquez, Roberto Cano-de-la-Cuerda, María Dolores Gor-García-Fogeda and Francisco Molina-Rueda

Sensors 2021, 21(14), 4940; https://doi.org/10.3390/s21144940 - 20 Jul 2021

Cited by 10 | Viewed by 3639

Abstract

Wearable exoskeletons have showed improvements in levels of disability and quality of life in people with neurological disorders. However, it is important to understand users’ perspectives. The aim of this study was to explore the patients’ and physiotherapists’ satisfaction from gait training with [...] Read more.

Wearable exoskeletons have showed improvements in levels of disability and quality of life in people with neurological disorders. However, it is important to understand users’ perspectives. The aim of this study was to explore the patients’ and physiotherapists’ satisfaction from gait training with the EKSO GT^® exoskeleton in people with multiple sclerosis (MS). A cross-sectional study with 54 participants was conducted. Clinical data and self-administered scales data were registered from all patients who performed sessions with EKSO GT^®. To evaluate patients’ satisfaction the Quebec User Evaluation with Assistive Technology and Client Satisfaction Questionnaire were used. A high level of satisfaction was reported for patients and for physiotherapists. A moderate correlation was found between the number of sessions and the patients’ satisfaction score (rho = 0.532; p < 0.001), and an excellent correlation between the physiotherapists’ time of experience in neurology rehabilitation and the satisfaction with the possibility of combining the device with other gait trainings approaches (rho = 0.723; p = 0.003). This study demonstrates a good degree of satisfaction for people with MS (31.3 ± 5.70 out of 40) and physiotherapists (38.50 ± 3.67 out of 45 points) with the EKSO GT^®. Effectiveness, safety and impact on the patients’ gait were the most highly rated characteristics of EKSO GT^®. Features such as comfort or weight of the device should be improved from the patients’ perspectives. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

12 pages, 11269 KiB

Open AccessArticle

Differences in Physiological Reactions Due to a Competitive Rehabilitation Game Modality

by José M. Catalán, José V. García-Pérez, Andrea Blanco, David Martínez, Luis D. Lledó and Nicolás García-Aracil

Sensors 2021, 21(11), 3681; https://doi.org/10.3390/s21113681 - 25 May 2021

Cited by 8 | Viewed by 2897

Abstract

Interpersonal rehabilitation games, compared to single-player games, enhance motivation and intensity level. Usually, it is complicated to restrict the use of the system to pairs of impaired patients who have a similar skill level. Thus, such games must be dynamically adapted. Difficulty-adaptation algorithms [...] Read more.

Interpersonal rehabilitation games, compared to single-player games, enhance motivation and intensity level. Usually, it is complicated to restrict the use of the system to pairs of impaired patients who have a similar skill level. Thus, such games must be dynamically adapted. Difficulty-adaptation algorithms are usually based only on performance parameters. In this way, the patient’s condition cannot be considered when adapting the game. Introducing physiological reactions could help to improve decision-making. However, it is difficult to control how social interaction influences physiological reactions, making it difficult to interpret physiological responses. This article aimed to explore the changes in physiological responses due to the social interaction of a competitive game modality. This pilot study involved ten unimpaired participants (five pairs). We defined different therapy sessions: (i) a session without a competitor; (ii) two sessions with a virtual competitor with different difficulty levels; (iii) a competitive game. Results showed a difference in the physiological response in the competitive mode concerning single-player mode only due to the interpersonal game modality. In addition, feedback from participants suggested that it was necessary to keep a certain difficulty level to make the activity more challenging, and therefore be more engaging and rewarding. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

16 pages, 7379 KiB

Open AccessArticle

Estimation of the Continuous Walking Angle of Knee and Ankle (Talocrural Joint, Subtalar Joint) of a Lower-Limb Exoskeleton Robot Using a Neural Network

by Taehoon Lee, Inwoo Kim and Soo-Hong Lee

Sensors 2021, 21(8), 2807; https://doi.org/10.3390/s21082807 - 16 Apr 2021

Cited by 23 | Viewed by 5183

Abstract

A lower-limb exoskeleton robot identifies the wearer′s walking intention and assists the walking movement through mechanical force; thus, it is important to be able to identify the wearer′s movement in real-time. Measurement of the angle of the knee and ankle can be difficult [...] Read more.

A lower-limb exoskeleton robot identifies the wearer′s walking intention and assists the walking movement through mechanical force; thus, it is important to be able to identify the wearer′s movement in real-time. Measurement of the angle of the knee and ankle can be difficult in the case of patients who cannot move the lower-limb joint properly. Therefore, in this study, the knee angle as well as the angles of the talocrural and subtalar joints of the ankle were estimated during walking by applying the neural network to two inertial measurement unit (IMU) sensors attached to the thigh and shank. First, for angle estimation, the gyroscope and accelerometer data of the IMU sensor were obtained while walking at a treadmill speed of 1 to 2.5 km/h while wearing an exoskeleton robot. The weights according to each walking speed were calculated using a neural network algorithm programmed in MATLAB software. Second, an appropriate weight was selected according to the walking speed through the IMU data, and the knee angle and the angles of the talocrural and subtalar joints of the ankle were estimated in real-time during walking through a feedforward neural network using the IMU data received in real-time. We confirmed that the angle estimation error was accurately estimated as 1.69° ± 1.43 (mean absolute error (MAE) ± standard deviation (SD)) for the knee joint, 1.29° ± 1.01 for the talocrural joint, and 0.82° ± 0.69 for the subtalar joint. Therefore, the proposed algorithm has potential for gait rehabilitation as it addresses the difficulty of estimating angles of lower extremity patients using torque and EMG sensors. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

11 pages, 6408 KiB

Open AccessArticle

Overground Robot-Assisted Gait Training for Pediatric Cerebral Palsy

by Seung Ki Kim, Dongho Park, Beomki Yoo, Dain Shim, Joong-On Choi, Tae Young Choi and Eun Sook Park

Sensors 2021, 21(6), 2087; https://doi.org/10.3390/s21062087 - 16 Mar 2021

Cited by 18 | Viewed by 5794

Abstract

The untethered exoskeletal robot provides patients with the freest and realistic walking experience by assisting them based on their intended movement. However, few previous studies have reported the effect of robot-assisted gait training (RAGT) using wearable exoskeleton in children with cerebral palsy (CP). [...] Read more.

The untethered exoskeletal robot provides patients with the freest and realistic walking experience by assisting them based on their intended movement. However, few previous studies have reported the effect of robot-assisted gait training (RAGT) using wearable exoskeleton in children with cerebral palsy (CP). This pilot study evaluated the effect of overground RAGT using an untethered torque-assisted exoskeletal wearable robot for children with CP. Three children with bilateral spastic CP were recruited. The robot generates assistive torques according to gait phases automatically detected by force sensors: flexion torque during the swing phase and extension torque during the stance phase at hip and knee joints. The overground RAGT was conducted for 17~20 sessions (60 min per session) in each child. The evaluation was performed without wearing a robot before and after the training to measure (1) the motor functions using the gross motor function measure and the pediatric balance scale and (2) the gait performance using instrumented gait analysis, the 6-min walk test, and oxygen consumption measurement. All three participants showed improvement in gross motor function measure after training. Spatiotemporal parameters of gait analysis improved in participant P1 (9-year-old girl, GMFCS II) and participant P2 (13-year-old boy, GMFCS III). In addition, they walked faster and farther with lower oxygen consumption during the 6-min walk test after the training. Although participant P3 (16-year-old girl, GMFCS IV) needed the continuous help of a therapist for stepping at baseline, she was able to walk with the platform walker independently after the training. Overground RAGT using a torque-assisted exoskeletal wearable robot seems to be promising for improving gross motor function, walking speed, gait endurance, and gait efficiency in children with CP. In addition, it was safe and feasible even for children with severe motor impairment (GMFCS IV). Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

Review

Jump to: Research, Other

36 pages, 2258 KiB

Open AccessEditor’s ChoiceReview

Converging Robotic Technologies in Targeted Neural Rehabilitation: A Review of Emerging Solutions and Challenges

by Kostas Nizamis, Alkinoos Athanasiou, Sofia Almpani, Christos Dimitrousis and Alexander Astaras

Sensors 2021, 21(6), 2084; https://doi.org/10.3390/s21062084 - 16 Mar 2021

Cited by 48 | Viewed by 10375

Abstract

Recent advances in the field of neural rehabilitation, facilitated through technological innovation and improved neurophysiological knowledge of impaired motor control, have opened up new research directions. Such advances increase the relevance of existing interventions, as well as allow novel methodologies and technological synergies. [...] Read more.

Recent advances in the field of neural rehabilitation, facilitated through technological innovation and improved neurophysiological knowledge of impaired motor control, have opened up new research directions. Such advances increase the relevance of existing interventions, as well as allow novel methodologies and technological synergies. New approaches attempt to partially overcome long-term disability caused by spinal cord injury, using either invasive bridging technologies or noninvasive human–machine interfaces. Muscular dystrophies benefit from electromyography and novel sensors that shed light on underlying neuromotor mechanisms in people with Duchenne. Novel wearable robotics devices are being tailored to specific patient populations, such as traumatic brain injury, stroke, and amputated individuals. In addition, developments in robot-assisted rehabilitation may enhance motor learning and generate movement repetitions by decoding the brain activity of patients during therapy. This is further facilitated by artificial intelligence algorithms coupled with faster electronics. The practical impact of integrating such technologies with neural rehabilitation treatment can be substantial. They can potentially empower nontechnically trained individuals—namely, family members and professional carers—to alter the programming of neural rehabilitation robotic setups, to actively get involved and intervene promptly at the point of care. This narrative review considers existing and emerging neural rehabilitation technologies through the perspective of replacing or restoring functions, enhancing, or improving natural neural output, as well as promoting or recruiting dormant neuroplasticity. Upon conclusion, we discuss the future directions for neural rehabilitation research, diagnosis, and treatment based on the discussed technologies and their major roadblocks. This future may eventually become possible through technological evolution and convergence of mutually beneficial technologies to create hybrid solutions. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

Other

Jump to: Research, Review

8 pages, 930 KiB

Open AccessCase Report

Effectiveness of Robotic Exoskeleton-Assisted Gait Training in Spinocerebellar Ataxia: A Case Report

by San-Ha Kim, Jae-Young Han, Min-Keun Song, In-Sung Choi and Hyeng-Kyu Park

Sensors 2021, 21(14), 4874; https://doi.org/10.3390/s21144874 - 17 Jul 2021

Cited by 5 | Viewed by 3313

Abstract

Spinocerebellar ataxia (SCA) is a hereditary neurodegenerative disorder that presents as ataxia. Due to the decline in balance, patients with SCA often experience restricted mobility and a decreased quality of life. Thus, many studies have emphasized the importance of physiotherapies, including gait training, [...] Read more.

Spinocerebellar ataxia (SCA) is a hereditary neurodegenerative disorder that presents as ataxia. Due to the decline in balance, patients with SCA often experience restricted mobility and a decreased quality of life. Thus, many studies have emphasized the importance of physiotherapies, including gait training, in SCA patients. However, few studies have examined the effectiveness of robotic gait training in SCA. Here, we report the therapeutic outcomes of exoskeleton-assisted gait training in a patient with SCA. A 23-year-old woman with SCA participated in a gait training program using a powered lower-limb robotic exoskeleton, ANGELLEGS. The 8-week training program consisted of standing training, weight-shifting exercises, and gait training. Several measures of general function, balance, gait, and cardiopulmonary function were applied before, after, and 4 weeks after the program. After the program, overall improvements were found on scales measuring balance and gait function, and these improvements remained at 4 weeks after the program. Cardiopulmonary function was also improved 4 weeks after the program. Robotic exoskeleton gait training can be a beneficial option for training balance, gait, and cardiopulmonary function in SCA. Full article

(This article belongs to the Special Issue Rehabilitation Robots and Sensors)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Rehabilitation Robots and Sensors

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (16 papers)

Research

Review

Other

Further Information

Guidelines

MDPI Initiatives

Follow MDPI