Training Tasks Research Articles

The Effectiveness Of Virtual Reality Along With Task Specific Training On Quality Of Life Of C6-C7 Level- Incomplete Spinal Cord Injury Patients

Background- Spinal cord injury is a devastating condition. In recent years, traumatic spinal cord injury has become one of the major disabling conditions in young males. These chronic complications negatively impact patients’ functional independence and thus affect the quality of life. Methods-Thirty-seven spinal cord injury patientsC6-C7 with American Spinal Cord Injury Association (C, D) who full-filled the inclusion criteria were recruited,  out of which 7 discontinued the therapy program, 15 spinal cord injury  patients in Group I (Virtual Reality with Task Specific Training) and 15 spinal cord injury patients in the Group II (only task specific) completed the study.Virtual Reality training was given as an intervention using NIRVANA which is a semi-immersive Virtual Reality training. Results-Group I, which received only Task Specific Training, revealed a statistically significantly positive change in Quality of life (Z = -2.671, p = 0.008) with a medium effect size of (r = 0.48). For Group II, which received Virtual Reality along with Task Specific Training,revealed a statistically significantly positive change in Quality of life (Z = -3.415 p = 0.001) with a large effect size of (r = 0.62) Conclusion-Both the groups showed significant positive improvements in quality of life inspinal cord injury patients, indicating that both task-oriented training and the use of Virtual Reality as treatment modalities have a direct impact on QoL. However, more significant improvement was seen in Group 2 where Virtual Reality was combined with Task Specific Training.

The efficacy of hazard perception training and education: A systematic review and meta-analysis

BackgroundHazard perception (HP) has been argued to improve with experience, with numerous training programs having been developed in an attempt to fast track the development of this critical safety skill. To date, there has been little synthesis of these methods. Objective: The present study sought to synthesise the literature for all road users to capture the breadth of methodologies and intervention types, and quantify their efficacy.Data Sources: A systematic review of both peer reviewed and non-peer-reviewed literature was completed. A total of 57 papers were found to have met inclusion criteria. Results: Research into hazard perception has focused primarily on drivers (with 42 studies), with a limited number of studies focusing on vulnerable road users, including motorcyclists (3 studies), cyclists (7 studies) and pedestrians (5 studies). Training was found to have a large significant effect on improving hazard perception skills for drivers (g = 0.78) and cyclists (g = 0.97), a moderate effect for pedestrians (g = 0.64) and small effect for motorcyclists (g = 0.42). There was considerable heterogeneity in the findings, with the efficacy of training varying as a function of the hazard perception skill being measured, the type of training enacted (active, passive or combined) and the number of sessions of training (single or multiple). Active training and single sessions were found to yield more consistent significant improvements in hazard perception. Conclusions: This study found that HP training improved HP skill across all road user groups with generally moderate to large effects identified. HP training should employ a training method that actively engages the participants in the training task. Preliminary results suggest that a single session of training may be sufficient to improve HP skill however more research is needed into the delivery of these single sessions and long-term retention. Further research is also required to determine whether improvements in early-stage skills translate to improvements in responses on the road, and the long-term retention of the skills developed through training.

Specificity of early motor unit adaptations with resistive exercise training.

After exposure of the human body to resistive exercise, the force-generation capacity of the trained muscles increases significantly. Despite decades of research, the neural and muscular stimuli that initiate these changes in muscle force are not yet fully understood. The study of these adaptations is further complicated by the fact that the changes may be partly specific to the training task. For example, short-term strength training does not always influence the neural drive to muscles during the early phase (<100ms) of force development in rapid isometric contractions. Here we discuss some of the studies that have investigated neuromuscular adaptations underlying changes in maximal force and rate of force development produced by different strength training interventions, with a focus on changes observed at the level of spinal motor neurons. We discuss the different motor unit adjustments needed to increase force or speed, and the specificity of some of the adaptations elicited by differences in the training tasks.

Retrieval for Extremely Long Queries and Documents with RPRS: A Highly Efficient and Effective Transformer-based Re-Ranker

Retrieval with extremely long queries and documents is a well-known and challenging task in information retrieval and is commonly known as Query-by-Document (QBD) retrieval. Specifically designed Transformer models that can handle long input sequences have not shown high effectiveness in QBD tasks in previous work. We propose a Re-Ranker based on the novel Proportional Relevance Score (RPRS) to compute the relevance score between a query and the top- k candidate documents. Our extensive evaluation shows RPRS obtains significantly better results than the state-of-the-art models on five different datasets. Furthermore, RPRS is highly efficient, since all documents can be pre-processed, embedded, and indexed before query time that gives our re-ranker the advantage of having a complexity of O(N) , where N is the total number of sentences in the query and candidate documents. Furthermore, our method solves the problem of the low-resource training in QBD retrieval tasks as it does not need large amounts of training data and has only three parameters with a limited range that can be optimized with a grid search even if a small amount of labeled data is available. Our detailed analysis shows that RPRS benefits from covering the full length of candidate documents and queries.

The Effect of a Table Tennis Exercise Program With a Task-Oriented Approach on Visual Perception and Motor Performance of Adolescents With Developmental Coordination Disorder.

In this study we investigated the effects of an 8-week table tennis exercise program with a task-oriented approach on visual perception and motor performance of 31 adolescents with developmental coordination disorder (DCD). The participants were identified by their teachers as having greater difficulty than their peers (450 students from three Korean middle schools) in physical education (PE) classes. On the Bruininks-Oseretsky Test of Motor Proficiency-2, these adolescents scored below the 15th percentile and showed difficulties in performing daily life activities due to motor performance problems; they did not have physical defects, intellectual or neurological impairments, or Attention Deficit Hyperactivity Disorder. Of 98 prospective adolescents with PE difficulties, we obtained personal assent and parents' informed consent from 54, and 31 of these met screening criteria for DCD through the Developmental Coordination Disorder Questionnaire-Korean. This final group was divided in non-random fashion (based on the proximal geographic grouping of the children's schools) between an experimental group (n = 16) and a control group (n = 15). The experimental group participated in the 8-week task-oriented table tennis training program with three 90-minute sessions per week, while the control group only participated in regular PE classes twice per week. We measured participants' visual perception and motor performance in the same environment before and after the intervention program. Participants' visual perception was significantly more improved in the experimental group than the control group, with specific improved skills in visual-motor search, visual-motor speed, figure-ground, and visual closure; copying and perceptual constancy skills did not improve significantly. In addition, total motor performance and motor sub-skills, including fine manual control, manual coordination, body coordination, strength, and agility were significantly more improved in the experimental group than in the control group. Thus, our task-oriented table tennis exercise program was of greater assistance than general PE classes for improving visual perception and motor performance in adolescents at risk of DCD.

Task-similarity is a crucial factor for few-shot meta-learning of structure-activity relationships.

Machine learning models support computer-aided molecular design and compound optimization. However, the initial phases of drug discovery often face a scarcity of training data for these models. Meta-learning has emerged as a potentially promising strategy, harnessing the wealth of structure-activity data available for known targets to facilitate efficient few-shot model training for the specific target of interest. In this study, we assessed the effectiveness of two different meta-learning methods, namely model-agnostic meta-learning (MAML) and adaptive deep kernel fitting (ADKF), specifically in the regression setting. We investigated how factors such as dataset size and the similarity of training tasks impact predictability. The results indicate that ADKF significantly outperformed both MAML and a single-task baseline model on the inhibition data. However, the performance of ADKF varied across different test tasks. Our findings suggest that considerable enhancements in performance can be anticipated primarily when the task of interest is similar to the tasks incorporated in the meta-learning process.

Instrument Detection and Descriptive Gesture Segmentation on a Robotic Surgical Maneuvers Dataset

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend the ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low-level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tools and the left-handed tools. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. On the other hand, for gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

Be sensei, my friend: Aikido training with a remotely controlled proxy trainer

Contact sports such as Aikido are preferred to be trained in person with an experienced trainer, as the attempts of remote training before and during the COVID-19 pandemic failed to reproduce the quality of the in-person training benefiting from the trainer’s physically present body. To address this issue of replicating in-person experience remotely, we proposed “Sensei possession,” an xReality-based training method for contact sports in which the trainer remotely guides a person who performs the physical interaction with the trainee on behalf of the real trainer in real-time. In this study, to test the effectiveness of “Sensei possession” on training performance and examine the concerns about its possible side effects on motivation, we conducted a between-participants experiment with an Aikido training task [N = 10 pairs (20 people)]. We compared the groups with or without live feedback on the proxy trainers under our hypothesis that live feedback would enhance trainees’ performance gain. As a result, the trainees in the group with live feedback on proxy trainers had more performance gain than those without live feedback, and no indication of negative effects on motivation was shown. We discussed our results concerning the previous research on micro-adaptive training and reported technical insights to improve the design of Sensei possession further.

A single exposure to 100% normo-baric oxygen therapy appears to improve sequence learning processes by increasing prefrontal cortex oxygen saturation

Previously, we showed that a normo-baric 100 % oxygen treatment (NbOxTr) enhances motor learning processes, e.g., visuomotor adaptation (VMA) and sequence learning (SL). However, this work was limited to behavioral outcomes and did not identify the physiological mechanistic underpinnings of these improvements. Here, we expand on this research to investigate the effects of a NbOxTr on the oxygen tissue saturation index (TSI) level of the prefrontal cortex (PFC) when performing a SL task and whether potential SL improvements relate to increased TSI levels in the PFC. Twenty four right-handed young, healthy adults were randomly assigned to a NbOxTr group (normo-baric 100 % oxygen, n = 12) or a control group (normal air, n = 12). They received their respective treatments via a nasal cannula during the experiment. Oxygen TSI levels of the right and left PFC were measured via near-infrared spectroscopy (NIRS) throughout different SL task phases (Baseline, Training, Testing). The NbOxTr increased the TSI of the PFC in the Training phase (p < 0.01) and positively affected SL retention in the Testing phase (p < 0.05). We also found a positive correlation between TSI changes in the right PFC during the gas treatment phase (3.4 % increase) and response time (RT) improvements in the SL task training and retention phase (all p < 0.05). Our results suggest that a simple NbOxTr increases the oxygenated hemoglobin availability in the PFC, which appears to mediate the retention of acquired SL improvements in healthy young adults. Future studies should examine treatment-related oxygenation changes in other brain areas involved and their relation to enhanced learning processes. Whether this NbOxTr improves SL in neurologically impaired populations should also be examined.

Recurrent neural network plasticity models: Unveiling their common core through multi-task learning

Recurrent neural network models are known to be particularly suitable for data-driven constitutive modeling due to their built-in memory variables. The main challenge preventing their widespread application to engineering materials lies in their excessive need of data for training. Here, we postulate that RNN models of elasto-plastic solids feature a large common core that is shared by all materials of the same class. The common core is complemented by material-specific layers with parameters that vary from material-to-material. After training RNN models for 25 different von Mises materials, we identify the common core of a multi-task model. Furthermore, we demonstrate through ensemble transfer learning that adding a new material to the multi-task model requires datasets that are two to three orders of magnitude smaller than the datasets needed for training an RNN from scratch. In addition, to multi-task learning, we introduce probabilistic ensembles of RNN plasticity models to quantify the epistemic uncertainty. A deep drawing simulation is performed to demonstrate the superior generalization capabilities of RNNs identified via multi-task learning as compared to those obtained through single task training.

Dual-Task Specific Training or Conventional Physiotherapeutic Interventions, Which one is more Effective?

Background: Physiotherapeutic interventions play a crucial role in motor re-learning and functional recovery for stroke patients with upper and lower limb motor impairments. Among these interventions, dual-task training (DTT) has demonstrated significant effectiveness in enhancing the functional recovery of stroke patients. Objective: This study aims to compare the effectiveness of DTT and conventional physical therapy in ambulating right-hemiplegic stroke patients.Material and Methods: A randomized control trial (RCT) was conducted at the Department of Rehabilitation Medicine, Saidu group of Teaching Hospital, 2nd March 2020 to 3rd August 2020. Chronic right-hemiplegic stroke patients meeting set inclusion criteria were randomly assigned to two groups: the treatment group (TG) receiving DTT and the control group (CG) undergoing conventional physical therapy. DTT interventions included walking forward, backward, and sideways on a smooth surface while holding an 80-gram sandbag. The CG received conventional physiotherapy involving mat activities, strengthening, stretching exercises, and ambulation/gait training. Pre- and post-tests collected clinical data analyzed on SPSS 22 included spatial and temporal variables, 10-Meter Walk Test (10MWT), Time Up &amp; Go Test (TUG), step length, cadence, cycle time, and stride length. Results: Out of 18 patients, each group had 50%, comprising 5 males (28%) and 4 females (22%). The mean age in CG was 57.20± 5.20, and in TG, it was 57.27± 6.10 years. Baseline clinical parameters were nearly identical between groups (P&gt;0.05). Post-test scores revealed significant improvements in spatial and temporal gait variables, 10MWT score, cadence, step length, stride, and cycle time in TG compared to CG (P&lt;0.05). Conclusion: Dual-task training and conventional physical therapy both significantly enhance the functional ability of right-hemiplegic patients across all gait temporal and spatial parameters. Keywords: Conventional physical therapy, Dual task training, Gait &amp; ambulation, Stroke.

The principles of physical training organisation of US Army officers

The article is devoted to the analysis of the principles of physical training organization of commissioned officers of the US Army, their implementation and effectiveness in the context of ensuring a high level of combat readiness. The US Armed Forces uses advanced technologies and scientific researches to continuously improve the physical training system, which includes the use of special training programs, monitoring of physical indicators and the development of new training methods based on scientific researches. The importance of an individual approach in training process training, as well as the integration of officers' physical training, is considered. The main goal is to understand and define the most effective and modern principles that ensure the optimal physical readiness of officers to perform their combat tasks. The article contains recommendations on optimizing the process of physical training, with the aim of increasing the functional capabilities of officers and ensuring their readiness to perform combat and training tasks in various conditions. The considerable attention is paid to the individual needs and capabilities of the US Armed Forces officers. The training programs can be adapted to specific needs and capabilities of officers, ensuring an efficient and safe physical fitness process. Physical training in the US Army is based on a high level of professionalism and motivation. This is stimulated by a system of recognition and awards, career development and provision of optimal conditions for training.

Creating a model of a training task set for a multitask practical training in the courses “Informatics” and “Information technologies in professional activity”

According to the federal state educational standards, the curriculum for socio-economic and humanitarian students of secondary vocational education (SVE) and higher education (HE) includes disciplines that provide mastery of competencies in the field of information and communication technologies. Along with the course of informatics, they include disciplines of the block “Information technologies in professional activity”: “Information Technologies in Court Activity” (SVE), “Information Technologies in Professional Activity” (for several specialties of SVE), “Information and Communication Technologies in Judicial Activity” (HE), “Information Technologies in Management” (HE), “Information Technologies in Translation Studies” (HE) and several other disciplines.Based on the analysis of scientific literature and an array of manuals — workshops provided to students and teachers by leading Russian electronic library systems (ELS), as well as own pedagogical work in teaching informatics and the block of academic courses “Information Technologies in Professional Activity”, the author proposes a model of training tasks set to be solved during the study of these courses. The relevance of the article subject is conditioned by the necessity to effectively use the time allocated by the curricula of socio-economic and humanitarian training areas of vocational education and higher education for the study of informatics and information technologies in professional activities. The novelty of the results presented by the author is confirmed by the absence of articles and reports on the topic in the Russian Science Citation Index (RSCI) database

Family caregiver outcomes after participating in a Hospital-based family involvement program after major gastrointestinal surgery: a subgroup analysis of a patient preferred cohort study

Background: Engaging families in postsurgical care is potentially beneficial for improving cancer patient outcomes and quality of care. We developed a family involvement program (FIP) and in this study, we aim to evaluate the impact of the FIP on family caregiver burden and well-being. Moreover, we aim to assess the fidelity of the program. Materials and methods: This is a preplanned subgroup analysis of a patient-preferred prospective cohort study that included family caregivers of patients who underwent major oncological surgery for gastrointestinal tumors. Only patient-nominated family caregivers could participate in the FIP. Caregivers received structured training in fundamental caregiving tasks from healthcare professionals and then actively participated in these tasks. Caregiver burden and wellbeing were measured four times (at hospital admission, at hospital discharge, and at one and three months post-hospital discharge) using the Caregiver Strain Index+ (CSI+) and the Care-related Quality of Life instrument (CarerQoL-7D). The fidelity of the FIP was assessed by recording completion of care activities. In addition, family caregivers were asked whether they would participate in the FIP again. Results: Most of the 152 family caregivers were female (77.6%), and their mean age was 61.3 years (SD=11.6). Median CSI+ scores ranged between -1 and 0 and remained below the cutoff point of experiencing burden. CarerQoL-7D results indicated no significant differences in family caregivers’ well-being over time. Upon discharge, over 75% of the family caregivers stated that they would recommend the FIP to others. The highest compliance with all fundamental care activities was observed during postoperative days 2 to 4. Conclusion: The family caregivers of oncological surgical patients who participated in the FIP exhibited acceptable levels of caregiver burden and well-being. These findings suggest that the FIP is a valuable intervention to equip family caregivers with the skills to navigate the uncertain period following a patient’s hospital discharge.

Importancia de la cohesión grupal sobre la persistencia en el equipo para la siguiente temporada: Un estudio longitudinal con jugadores senior y en formación de deportes de equipo

The objective of the present study was to analyze the relationship between the group cohesion of the team players with the intention of persistence in the team. For this, a total of 413 handball, basketball and soccer players aged between 16 and 39 years (M = 22.32; SD = 5.30), completed the measures of group cohesion and team persistence. Structural equation modeling was used to test the relationships between both variables. First, the results revealed positive correlations of the task and social cohesion factors with persistence in the team. Second, the regression analysis showed a positive and significant prediction between task cohesion and the intention to persist in the team. However, social cohesion did not show a significant prediction regarding the feeling of persistence to the team. Therefore, the union of the players in the training tasks and during the development of the competition, contributes to the feeling of persisting in a team, thereby increasing the block of players for several seasons.

A hybrid brain-muscle-machine interface for stroke rehabilitation: Usability and functionality validation in a 2-week intensive intervention.

Introduction: The primary constraint of non-invasive brain-machine interfaces (BMIs) in stroke rehabilitation lies in the poor spatial resolution of motor intention related neural activity capture. To address this limitation, hybrid brain-muscle-machine interfaces (hBMIs) have been suggested as superior alternatives. These hybrid interfaces incorporate supplementary input data from muscle signals to enhance the accuracy, smoothness and dexterity of rehabilitation device control. Nevertheless, determining the distribution of control between the brain and muscles is a complex task, particularly when applied to exoskeletons with multiple degrees of freedom (DoFs). Here we present a feasibility, usability and functionality study of a bio-inspired hybrid brain-muscle machine interface to continuously control an upper limb exoskeleton with 7 DoFs. Methods: The system implements a hierarchical control strategy that follows the biologically natural motor command pathway from the brain to the muscles. Additionally, it employs an innovative mirror myoelectric decoder, offering patients a reference model to assist them in relearning healthy muscle activation patterns during training. Furthermore, the multi-DoF exoskeleton enables the practice of coordinated arm and hand movements, which may facilitate the early use of the affected arm in daily life activities. In this pilot trial six chronic and severely paralyzed patients controlled the multi-DoF exoskeleton using their brain and muscle activity. The intervention consisted of 2 weeks of hBMI training of functional tasks with the system followed by physiotherapy. Patients' feedback was collected during and after the trial by means of several feedback questionnaires. Assessment sessions comprised clinical scales and neurophysiological measurements, conducted prior to, immediately following the intervention, and at a 2-week follow-up. Results: Patients' feedback indicates a great adoption of the technology and their confidence in its rehabilitation potential. Half of the patients showed improvements in their arm function and 83% improved their hand function. Furthermore, we found improved patterns of muscle activation as well as increased motor evoked potentials after the intervention. Discussion: This underscores the significant potential of bio-inspired interfaces that engage the entire nervous system, spanning from the brain to the muscles, for the rehabilitation of stroke patients, even those who are severely paralyzed and in the chronic phase.

AN ANALYSIS OF THE CURRICULUM “FOREIGN LANGUAGE FOR PROFESSIONAL PURPOSES” IN THE CONTEXT OF EDUCATIONAL PROGRAMME “STATE BORDER SECURITY” OF MASTER’S DEGREE

Peculiarities and objectives of the Educational programme “State Border Security” for the second (Master’s) level of higher education have been analysed. Theoretical content of the subject area, methods, techniques and technologies which include general and specific methods of military science, information and communication technologies and techniques, methods and techniques for ensuring the security of the state border have been studied. Tools and equipment, teaching and training consisting of problem-oriented and contextual learning, activity and competence-oriented technologies, practical performance of training and combat tasks, practical training and daily activities have been specified.Assessment that is divided into forms of control and assessment of educational achievements were investigated.We studied program competences (Integral competence, General competencies and Special (professional, subject) competencies) and Program learning outcomes. Educational programme components were specified, namely Curriculum “Foreign language for professional purposes” was described with the aim to show how students’ professional communicative competence in English, which involves the study of such aspects of language as speaking, reading, translating, listening and writing is forming.Content of the discipline, planned educational activities, forms (methods) of study were investigated, including Bloom’s taxonomy levels (knowledge, comprehending, application, analysis, synthesis and assessment).Five-stage lesson plan (introduction, input, practice, production and conclusion) and credit tasks were described.

Performance on a contour integration task as a function of contour shape in schizophrenia and controls

Contour Integration (CI) is the ability to integrate elemental features into objects and is a basic visual process essential for object perception and recognition, and for functioning in visual environments. It is now well documented that people with schizophrenia (SZ), in addition to having cognitive impairments, also have several visual perceptual deficits, including in CI. Here, we retrospectively characterize the performance of both SZ and neurotypical individuals (NT) on a series of contour shapes, made up of Gabor elements, that varied in terms of closure and curvature. Participants in both groups performed a CI training task that included 7 different families of shapes (Lines, Ellipse, Blobs, Squiggles, Spiral, Circle and Letters) for up to 40 sessions. Two parameters were manipulated in the training task: Orientation Jitter (OJ, i.e., orientation deviations of individual Gabor elements from ideal for each shape) and Inducer Number (IN, i.e., number of Gabor elements defining the shape). Results show that both OJ and IN thresholds significantly differed between the groups, with higher (OJ) and lower (IN) thresholds observed in the controls. Furthermore, we found significant effects as a function of the contour shapes, with differences between groups emerging with contours that were considered more complex, e.g., due to having a higher degree of curvature (Blobs, Spiral, Letters). These data can inform future work that aims to characterize visual integration impairments in schizophrenia.

Between-task transfer of item-specific control is replicable and extends to novel conditions.

Learning-guided control refers to adjustments of cognitive control settings based on learned associations between predictive cues and the likelihood of conflict. In three preregistered experiments, we examined transfer of item-specific control settings beyond conditions under which they were learned. In Experiment 1, an item-specific proportion congruence (ISPC) manipulation was applied in a training phase in which target color in a Flanker task was biased (mostly congruent or mostly incongruent). In a subsequent transfer phase, participants performed a color-word Stroop task in which the same target colors were unbiased (50% congruent). The same design was implemented in Experiment 2, but training and transfer tasks were intermixed within blocks. Between-task transfer was evidenced in both experiments, suggesting learned control settings associated with the predictive cues were retrieved when encountering unbiased transfer items. In Experiment 3, we investigated a farther version of between-task transfer by using training (color-word Stroop) and transfer (picture-word Stroop) tasks that did not share the relevant (to-be-named) dimension or response sets. Despite the stronger, between-task boundary, we observed an ISPC effect for the transfer items, but it did not emerge until the second half of the experiment. The results provided converging evidence for the flexibility and automaticity of item-specific control. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Adaptive hybrid-mode assist-as-needed control of upper limb exoskeleton for rehabilitation training

In this paper, a novel adaptive hybrid-mode assist-as-needed (AHMAAN) control algorithm is designed for the exoskeleton-assisted upper limb rehabilitation training. The overall control framework includes an outer control loop to calculate the required interaction force, and an inner control loop to drive the exoskeleton track subject’s motion, and provide specific target interaction force obtained from the outer control loop. In the outer control loop, a hybrid control mode is proposed, which consists of resistive mode and assistive mode. In this regard, a virtual tunnel is firstly established around the defined training task path, and the training mode is switched according to the deviation between the subject’s position and the boundary of the virtual tunnel. Furthermore, for tuning the strength of the resistance or assistance to the subjects with different motor capabilities, two adjustable gain factors are designed, whose values are adaptively adjusted according to the subject’s training performance by using a fuzzy logic. Then, for the inner control loop, a barrier Lyapunov function-based controller is designed to constrain exoskeleton tracking errors within the defined boundary. Meanwhile, time delay estimation (TDE) technology is used to estimate the uncertain terms of the system, and a robust adaption law is developed to compensate TDE error. Experimental tests have been performed on an upper limb exoskeleton with three healthy subjects to evaluate the effectiveness of the developed method. The results show that the proposed control scheme can be effectively applied in a variety of rehabilitation requirements and achieves better training performance than classical hybrid-mode assist-as-needed control method.