Search Results (165)

Lower-limb rehabilitation exoskeletons have the potential to improve gait recovery after stroke by providing intensive and repetitive training. However, conventional control strategies often rely on fixed control parameters and exhibit limited adaptability to patient-specific characteristics, sensor noise, and dynamic uncertainties. This paper proposes an adaptive control framework that combines deep reinforcement learning (RL) with model-based impedance control for personalised lower-limb exoskeleton assistance. Patient-specific biological parameters are incorporated into the simulation environment and reward formulation to improve adaptability and robustness. Three state-of-the-art deep RL algorithms, Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Soft Actor-Critic (SAC), are evaluated in a continuous control environment under varying signal-to-noise ratio (SNR) conditions ranging from 5 dB to noise-free conditions. Results demonstrate that TD3 achieves the most stable learning performance, obtaining a mean reward of −354.24 under noise-free conditions, while DDPG provides the highest joint-angle tracking accuracy with an RMSE of 0.0369 rad. SAC exhibits superior robustness in noisy environments, achieving the highest learning ratio of 0.51 at 5 dB SNR. Furthermore, the proposed personalised framework reduces tracking errors by up to 27% compared with non-personalised baseline approaches. The findings indicate that integrating patient-specific information with RL-based adaptive control can significantly enhance robustness, tracking performance, and personalisation in exoskeleton-assisted gait rehabilitation, providing a promising direction for future intelligent rehabilitation systems. Full article

EEG-based motor imagery (MI) decoding is commonly evaluated in open loop, but strong offline performance does not necessarily translate into stable real-time control once decoder outputs drive a physical device. This issue is especially relevant for lower-limb exoskeletons, where initiating movement, sustaining movement, stopping movement, and maintaining rest can impose different controller-level demands. This study presents a proof-of-concept controller-level validation of an EEG-driven ankle exoskeleton framework, using a staged design that links open-loop decoder development to real-time closed-loop controller testing. Open-loop EEG data were collected from nine able-bodied participants during static and dynamic ankle MI using an eight-channel g.tec Unicorn Hybrid Black system, with matched PA-SEMI outputs available for eight participants in the primary open-loop comparison. We used a hybrid feature representation combining spectral, spatial covariance, and temporal complexity descriptors to compare a supervised Passive–Aggressive (PA) classifier with a Semi-supervised latent learning network (SEMI). Performance was assessed using epoch-level and persistence-based event metrics intended to reflect controller triggering. Under the evaluated model-specific protocols, SEMI produced higher open-loop accuracy and lower false-trigger rates than PA. The reported SEMI analysis was transductive: feature windows from the target-participant evaluation runs were available without labels during consistency training, and their labels were withheld until final evaluation. However, we selected PA for the primary matched closed-loop validation because it could be retrained, checked, and deployed within the same-day workflow. Since SEMI was not evaluated in a balanced matched closed-loop comparison, this study does not determine whether PA or SEMI provides superior real-time controller performance. Deployment-oriented PA updates were audited using limited same-day calibration data and evaluated in matched PA-based closed-loop trials with three participants, based on online controller logs. The closed-loop experiments were conducted on RehAnkle, a pre-commercial robotic ankle rehabilitation device operated here as a single-active-DoF ankle platform for dorsiflexion-oriented EEG control. In closed-loop trials, start and stop commands were generally reliable, whereas sustained movement and sustained rest were less stable. These proof-of-concept results indicate that command generation and state maintenance should be evaluated as separate controller-level problems, and that open-loop accuracy alone is insufficient to characterize real-time exoskeleton control. Full article

This paper proposes a hierarchical control architecture that is established at both lower limb joint and platform levels based on a simplified admittance model, where compliance is regulated through virtual mass and damping. At the lower limb joint level, admittance control governs lower limb motion tracking, while at the platform level it adjusts the omnidirectional mobile platform velocity in response to human interaction forces. Within this framework, a Sarsa-based reinforcement learning agent dynamically optimizes the parameters of a Sigmoid function using dual state inputs. Based on hip joint angle error and human–robot interaction force, the controller dynamically adjusts virtual mass and damping to optimize the trade-off between tracking error and dynamic compliance. The simulation and experimental results on the prototype system demonstrate that, compared with traditional Sigmoid parameter-tuned admittance control, the proposed approach significantly enhances gait smoothness (dimensionless squared jerk reduced by 65.62% and 36.74% for hip and knee joints), and increases human–robot interaction compliance (RMS interaction force was reduced from 3.2502 N to 2.5109 N; EPUD decreased from 12.14 to 9.53). Moreover, the proposed strategy achieves smaller maximum overshoot (0.45° vs. 0.9°) and faster settling time (2.6 s vs. 4.59 s). These findings indicate that integrating reinforcement learning with Sigmoid parameter adaptation provides a systematic and effective solution for adaptive compliance regulation in mobile exoskeleton systems, enhancing adaptability, safety, and functional relevance for stroke patients undergoing lower limb rehabilitation training. Full article

In recent years, the potential of exoskeletons to enhance human capabilities has attracted significant research interest. Nevertheless, the control of Rehabilitation Lower-Limb Exoskeletons (RLLEs) is challenging because of their strong nonlinear behaviour. In the paper, a Grey Fuzzy Sliding-Mode (GFSM) controller, which is designed based on the optimization accuracy and estimation capability of the fuzzy logic system, was used for trajectory tracking of a RLLE’s joints. This paper presents the tuning of the controller parameters optimally using Grey Wolf Optimization (GWO) integrated with an Interval Type-2 Fuzzy Logic System (IT2FLS) in real-time. The GFSM was selected as the controller law, in which initially, GWO was used to tune the parameters based on the estimated RLLE’s mathematical model. The optimal tuned parameters were employed to determine the defuzzification range of the fuzzy logic system. IT2FLS was provided to tune the real-time controller parameters. The performance of the GFSM was validated by human-RLLE experiments which showed superior performance compared to other conventional controllers. The experimental results show that the controller achieved reductions in the average error of 81.8%, 82.9%, 84.1%, and 80.6%, respectively, compared with conventional adaptive control methods. These findings indicate that the GFSM can be used to improve motor function recovery in individuals with hemiplegia. By integrating biomechanically inspired motion assistance with IT2FLS, our proposed GFSM controller contributes to the development of biomimetic rehabilitation exoskeletons capable of reproducing natural human gait. Full article

Gait asymmetry and reduced gait speed (GS) are common after stroke. This systematic review and meta-analysis evaluated the effects of gait training with lower-limb robotic exoskeletons or exoskeleton-type devices on gait asymmetry and GS compared with conventional rehabilitation or non-robotic gait training. PubMed, Embase, Web of Science, the Cochrane Library, and Scopus were searched from inception to 21 June 2026. Randomized controlled trials (RCTs) reporting spatial gait asymmetry (SGA), temporal gait asymmetry (TGA), or GS were included. Standardized mean differences (SMDs; Hedges’ g) and 95% confidence intervals (CIs) were pooled using random-effects models. Eleven RCTs involving 532 randomized participants were included. Training with these devices reduced SGA (SMD = −0.68, 95% CI −1.13 to −0.22, p < 0.01) and improved GS (SMD = 0.46, 95% CI 0.12 to 0.81, p = 0.01), but did not significantly affect TGA (SMD = −0.85, 95% CI −1.90 to 0.20, p = 0.11). The certainty of evidence, assessed using the Grading of Recommendations Assessment, Development and Evaluation (GRADE) framework, was very low for all three outcomes. Gait training with lower-limb robotic exoskeletons or exoskeleton-type devices may reduce SGA and improve GS after stroke, whereas its effect on TGA remains uncertain. Full article

In this paper, we propose an assist-as-needed (AAN) backstepping control scheme for a lower-limb exoskeleton with nonlinear dynamics and uncertain human–robot interactions. The main objective is to achieve a good trajectory tracking capability while adaptively controlling the assistance of the robot according to the user’s effort. The adopted dynamic model is nonlinear, which includes joint dynamics and external human interaction torque. This allows for the derivation of the tracking error formulation. The backstepping control law, formulated based on the filtered tracking error, ensures stable closed-loop performance with bounded tracking errors. We incorporate an AAN scaling framework based on estimated human effort to regulate the overall control torque as a convex combination of the nominal backstepping torque and the impedance-based assistance torque. The proposed controller was tested by numerical simulations and was compared with the sliding mode control (SMC) and the proportional–integral–derivative (PID) control. The overall root-mean-square tracking error for the proposed controller was 0.0962 rad, while for the SMC controller and PID controller, it was 0.0819 rad and 0.1246 rad, respectively. Moreover, the proposed controller reduced the peak human–robot interaction torque to 14.68 N·m compared to 15.36 N·m for SMC and 15.81 N·m for PID, adaptively controlling assistance based on the applied effort of the user. The assistance ratio went down from an average of 0.7988 in the low-effort condition to 0.6960 in the higher-effort condition, indicating effective adaptation while maintaining stable tracking performance. Although the PID controller achieved the lowest torque-variation index, the proposed controller achieved a more favorable trade-off among tracking accuracy, adaptive assistance, and acceptable torque smoothness. Finally, the proposed AAN backstepping controller achieved a practical trade-off between tracking accuracy, adaptive assistance, torque smoothness, and interaction safety, suggesting its potential in rehabilitation and assistive exoskeleton applications. Full article

Stroke is a major cause of lower-limb paresis, and clinical practice has long shown that early, repetitive gait training can accelerate motor recovery. End-effector gait trainers mounted on a wheeled walker provide a portable and low-cost alternative to bulky treadmill-based exoskeletons. This paper presents a geared five-bar linkage as the trajectory-generating mechanism of a Walker Gait Trainer (WGT), a single-actuator rehabilitation device for over-ground use. The two cranks of the five-bar linkage are linked by a gear train made up of two identical spur gears and an intermediate idler. This arrangement reduces the dimensional synthesis problem from four defect constraints, Grashof, order, and two circuit constraints, to a single order constraint, because branch and circuit defects are removed by design when both cranks are compelled to rotate continuously. Dimensional synthesis is formulated as a path-generation problem based on seven precision points obtained from normative gait data, and the mechanism dimensions are found through a systematic design-by-analysis search carried out interactively in the GIM kinematic simulation environment, using the closed-form kinematic model developed in this study. The final mechanism is then reconstructed in GIM as a kinematic cross-check of the closed-form model. The geared five-bar linkage reproduces the typical teardrop ankle path of healthy gait with one fewer link than conventional six-bar designs, while also adding the gear ratio as an extra parameter for shaping the trajectory, which is not available in six-bar topologies. The paper also presents the full device integration, in which the input crank is powered by a single speed-controlled actuator mounted on the walker frame, together with a three-dimensional CAD assembly model. Full article

Background/Objectives: Lower-limb exoskeletons require reliable movement recognition mechanisms to support adaptive locomotor assistance and rehabilitation. Electromyographic (EMG) signals provide valuable information on muscle activation and user intention, enabling safe and responsive human–exoskeleton interaction. This study aims to develop and experimentally validate an EMG-based platform for intelligent lower-limb movement recognition and locomotor assistance applications. Methods: The proposed platform integrates multichannel EMG acquisition, embedded signal processing, and artificial intelligence for movement classification. EMG signals associated with six movement classes (left/right kneeling, stepping, and dash) were acquired from ten healthy male participants aged 19–24 years. Signal preprocessing, normalization, dataset generation, and model training were performed using a dedicated processing framework. Continuous EMG acquisition without threshold-based segmentation was employed to preserve complete neuromuscular information and improve dataset consistency. Movement classification was implemented using a lightweight one-dimensional convolutional neural network (1D-CNN). Model performance was evaluated using Stratified 5-Fold Cross-Validation and Leave-One-Subject-Out (LOSO) protocols. Results: A dataset containing 608 multichannel EMG recordings was generated for training and validation. The proposed 1D-CNN model achieved an accuracy of 92.43 ± 1.69% and a macro F1-score of 0.9093 ± 0.0247 under Stratified 5-Fold Cross-Validation. LOSO evaluation yielded an accuracy of 62.11 ± 23.26%, highlighting the significant impact of inter-subject variability on classification performance. Conclusions: The developed platform provides an effective framework for EMG-based lower-limb movement recognition in intelligent exoskeleton systems. The results demonstrate the feasibility of integrating multichannel EMG sensing and AI-based inference into adaptive locomotor assistance systems while emphasizing the importance of improving subject-independent generalization. The proposed platform also establishes a foundation for future research on multimodal sensing and real-time adaptive exoskeleton control. Full article

Background/Objectives: Spinal cord injury (SCI) causes heterogeneous motor, sensory, autonomic, and participation limitations; recovery priorities vary by injury level, completeness, time since injury and residual function. Robotic rehabilitation has expanded from assistive technology to restorative, compensatory and health-promoting interventions, but patient-tailored prescription frameworks remain underdeveloped. Methods: PubMed/MEDLINE was searched from database inception to May 2026 using predefined domain-specific strategies, and findings were synthesized narratively to integrate mechanistic, clinical, safety and implementation evidence. Results: Robotic systems can increase task-specific repetition, sensorimotor feedback, active engagement and quantitative monitoring. Upper-limb robotics are feasible in cervical SCI and may support reach, grasp and activities of daily living, although SCI-specific controlled evidence remains limited. Lower-limb exoskeletons and locomotor robots can support gait practice, upright mobility, exercise exposure and selected secondary health outcomes, but walking speed, energy expenditure, cost, supervision needs and community translation remain important barriers. Sensory and non-motor effects, including proprioceptive input, spasticity, pain, bowel routine, cardiometabolic conditioning, participation and psychological well-being, are clinically relevant but should be interpreted according to evidence strength. Robotics combined with functional electrical stimulation, virtual reality, brain–computer interfaces, non-invasive brain stimulation and artificial intelligence-driven adaptation is promising but not yet routine. Conclusions: Robotic rehabilitation in SCI should be prescribed through a severity-based process that considers lesion level, American Spinal Injury Association Impairment Scale grade, residual voluntary and sensory function, safety, patient priorities and measurable goals. The proposed framework supports transparent selection and prospective validation of individualized robotic rehabilitation and shifts decisions beyond device availability toward clinically meaningful and equitable implementation. Full article

Exoskeletons are widely utilized across various domains, including biomedical and rehabilitative engineering. In clinical applications, precise joint torque evaluation is critical to ensuring exoskeleton efficiency, especially when assisting patients with impaired mobility. This work presents a straightforward inverse-dynamics framework to compute human joint torques using motion capture and force plate data. Estimating these torques is a key requirement for exoskeleton systems to deliver appropriate and individualized assistive support. A key innovation of the proposed model is the explicit integration of a three-link chain—comprising the thigh, shank, and foot—treated as a cohesive multi-segment limb. By formally incorporating the foot segment, the model enables a more rigorous representation of ground reaction forces (GRF) and the dynamic migration of the center of pressure (COP). The proposed framework was validated against OpenSim 4.0 using benchmark datasets involving walking, squatting, and drop-jump maneuvers. The results demonstrated strong agreement with OpenSim, yielding normalized root mean square errors of approximately 10% across major lower-limb joints during walking. In contrast, the squatting posture provided a significant magnitude offset, despite maintaining close temporal phase alignment. Beyond torque estimation, the results provide insight into the sensitive interplay among COP trajectories, foot geometry, and GRF orientation. The proposed framework offers a computationally efficient tool for biomechanical analysis and provides a practical foundation for future lower-limb exoskeleton and assistive robotic applications. Full article

With the increasing number of stroke patients, there is a growing demand for lower-limb rehabilitation exoskeletons. While current mechanisms are preferred for their light weight and dexterous design in limited environments, the alignment of the structures and motion are still not matched perfectly to human movements. This study develops a novel structure and configuration optimization method for knee part rehabilitation with special passive self-alignment modules. The driving segment is mechanically coupled to the patients’ lower limb. All components are designed with high rigidity and fully constrained to ensure smooth and continuous motion. Then, the kinematics are systematically derived to establish the foundation for the control system. Next, the application of the particle swarm optimization algorithm determines the optimal parameters for each revolute joint during the bending motion, and reduces the non-ideal S-shaped motion deformation curve caused by the offset of the joint rotation center and the load at the end effector successfully. The final results demonstrate that the optimized SRE achieves 97.5% motion accuracy under large-angle knee movement. This work presents simulation-only validation, and clinical testing remains future work. The proposed mechanism provides a promising solution for post-stroke rehabilitation, and is also applicable to geriatric lower-limb weakness and orthopedic postoperative recovery. Full article

This study presents the design and development of a wearable lower-limb exoskeleton system aimed at supporting motion assistance in monoplegia-related conditions. The proposed approach integrates a simplified sensing configuration with a data-driven neuro-fuzzy control framework based on an Adaptive Neuro-Fuzzy Inference System (ANFIS). Motion data are acquired from the healthy limb using bend flex sensors and are used to generate control signals for the actuation of the impaired limb through an Arduino-based embedded platform. The mechanical structure is developed using a lightweight 3D-printed design combined with high-torque DC motors and gear transmission mechanisms. Experimental evaluation conducted under controlled conditions demonstrates that the system is capable of capturing and reproducing fundamental motion patterns, with the ANFIS model providing a consistent mapping between sensor inputs and actuator responses. The obtained results indicate a satisfactory level of performance for motion pattern reproduction, particularly in terms of temporal behavior and transition between movement states. The presented system emphasizes low-cost implementation, computational efficiency, and practical implementation, making it suitable as a proof-of-concept framework for wearable assistive technologies. While the results demonstrate the feasibility of the proposed approach for motion reproduction, further studies involving extended testing and user-specific adaptation are required to assess its potential applicability in real-world scenarios. Full article

Robotic lower-limb exoskeletons are an increasingly important tool in the rehabilitation of patients with motor impairments, and their effectiveness depends on how faithfully the device reproduces the natural gait pattern. Inertial measurement units (IMUs) are widely used to acquire body-worn kinematic data for gait monitoring, but compact, interpretable models linking IMU-derived hip- and knee-flexion features to gait phase under exoskeleton-assisted conditions are still lacking. We collected gait data from two independent experiments: Experiment 1, 20 healthy adults (10 M, 10 F; 22.2 ± 1.9 years) walking freely on level ground, stairs and a ramp with seven Noraxon IMUs; and Experiment 2, six healthy adults (4 M, 2 F; 31.0 ± 8.9 years) walking with and without the Exowalk (HR-02) over-ground exoskeleton with five IMUs. Eight bilateral hip- and knee-flexion features were extracted, and a binary logistic-regression model with stance/swing as the dependent variable was fitted on Experiment 1 and externally cross-validated on Experiment 2. The model classified gait phases with an accuracy of 90.83% (sensitivity 87.50%, specificity 92.50%, positive predictive value 85.37%) on Experiment 1. External validation retained 91.7% accuracy during free walking but dropped to 41.7% under Exowalk-assisted walking, indicating that the device alters the inertial signature of gait. The findings identify swing-phase hip flexion and the minimum swing-phase knee flexion as the kinematic descriptors most predictive of gait phase, and provide quantitative design and control targets for next-generation IMU-instrumented lower-limb rehabilitation exoskeletons. Full article

Background: Evidence on powered wearable exoskeleton gait training in patients with chronic hypoxic-ischemic encephalopathy (HIE) is virtually absent, and existing studies have focused on macroscopic functional outcomes while neglecting joint-level neuromuscular force-generation characteristics such as rate of force development (RFD). Objective: To examine the effects of a six-week powered exoskeleton gait training program on isometric hip strength and RFD, sit-to-stand (STS) performance, frontal-plane hip strength, and center-of-pressure (CoP) dynamics in a patient with chronic HIE-induced quadriparesis. Methods: A case report with pre- and post-intervention evaluation was conducted. A 47-year-old male with chronic HIE-induced quadriparesis (onset 2017) completed 18 sessions (three per week, six weeks) of powered lower-limb exoskeleton gait training. Outcomes included isometric hip peak force and RFD (DynaMo, Vald Performance), STS peak force and body mass-normalized RFD (ForceDecks, Vald Performance), frontal-plane hip strength (ForceFrame, Vald Performance), and CoP path length and mean velocity. Results: Hip extension peak force increased by 247–256% bilaterally, and hip extension RFD increased by 174–188%, whereas hip flexion peak force showed minimal change (+3.3–5.2%). Body mass-normalized STS RFD increased by 250% (10 to 35 N·s⁻¹·kg⁻¹), representing the largest relative gain. Hip abduction strength increased by 27.1–36.8% with improved bilateral symmetry; hip adduction imbalance reversed from right to left dominance. CoP path length and mean velocity each decreased by 3.7%. Conclusions: Six weeks of powered exoskeleton gait training selectively enhanced time-dependent neuromuscular output—particularly RFD—beyond maximal strength gains, with meaningful improvements in functional weight acceptance during STS. These findings support exoskeleton-based training as a promising rehabilitation strategy for patients with chronic CNS injury. Full article

Stroke is the second leading cause of death globally and a major contributor to lower-limb disability, affecting gait, balance, and functional independence in elderly populations. While robot-assisted rehabilitation has demonstrated effectiveness in motor recovery, access remains limited due to high costs and geographic barriers, particularly in Latin America. This study presents ExoKnee, a low-cost knee exoskeleton designed through biomimetic principles and 3D-printed fabrication as a proof-of-concept device targeting gait rehabilitation in elderly adults. The system integrates a single-degree-of-freedom pneumatic actuator controlled by electromyography (EMG) signals from the quadriceps muscle, enabling knee flexion and extension (90° to 180°). The design was evaluated through finite element analysis and dynamic simulations in MATLAB/Simulink R2024a under constant, stepwise, and sinusoidal reference inputs in a digital-twin environment. Expert validation using the Content Validity Coefficient yielded a mean score of 0.8747, reflecting preliminary expert agreement on the conceptual design’s coherence and relevance. The prototype demonstrated controlled movements through a 6-bar pneumatic system with EMG-triggered relay activation, validated at the proof-of-concept level through simulation and single-subject threshold calibration. ExoKnee addresses critical gaps by offering an anthropometrically informed, biosignal-driven, and locally manufacturable rehabilitation platform for low- and middle-income countries, pending clinical validation. Future work will focus on clinical trials and adaptive EMG control strategies. Full article