Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network

This study addresses gait reference trajectory tracking control in a 13-degree-of-freedom lower-limb rehabilitation robot, where patients exhibit nonlinear perturbations in lower-limb muscle groups and gait irregularities during exoskeleton-assisted walking. We propose a novel control strategy integ...

Full description

Saved in:
Bibliographic Details
Main Authors: Jing Li, Huimin Jiang, Moyao Gao, Shuang Li, Zhanli Wang, Zaixiang Pang, Yang Zhang, Yang Jiao
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/11/6053
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850129380223746048
author Jing Li
Huimin Jiang
Moyao Gao
Shuang Li
Zhanli Wang
Zaixiang Pang
Yang Zhang
Yang Jiao
author_facet Jing Li
Huimin Jiang
Moyao Gao
Shuang Li
Zhanli Wang
Zaixiang Pang
Yang Zhang
Yang Jiao
author_sort Jing Li
collection DOAJ
description This study addresses gait reference trajectory tracking control in a 13-degree-of-freedom lower-limb rehabilitation robot, where patients exhibit nonlinear perturbations in lower-limb muscle groups and gait irregularities during exoskeleton-assisted walking. We propose a novel control strategy integrating iterative learning with RBF neural network-based sliding mode control, featuring a single hidden-layer pre-feedback architecture. The RBF neural network effectively approximates uncertainties arising from lower-limb muscle perturbations, while adaptive regulation through parameter simplification ensures precise torque tracking at each joint, meeting real-time rehabilitation requirements. MATLAB 2021 simulations demonstrate the proposed algorithm’s superior trajectory tracking performance compared to conventional sliding mode control, effectively eliminating control chattering. Experimental results show maximum angular errors of 1.77° (hip flexion/extension), 1.87° (knee flexion/extension), and 0.72° (ankle dorsiflexion/plantarflexion). The integrated motion capture system enables the development of patient-specific skeletal muscle models and optimized gait trajectories, ensuring both training efficacy and safety for spasticity patients.
format Article
id doaj-art-4ccfc6041f9148d18c6dfb5a11d153c4
institution OA Journals
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-4ccfc6041f9148d18c6dfb5a11d153c42025-08-20T02:33:01ZengMDPI AGApplied Sciences2076-34172025-05-011511605310.3390/app15116053Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural NetworkJing Li0Huimin Jiang1Moyao Gao2Shuang Li3Zhanli Wang4Zaixiang Pang5Yang Zhang6Yang Jiao7School of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, ChinaInstitute of Electromechanical Technology, Jilin Academy of Agricultural Machinery, Changchun 130021, ChinaSchool of Mechatronic Engineering, Changchun Institute of Technology, Changchun 130012, ChinaSchool of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, ChinaSchool of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, ChinaSchool of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, ChinaSchool of Mechatronic Engineering, Changchun University of Technology, Changchun 130012, ChinaAeronautical Basic College, Air Force Aviation University, Changchun 130022, ChinaThis study addresses gait reference trajectory tracking control in a 13-degree-of-freedom lower-limb rehabilitation robot, where patients exhibit nonlinear perturbations in lower-limb muscle groups and gait irregularities during exoskeleton-assisted walking. We propose a novel control strategy integrating iterative learning with RBF neural network-based sliding mode control, featuring a single hidden-layer pre-feedback architecture. The RBF neural network effectively approximates uncertainties arising from lower-limb muscle perturbations, while adaptive regulation through parameter simplification ensures precise torque tracking at each joint, meeting real-time rehabilitation requirements. MATLAB 2021 simulations demonstrate the proposed algorithm’s superior trajectory tracking performance compared to conventional sliding mode control, effectively eliminating control chattering. Experimental results show maximum angular errors of 1.77° (hip flexion/extension), 1.87° (knee flexion/extension), and 0.72° (ankle dorsiflexion/plantarflexion). The integrated motion capture system enables the development of patient-specific skeletal muscle models and optimized gait trajectories, ensuring both training efficacy and safety for spasticity patients.https://www.mdpi.com/2076-3417/15/11/6053lower limb rehabilitation robotRBF neural networkiterative learningtrajectory trackingrehabilitation training experiment
spellingShingle Jing Li
Huimin Jiang
Moyao Gao
Shuang Li
Zhanli Wang
Zaixiang Pang
Yang Zhang
Yang Jiao
Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
Applied Sciences
lower limb rehabilitation robot
RBF neural network
iterative learning
trajectory tracking
rehabilitation training experiment
title Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
title_full Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
title_fullStr Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
title_full_unstemmed Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
title_short Research on Iterative Learning Method for Lower Limb Exoskeleton Rehabilitation Robot Based on RBF Neural Network
title_sort research on iterative learning method for lower limb exoskeleton rehabilitation robot based on rbf neural network
topic lower limb rehabilitation robot
RBF neural network
iterative learning
trajectory tracking
rehabilitation training experiment
url https://www.mdpi.com/2076-3417/15/11/6053
work_keys_str_mv AT jingli researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT huiminjiang researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT moyaogao researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT shuangli researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT zhanliwang researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT zaixiangpang researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT yangzhang researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork
AT yangjiao researchoniterativelearningmethodforlowerlimbexoskeletonrehabilitationrobotbasedonrbfneuralnetwork