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 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.