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.

Intelligent lower-limb exoskeleton rehabilitation robots are increasingly superseding traditional rehabilitation equipment, making them a focus of research in this field. However, existing systems remain challenged by dynamic instability resulting from various disturbances during actual walking. To address this limitation, this study proposes a novel dynamic stability criterion. Through an analysis of the principles and limitations of the traditional zero-moment point (ZMP) stability criterion, particularly during the late single-leg support phase, a new stability criterion is introduced, which is founded on the swing projection polygon during single-leg support. This approach elucidates the variation patterns of the stability polygon during a single-step motion and facilitates a qualitative analysis of the stability characteristics of the human–robot system in multiple postures. To further enhance the stability and smoothness of gait trajectories in lower-limb exoskeleton rehabilitation robots, the shortcomings of conventional gait planning approaches, namely their non-intuitive nature and discontinuity, are addressed. A recurrent gait planning method leveraging Long Short-Term Memory (LSTM) neural networks is proposed. The integration of the periodic motion characteristics of human gait serves to validate the feasibility and correctness of the proposed method. Finally, based on the recurrent gait planning method, the dynamic stability of walking postures is verified through theoretical analysis and experimental comparisons, accompanied by an in-depth analysis of key factors influencing dynamic stability.