Adaptive RBF neural network control for gait trajectory following in a rehabilitation exoskeleton
TL;DR
This study develops an adaptive trajectory-tracking method driven by an RBF neural network that yields faster error attenuation, smaller steady-state oscillation, along with improved resistance to disturbances in the hip and knee motions.
Abstract
Improving trajectory-following accuracy remains a central issue in lower-limb rehabilitation exoskeletons, especially when joint motion is affected by nonlinear coupling, parameter drift, and interaction disturbances during repetitive gait training. To address this problem, this study develops an adaptive trajectory-tracking method driven by an RBF neural network. A single exoskeleton leg is first represented as a two-degree-of-freedom planar double-link mechanism in the sagittal plane, and the swing-phase dynamics are formulated via the Lagrange approach. On this basis, a nominal-model decomposition framework is introduced so that uncertain dynamics and external perturbations can be approximated online by the RBF network. A joint-space controller is then constructed to improve tracking stability and robustness. MATLAB simulations and prototype experiments are further carried out, with conventional PID control used for comparison. The results indicate that the proposed approach yields faster error attenuation, smaller steady-state oscillation, along with improved resistance to disturbances in the hip and knee motions. Overall, the proposed approach is effective for accurate gait-following control in rehabilitation exoskeletons.