Adaptive control of upper limb rehabilitation robot based on RBF neural network compensation

For stroke patients, sudden muscle force disturbances may occur in the upper limb rehabilitation exercise. Combining the neural networks ability to approximate arbitrary functions, using the advantages of adaptive control in solving system uncertainties, and applying the theory of Lyapunov stability to prove the asymptotic stability of the closed-loop system, a compensation based on RBF neural network the adaptive control algorithm of the upper limb rehabilitation robot was proposed in this paper to compensates for the defects caused by sudden muscle force interference.