Iterative Learning Control Based on Radial Basis Function Network for Exoskeleton Arm

In this paper, we propose iterative learning control (ILC) scheme for exoskeleton arm driven by pneumatic artificial muscles (PAM), with special and unknown parameters, performing repetitive tasks. This desired control input of ILC was estimated by radial basis function (RBF) neural network incorporated experience database. An ILC controller, which uses the position of the joint where an angular sensor is used as the input of the ILC controller, is developed and tested on exoskeleton arm under well controlled conditions. RBF neural network was proposed to obtain the initial value of ILC. The experiment result on the experimental platform show that the algorithm is successful also in the application of exoskeleton arm.