Prescribed performance velocity field control of robotic exoskeletons with neural network

Abstract

This paper addresses the problem of velocity field control (VFC) of robotic exoskeletons. This control strategy gives better performance over the trajectory tracking method in counter following problem when the actual timing of the task is not important, and has potential applications in rehabilitation. In this paper, we propose a prescribed performance controller for VFC of exoskeletons in order to gain a desired behavior of the system in both transient and steady-state phases. The proposed controller includes a neural network term to deal with unknown dynamics of the system. Through simulation studies, the controller is tested on a lower-limb exoskeleton, and results show a superior performance of the controller in comparison with a classic one.