Active Neural Network Control for a Wearable Upper Limb Rehabilitation Exoskeleton Robot Driven by Pneumatic Artificial Muscles.

Abstract

Pneumatic artificial muscle (PAM) has been widely used in rehabilitation and other fields as a flexible and safe actuator. In this paper, a PAM-actuated wearable exoskeleton robot is developed for upper limb rehabilitations. However, accurate modeling and control of the PAM is difficult due to the complex hysteresis. To solve this problem, this paper proposes an active neural network method for the hysteresis compensation, where a neural network (NN) is utilized as the hysteresis compensator and an unscented Kalman filtering is used to estimate the weights and approximation error of the NN in real time. Compared with other inversion-based compensations, the NN is directly used as the hysteresis compensator without the need of inversion. In addition, the proposed method does not require pre-training of the NN as the weights can be dynamically updated. In order to verify the effectiveness and robustness of the proposed method, a series of experiments have been conducted on the self-built exoskeleton robot. Compared with other popular control methods, the proposed method can track the desired trajectory faster, and the tracking accuracy is gradually improved through iterative learning and updating.