Neural Network Adaptive Control of Hand Rehabilitation Robot Driven by Flexible Pneumatic Muscles

The aim of this study is to design a reliable and stable controller for hand rehabilitation robot driven by flexible pneumatic muscles(FPMs) for post stroke patients. Position control is key to perform effective rehabilitation robotic exercise. However, it is difficult to achieve precise control due to the nonlinearity and hysteresis of the flexible muscles. The efficient control system is required to realize the high-precision control of the joint angle. In this paper, to achieve the stability and anti-interference ability of the system, an improved neural network adaptive control(INNAC) method is proposed. The neural network is used to estimate the unknown items and the adaptive control is used to realize the adaptive characteristics in the unknown environment, so as to realize the stability and high precision control of the control system when encountering human interferences. Finally, experiments were carried out on robot with human participants for five fingers movement assistance. The results show that the control system can achieve good control effect and anti-interference ability