A New Control Approach to Robot Assisted Rehabilitation

Abstract

The goal of our research is to develop a novel control framework to assist stroke patients during rehabilitation therapy. This framework is expected to provide an optimal time-varying assistive force to stroke patients in varying physical and environmental conditions. An artificial neural network (ANN)-based PI-gain scheduling direct force controller is designed to provide optimal force assistance. The human arm model is integrated within the control framework where the ANN uses estimated human arm parameters to select the appropriate PI gains. An online technique to estimate human arm parameters as well as off-line analyses of the force controller are presented in this paper to demonstrate the feasibility and efficacy of the proposed method.