Autonomously Adapting Robotic Assistance for Rehabilitation Therapy

Abstract

The goal of our research is to develop a novel control framework to provide robotic assistance for rehabilitation of the hemiparetic upper extremity after stroke. The control framework is designed to provide an optimal time-varying assistive force to stroke patients in varying physical and environmental conditions. An artificial neural network (ANN) based proportional-integral (PI) gain scheduling direct force controller is designed to provide optimal force assistance in a precise and smooth manner. The human arm model is integrated within the control framework where ANN uses estimated human arm parameters to select the appropriate PI gains. Experimental results are presented to demonstrate the effectiveness and feasibility of the proposed control framework