Smooth Human-Robot Interaction in Robot-Assisted Rehabilitation

The goal of this work is to develop a control framework to provide robotic assistance for rehabilitation tasks to the subjects in such a manner that the interaction between the subject and the robot is smooth. This is achieved by designing a methodology that automatically adjusts the control gains of the robot controller to modify the interaction dynamics between the robot and the subject. In order to automatically determine the control gains for each subject, an artificial neural network (ANN) based proportional-integral (PI) gain scheduling controller is proposed. The human arm model is integrated within the controller where the ANN uses estimated human arm parameters to select the appropriate PI gains for each subject such that the resultant interaction dynamics between the subject and the robot could result in smooth interaction. Experimental results are presented to demonstrate the efficacy of the proposed ANN-based PI gain scheduling controller on unimpaired subjects.