Development and control of an intelligent assistive exo-glove via fuzzy controller and emotional learning system

Abstract

The aim of this article is design, fabricate, and control a conceptual prototype of a flexible wearable robot to increase fingers’ force using a novel cable mechanism. In this robot, force and position are controlled in separate phases by a fuzzy system equipped with emotional learning. A Flexible structure has been chosen for this robot, because flexible gloves are lighter and much more suitable for use in daily tasks compared to rigid structures. Since this system is supposed to be substituted for weak or damaged limb, it should have a behavior similar to the body organs as much as possible. Therefore, a novel mechanism, inspired by the natural movement mechanism of the human hand, has been designed and tried to use a control method similar to the human brain. In order to control the glove, a proportional linear and a fuzzy controller were selected and designed. Then they were implemented through the Simulink environment of MATLAB software and applied to the glove using a real-time interface system. Finally, through some experiments, the performance of the glove and controllers have been evaluated and compared in the case of using linear and emotional learning fuzzy controllers. As expected, using the fuzzy controller with an emotional learning system makes low tracking errors result and represents appropriate performance. Compared to the linear controller, the overshoot decreased up to the one-third, and the settling time declined to one-fifth.