A Design Method of Man-machine Cooperative Controller Based on Hybrid Human Behavior Model

Recently, the demand for a man-machine cooperative system was rapidly growing in industrial fields. To meet this demand, the human model has been required to design the suitable assist controller in the man-machine cooperative system. In this paper, we construct the human model with Piece-Wise ARX model and apply it to design the controller. At first, the Piece-Wise ARX human behavior model is constructed by the hierarchal clustering, the support vector machine and the least square method. Then, we obtain the responses by computing the derived human model and the robot controller dynamics. Finally, we try to optimize the parameter of the controller with a forward computation and a criterion.