The direct teaching of tool manipulation skills via the impedance identification of human motions

A novel approach to the teaching of skills that human workers have acquired in performing specific tasks is presented. A skilled worker shows how to perform a given task, and his motions are measured. The force exerted by the worker and the displacement of the tool manipulated by the worker are monitored and stored in a computer. The data are analyzed to find the control law of the human expert. The functional relationship between the force and the displacement is derived from the data by using a curve-fitting technique. The identified relationship is used as a reference model for controlling a manipulator arm to replicate the expert motion. The method is applied to the impedance control of a simple grinding robot