PARAMETRIC MOTOR CONTROL - A NEW APPROACH TO THE CONTROL OF POINT-TO-POINT MANIPULATOR MOVEMENTS

We propose a control scheme for point-to-point movements of robotic ma nipulators, which is based on an established concept about human movem ent control. In this approach, actuator drive signals have an invarian t shape and are parametrically modifled to fit the requirements of dif ferent tasks. The appropriate parameter values are provided by an Arti ficial Neural Network before movement onset. Explicit solutions of the inverse kinematic and inverse dynamic equations, or multiple feedback loops, are not required for this approach. We found that Parametric M otor Control yields satisfactory performance, allowing the manipulator to discriminate between targets in a 5 x 3 grid and to generalize to new target locations. The new control scheme has potential benefits fo r scenarios where complex manipulators must be controlled in real time . (C) 1996 John Wiley & Sons, Inc.