APPLICATION OF MULTILAYER PERCEPTRONS TO DECOUPLE THE DYNAMICAL BEHAVIOUR OF ROBOT LINKS

Abstract

The paper extends a previously proposed method for improving the path accuracy of robots. Especially during high speed movements nonlinear couplings between the joints deteriorate and degrade the robot's accuracy. Such couplings cannot be compensated by linear feedforward control. They require additionally a general function approximator as e. g. a multilayer perceptron. The learning system translates I/O data of robot movements to training data for the neural nets. Linear controllers and multilayer perceptrons are combined after training to improve the execution of sensor planned paths which are not explicitely trained before. The method is verified in experiments using a high speed path which originally is sensed by a compliant force- / torque sensor. 1 Introduction For most industrial robots the accuracy achievable with the standard control system does not exceed some millimeters for off-line programmed paths. But several applications, as laser cutting, require accuracies of at lea...