Application of neural network with real-time training to robust position/force control of multiple robots

Abstract

A robust controller that compensates the uncertainties of the dynamic system of the multiple robotic system in order to obtain good tracking performance of position and force simultaneously while satisfying the constraint conditions is presented. A neural network architecture is proposed as one approach to its design and implementation. An online learning rule is provided for repeatedly assigned tasks so that the system is robust to the structured and unstructured uncertainties and the controller adjusts itself repeatedly to improve the performance progressively for each repeated task.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>