Adaptive Neural Network Nonlinear Control Of A Flexible Robot Manipulator

Abstract

In this project, we present the design of an adaptive output feedback control methodology for the flexible robot benchmark problem. Its model is presented with some proposed solutions for the uncertainties due to unmodeled dynamics and parameteric uncertainties/ Our objective is to design a controller that forces the system output (the angular joint positions) to track a smooth reference trajectory with bounded errors. The proposed method is based on a feedback linearization controller associated to a feed-forward neural network and it has proven to be a very effective way to design controllers based on approximate knowledge of the system dynamics.