Intelligent adaptive control of robotic dynamic systems with a new hybrid neuro-fuzzy-fractal approach

Abstract

We describe a new method for adaptive model based control of robotic dynamic systems using a new neuro fuzzy fractal approach. Intelligent control of robotic systems is a difficult problem because the dynamic of these systems is highly nonlinear. We describe an intelligent system for controlling robot manipulators to illustrate our neuro fuzzy fractal hybrid approach for adaptive control. We use a new fuzzy inference system for reasoning with multiple differential equations for model selection based on the relevant selection parameters for the problem. In this case, the fractal dimension of a time series of measured values of the variables is used as a selection parameter. We use neural networks for identification and control of robotic dynamic systems. The neural networks are trained with the Levenberg-Marquardt (LM) algorithm with real data to achieve the desired level of performance.