Mobile robot modeling using local model networks

Abstract

This article deals with the modeling issue of plants with unknown description. The modeling approach is based on the Local Model Network structure. Local Models perform local linearization and their structure is quite similar to the Takagi-Sugeno fuzzy models. Local Neural Models (LNM) function as linear filters, giving a satisfying estimation for the plant's output within parts of the operating regime. Their training is performed off-line, which ensures a reliable method. The method is applied on the Robuter <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">TM</sup> mobile robot.