Navigation of an autonomous mobile robot using intelligent hybrid technique

Abstract

The hallmark of this paper describes Adaptive Neurofuzzy (ANFIS) based navigation for an autonomous mobile robot in a real world cluttered environment. ANFIS has the advantage of both expert knowledge of the fuzzy inference system and the supervised learning capability of artificial neural networks. In this architecture the front obstacle distance (FOD), left obstacle distance (LOD), right obstacle distance (ROD) (from the robot) and target angle (angle to the source) are collected from the array of ultrasonic sensors mounted on a mobile robot and given as input to the ANFIS controller and output from the controller is steering angle. Finally, simulation experiments using MATLAB program have shown that, the ANFIS model is suitable and effective for path planning of a mobile robot in uncertain terrain to find and reach to target objects.