A Hybrid Intelligent System for Pipeline Robot Navigation in Unknown Environment

Abstract

This paper developed a fuzzy logic controller with a neural network control system for sensor based pipeline robot navigation in pipe environment. The fuzzy controller creates initial membership functions and fuzzy logic rules. the neural network, which automatically process range information for determining a good steering angle in local regions. This NN-fuzzy system is used to control the mobile pipeline robot, which is equipped with an array of ultrasonic sensors to acquire the distance between the pipeline robot and obstacle. On the basis of this system, a strategy for combining local behavior control with global behavior control planning was proposed in this paper. Finally a pipeline robot runs in simulation environment. The experimental results show that appropriate control mechanisms of the fuzzy controller are obtained by evolution. The controller has evolved well enough to smoothly drive the pipeline robot in different pipe environment.