Autonomous motion control of mobile robots using fuzzy-neural networks

Summary form only given. This paper analyzes the kinematic model of mobile robots as well as the design of control systems for autonomous motion of the robot. One fuzzy controller and two neural controllers were designed. The fuzzy controller is based on the knowledge and experience of human operator. The neural controllers consist of a fuzzy-based neurocontroller and a fuzzy-neural controller trained to optimize a given cost function. The fuzzy-neural controllers implement the process of fuzzy reasoning through a neural network structure so that they behave as fuzzy systems with learning capabilities. A sensorless experimental mobile robot was constructed to analyze the feasibility and practical implementation of fuzzy and neural controllers. It was found that the robot with fuzzy-neural control performed better than the fuzzy controller and fuzzy-based neural controller in terms of positioning accuracy and collision avoidance. Likewise, the neural controllers require less computing time and computing memory than the fuzzy controller.