A Neural Network Based Control System for a Mobile Robot Employing Link Mechanism

Abstract

The transportation using wheels is one of the most popular transportation mechanisms for mobile robots because its energy efficiency is high, the wheel mechanism is simple and the control system is well investigated. Therefore, the wheel type mobile robots are one of the most practical and widespread robots. However, the wheel type mobile robots have the difficulty in the rough terrain movement. In this research, a 6-wheeled mobile robot employing the linkage mechanism, Zaurus, has been developed to extend maneuverability of wheel type mobile robots. In order to evaluate its maneuverability, the experiments to climb over a bump with twice height of diameter of the robot's wheel have been carried out. Neural Network and PID controllers are introduced as the control system and their performance are compared.