Experimental studies of balancing control for a disc-typed mobile robot using a neural controller: GYROBO

Abstract

In this paper, a disc typed one wheeled mobile robot is designed, implemented and controlled. The disk type robot called GYROBO has three actuators to move forward and backward and to balance itself. Gyro effects generated by two actuators are used to help the GYROBO to maintain balancing. Design of balancing mechanism is raised an important issue since there is a limited space. Thus, we have a successful design after several modifications of design. Since the performance of a simple PD control algorithm is poor, neural network as a nonlinear controller is added to form the reference compensation technique as a neural network control. Experimental studies of a self balancing task are presented to show the better performance by the neural network.