The implementation of wheeled robot using adaptive output recurrent CMAC

In this study, an adaptive output recurrent cerebellar model articulation controller (AORCMAC) is investigated to control the two-wheeled robot. The main purpose is to develop a self-dynamic balancing and motion control strategy. The proposed AORCMAC has superior capability to the conventional cerebellar model articulation controller in efficient learning mechanism and dynamic response. The dynamic gradient descent method is adopted to online adjust the AORCMAC parameters. Therefore, AORCMAC has superior capability to the conventional cerebellar model articulation controller (CMAC) in efficient learning mechanism and dynamic response. Finally, the effectiveness of the proposed control system is verified by the experiments of the two-wheeled robot standing control. Experimental results show that the the two-wheeled robot can stand upright stably with uncertainty disturbance by using the proposed AORCMAC.

I. Introduction

IN the past several years, there are several literatures to study the topic “two-wheeled robot”. The main topic of this research is how to keep the robot's balance. This system would become a primary tool for studying balance in active balancing system. It is also to be an important precursor to the field of legged machines and locomotion studies for robotics. There are many researches in this filed. In [1], a trajectory tracking algorithm based on a linear state space model was proposed to control mobile robot. Graser et al. [2] used Newtonian approach and linearization method to get a dynamic model to design a controller for a mobile. In [3], a dynamic model was derived with respect to the wheel motor torques as input while taking the nonholonomic no-slip constrains into considerations. Furthermore, two controllers were proposed to stabilize the vehicle's pitch and position. Until now, at least one commercial product is available such as “Segway”.