Design of neural-fuzzy-based controller for two autonomously driven wheeled robot

An intelligent control architecture for two autonomously driven wheeled robot is developed in this paper. Consider the parametric variation, external load disturbance, nonlinear friction, unpredicted and unstructured uncertainties for the practical applications, the transient and unmodelled uncertainty will be occurred. In the proposed control scheme, the fuzzy inference is designated as a main controller and the neural network is an auxiliary part. In the fuzzy controller, the translation width and total sliding surface are adopted to reduce the chattering phenomena. The neural uncertainty observer is added in the balance, speed and synchronous controllers to reduce the accumulated error and ascend the stability. The hardware includes a microcontroller, gyroscope, accelerometer, and two autonomous motors, etc. The effectiveness is verified by simulation and experimental results, and the result is compared with conventional PD control scheme for the same robot.