Motion control of intelligent underwater robot based on CMAC-PID

Abstract

Intelligent underwater robot has been drawing increasing interests in various areas such as ocean resource exploitation and etc. It is well known that the dynamics of underwater robot are highly nonlinear and complex.The proportional-integral-derivative (PID) control scheme has been widely used for most industrial processes which are represented by nonlinear systems. However, it is difficult to find an optimal set of PID gains. On the other hand, Cerebellar Model Articulation Controller (CMAC) has been proposed as one of artificial neural networks. In this paper, conventional PID controller was combined with CMAC to form a compound CMAC-PID control strategy. The proposed control scheme was numerically evaluated on a simulation example about motion control in a fixed depth for an underwater robot. The simulation results revealed the compound CMAC-PID controller had excellent control performance such as systemic stability, disturbance resistance, fast response rate and small overshoot. It can be concluded that the compound controller is robust, self-adaptive and effective.