A learning control system for unmanned underwater vehicles

Unmanned underwater vehicles have become an important tool for various underwater tasks because they have greater speed, endurance and depth capability as well as a higher factor of safety than human divers. However, most vehicle control systems were designed based on a simplified vehicle model and they often resulted in poor performance because of the nonlinear and time-varying vehicle dynamics having parameter uncertainties. This paper describes a new adaptive and learning (AL) control system.