Experimental study on a learning control system with bound estimation for underwater robots

Abstract

Underwater robotic vehicles (URVs) have become an important tool for various underwater tasks because of their greater speed, endurance, depth capability and a lower risk factor than human divers. However, most vehicle control system designs are based on simplified vehicle models and often result in poor vehicle performance due to the nonlinear and time-varying vehicle dynamics having parameter uncertainties. This paper describes a new vehicle control system capable of learning and adapting to changes in the vehicle dynamics and parameters. This control system is compared with a conventional linear control system through extensive wet tests. Results show the learning and adapting capabilities of the presented control system.