Self-Organizing Neuro-Fuzzy Control for Underwater Robotic Vehicles.(Dept.E)

Abstract

Underwater robotic 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 system designs have been based on a simplified vehicle model, which has often resulted in poor performance because the nonlinear and time-varying vehicle dynamics lave parameters uncertainty. It is desirable to have an advanced control system with the capability of learning and adapting to change in the vehicle dynamies and parameters. The proposed system is possessing neural network's learning ability. There are no rules initially in the proposed system. They are created and adapted as on-line leaning proceeds via simultaneous structure and parameter identification. The identification process of the controller includes both structure and parameter learning.