Adaptive neural network controller applied to dynamic positioning of a remotely operated vehicle

In many operations, it is required that the ROV keeps its position close to some underwater structure (station keeping) precisely. An adaptive controller for dynamic positioning of a remotely vehicle (ROV) with unknown parameters and disturbances is addressed in this paper. The additional forces caused by the umbilical cables and ocean currents can be estimated and compensated. An RBF neural network compensator is proposed to deal with the dynamic uncertain nonlinear mapping and cross coupling terms, because the dynamics of ROV are highly nonlinear nature and the hydrodynamic coefficients are difficult to be accurately estimated. The adaptation Laws and network weights adaptation law are derived from the Lyapunov stability analysis, and the stability of close-loop system is proved. Simulation results indicate that the proposed control method has good control performance.