ANFN controller based on differential evolution for Autonomous Underwater Vehicles

The Autonomous Underwater Vehicles (AUVs) dynamics have six degrees of freedom and are highly nonlinear and time varying and the hydrodynamic coefficients of vehicles are difficult to estimate accurately because of the variations of these coefficients with different navigation conditions and external disturbances such as currents and waves. The path controller of the AUV is a challenging problem due to the nonlinearities and uncertainties of the AUV dynamics. Thus, the controller should be adaptive to handle variations in the dynamics of the AUV at different maneuvering regimes and disturbances arising from both the internal and external sources. In the present paper Adaptive Neural Fuzzy Network (ANFN) controller is designed and applied to guide and control the AUV. Initially, the controller parameters are generated randomly and tuned by Differential Evolution algorithm (DE). The back propagation algorithm based upon the error between the actual outputs of the plant and the desired values is then used to adopt the controller parameters online. The proposed ANFN controller adopts a functional link neural network (FLNN) as the consequent part of the fuzzy rules. Thus, the consequent part of controller is a nonlinear combination of input variables. The results show that the performance of the AUV with the ANFN controller is having better dynamic performance as compared to the conventional PID, even in the presence of noise and parameter variations.