An Observer-Based Adaptive Neural Network Finite-Time Tracking Control for Autonomous Underwater Vehicles via Command Filters

Due to the hostile marine environment, there will inevitably be unpredictable factors during operation of unmanned underwater vehicles, including changes in ocean currents, hull dimensions, and velocity measurement uncertainties. An improved finite-time adaptive tracking control issue is considered for autonomous vehicles (AUVs) with uncertain dynamics, unknown external disturbances, unavailable speed information. A state observer designed estimate position vehicle via a neural network (NN) approach. The NN used uncertainties disturbances. controller backstepping command filter techniques. multi-input multi-output (MIMO) AUVs established, corresponding MIMO compensation signal constructed eliminate effect filtering error. All signals closed-loop system are proved bounded. example comparison given show effectiveness our method.