Adaptive Sliding Mode Control for AUV based on Backstepping and Neural Networks

Abstract Automatic underwater vehicle (AUV) inevitably suffers from various interference issues in the marine environment. Due to the limitations of underwater measurement methods and tools, as well as the complexity of AUV’s control parameters in the underwater environment, dynamic measurement errors are easily cascaded and amplified, leading to the failure of the control system. In response to this phenomenon, this paper focuses on overcoming the influence of internal and external unknown factors in the tracking and control process of AUV trajectories. The internal factors are mainly the uncertainties generated by the model mismatch problem, and the external factors are mainly from the dynamic ocean currents. The AUV disturbances mainly affect the kinematics and dynamics levels directly or indirectly. In order to achieve the control of internal and external dynamic disturbances, we have designed a control system that employs backstepping and a sliding mode controller with radial basis function neural networks to achieve the cascaded control of kinematics and dynamics. Comparison of multiple sets of simulations shows that our proposed algorithm has excellent anti-disturbance performance for dynamic conditions with low measurement accuracy.