To eliminate the effect of ocean currents for optimal path planning for unmanned underwater vehicles (UUVs) in the underwater environment, an intelligent algorithm is designed and proposed in this paper. The algorithm consists of two parts: an artificial potential field-based algorithm that derives the shortest path and avoids collision accidents; and an adjusting function that eliminates the effect of ocean currents. The planning results of the intelligent algorithm are presented in detail, and compared with the conventional algorithm that does not consider the effect of currents. The effectiveness of the optimised path planning method given in this paper is proved.

This paper focuses on depth trajectory tracking control for a Remotely Operated Vehicle (ROV) with dead-zone nonlinearity and saturation nonlinearity of thruster; an adaptive sliding mode control method based on neural network is proposed. Through the analysis of dead-zone nonlinearity and saturation nonlinearity of thruster, the depth trajectory tracking control system model of a ROV which uses thruster control signals as system input has been established. According to the principle of sliding mode control, an adaptive sliding mode depth trajectory tracking controller is built by using three-layer feed-forward neural network for online identification of unknown items. The selection method and update laws of the control parameters are also given. The uniform ultimate boundedness of trajectory tracking error is analysed by Lyapunov theorem. Finally, the effectiveness of the proposed method is illustrated by simulations.

In this paper, for the over-actuated Autonomous Underwater Vehicle (AUV) system, a novel tracking controller with thruster fault accommodation is proposed. Firstly, a cascaded control method is proposed for AUV robust tracking control. Then, we deal with the tracking control problem when one or more thrusters are completely or partly malfunctioning. Different control strategies are used to reallocate the thruster forces. For the cases that thrusters are partly malfunctioning, a weighted pseudo-inverse is firstly used to generate the normalised thruster forces. When the normalised thruster forces are out of maximum limits, the Quantum-behaviour Particle Swarm Optimisation (QPSO) is used for the restricted usage of the faulty thruster and to find the solution of the control reallocation problem within the limits. Compared with the weighted pseudo-inverse method, the QPSO algorithm does not need truncation or scaling to ensure the feasibility of the solution due to its particle search in the feasible solution space. The proposed controller is implemented in order to evaluate its performance in different faulty situations and its efficiency is demonstrated through simulation results.

In this paper, we investigate the problem of robust stability for a class of delayed neural networks of neutral-type with linear fractional uncertainties. The activation functions are assumed to be unbounded, non-monotonic and non-differentiable, and the delay is assumed to be time-varying and belonging to a given interval, which means that the lower and upper bounds of the interval time-varying delay are available. By constructing a general form of the Lyapunov–Krasovskii functional, and using the linear matrix inequality (LMI) approach, we derive several delay-dependent stability criteria in terms of LMI. Finally, we give a number of examples to illustrate the effectiveness of the proposed method.