In order to solve the trajectory tracking control problem with the drive saturation (thrust overrun) for the 4500m-Human Occupied Vehicle named “Deep-sea Warrior”, a model predictive adaptive constraint control strategy is put forward. The proposed control strategy mainly consists of two controllers. The first part is a kinematics controller designed by quantum-behaved particle swarm optimization model predictive control method. The second part is a dynamic controller designed by an adaptive algorithm. The ocean current is incorporated into the kinematics and dynamics model of the 4500m-HOV. The thrusts of four degrees of freedom under the ocean current are calculated from designed controllers. Then the thrusts are assigned to six thrusters on the 4500m-Human Occupied Vehicle according to its thruster arrangement. An ocean current observer based on artificial fish PI control is designed for unknown currents. The simulation results of tracking control in three-dimensional underwater environment are given, which illustrates that the proposed control strategy can not only meet the hardware requirements but also achieve a stable and efficient tracking control performance because of its constraint to speed, the effect of the ocean current on kinematics and dynamics models and the dual feedback mechanism.

Aiming at the drive saturation problem of tracking control which is one of the main research directions, a hybrid control strategy based on quantum-behaved particle swarm optimization-model predictive control (QPSO-MPC) and adaptive sliding mode control (ASMC) is put forward for “Jiaolong“ Human Occupied Vehicle (HOV). The hybrid control strategy includes a QPSOMPC-based kinematic controller and an ASMC-based dynamic controller. The kinematic controller transforms the position error into the virtual desired speed. Then the error between the desired speed and real speed is used as the input for the dynamic controller, the thrusts of 6 DOF are obtained. The thrusts are distributed to eight thrusters in accordance with thrusters‛ configuration of “Jiaolong” HOV. The innovation of this hybrid control strategy is it takes into account the limited speed for HOV. The constraints on speed and speed increment are added in the optimization part of the kinematic controller. Compared with backstepping control and bioinspired backstepping control, the proposed strategy can deal with the speed jump phenomenon and the drive saturation caused by exceeded speed variation. From the simulation results, the hybrid strategy is able to achieve stable and accurate tracking control under the condition of satisfying the physical constraints.

The issue of marine litter has been an important concern for marine environmental protection for a long time, especially underwater litter. It is not only challenging to clean up, but its prolonged presence underwater can cause damage to marine ecosystems and biodiversity. This has led to underwater robots equipped with powerful visual detection algorithms becoming the mainstream alternative to human labor for cleaning up underwater litter. This study proposes an enhanced underwater litter detection algorithm, YOLOv7t-CEBC, based on YOLOv7-tiny, to assist underwater robots in target identification. The research introduces some modules tailored for marine litter detection within the model framework, addressing inter-class similarity and intra-class variability inherent in underwater waste while balancing detection precision and speed. Experimental results demonstrate that, on the Deep Plastic public dataset, YOLOv7t-CEBC achieves a detection accuracy (mAP) of 81.8%, markedly surpassing common object detection algorithms. Moreover, the detection frame rate reaches 118 FPS, meeting the operational requirements of underwater robots. The findings affirm that the enhanced YOLOv7t-CEBC network serves as a reliable tool for underwater debris detection, contributing to the maintenance of marine health.

Targeting the problem of fault diagnosis in magnetic coupling underwater thrusters, a fault pattern classification method based on load feature extraction is proposed in this paper. By analyzing the output load characteristics of thrusters under typical fault patterns, the load torque model of the thrusters is established, and two characteristic parameters are constructed to describe the different fault patterns of thrusters. Then, a thruster load torque reconstruction method, based on the sliding mode observer (SMO), and the fault characteristic parameter identification method, based on the least square method (LSM), are proposed. According to the identified fault characteristic parameters, a thruster fault pattern classification method based on a support vector machine (SVM) is proposed. Finally, the feasibility and superiority of the proposed aspects are verified, through comparative simulation experiments. The results show that the diagnostic accuracy of this method is higher than 95% within 5 seconds of the thruster fault. The lowest diagnostic accuracy of thrusters with a single failure state is 96.75%, and the average diagnostic accuracy of thrusters with five fault states is 98.65%.

This paper aims to address the obstacle avoidance problem of autonomous underwater vehicles (AUVs) in complex environments by proposing a trajectory planning method based on the Gauss pseudospectral method (GPM). According to the kinematics and dynamics constraints, and the obstacle avoidance requirement in AUV navigation, a multi-constraint trajectory planning model is established. The model takes energy consumption and sailing time as optimization objectives. The optimal control problem is transformed into a nonlinear programming problem by the GPM. The trajectory satisfying the optimization objective can be obtained by solving the problem with a sequential quadratic programming (SQP) algorithm. For the optimization of calculation parameters, the cubic spline interpolation method is proposed to generate initial value. Finally, through comparison with the linear fitting method, the rapidity of the solution of the cubic spline interpolation method is verified. The simulation results show that the cubic spline interpolation method improves the operation performance by 49.35% compared with the linear fitting method, which verifies the effectiveness of the cubic spline interpolation method in solving the optimal control problem.