Swarm intelligence algorithms have better intelligence and adaptation compared with the traditional route planning method. A three-dimensional route planning method based on the beetle swarm optimization (BSO) algorithm was proposed. The iterative updating strategy of the BSO algorithm cooperated with the search mechanism of the beetle monomer and the updating strategy of the particle swarm optimization (PSO) algorithm, thus accelerating iterative convergence and decreasing the probability of trapping in the local optimal solution of the algorithm. The practical engineering problem of three-dimensional route planning was addressed by processing uneven ground barriers using the penalty function, and a smooth route is gained from cubic spline interpolation. In this study, a three-dimensional environmental model was constructed by using actual elevation data from the USGS/NASA SRTM, and a simulation experiment of three-dimensional route planning was performed using the proposed method. The proposed method was compared with other algorithms. Experimental results demonstrated that when the iteration time was set to 50, the route planning length based on BSO algorithm was about 90% of the route planning based on the PSO algorithm. Moreover, the proposed route planning method had high convergence rate and stable convergence result and is applicable to three-dimensional route planning.INDEX TERMS Beetle swarm optimization (BSO), particle swarm optimization (PSO), route planning.

No abstract

The traditional netcage inspection requires divers to complete, which is inefficient and dangerous. The underwater robot inspection is a way to solve the problem. When the robot is in motion, the camera shoots the netcage, replacing the manual inspection. A new hybrid control strategy based on neural network (NN) and proportional integral differential (PID) is proposed for underwater three‐dimensional path tracking, which overcomes the defect that the traditional feedback regulation can only work after the occurrence of deviation. A feedforward controller based on neural network is designed to predict the disturbance of the controlled object and enhance the anti‐interference ability of the system. Firstly, implement global path tracking based on azimuth and course. Then when the remotely operated vehicle (ROV) deviates from the path, local path planning with rapidly‐exploring random trees (RRT) algorithm. ROV tracks local path and returns to the global path. Finally, using the moving average (MA) algorithm of RRT path smoothing, a smooth path is obtained to minimize ROV jitter, which ensures that the ROV can clearly take pictures of the netcage, and the service life of the ROV is extended. ROV can replace manual inspection, and it only takes about 30 min to rotate a circle, greatly improving work efficiency. The control approach was tested underwater at different depth path tracking scenarios. The experimental results show that in the case of waves <0.5 m, the average tracking error of ROV is <0.5 m, the fluctuation of roll angle and pitch angle is <6°, the average distance error from ROV to mesh netcage is about 0.2 m, and the underwater netcage inspection task is completed stably. [Video attachment: https://youtu.be/NKcgPcej5sI].