A Novel Global Path Planning Algorithm for Underwater Vehicle Engineering Applications

This paper presents an intelligent global path planning technology aimed at safely and intelligently navigating autonomous underwater vehicles to the operational area in specific engineering application scenarios, and reducing the cost of manual remote control. Firstly, a novel environment modeling method named SDS‐DNP, which consists of the Satellite Map Semantic Segmentation Network (SatDeepSeg) and the Distance Normalization Processing Algorithm (DistNormProc), is introduced. This method swiftly converts satellite maps into high‐precision safety factor maps, providing accurate environmental information for AUVs. Secondly, the AIW‐CE‐SMO (Adaptive Weight and Cooperative Evolution Spider Monkey Optimization) algorithm is proposed for global optimal path search. The simulation and lake experiment results show that the SDS‐DNP method can accurately model the environment even when the contrast between islands and lakes in satellite maps is low. In addition, the proposed method takes only 0.84 s, while the grid method takes 3.96 s, which is based on the premise of selecting a larger grid. Its efficiency is 78.84% higher than the grid method. Compared with traditional intelligent algorithms, the AIW‐CE‐SMO algorithm proposed in this paper has an optimal path length standard deviation between 0.55 and 5.99, and a running time between 10 and 15 s, which proves the stability and high efficiency of the algorithm. In addition, the actual experiment in the lake proves the effectiveness of the proposed algorithm.