TY - EJOU AU - Cao, Xiang AU - Chen, Ling AU - Guo, Liqiang AU - Han, Wei TI - AUV Global Security Path Planning Based on a Potential Field Bio-Inspired Neural Network in Underwater Environment T2 - Intelligent Automation \& Soft Computing PY - 2021 VL - 27 IS - 2 SN - 2326-005X AB - As one of the classical problems in autonomous underwater vehicle (AUV) research, path planning has obtained a lot of research results. Many studies have focused on planning an optimal path for AUVs. These optimal paths are sometimes too close to obstacles. In the real environment, it is difficult for AUVs to avoid obstacles according to such an optimal path. To solve the safety problem of AUV path planning in a dynamic uncertain environment, an algorithm combining a bio-inspired neural network and potential field is proposed. Based on the environmental information, the bio-inspired neural network plans the optimal path for the AUV. The potential field function adjusts the path planned by the bio-inspired neural network so that the actual AUV can avoid obstacles. The proposed approach for AUV path planning with safety consideration is capable of planning a real-time “comfortable” trajectory by overcoming either “too close” or “too far” shortcomings. Simulation and experimental results show that the proposed algorithm considers both AUV security and path rationality. The planned path can meet the need for collision-free navigation of AUVs in a dynamic, uncertain environment. KW - Autonomous underwater vehicle; bio-inspired neural network; path planning; potential field DO - 10.32604/iasc.2021.01002