Multi-AUV dynamic trajectory optimization and collaborative search combined with task urgency and energy consumption scheduling in 3-D underwater environment with random ocean currents and uncertain obstacles

A double layer bio-inspired self-organizing map (DLBSOM) algorithm for multiple autonomous underwater vehicle (multi-AUV) dynamic task planning to search for multi-targets in the 3-D underwater environments affected by random ocean currents and dynamic uncertainty obstacles is proposed. Combined with a task urgency bio-inspired neural network (TUBNN) model that is applied to construct the neuron activity network to complete initial task assignment and path planning with the constraint of energy consumption. The decoupling of the task assignment and path planning in the initial task planning is solved through the corrected redistribution mechanism and end-to-end trajectory optimization method. The unknown obstacles information is fused with the diamond-shaped local neuronal network constructed by the diamond closed curve function. Through the function curve, the local neuronal network can be precisely adjusted according to AUV operation information and equipment performance to achieve the saving of computing resources and quick processing speed. Subsequently, the distance-speed comprehensive evaluation (DSCE) strategy is used to complete dynamic avoidance decision. By the General Bathymetric Chart of the Oceans (GBCO) and the Integrated Ocean Observing System (IOOS), the environment is generated to complete multiple sets of simulations that demonstrate the efficiency and adaptability of the DLBSOM algorithm in multi-AUV collaborative search.