考虑智能水下机器人在水下行走，受二维海流的影响程度-An improved self-organizing map-based approach is proposed for multiple autonomous underwater vehicle (multi-AUV) system to complete the allocation of targets and path planning in the paper. Each target is to be visited by one and only one AUV, and a shortest path between a starting point and the destination for each AUV in the presence of the variable current environment is to be found. Firstly, the SOM neuron network is developed to assign a team of AUVs to achieve multiple target locations in 2-D ocean environment. Then, the velocity synthesis approach is applied to plan a shortest path for each AUV to visit the corresponding target in dynamic environment subject to the ocean current being variable. Lastly, to demonstrate the effectiveness of the proposed approach, simulation results are given in this paper.