Coverage path planning of unmanned surface vehicle based on improved biological inspired neural network

Abstract

In order to meet the requirements of coverage path planning task for unmanned surface vehicle, a coverage apth planning algorithm of unmanned surface vehicle based on improved biological inspired neural network is proposed. The template model method and jump point search algorithm are introduced on the basis of biological inspired neural network to solve the problem that the original algorithm cannot completely cover and lock when adjacent to obstacles. To meet the task requirements and enrich the functionality of the algorithm, the island type obstacle template is introduced to make the algorithm give priority to island coverage detection. The problem of obstacle disappearance is solved by enhancing the ability of algorithm to cover specific area first. In the simulation, six marine maps with different complexity are established to verify the effectiveness of the path planning algorithm. Compared with the other coverage path planning algorithms, the simulation experiment proves that the proposed improved biological inspired neural network path planning algorithm improves the efficiency of coverage path planning, shortens the path length and reduces the path repetition rate on the premise of ensuring 100% coverage. Furthermore, the proposed improved biological inspired neural network algorithm achieves the shortest path planning time.