Collaborative planning algorithm for incomplete navigation graphs

Abstract

In a complex environment, in order to improve the efficiency of multi-AUV collaborative work, this paper proposes a new collaborative hunting algorithm based on the Bionic Neural Wave Network (BNWN) algorithm. This algorithm integrates search, tracking and capture of targets by multi-AUV under the incomplete navigation graphs. A search mechanism with memory tabu that to avoid redundant search and improve global search efficiency is designed. Then a real-time redistribution method is embedded into this algorithm to ensure the optimal matching state during the tracking and capture process. Further, multi-AUV track and capture prey based on energy consumption models and self-learning models, and recast time-varying navigation maps through the recognition mechanisms, under the whole collaborative operations. Simulation results have proved that the number of multi-AUV path turns is reduced and the execution time is shortened by an average of 81%. In this way, the optimal matching state is maintained, the repeated search and partial self-locking problems are overcome, and the efficient capture of intelligent prey is realized.