| Abstrakt: |
Gls UUV is an intelligent underwater platform that can operate autonomously. However, it is difficult for unmanned underwater vehicle (UUV) to make correct decisions timely and independently in the face of uncertain events. Therefore, it is necessary to assess the threat of uncertain events and guide UUV to make timely and accurate decisions. This article studies the threat assessment strategy of a human-in-the-loop UUV under uncertain events. First, the uncertain events are classified according to their characteristics, and the Bayesian network (BN) is constructed by taking the characteristic variables of uncertain events as neurons. Then, the human experiences are combined with the genetic optimization algorithm to determine the BN parameters. According to the reasoning of the BN, the threat of uncertain events is evaluated. Finally, according to the threat assessment results, the PSO and A/B model are used to replan the task. The proposed algorithm uses BN to represent uncertain events and introduces human experiences to optimize network parameters, eliminating subjective bias and improving the accuracy of threat assessment. At the same time, the task replanning strategy is introduced to ensure the security of UUV. Four typical UUV tasks are designed, and the trigger elements of uncertain events are set in the simulation to verify the performance of the proposed algorithm. The simulation and experiment results show that a UUV can accurately assess the threat level of uncertain events during the task execution process when using the proposed strategy. The safety of the human-in-the-loop UUV operation is guaranteed by task replanning. |
