Demand and Method Discussions for Intelligent Decisions of Torpedo Attacking by Unmanned Undersea Vehicle

The autonomous technology of unmanned equipment is currently the most dynamic frontier technology field. Therefore, improving the intelligence of decision-making is an inevitable trend in the development of future unmanned undersea vehicles (UUVs). Torpedo attack decision-making is a critical aspect of UUVs on operational missions and also the basis and prerequisite for the formation of self-organized cross-domain cooperation, autonomous swarm confrontation, and other operational capabilities. Beginning with a summary of the characteristics of their operational use and typical operational mission styles, the advantages and shortcomings of UUVs with manned platforms in operational applications were compared, and their decision-making content differed from that of traditional torpedo attacks was analyzed. The key problems that need to be solved to realize the decision-making function were expounded. Based on the development of machine learning technology, it is proposed that an intelligent decision-making method is suitable for solving the problems of large uncertainty of observation data, difficulty in guaranteeing real-time decision-making, and weak interaction ability of model perception. This study can provide a reference for future research in the field of unmanned equipment development and intelligent decision-making.