Dynamic Assignment of Multi-UAV Marine Search and Rescue Missions Under the Condition of Intelligence Support
Xingjun Chen, Zimeng Wang, Junpeng Zhang · 2023
In recent years, the problem of multi-UAV task assignment has been widely studied and is generally considered to be NP-hard. The solution model of this problem consists of an objective function and constraints. For the objective function, the current mainstream research direction is to aim at the shortest execution time or the highest mission execution gain, while the constraints need to be based on specific practical problems. In actual scenarios, the multi-unmanned task allocation research model often ignores the dynamic properties of the target due to the fast speed of the UAV during the construction process. It leads to the problem of uneven resource allocation that does not fit the actual situation of the battlefield. In this paper, considering that most of the search and rescue targets are dynamic targets, we give the distribution areas for targets with known and uncertain headings. And build a dynamic assignment model for multi-UAV marine search and rescue missions under the condition of intelligence support. Finally, the traditional genetic algorithm and distributed NSGA-III algorithm are used to solve the problem to prove the validity of the model. The experimental results show that the proposed methods can effectively solve the problem of dynamic assignment of multi-UAV tasks, and provide feasible ideas and technical support for how to deal with dynamic targets in the problem of multi-UAV task assignment.