Research on UAV Cooperative Task Assignment Based on Dynamic Multi-objective Evolutionary Algorithm

Abstract

In recent years, more and more attention has been paid to the research of unmanned aerial vehicle (UAV) cooperative task assignment. In order to complete the task with the lowest cost, some researchers use multi-objective to optimize the assignment. But few of them consider the complex dynamic scenarios. According to the coordinated task assignment problem of scheduling jammer and attack UAV resources to targets, a dynamic multi-objective optimization cooperative task assignment model is established. It takes the scheduling cost, path cost, risk cost and total task time cost as the optimization objectives. To solve this model, this paper proposes an improved dynamic multi-objective adaptive weighted particle swarm algorithm. In the initialization stage, a heuristic method is used to increase the effectiveness of the solution. Besides, the adaptive mutation and subgroup methods are adopted to improve the diversity of the solution. Then, an effective environment change detection and environment change response strategy are designed to deal with dynamic scene changes. Finally, the Hypervolume (HV) metric is calculated in the experiments in different instances. Compared with the popular and classic dynamic multi-objective algorithms, the simulation results verify that the proposed algorithm is effective and can cope with the changes of the environment better in solving the problem of UAV collaborative task assignment.