军事后勤中的多目标无人机任务规划

Multi-Objective UAV Mission Planning in Military Logistics

在无人机军事后勤运输任务规划的研究中,在进行无人机运输任务规划时会存在多个冲突的目标。为了求解多目标无人机任务规划问题,提出应用线性权重法将其转化为单目标无人机任务规划问题,考虑问题的组合优化特性,提出了实数编码的烟花算法。最后在一个经典车辆路径测试问题的基础上拓展为多目标无人机任务规划问题,以验证算法的有效性。实验结果表明,只考虑某一目标时得到的最优路径方案对于其它目标来说可能是较差的方案;可在作无人机任务规划时要权衡不同的目标以得到最优的综合结果。提出的线性权重法与实数编码烟花算法相结合的混合算法可以有效解决军事后勤中的多目标无人机任务规划问题。

The application of UAVs in military logistics transportation is of significant importance. Considering the multiple conflicting objectives during UAV mission planning for military logistics, a linear weighted method was used to convert the original multi-objective problem into the problem of single objective UAV mission planning. Then, giv- en the combinatorial characteristic of the multi-objective UAV mission planning in military logistics, a real number encoding fireworks algorithm （FWA） was proposed. Finally, a ease study was generated by extending E-n22-k4, i. e. a benchmark problem for CVRP to validate the effectiveness of the proposed algorithm. The results show that the optimal route scheme considering only one objective might be a poor route scheme for other objectives and that differ- ent optimization objectives should be weighed to gain the optimal overall route scheme during UAV mission planning. And the hybrid algorithm combineding linear weighted method and real number encoding FWA can solve the problem of muhi-objeetive UAV mission planning in military Logistics effectively.