基于改进人工鱼群算法无人机航迹规划研究

发布时间：2018-05-24 02:02

本文选题：无人机航迹规划 + 人工鱼群算法　；参考：《南昌航空大学》2015年硕士论文

【摘要】：当今世界,无人机得到了越来越广泛的应用。在军事方面,无人机的使用能够降低战斗中的伤亡,提升人力的效率和飞行器的性能。在民用方面,无人机的使用能够克服地理条件的限制,降低工作的成本以完成货物的运输、空中拍摄等任务。我国是世界上军事和经济的大国,所以无论是军用还是民用领域都对无人机有较大的需求。无人机任务规划中的重要部分就是无人机的航迹规划,应用于无人机航迹规划的算法有很多种,然而每种算法都有自己的优点和缺点,优秀的航迹规划算法能够帮助无人机快速地自动找到符合要求的最短航迹,因此研究并提出一种性能优秀的航迹规划算法具有广阔的应用价值和实际意义。本文主要对无人机航迹规划的算法进行了研究,其中针对使用基于网格划分策略的改进人工鱼群算法计算无人机路径规划问题中寻优精度与算法计算量的矛盾,提出一种改进人工鱼群算法,并将该算法应用于无人机航迹规划问题中,对其进行了软件仿真。主要从以下方面对课题进行了研究。首先明确了航迹规划的工作目的和描述航迹规划问题的建模方法,回顾了前人已经提出的各种应用于航迹规划问题的算法。其次介绍了基本人工鱼群算法中的主要概念,对人工鱼的行为进行了描述,并阐述了算法的执行步骤和寻优原理。分析了算法中各个主要参数对人工鱼群算法的性能的影响,为算法的改进提供了理论依据。随后总结了当前主要的人工鱼群算法改进策略,详细介绍了基于网格划分策略的改进人工鱼群算法,根据该算法的特点,提出一种改进人工鱼群算法,该算法引入自适应步长和执行概率自适应分段网格遍历策略。算法前期用较大步长全局搜索较优路径,后期用较小步长及网格分段遍历策略在较优解附近进行局部遍历得到更精确最优解。最后将提出的改进鱼群算法应用于无人机航迹规划问题中,在MATLAB仿真环境下建立了航迹规划任务的模型,分别使用包括所提改进人工鱼群算法在内的三种算法进行寻优,通过软件仿真结果数据的对比分析,表明所提改进人工鱼群算法比原始鱼群算法和自适应步长人工鱼群算法结果更精确、稳定,较基于简单网格划分策略的人工鱼群算法计算量更小。
[Abstract]:In today's world, unmanned aerial vehicles (UAVs) have been used more and more widely. On the military side, the use of UAVs can reduce combat casualties, improve human efficiency and aircraft performance. In civilian use, UAVs can overcome geographical constraints and reduce the cost of work to complete cargo transport, aerial photography and other tasks. China is a large military and economic country in the world, so there is a great demand for UAVs in both military and civilian fields. The important part of UAV mission planning is UAV track planning. There are many algorithms used in UAV track planning. However, each algorithm has its own advantages and disadvantages. The excellent track planning algorithm can help UAV find the shortest track quickly and automatically, so it has broad application value and practical significance to study and propose an excellent track planning algorithm. In this paper, the algorithms of UAV path planning are studied, and the contradiction between the optimization accuracy and the computational complexity of the UAV path planning problem based on the improved artificial fish swarm algorithm based on mesh division strategy is discussed. An improved artificial fish swarm algorithm is proposed and applied to UAV trajectory planning problem. Mainly from the following aspects of the study of the subject. Firstly, the purpose of track planning and the modeling method to describe the problem of track planning are defined, and the algorithms used in track planning are reviewed. Secondly, this paper introduces the main concepts of the basic artificial fish swarm algorithm, describes the behavior of the artificial fish, and expounds the execution steps and optimization principle of the algorithm. The influence of main parameters on the performance of artificial fish swarm algorithm is analyzed, which provides a theoretical basis for the improvement of the algorithm. Then it summarizes the main improvement strategies of artificial fish swarm algorithm, and introduces the improved artificial fish swarm algorithm based on mesh generation strategy in detail. According to the characteristics of this algorithm, an improved artificial fish swarm algorithm is proposed. The algorithm introduces adaptive step size and execution probability adaptive piecewise traversal strategy. The algorithm uses a large step size to search for the optimal path globally, and a smaller step size and a mesh segment traversal strategy to obtain a more accurate optimal solution by local traversal near the optimal solution. Finally, the proposed improved fish swarm algorithm is applied to UAV trajectory planning problem. In the MATLAB simulation environment, the model of track planning task is established, and three algorithms, including the proposed improved artificial fish swarm algorithm, are used to optimize the flight path planning. Compared with the original fish swarm algorithm and the adaptive step size artificial fish swarm algorithm, the improved artificial fish swarm algorithm is more accurate and stable than the original fish swarm algorithm and the adaptive step size artificial fish swarm algorithm. Compared with the artificial fish swarm algorithm based on simple mesh generation strategy, the computational complexity of artificial fish swarm algorithm is much smaller.
【学位授予单位】：南昌航空大学
【学位级别】：硕士
【学位授予年份】：2015
【分类号】：V279

【参考文献】