UAV Online Path Planning Based on Improved Genetic Algorithm
Xiaohai Wang
1
,XiuyunMeng
2
1. School of Aerospace Engineering, Beijing Institute of Technology, Beijing 100081
E-mail: wxhumi@foxmail.com
2. School of Aerospace Engineering, Beijing Institute of Technology, Beijing 100081
E-mail: mengxy@bit.edu.cn
Abstract: When the traditional Genetic Algorithm(GA) is used for unmanned aerial vehicle(UAV) path planning, the
shortcomings of local search ability are reflected when the planning time is more urgent. To address this shortcoming, this paper
proposes an improved genetic algorithm that limits the new gene's generating region. The generating region of the evolution
operator is dynamically adjusted. The algorithm is applied to UAV online path planning for tracking moving target. The
simulation results show that the method enhances the local search ability of the algorithm and improves the searching efficiency.
UAV online path planning can be completed well with the improved genetic algorithm.
Key Words: Improved Genetic Algorithm, Local search ability, Searching Efficiency, Online Path Planning, Moving Target
1 Introduction
With the development of modern unmanned aerial
vehicle(UAV) technology, UAVs are increasingly being
used for tasks such as shooting, material transportation and
firepower. At the same time, the environment in which the
UAVs perform tasks has become more and more
complicated. It is time-consuming and laborious to human
planning. Therefore, various path planning algorithms have
emerged. Commonly used path planning methods include A*
algorithm, neural network method, genetic algorithm(GA)
and so on. GA has attracted significant attention because of
ease of implementation for both continuous and discrete
problems
[1]
. On the one hand, GA does not need to spend a
lot of time to construct the structural space; on the other hand,
due to the population characteristics of the genetic algorithm,
it has a good global search ability, which can effectively
avoid the planned path falling into local optimum
[2]
.
However, the traditional genetic algorithm has weaker
search ability for local areas and slower search speed. For
this defect, the literature [3] proposed a UAV path planning
method based on genetic algorithm-pattern search method.
Literature [4] proposed a planning method based on multi
niche genetic algorithm. Literature [5] combined GA with
MAKLINK graph for path planning, which improved the
searching speed of the GA. Literature [6] presented an
improving method based on guide points, combined GA with
SAS to improve the local search ability of the algorithm. The
improved genetic algorithm with restricted mutation
generating region(R-IGA) proposed in this paper set a
reasonable dynamic limit on the generating range of the
evolutionary operator, which makes it search within the
limited range, enhances the local search ability of the genetic
algorithm, and reduces the search time. It makes the genetic
algorithm more feasible for UAV online path planning.
The structure of this paper is as follows. First, model the
UAV path planning problem, then give the flow of the
genetic algorithm, then give the improving strategy of the
genetic algorithm, design the comparison experiment to
analysis the performance of the improved genetic algorithm,
and finally the improved genetic algorithm is used for online
path planning, and simulation experiments are carried out to
observe its effects.
2 Path Planning Problem Modeling
The path planning is to find the optimal path for the UAV
to complete the scheduled task under the condition of
ensuring the safe completion of the UAV, taking into
account the constraints of fuel consumption, mission
requirements, mission area terrain and no-fly zone. The
modeling of the path planning problem mainly includes the
representation of the planning space, the representation of
the path and the evaluation of the path.
2.1 Planning space and path representation
Before planning the path, the planning space should first
be expressed in a certain way. Establish a spatial coordinate
system
O xyz
with a certain point (generally the starting
position of the UAV) in space as the origin. The
x
-axis is
pointing to the east, the
y
-axis is pointing to the north. The
z
-axis is vertical to the
O xy
plane, pointing upwards. Then
the planning space can be expressed as
^`
max max max
(, ,)| 0 ,0 ,0xyz x x y y z zdd dd dd
. Discretize the
three-dimensional space region when representing the terrain
and represent it as a two-dimension matrix. The rows and
columns of the matrix represent the size of the planned area
in the horizontal direction, and the elements in the matrix
represent the altitude of the terrain at the corresponding
coordinates. The path is represented by a sequence of spatial
position points as {S,P
1
,...,P
n-1
,G}. Where S represents the
starting point, P
1
, ..., P
n-1
represents the intermediate path
node, and G represents the target point.
2.2 Path evaluation
The constraints such as fuel consumption, no-fly zone,
mission area terrain and UAV dynamics are expressed as
Proceedings of the 38th Chinese Control Conference
Jul
y
27-30, 2019, Guan
g
zhou, China
4101
Authorized licensed use limited to: NANJING UNIVERSITY OF AERONAUTICS AND ASTRONAUTICS. Downloaded on January 28,2021 at 14:47:43 UTC from IEEE Xplore. Restrictions apply.
下载后可阅读完整内容，剩余5页未读，立即下载
mchahaha
- 粉丝: 0
- 资源: 4
我的内容管理
展开
最新资源
- Hadoop生态系统与MapReduce详解
- MDS系列三相整流桥模块技术规格与特性
- MFC编程：指针与句柄获取全面解析
- LM06：多模4G高速数据模块，支持GSM至TD-LTE
- 使用Gradle与Nexus构建私有仓库
- JAVA编程规范指南：命名规则与文件样式
- EMC VNX5500 存储系统日常维护指南
- 大数据驱动的互联网用户体验深度管理策略
- 改进型Booth算法：32位浮点阵列乘法器的高速设计与算法比较
- H3CNE网络认证重点知识整理
- Linux环境下MongoDB的详细安装教程
- 压缩文法的等价变换与多余规则删除
- BRMS入门指南：JBOSS安装与基础操作详解
- Win7环境下Android开发环境配置全攻略
- SHT10 C语言程序与LCD1602显示实例及精度校准
- 反垃圾邮件技术：现状与前景
资源上传下载、课程学习等过程中有任何疑问或建议，欢迎提出宝贵意见哦~我们会及时处理！
点击此处反馈
