A New Method of the Shortest Path Planning for Unmanned Aerial
Vehicles
Darong Huang
1,2
, Dong Zhao
1
, Ling Zhao
1
1. School of Information Science and Engineering, Chongqing Jiaotong University, Chongqing 400074
E-mail: zdfx888@163.com
2. Department of real estate equipment engineering, Chongqing real estate college, Chongqing 401331
Abstract: In this paper, the optimal route and deployment scheme are designed to ensure the shortest retention time for
unmanned aerial vehicles (UAV) in risk area. Firstly, according to the known data and radar scanning range, the regional
distribution map of target grope and base are obtained, respectively. Secondly, based on the different scanning bandwidth of
loads, target points are classified by using clustering analysis. This makes the target points fall on the scanning bandwidth of
UAV as far as possible, accordingly reducing the UAV’s scanning times. This problem can be regarded as a travelling salesman
problem in radar scanning range. Finally, the deployment result and locally optimal route are obtained by 0-1 programming in
LINGO. Furthermore, particle swarm optimization is used to improve the local optimal path and the global optimal route can
then be generated.
Key Words: UAV, GA, PSO, The Shortest Path.
1. Introduction
With the development of UAV technology, UAV
technology has shown its peculiar advantages in various
fields, such as investigation, monitoring and local fire
suppressing, etc. Since path planning for UAV is the key
technology support for autonomous flight, many
researchers has investigated UAV path planning and
obtained some meaningful results.1
As we known, the path planning algorithms is the core
of the path planning. The research methods for UAV path
planning mainly focus on optimization algorithm. For
example, in [1], the authors applied an improved adaptive
genetic algorithm (GA) on autonomous agent dynamic path
*This work is supported by National Nature Science Foundation under Grant
61573076, the Scientific Research Foundation for the Returned Overseas
Chinese Scholars under Grant 2015-49 and Program for Excellent Talents of
Chongqing Higher School under Grant 2014-18,the research project for the
education of graduate students of Chongqing Under Grant yjg152011,
Chongqing Association of Higher Education 2015-2016 Research Project under
Grant CQCJ15010C, Higher education reform project of Chongqing Municipal
Education Commission under Grant 163069, and the key research topics of the
13th Five-years plan of Chongqing education science under Grant
2016-GX-040.
.
planning. In [2], the authors used the GA and the particle
swarm optimization algorithm (PSO) to cope with the
complexity of the problem and compute feasible and
quasi-optimal trajectories for fixed wing UAVs in a
complex 3D environment, while considering the dynamic
properties of the vehicle. In [5], an improved ant colony
optimization algorithm (IACO) was presented for solving
mobile agent routing problem. Compared with GA,
simulated annealing (SA), and basic ant colony algorithm,
the authors demonstrated the IACO has much higher
convergence speed. GA has been widely applied on many
fields. However, there exists “premature” phenomenon
during the process of searching path by GA. Besides, the
path planning time of GA is long. In [3], the authors
inducted time-bias into the cost function of A* algorithm.
Nevertheless, the A* algorithm has slow search speed and
occupies large memory space. In [4], the authors used path
planning method which combines the threat intensity
assessment algorithm for Bayesian network model and ant
colony algorithm and improved ant colony algorithm
according to characteristic of UAV path planning
.
In this paper, based on the actual situation, we acquire
the most appropriate location of UAV. By improving
particle swarm optimization, the optimal route of UAV is
2017 IEEE 6th Data Driven Control and Learning Systems Conference
Ma
26-27, 2017, Chon
qin
, China
978-1-5090-5461-9/17/$31.00 ©2017 IEEE
DDCLS'17
599