International Core Journal of Engineering 2020-26 | Page 151

each segment, the shortest path generated is optimized and
smoothed as shown in Figure 6(a), at which point
than 0.6, the algorithm converges about 120 times when
iterating. The two calculations based on the traditional ant
colony algorithm have not converged the two algorithms in
the generated path length there are also large differences, the
improved algorithm generated the path length of 18km and
17km respectively, while the traditional algorithm generated
path length is more than 20km.
L route  d ij
,The path can be fixed-wing drone, the minimum
turning radius of the line is the minimum turning radius of the
fixed-wing drone R 800m .The optimized path length is
17km and the safety is 0.76, as shown in Figure 6(b).
V. C ONCLUSIONS
Comparing the improved ant colony algorithm with the
traditional algorithm proposed in this paper, when setting the
path safety level to 1.0, the obstacle size is set to a square with
a side length of 550m, based on the traditional ant colony
algorithm to obtain the optimal path and convergence curve as
shown in Figure 7.
(1) Fixed-wing drones and rotors can be used to transport
mountain emergency supplies. Rotor-type drones offer
flexibility and powerful loads of the same size; Longer service
life must be based on a comprehensive analysis of aerospace
terrain and weather conditions.
When the path safety is not less than 0.6, the obstacle is set
to a square with a edge length of 350m, and the optimal path
and convergence curve are shown in Figure 8 .
(a) Shortest path
(2) The improved ant colony algorithm proposed in this
paper makes use of The Tyson polygon structure to construct
the initial solution, and combines Jordan's case with the safe
distance of the mountain barrier to improve the efficiency of
ant colony search. The analysis shows that the improved ant
colony algorithm is more conventional. The algorithm
approaches faster and the search path length is shorter.
(3) The algorithm assumes that the drone maintainsa
certain height during obstacle avoidance trips in mountainous
areas. Thresholds a and b can be adjusted for security levels to
reflect the relationship between UAVs at different altitudes
and threat points. In lower jobs, algorithms can be extended to
three-dimensional space. Plan drones by increasing
restrictions on drones and forming three-dimensional lines.
(b) Path optimization and smoothing
Fig6: Optimal path when safety value is not less than 0.6
R EFERENCES
[1]
[2]
[3]
Fig7: Optimal path and convergence curve based on traditional ant colony
algorithm
[4]
[5]
[6]
Fig8:Optimal path based on traditional ant colony algorithm when safety
value is not less than 0.6
[7]
Through the results of the operation and convergence, it
can be seen that under the same safety conditions, the path
obtained by using the improved ant colony algorithm is shorter,
the convergence efficiency is faster when the safety is set to
1.0, the improved algorithm converges approximately when
iterating to 100 times, and when the safety is set to not less
129
TISDALE J, KIM Z W, HEDRICK J K. Autonomous UAV path
planning and estimation(JI. IEEE Robotics & Automation Magazine,
2009, 16(2): 35-42.
JENNINGS A L, ORDONEZ R, CECCARELLI N. Dynamic
programming applied to UAV way point path planning in wind[C].
IEEE International Conference on Computer-aided Control Systems,
2008.
ZHANG Y, WAN X Y, ZHENG X D, et al. Cellular genetic algorithm
for multi objective optimization based on orthogonal design [J]. Acta
Electronica Sinica, 2016, 23(10:4742-4746.
GAUTAM S A. VERMA N Path planning for unmanned aerial vehicle
based on genetic algorithm and artificial neural network in 2D[J].
International Journal for Scientific Research Development, 2014, 2(2):
232-0613.
ROBERGE V, TARBOUCHI M, LABONTE G. Comparison of
parallel genetic algorithm and particle swarm optimization for real-
time UAV path planning[J]. IEEE Transactions on Industrial
Informatics,2013,9(1):132-141.
Li Xigang, Cai Yuanli based on improved ant colony algorithm of the
drone path planning . . . flight mechanics,2017,35(1):52-56.XG, CAIY
L. UAV path planning based on improved ant colony algorithm [J].
Flight Dynamics, 2017, 35(1): 52-56]
Liu Shaohua, Luo Xiaolong, He Yubin, et al.Research Changjiang
University Journal based on The Tyson Polygon Generation Algorithm
based on Delauany Triangle Network(2007,4(1):100-103.IUSH,
LUOXI,HE Y B, et al. Research on tyson polygon generation algorithm
based on delauany triangulation[J. Journal of Yangtze University(Nat
Sci Edit), 2007, 4(1): 100-103.]