<abstract xmlns="http://www.w3.org/1999/xhtml"><p>Path planning plays an extremely important role in the design of LAVs (Loitering Air Vehicles) to accomplish the air combat task fleetly and reliably. The planned path should ensure that LAVs reach the destination along the optimal path with minimum probability of being found and minimal consumed fuel. Traditional methods tend to find local best solutions due to the large search space. So it takes a lot of time and consumes a lot of computing resources. In this paper, a new young intelligent algorithm-fireworks algorithm is introduced, and EFWA (enhanced fireworks algorithm)-its enhanced version is used to find the optimal solution. At the same time, the battlefield prior knowledge is fully utilized to predict the existence space of the potential optimal trajectory. Greatly the search space reduced, plan planning efficiency is significantly improved. Path planning method effectiveness in this paper has further been improved compared with FACPSO. Moreover, the EFWA on prior knowledge performs well on the application of dynamic path planning when the threats cruise randomly than FAC-PSO.</p></abstract>

Path planning plays an extremely important role in the design of LAVs (Loitering Air Vehicles) to accomplish the air combat task fleetly and reliably. The planned path should ensure that LAVs reach the destination along the optimal path with minimum probability of being found and minimal consumed fuel. Traditional methods tend to find local best solutions due to the large search space. So it takes a lot of time and consumes a lot of computing resources. In this paper, a new young intelligent algorithm-fireworks algorithm is introduced, and EFWA (enhanced fireworks algorithm)-its enhanced version is used to find the optimal solution. At the same time, the battlefield prior knowledge is fully utilized to predict the existence space of the potential optimal trajectory. Greatly the search space reduced, plan planning efficiency is significantly improved. Path planning method effectiveness in this paper has further been improved compared with FACPSO. Moreover, the EFWA on prior knowledge performs well on the application of dynamic path planning when the threats cruise randomly than FAC-PSO.

LAV Path Planning by Enhanced Fireworks Algorithm on Prior Knowledge

Applied Mathematics and Nonlinear Sciences

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

{"article-title":"LAV Path Planning by Enhanced Fireworks Algorithm on Prior Knowledge"}

Path planning plays an extremely important role in the design of LAVs (Loitering Air Vehicles) to accomplish the air combat task fleetly and reliably. The...

n	FAC-PSO	EFWA on Prior Knowledge
10	10.2	0.8
15	11.3	1.2
20	13.7	1.5

Index	Position	Radius
1	(10,30)	14
2	(10,50)	10
3	(20,80)	20
4	(40,50)	12
5	(45,50)	15
6	(50,70)	12
7	(75,70)	14
8	(80,40)	12

Step	Time	Step	Time
1	3.0	11	1.5
2	2.7	12	1.4
3	2.9	13	1.3
4	2.7	14	1.6
5	2.6	15	1.4
6	2.3	16	1.4
7	2.1	17	1.0
8	1.9	18	0.8
9	1.8	19	0.6
10	1.7	20	0.5

LAV Path Planning by Enhanced Fireworks Algorithm on Prior Knowledge

Published Online: Jan 01, 2016

Page range: 65 - 78

Received: Jun 07, 2015

Accepted: Nov 09, 2015

DOI: https://doi.org/10.21042/AMNS.2016.1.00006

© 2016 Li Bing, You Ning, Du YeHong, published by Sciendo

This work is licensed under the Creative Commons Attribution-NonCommercial-NoDerivatives 3.0 License.

Fig. 1

Fig. 2

Fig. 3

Fig. 4

Fig. 5

Fig. 6

Fig. 7

Fig. 8

Fig. 9

Fig. 10

Fig. 12

Average computation time(s)

Information of 2D threatening objects

time consuming of each step(s)

Step	Time	Step	Time
1	3.0	11	1.5
2	2.7	12	1.4
3	2.9	13	1.3
4	2.7	14	1.6
5	2.6	15	1.4
6	2.3	16	1.4
7	2.1	17	1.0
8	1.9	18	0.8
9	1.8	19	0.6
10	1.7	20	0.5

Step	Time	Step	Time
1	3.0	11	1.5
2	2.7	12	1.4
3	2.9	13	1.3
4	2.7	14	1.6
5	2.6	15	1.4
6	2.3	16	1.4
7	2.1	17	1.0
8	1.9	18	0.8
9	1.8	19	0.6
10	1.7	20	0.5

Step	Time	Step	Time
1	3.0	11	1.5
2	2.7	12	1.4
3	2.9	13	1.3
4	2.7	14	1.6
5	2.6	15	1.4
6	2.3	16	1.4
7	2.1	17	1.0
8	1.9	18	0.8
9	1.8	19	0.6
10	1.7	20	0.5