A decomposition-based constrained multi-objective evolutionary algorithm with a local infeasibility utilization mechanism for UAV path planning

Unmanned Aerial Vehicle (UAV) path planning problems can be treated as constrained multi-objective optimization problems, which often have complicated constraints in real-world scenarios. Algorithms for solving them require a powerful constraint-handling technique to utilize infeasible information....

Full description

Saved in:

Bibliographic Details
Published in:	Applied soft computing Vol. 118; p. 108495
Main Authors:	Peng, Chaoda, Qiu, Shaojian
Format:	Journal Article
Language:	English
Published:	Elsevier B.V 01.03.2022
Subjects:	Constraint-handling technique Evolutionary algorithm Multi-objective optimization UAV path planning UAV path planning Multi-objective optimization Constraint-handling technique Evolutionary algorithm
ISSN:	1568-4946, 1872-9681
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Description
Summary:	Unmanned Aerial Vehicle (UAV) path planning problems can be treated as constrained multi-objective optimization problems, which often have complicated constraints in real-world scenarios. Algorithms for solving them require a powerful constraint-handling technique to utilize infeasible information. However, this has seldom been explored in this field. To remedy this issue, this paper proposes a decomposition-based constrained multi-objective evolutionary algorithm (M2M-DW) with a local infeasibility utilization mechanism for UAV path planning. Therein, M2M-DW is adopted as a solution optimizer since it can utilize infeasible individuals. However, this may result in poor performance due to the arbitrary use of infeasible individuals. To solve this issue, a local infeasibility utilization mechanism is proposed to effectively utilize the infeasible information. Besides, an improved mutation scheme is designed to further explore the promising regions. Experimental studies are conducted on three sets of UAV path planning problems with different difficulties, and the results highlight the effectiveness of the proposed algorithm in terms of reliability and stability in finding a set of feasible optimal solutions. •Three sets of UAV path planning problems with different difficulties are presented.•A constraint-handling technique with a local infeasibility utilization is proposed.•An improved mutation scheme enhances the search ability of the proposed method.•Systematic experiments are designed to verify the performance of the proposed method.
ISSN:	1568-4946 1872-9681
DOI:	10.1016/j.asoc.2022.108495