A hybrid algorithm based on grey wolf optimizer and differential evolution for UAV path planning. (1st April 2023)

• Record Type: Journal Article
• Authors: Yu, Xiaobing; Jiang, Nijun; Wang, Xuming; Li, Mingyuan
• Is Part Of: Expert systems with applications. Volume 215(2023)
• Publication Date: 2023-04-01
• Subjects: UAV path planning -- GWO -- DE -- Hybrid -- Exploration -- Exploitation; Expert systems (Computer science) -- Periodicals; Systèmes experts (Informatique) -- Périodiques; Electronic journals; 006.33
• DOI: 10.1016/j.eswa.2022.119327
• Languages: English
• ISSNs: 0957-4174

Abstract

Highlights: The position-updated function of GWO is extended to boost the exploitation of GWO. A rank-based mutation operator is introduced into DE to enhance the exploration capacity. A hybrid algorithm, HGWODE, is developed. The HGWODE is used to solve the UAV path planning. Abstract: Autonomous navigation is significant to UAVs, especially in disaster scenarios. A Hybrid GWO and Differential Evolution (HGWODE) algorithm is developed to solve UAV path planning. In HGWODE, GWO and DE algorithms cooperate well to balance exploitation and exploration. The position-updated equation of GWO is improved, which makes alpha, beta, and delta wolves search around the alpha wolf, and omega wolves search around the top three wolves to boost the exploitation. A rank-based mutation strategy is implemented in DE algorithm to promote exploitation while maintaining the exploration capacity. We test HGWODE on CEC 2014 and UAV path planning. The proposed HGWODE is superior to GWO and several GWO variants when solving test functions and UAV path planning models. UAV path from HGWODE is smoother and shorter than its rivals.