Hybrid Algorithm Based on Comprehensive Learning Particle Swarm Optimisation with Local Search and Firefly Algorithm for UAV Path Planning

Unmanned Aerial Vehicles (UAVs) have been widely used in military and civilian fields because of their low operating cost, no risk of human casualties, and convenient use. Path planning is the key technology for UAV flights to complete tasks efficiently, stably, safely, and autonomously. This paper proposes a new hybrid algorithm (HFCLPSOLS) based on Comprehensive Learning Particle Swarm Optimisation with Local Search (CLPSOLS) and Firefly Algorithm (FA) for UAV path planning. The new algorithm establishes a temporary position set and incorporates the position attraction rule of FA into CLPSOLS to improve accuracy and convergence speed. In addition, we also introduce the concept of stability cost for UAVs, aiming to improve the flying quality. The performance of the proposed HFCLPSOLS is compared with other variants of PSO in four different environments. The experimental results show that HFCLPSOLS combines the strength of CLPSOLS and FA, improving the searching accuracy and speed in various situations.