Unmanned aerial vehicle trajectory planning based on enhanced sparrow search algorithm

Abstract

In order to solve the problems of the original sparrow search algorithm (SSA) in the unmanned aerial vehicle (UAV) trajectory planning, such as low optimization accuracy and slow convergence speed, an enhanced sparrow search algorithm (ESSA) was proposed. Firstly, Halton sequence was used to initialize the population to increase the diversity of the population and improve the subsequent search accuracy of the algorithm. Secondly, the quasi-reflection learning mechanism is introduced to improve the individual quality of the algorithm after each iteration, and improve the optimization accuracy and convergence speed of the algorithm. The improved algorithm is applied to the trajectory planning of the UAV, the results show that the flight cost of the UAV trajectory found by ESSA is lower and the convergence speed is faster.