Hybrid chaos game and grey wolf optimization algorithms for UAV path planning

Abstract

The grey wolf optimizer is a renowned algorithm within the realm of swarm intelligence. However, it is hindered by a few drawbacks such as slow convergence rate, limited population diversity, and a propensity to fall into local optima in certain scenarios. In this study, we introduce a groundbreaking hybrid algorithm called Hybrid chaos game and grey wolf optimization, which ingeniously fuses the grey wolf optimizer with the Chaos Game Optimizer. This novel amalgamation significantly bolsters both the exploratory and exploitative facets of the grey wolf optimizer, enriching its diversity and enhancing its convergence precision, while preserving robust exploratory capabilities. In order to fully demonstrate the superior performance of the algorithm, the paper is divided into two parts. In the first part, the proposed algorithm is analyzed through rigorous experiments on different classes of test functions of the Congress on Evolutionary Computation benchmark 2014 using Friedman statistical test, among them, comparing the original grey wolf optimizer algorithm, it achieved better results among 28 functions. In the second part, the proposed algorithm is used to solve unmanned aerial vehicle path planning problems. These real-world problems are used as test problems to evaluate the solving ability of the proposed algorithm.The results show that the proposed algorithm still has a good performance in 6 scenarios of different complexity in the setup. The main goal of hybrid Chaotic Game Optimization and Grey Wolf Optimization is to provide an alternative perspective for dealing with complex optimization problems.