AUTHOR=Cheng Xuezhen , Li Jiming , Zheng Caiyun , Zhang Jianhui , Zhao Meng 

TITLE=An Improved PSO-GWO Algorithm With Chaos and Adaptive Inertial Weight for Robot Path Planning

JOURNAL=Frontiers in Neurorobotics

VOLUME=Volume 15 - 2021

YEAR=2021

URL=https://www.frontiersin.org/journals/neurorobotics/articles/10.3389/fnbot.2021.770361

DOI=10.3389/fnbot.2021.770361

ISSN=1662-5218

ABSTRACT=To enable a robot to search for the optimal path in a complex environment, an improved gray wolf optimization particle swarm optimization algorithm (IPSO-GWO) is proposed. First, gray wolf optimization is performed for the particle swarm algorithm, and then gray wolf sorting is performed for the particles with the best fitness value during each iteration of the algorithm to increase the search performance of the particles. Additionally, a chaotic sequence is used to initialize the particles. The uniformity of the distribution in the search space is improved, and the premature particles in the algorithm iteration process are processed with the chaotic sequence, which improves the optimization ability and diversity of the particles. Second, to increase the iterative speed of the particles, a combined particle adaptation is proposed. Finally, the IPSO-GWO algorithm is simulated, which the simulation results show that the IPSO-GWO algorithm can quickly avoid local optima during path planning, accelerate convergence, and provide obvious advantages in path planning.