Path Planning of UAV Based on Improved White Shark Optimization Algorithm

To overcome the problems of standard white shark optimization algorithm (WSO) in UAVs path planning, like expensive cost of path length and turning, this paper proposes an upgraded WSO, called the EAGWSO. Firstly, aiming at the uneven population distribution in WSO, the elite reverse learning strategy is utilized to establish the population of white sharks, which boosts the solution quality. Secondly, an adaptive control factor is used to further adjust random white sharks' location, so that the algorithm approaches the worldwide ideal solution gradually. Then, the Gaussian evolution mechanism is integrated to disrupt the greatest white sharks position of the partial optimum. Finally, the proposed EAGWSO is employed to address the UAVs path planning issues. In contrast to the WSO, the simulation results demonstrate that the proposed EAGWSO has faster convergence speed, shorter path length and lower turning cost, which is excellent for handling path planning problem of UAVs.