Obstacle Avoidance and Path Planning for Quadrotor based on Differential Evolution - Artificial Bee Colony Algorithm

Abstract

When the traditional artificial bee colony algorithm approaches the global optimal solution, the algorithm has the disadvantages of lower diversity, slower search speed, premature convergence, and trapping into local extremes. Based on the principle of differential evolution algorithm and combined with differential evolution algorithm, a differential evolution - artificial bee colony algorithm is proposed. Firstly, the global search ability of artificial bee colony algorithm is used to conduct global search. When approaching the global optimal solution, the diversity, crossover, and selection process of differential evolution algorithm is used to increase the diversity of solutions and avoid falling into local extremes. Finally, the differential evolution - artificial bee colony algorithm, artificial bee colony algorithm and differential evolution algorithm are compared in the urban environment model. The results show that the differential evolution - artificial bee colony algorithm is obviously superior to the other two algorithms in the quality and stability of path planning and obstacle avoidance for quadrotor.