Research of UAV track planning and dynamic obstacle avoidance algorithm
Xia Chen, Linhao Hou · 2020
Track planning and dynamic obstacle avoidance algorithm of UAV are proposed in this paper. In global path planning, an improved genetic algorithm is put forward. There are four kinds of operators: selection operator, crossover operator, mutation operator and deletion operator, in which the deletion operator is added. Meanwhile, the roulette method is improved to the directional selection method in the new algorithm. The total cost function is established according to length, smoothness and security. The optimal path is obtained and smoothed. In local path planning, candidate paths are generated by a cubic spline method. The optimal candidate path is chosen by the total cost function. Simulation results show that the new algorithm of this paper is superior to genetic algorithm and ant colony algorithm and improved ant colony algorithm in path length, running time and iteration times. Dynamic obstacle avoidance algorithm can avoid sudden threats.