Path planning for Unmanned Air Vehicles using an improved artificial bee colony algorithm

Unmanned Aerial Vehicles (UAV) path planning can be considered as a complicated function optimization problem with constraint condition. Population based algorithm, especially the artificial bee colony (ABC) algorithm, is known as an effective tool to solve this problem. ABC algorithm is a relatively predominant optimization technique with an advantage of having fewer control parameters over other population algorithms. Considering the ergodicity and the stochastic of the chaotic map, we propose a modified strategy of initialization for the standard ABC, which utilizing the logistic map and opposition based learning to generate the initial population as well as the scout bee position. In addition, the employed bee search equation is modified by adding weight coefficients for the purpose of increasing the convergence speed. Then we test the modified artificial bee colony algorithm in four function optimization problems and path planning problems. The results demonstrate a superior performance of our algorithm in solving UAV path planning in two dimensions compare with the standard ABC algorithm.