An Improved Fast Convergent Artificial Bee Colony Algorithm for Unmanned Aerial Vehicle Path Planning in Battlefield Environment
Chengfang Wu, Xiaoyan Huang, Yuanlin Luo, Supeng Leng
Abstract
Unmanned aerial vehicle (UAV) path planning aims to seek an optimal path from the starting point to the terminal point with the threats and constraints in the battlefield environment well considered. In this work, an improved fast convergent artificial bee colony algorithm (FC-ABC) is proposed for this optimization problem. In the proposed FC-ABC algorithm, the physical constraints information of UAV is fully utilized when exploring the solution space. In the process of population initialization, an innovative method is introduced to ensure the diversity of the population and improve the search efficiency. In the neighborhood exploration phase, a heuristic adaptive neighborhood search method combining physical constraints and optimal nectar source information is applied to accelerate the algorithm convergence and improve the accuracy of the optimal solution. During the selection of employed bee, the ε-Boltzmann selection strategy is adopted to enhance the global search capability and avoid falling into local optimization. Simulation results demonstrate that the FCABC algorithm shows stronger stability, faster convergence and higher convergence accuracy than the conventional ABC algorithm and two other modified ABC algorithms.