Multi-UAV task assignment based on improved Wolf Pack Algorithm
Haowen Chen, Jinyu Xu, Chao Wu · 2020
Aiming at the task allocation problem of heterogeneous multi-UAVs with different loads, an improved wolf pack algorithm is proposed. For the heterogeneous UAVs with multiple payloads, this paper divides the complex combat tasks into three subtasks: reconnaissance, strike and evaluation, and builds a task allocation model based on the specific load performance. The Gaussian walking in Stochastic Fractal Search (SFS) after chaos optimization is introduced into the wolf pack algorithm (WPA) through an adaptive mechanism, and a chaotic wolf pack algorithm based on enhanced Stochastic Fractal Search (MSFS-CWPA) is proposed. After the classic benchmark function including single/ multiple peak and the example verification of heterogeneous multi-UAV task allocation, the results show that MSFS-CWPA has higher convergence accuracy and robustness than the standard WPA and other improved WPA.