Research on Hybrid Discrete Particle Swarm Algorithm to Solve UAV Task Assignment Problem
Shaokun Yan · 2021 7th International Conference on Computer and Communications (ICCC) · 2021
Aiming at the target allocation problem of multiple UAVs executing multiple combat tasks at the same time, the traditional particle swarm algorithm has problems such as local optimal solution and unbalanced task load. In order to solve this problem, this paper proposes an unmanned aerial vehicle task allocation model based on hybrid discrete particle swarm algorithm. Compared with the traditional discrete particle swarm, the improvement of the algorithm is mainly reflected in the following two aspects: the introduction of the simulated annealing algorithm search mechanism to enhance the local search capability of the algorithm; the use of a two-dimensional vector coding scheme based on task sequence and UAV coding, the introduction of Transformation, reconstruction and other operational procedures, enhance the algorithm’s global search capabilities. The simulation results show that the algorithm proposed in this paper can effectively avoid local optimal solutions and improve the balance of task allocation, which proves the feasibility and effectiveness of the algorithm.