Research On Multi-uav Mission Planning Method Based On Intelligent Algorithm

With the rapid development of automation,unmanned aerial vehicles（UAV）play very important roles in the field of military air combat.The UAV mission planning technology is one of the most important technologies in the system.Therefore,it is of great theoretical and practical significance to study the UAV mission planning.The research content of this paper mainly includes the following three aspects:The UAV path planning based on the fusion algorithm of genetic and improved ant colony（G-IACO）is researched.The optimal solution that obtained by genetic algorithm initializes the pheromone of ant colony to improve the convergence speed.In order to avoid the problem of local extremum,the state transition rule in ant colony algorithm is improved.The step size can be adjusted for evading sudden threats and the gradient descent method is used to smooth the track.The simulation results show that the algorithm proposed can not only safely avoid threats,but also converge faster.The multi-UAV and multi-target air combat mission planning problem is researched.Considering the relative distance between the UAVs and the targets,turning angle and load balance,the objective function is established.A multi-UAV task allocation method based on self-organizing neural network is given considering the constraints such as multi-UAV collaboration.Then,the fusion algorithm proposed in this paper is used for multi-UAV track planning.This method can effectively complete the task allocation and track planning,and resources are evenly distributed among UAVs,and the effectiveness and applicability of the method are verified.Dynamic track planning of multi-UAV rendezvous is researched.First,the method of multi-UAV rendezvous collaborative track planning under uncertain conditions is given,including online track replanning and collaborative track planning.Then,the multi-UAV rendezvous model was established,and the consensus algorithm was adopted to achieve multi-UAV rendezvous at the same moment.The simulations respectively verify the two situations of no sudden threats and sudden threats,which show that under the dynamic cooperative track planning method and decentralized controller,multiple UAVs can achieve better simultaneous rendezvous problems.