Research On Path Planning Algorithm Of Unmanned Aerial Vehicle In Complex Environment

With the development of science,technology and economy,UAVs have become an indispensable and important weapon in the future wars.UAV cluster technology is a key point to improve the efficiency.It has great research value.Cluster UAVs mission planning technology is one of the core technology to ensure the success rate of the UAV’s mission,the safety factor,the consumption of resources and efficiency.Task allocation and path planning are the two of the most important parts of the technology.The two both are combinatorial optimization problems.It is very important to minimize task execution time and resource and to maximize revenue.Due to insufficient autonomy and intelligence,complex task environment,unbalanced load and difficult to distribute and to build the collaborative system modeling,etc.,the task planning system coordination and cooperation efficiency is reduced,and the task cannot be completed successfully or the maximum benefit cannot be guaranteed.It is difficult to meet the needs of intelligent autonomous coordination in terms of coordination and cooperation when the UAVs are in a war environment.In response to the above problems,this paper proposes a UAVs’ s task planning method based on swarm intelligence algorithm,which aims to improve the autonomy and intelligence,improve the efficiency of collaboration and the task success rate.The UAV cluster can maximize the benefits while minimizing resource consumption.Firstly,this paper divides the task planning technology into upper-level task allocation and lower-level trajectory planning.Research on the wolf pack algorithm based on the division of labor mechanism,treat all drones as an intelligent agent,simulate the predation behavior of the wolf pack,negotiate with each other,and cooperate in combat.Aiming at the shortcomings of slower convergence speed and weaker local search ability in the later stage of wolf pack algorithm evolution,an improved wolf pack algorithm is proposed to improve the efficiency and accuracy of the algorithm’s solution.Secondly,this paper conducts in-depth research on the problem of UAV cluster trajectory planning,simulates the social behavior of ant colony foraging,and finds the optimal trajectory corresponding to the UAVs cluster.Aiming at the shortcomings of the ant colony algorithm that the sub-optimal solution impact the optimization and the initial pheromone distribution is not uniform,the convergence speed is slow.An improved ant colony algorithm is proposed to improve the convergence speed and stability of the algorithm.Finally,on this basis,this paper conducts experimental verification on the two improved algorithms proposed.Through the UAV static target allocation and dynamic collaborative task allocation experiments,it proves the effectiveness and feasibility of the improved wolf pack algorithm for solving such problems.Through a comparative experiment with the traditional wolf pack algorithm,the superiority of the algorithm is proved.Through the simulation experiment of the three-dimensional trajectory planning of the UAV cluster,the effectiveness and feasibility of the improved ant colony algorithm in solving the trajectory planning problem are proved Through the VRPTW problem,comparative experiments with traditional ant colony and particle swarm algorithm are carried out to verify the superiority of the improved ant colony algorithm.The experimental results show that the improved wolf colony algorithm improves the global search ability and computational efficiency;the improved ant colony algorithm can quickly obtain the global optimal solution,and the stability of the algorithm is also improved.