Research On UAV Track Planning Based On Swarm Intelligence Algorithm

UAVs have gained wide application in many fields,including military and livelihood,because they can replace humans in specific situations to perform more complex tasks in dangerous environments.With the expansion of the use of UAVs,the problem of autonomous flight of UAVs has become the focus of research in recent years.Since the21 st century,the emerging swarm intelligence algorithms based on the bionic principle have gained wide attention for their better trajectory finding ability in solving the UAV path planning problem,among which the ant colony algorithm and particle swarm algorithm are the two most classical algorithms.As two of the most classical algorithms,the ant colony algorithm and the particle swarm algorithm have great potential research value and important research significance in the application field of UAV path planning due to the advantages of less parameters required for calculation and strong optimization function.In this thesis,the shortcomings of the two classical algorithms are improved and optimized respectively,which can quickly plan a reasonable and feasible flight path for UAVs.The following research work has been accomplished in this thesis:1)In the UAV track path planning problem,3D environment modeling,threat modeling,fitness function modeling and constraint modeling are the basis of path planning.Based on the different flight environments and the algorithms used,this thesis establishes the three-dimensional environment model of the UAV,the fitness function model and the model of the UAV’s own constraints.12)Aiming at the problems that the ant colony optimization algorithm is easy to fall into the local extreme value and the early convergence speed is slow,a three-dimensional path planning algorithm for UAV based on the improved ant colony optimization algorithm is proposed.The algorithm first adds new heuristic information to the heuristic function,and introduces an adaptive path guidance factor,so that the ants can determine the approximate direction of the feasible solution in the early stage of the algorithm,reducing the blindness of the ants in the next path selection,thereby reducing the search in the early stage of the algorithm.Second,the update rules of pheromone are improved,and the comprehensive performance index of the path is introduced to make it jump out of the local extreme value,thereby improving the smoothness and security of the path.3)Aiming at the problem that the particle swarm optimization algorithm is easy to fall into the local extreme value and the search effect is not good,a three-dimensional path planning algorithm for UAV based on improved PSO is proposed.The algorithm optimizes and improves the inertia weight with the help of the exponential form of inertia weight adjustment strategy,so that it can dynamically adjust the local search ability and global search ability of the particle,so that the algorithm jumps out of the rejection optimal value,thereby improving the search effect of the algorithm.4)Finally,combined with the advantages and disadvantages of ant colony algorithm and particle swarm optimization,an improved hybrid algorithm based on ant colony and particle swarm is proposed.The algorithm first uses the improved particle swarm optimization algorithm to pre-search the track path,and then the initial pheromone concentration of the ant colony optimization algorithm is reasonably allocated according to the length of the pre-search path,which is beneficial to improve the initial search of the ant colony optimization algorithm.It can plan the optimal track path of the UAV more quickly and efficiently in the three-dimensional environment.