Research On The Terrain Matching Navigation Method Of UAV Based On Swarm Intelligence

With the rapid development of science and technology,UAVs have been used in many fields such as aerial photography,agriculture,and disaster relief.The terrain matching navigation technology plays a key role in UAV system.Therefore,as the core technology of the UAV terrain matching navigation technology,UAV path planning has also attracted the attention of many researchers.The main goal of UAV path planning is to find a smooth and feasible path while satisfying the existing constraints.Due to their excellent performance,fast convergence speed and simple implementation,swarm intelligence algorithms are rapidly applied in the field of UAV path planning.However,there are still some problems in the existing UAV path planning research.For example,the modeling does not fully take into account the size of the UAV,and some swarm intelligence algorithms cannot be well adapted to the path planning model,resulting in poor experimental results.This paper selects the recently proposed two algorithms,intelligent clonal optimizer and Aquila optimizer,as the object.Two algorithms are analyzed in detail.Aiming at the shortcomings of intelligent clonal optimizer and Aquila optimizer,the corresponding improvement strategy is introduced.Finally,two improved algorithms are proposed.According to the characteristics of the terrain and the maneuverability of the UAV,this paper proposed an objective function and four constraints,and mathematically modeled the path planning problem of the UAV.Different from the previous UAV modeling,the new model fully considers the maneuverability of UAV and its own volume,so that the UAV can avoid obstacles in all directions.The model restricts the flight mode of the UAV in the horizontal and vertical directions,so that the UAV always maintains a certain safe distance from obstacles.At the same time,the model restricts the flight angle of the UAV,so that the UAV cannot actions that exceed their own functions to ensure flight safety.According to the iterative process of intelligent clonal optimizer,the reason of the update stagnation of the optimal value of the algorithm and the slow convergence speed of the algorithm on the UAV path planning problem is analyzed,and an improved intelligent cloning optimizer is proposed.The proposed algorithm introduces an opposition-based learning strategy,which can make full use of the location information of known individuals to enhance the exploration ability of the algorithm.At the same time,the proposed algorithm introduces an adaptive parameter strategy,which updates the parameters used to control the exploration and development process in the intelligent clonal optimizer according to the number of optimal value stagnation to achieve the purpose of eliminating the stagnation phenomenon,and strengthen the convergence ability of the algorithm in UAV path planning.The performance of the proposed algorithm is verified by benchmark function simulation experiments and UAV path planning simulation experiments.The experiments show that the improved intelligent clonal optimizer has excellent performance in numerical optimization problems.The performance of the proposed algorithm is poor in UAV path planning,but the performance is still greatly improved than the original algorithm.Aiming at the problem that Aquila optimizer is easy to fall into local optimum when dealing with complex optimization problems,such as UAV path planning,an opposition-based learning strategy and local escaping operator are introduced,and an improved Aquila optimizer is proposed.The opposition-based learning strategy effectively enhances the population diversity of the algorithm,enabling the algorithm to fully explore the entire search space.The local escaping operator endows the proposed algorithm with the ability to escape from the local optimum.The global optimization simulation experiment and the UAV path planning experiment prove that the improved Aquila optimizer has better performance than other algorithms,and obtains the optimal flight path among all algorithms.Finally,based on the proposed UAV path planning model,an Android app for UAV path planning is developed using java and python languages,which realizes path planning on mobile devices.