Article Preview
Top1. Introduction
In recent years, with the continuous development of UAV technology, it is widely used in military, agriculture, meteorology, transportation, geographic mapping and other fields (Libaosheng et al., 2022). Now, with the diversity of Internet of things data, new concepts such as UAV Internet have even been developed and even developed new concepts such as UAV Internet (Nayyar et al., 2020). UAV path planning is to find an optimal or feasible flight path from the starting point to the target point under the constraints of UAV performance, farthest flight distance, fuel consumption, terrain and meteorological threat, so as to complete the specified combat mission safely and efficiently. It is a typical multi-objective optimization problem (Zhang et al., 2017). With the increasing complexity of planning problems, the difficulty of UAV safe implementation of various tasks has increased sharply. Finding a good path planning is its basic guarantee. In order to solve the problem of path planning under different conditions, scholars at home and abroad have proposed many algorithms to optimize path planning, such as A* algorithm (Tan & Pei, 2012), Voronoi diagram algorithm (Pehlivanoglu, 2012), dynamic programming method (Jennings et al., 2008), genetic algorithm (Liu & Wang, 2019), ant colony algorithm (Duan, 2005) and particle swarm optimization algorithm (Xianxiang et al., 2011). Literature (Yu & Wang, 2019) uses a * algorithm to delete the redundant part in the UAV search space, so as to reduce the search space, improve the search efficiency, and have good judgment ability for path selection in complex environment. Literature (Jun et al., 2021) proposes to use collaborative Particle Swarm Genetic Algorithm to generate prediction path, and determine the optimal search path through fitness function. This path meets the limit of UAV minimum turning radius, and can avoid threat areas and strengthen search in key areas. By changing the search mechanism of ant colony algorithm and using the two-way search mechanism, document (Lu, 2011) enhances the global search ability and improves the flight efficiency of UAV. Literature (Tang et al., 2021) introduced sparrow search algorithm (SSA) into cubic mapping strategy to enhance the diversity of the population, and enhanced the optimization ability of the algorithm through elite reverse learning and sine cosine algorithm. Finally, nonlinear decline and Gaussian walk strategy were adopted to prevent premature convergence of the algorithm, which achieved good results in UAV path planning. Literature (Khan et al., 2020) protects the information security of UAVs by setting up new security protocols, so as to increase the service life of UAVs. Literature (Wei et al., 2022) enhances the safety of UAV multi task cooperative path flight and improves flight efficiency by organizing UAV self-organizing networks with different network structures. Literature (Shu et al., 2021) used over depth q-network learning to plan the local flight path of UAV, making the planned path more accurate and efficient, and effectively improving the benefits of data collection. Literature (Yin et al., 2021) proposed an improved ant colony algorithm to be applied to UAV path planning. By changing the pheromone volatilization factor and the upper and lower limits of pheromone, the search ability of the algorithm is enhanced, and the adaptive heuristic function factor is introduced to enable the ant colony to effectively select a better path. Literature (Shuzhao et al., 2021) proposed a path planning method for unmanned aerial vehicles (UAVs) based on improved genetic algorithm, which improved the selection operator, crossover operator and mutation operator of genetic algorithm to plan a smooth flight path. Literature (Caojianqiu et al., 2022) proposed a mutation gray wolf optimization algorithm based on A* initialization. First, A* algorithm was used to initialize the head wolf, so that the subsequent algorithm had a better starting point. In the iteration process, a new modified mutation operator was proposed to optimize the population. It has been applied to path planning and achieved good results. Literature (He et al., 2021) proposed an intelligent penetration method of UAV Based on improved moth extinguishing fire optimization algorithm. By introducing crossover operator and Gauss mutation operator, it causes flame mutation, accelerates the optimization speed in the early stage of iteration, and introduces adaptive weight in the later stage of the algorithm to enhance the overall search ability of the algorithm, which can be applied to UAV to select a better path. Literature (Lan & Tao, 2021) proposed an improved bacterial foraging optimization algorithm, which applies UAV path planning, adds the learning factor of particle swarm optimization algorithm when bacteria swim, changes the fixed step size, and changes the fixed migration probability to the adaptive migration probability. The planned path length is shorter and smoother. Literature (Xionghuajie & He, 2020) proposes an improved particle swarm optimization algorithm, which divides UAV track planning into two parts: overall track planning and inter node track planning. Combined with environmental conditions, the evaluation functions of particle swarm optimization algorithm are designed respectively. The particle swarm optimization algorithm is improved by designing the segmented inertia weight adjustment formula, which improves the speed and accuracy of the path planning. Literature (Fu & Hu, 2021) integrating the longicorn whisker algorithm with the particle swarm optimization algorithm, the improved particle swarm optimization algorithm has less cost in path planning, so as to reduce the flight cost. The literature comparison table is shown in Table 1 below.