A Novel Three-Dimensional Path Planning Method for Fixed-Wing UAV Using Improved Particle Swarm Optimization Algorithm

Abstract

This paper proposed an improved particle swarm optimization (PSO) algorithm to solve the three-dimensional problem of path planning for the fixed-wing unmanned aerial vehicle (UAV) in the complex environment. The improved PSO algorithm (called DCA ∗ PSO) based dynamic divide-and-conquer (DC) strategy and modified A ∗ algorithm is designed to reach higher precision for the optimal flight path. In the proposed method, the entire path is divided into multiple segments, and these segments are evolved in parallel by using DC strategy, which can convert the complex high-dimensional problem into several parallel low-dimensional problems. In addition, A ∗ algorithm is adopted to generated an optimal path from the particle swarm, which can avoid premature convergence and enhance global search ability. When DCA ∗ PSO is used to solve the large-scale path planning problem, an adaptive dynamic strategy of the segment selection is further developed to complete an effective variable grouping according to the cost. To verify the optimization performance of DCA ∗ PSO algorithm, the real terrain data is utilized to test the performance for the route planning. The experiment results show that the proposed DCA ∗ PSO algorithm can effectively obtain better optimization results in solving the path planning problem of UAV, and it takes on better optimization ability and stability. In addition, DCA ∗ PSO algorithm is proved to search a feasible route in the complex environment with a large number of the waypoints by the experiment.

A Fuzzy Logic Path Planning Algorithm Based on Geometric Landmarks and Kinetic Constraints

“…The four corners of the rectangular map are marked to determine the range of coordinates. The coordinates of the upper left corner of the map are marked as (0, 0), the coordinates of the lower right corner are (500, 500), the coordinates of the start point are (10,10), and the coordinates of the endpoint are (490, 490). In addition, set the size of the mobile robot to 10×10, the maximum speed to 10, the maximum rotation angle to 60°, and the maximum acceleration to 3.…”

“…In addition, set the size of the mobile robot to 10×10, the maximum speed to 10, the maximum rotation angle to 60°, and the maximum acceleration to 3. Set the start point to (10,10); the start angle is 60°; the speed is 4; the endpoint to (490, 490). The termination area is a circular area of radius 20 with the termination point as the circle's center.…”

“…This algorithm is based on empirical construction, through multiple training to achieve convergence, but in general, whether the parameters set correctly for the map primarily affect the convergence speed of the algorithm. For example, ant colony algorithms [2,13,14,16], particle swarm algorithms [10,17,26,27], and others. The fifth category of hybrid algorithms, on the other hand, obtains the advantages of multiple algorithms at the same time by integrating the above four types of algorithms, but this is usually obtained by paying more time complexity.…”

A scheduling route planning algorithm based on the dynamic genetic algorithm with ant colony binary iterative optimization for unmanned aerial vehicle spraying in multiple tea fields

“…Wu et al (2019) proposed a path planning method based on the beetle search algorithm, overcoming the trade-off between high computational complexity and the UAV requirement for realtime trajectory planning. The offline UAV path planning method based on the improved particle swarm algorithm proposed by Huang (2021) can realize the planning of 3D routes. This algorithm greatly reduces the computational effort and improves the route planning efficiency.…”

“…Qu et al (2020) proposed a UAV path planning method with a hybrid gray wolf optimization algorithm, which combines the gray wolf optimization algorithm and the symbiotic biological search method to smooth the generated routes and make the routes more suitable for UAVs. However, these aforementioned studies are limited to planning of UAV remote sensing and obstacle avoidance routes (Wu et al, 2019;Qu et al, 2020;Huang, 2021;Jiang et al, 2021), which is different from the scheduling problem and cannot be applied to the UAV multi-tea field scheduling route planning scenario. Pang et al (2021) proposed an adaptive route planning approach based on an artificial potential field method.…”