Enhanced PSO with adaptive weights and Gaussian mutation based 3D path planning for UAVs
-
Gaofeng Che
School of Artificial Intelligence and Computer Science, Liaocheng University, Liaocheng 252000, China;
Abstract
Path planning remains a pivotal metric for evaluating unmanned aerial vehicles (UAVs) autonomy, where intelligent algorithms serve as the cornerstone for generating high-quality trajectories. Path planning is an indispensable part of the autonomous control system for UAVs. In addition, UAV mission planning has been proven to be an NP-hard problem. This paper systematically analyzes the state-of-the-art intelligent optimization algorithms for UAVs' path planning. Considering that traditional particle swarm optimization (PSO) and adaptive weight particle swarm optimization (AWPSO) easily converge to local optima, this work develops an enhanced PSO with adaptive weight and Gaussian mutation (EPSO-AWGM). The introduction of adaptive weight factors and Gaussian mutation operators helps the algorithm escape local optimum solutions. Moreover, the cubic spline method is utilized to smooth the UAVs' flight paths. To verify the performance of the proposed EPSO-AWGM algorithm and the quality of UAV path planning in a 3D environment, this paper sets the traditional PSO and AWPSO as control groups, conducting comparative simulation experiments on 3D terrain path planning. The simulations uniformly set initial parameters, with a particle population size of 20 and a maximum iteration count of 50. All algorithms operate in a 3D environment containing five mountain obstacles, with a unified starting coordinate at (1,1,1) and an ending coordinate at (29,29,17). To ensure objective experimental results and eliminate random error interference, all three algorithms are independently run 20 times. Simulation results show that the proposed EPSO-AWGM can obtain shorter and higher-quality flight paths. It therefore has great application potential in practical UAV path planning scenarios.
Copyright (c) 2026 Gaofeng Che
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
[1]Haam S, Kim H, Yoo M, et al. Optimal additional evacuation route analysis in deep underground station structures using Dijkstra’s algorithm. Developments in the Built Environment. 2025; 24: 100784. doi: 10.1016/j.dibe.2025.100784
[2]Akay R, Yildirim MY. SBA*: An efficient method for 3D path planning of unmanned vehicles. Mathematics and Computers in Simulation. 2025; 231: 294–317. doi: 10.1016/j.matcom.2024.12.015
[3]Zhang B, Cai X, Li G, et al. Path planning in radioactive environment of nuclear facilities based on modified A-star algorithm and search neighborhood optimization. Nuclear Engineering and Technology. 2025; 57(10): 103711. doi: 10.1016/j.net.2025.103711
[4]Eltamaly AM, Rabie AH. A star-nosed mole optimizer (SNMO): A novel optimization algorithm. Computers and Electrical Engineering. 2026; 135: 111179. doi: 10.1016/j.compeleceng.2026.111179
[5]Yang TY, Zou L, Wu ZX, et al. An improved A-star algorithm coupled with graph division and AIS data for ship path planning. Ocean Engineering. 2025; 330: 121234. doi: 10.1016/j.oceaneng.2025.121234
[6]Veisi O, Moradi MA, Gharaei B, et al. Sustainable forestry logistics: Using modified A-star algorithm for efficient timber transportation route optimization. Forest Policy and Economics. 2025; 173: 103456. doi: 10.1016/j.forpol.2025.103456
[7]Khalid K, Ayaz Y, Ali S, et al. Fast and efficient motion planning: using hybrid sampling and simulated annealing. Expert Systems with Applications. 2026; 331: 133173. doi: 10.1016/j.eswa.2026.133173
[8]Yang Z, Deng L, Mao X, et al. A differential evolutionary algorithm improvement framework based on artificial potential fields. Applied Soft Computing. 2026; 192: 114714. doi: 10.1016/j.asoc.2026.114714
[9]Jia Y, Wang S, Liu Z, et al. DPI-RRT*: a fast RRT* algorithm for mobile robot based on dynamic probability adjustment and bi-directional insertion. Engineering Computations. 2026; 43(6): 2365–2396. doi: 10.1108/EC-12-2024-1148
[10]Lv L, Wu L, Xiao R, et al. Constrained multi-objective wolf pack algorithm based on diversity guidance and feasibility enhancement. Applied Soft Computing. 2026; 200: 115387. doi: 10.1016/j.asoc.2026.115387
[11]Xiao W, Dong N, He K. A hybrid global wolf pack algorithm-based incremental conductance method under partial shading conditions. Solar Energy. 2025; 291: 113388. doi: 10.1016/j.solener.2025.113388
[12]Yang X, Liu Y, Wang Y. Target quality variable prediction from multivariate process trajectories using kernel entropy component analysis and an adaptive neuro-fuzzy inference system optimized by improved Gaussian quantum-behaved particle swarm optimization. Expert Systems with Applications. 2026; 327: 132885. doi: 10.1016/j.eswa.2026.132885
[13]Che G, Liu L, Yu Z. An improved ant colony optimization algorithm based on particle swarm optimization algorithm for path planning of autonomous underwater vehicle. Journal of Ambient Intelligence and Humanized Computing. 2020; 11(8): 3349–3354. doi: 10.1007/s12652-019-01531-8
[14]Yan M, Yuan H, Xu J, et al. Task allocation and route planning of multiple UAVs in a marine environment based on an improved particle swarm optimization algorithm. EURASIP Journal on Advances in Signal Processing. 2021; 2021(1): 94. doi: 10.1186/s13634-021-00804-9
[15]Hu J, Wu H, Zhan R, et al. Self-organized search-attack mission planning for UAV swarm based on wolf pack hunting behavior. Journal of Systems Engineering and Electronics. 2021; 32(6): 1463–1476. doi: 10.23919/JSEE.2021.000124
[16]Liu W, Zheng X. Three-Dimensional Multi-Mission Planning of UAV Using Improved Ant Colony Optimization Algorithm Based on the Finite-Time Constraints. International Journal of Computational Intelligence Systems. 2020; 14(1): 79. doi: 10.2991/ijcis.d.201021.001
[17]Su M, Cheng Y, Hu J, et al. Combined Optimization of Swarm Task Allocation and Path Planning Based on Improved Ant Colony Algorithm. Unmanned Systems Technology. 2021; 4: 40–50. (in Chinese)
[18]Zhou X, Gao F, Fang X, et al. Improved Bat Algorithm for UAV Path Planning in Three-Dimensional Space. IEEE Access. 2021; 9: 20100–20116. doi: 10.1109/ACCESS.2021.3054179
[19]Liu G, Shu C, Liang Z, et al. A Modified Sparrow Search Algorithm with Application in 3d Route Planning for UAV. Sensors. 2021; 21(4): 1224. doi: 10.3390/s21041224
[20]Cao J, Zhang G, Xu P. A* initialized mutable gray wolf optimizer for UAV path planning. Computer Engineering and Applications. 2022; (4): 275–282. (in Chinese)
[21]Goel U, Varshney S, Jain A, et al. Three Dimensional Path Planning for UAVs in Dynamic Environment using Glow-worm Swarm Optimization. Procedia Computer Science. 2018; 133: 230–239. doi: 10.1016/j.procs.2018.07.028
[22]Xu H, Jiang S, Zhang A. Path Planning for Unmanned Aerial Vehicle Using a Mix-Strategy-Based Gravitational Search Algorithm. IEEE Access. 2021; 9: 57033–57045. doi: 10.1109/ACCESS.2021.3072796
[23]Xu Z, Zhang E, Chen Q. Rotary unmanned aerial vehicles path planning in rough terrain based on multi-objective particle swarm optimization. Journal of Systems Engineering and Electronics. 2020; 31(1): 130–141. doi: 10.21629/JSEE.2020.01.14
[24]Huang C. A Novel Three-Dimensional Path Planning Method for Fixed-Wing UAV Using Improved Particle Swarm Optimization Algorithm. International Journal of Aerospace Engineering. 2021; 2021(1): 7667173. doi: 10.1155/2021/7667173
[25]Zhang W, Zhang S, Wu F, et al. Path Planning of UAV Based on Improved Adaptive Grey Wolf Optimization Algorithm. IEEE Access. 2021; 9: 89400–89411. doi: 10.1109/ACCESS.2021.3090776
[26]Mai Z, Xin Z, Zhang X. Research on Robot Path Planning Based on Improved Traditional RRT Algorithm. Machine Building & Automation. 2022; (6): 177–179. (in Chinese)
[27]Kang B, Huang J. Variable step size rapidly-exploring random tree (RRT) path planning algorithms and simulation of a mobile robot based on environment complexity. Journal of Beijing University of Chemical Technology (Natural Science). 2023; 50(4): 87–93. doi: 10.13543/j.bhxbzr.2023.04.011 (in Chinese)
