Aug 2026· Discover Computing· Vol 29· 0 citations· 52 references
TL;DR
Experiments show that HLGWO generally outperforms several comparison algorithms in convergence accuracy, stability, and path cost, thereby improving the safety, feasibility, and optimization performance of 3D UAV path planning in complex environments.
Abstract
To address the tendency to fall into local optima, insufficient convergence accuracy, and path-quality fluctuations in three-dimensional UAV path planning under complex terrain and multiple constraints, this study proposes a hybrid improved Grey Wolf Optimization algorithm, termed HLGWO. A unified objective function is first constructed by considering path length, safety risk, flight altitude, turning smoothness, and terrain complexity, and an adaptive weighting mechanism is introduced to meet the requirements of different flight stages. Within the standard GWO framework, Latin Hypercube Sampling is used to improve the initial population distribution, Gaussian random walk is incorporated to enhance local search capability, and a Differential Evolution operator is introduced to promote information exchange and refined exploitation among individuals. Experiments on the CEC2005 and CEC2020 benchmark suites, together with eight real DEM-based UAV flight scenarios, show that HLGWO generally outperforms several comparison algorithms in convergence accuracy, stability, and path cost, thereby improving the safety, feasibility, and optimization performance of 3D UAV path planning in complex environments.
Aiming at the problems of slow convergence speed, low optimization accuracy, susceptibility to local optima, and insufficient stability of the traditional Red Kite Optimization Algorithm (ROA) for unmanned aerial vehicle (UAV) path planning in complex three-dimensional environments, this paper proposes an Improved Red Kite Optimization Algorithm (IROA). Firstly, the Personal History Memory Mechanism (PHMM) is introduced, which replaces random perturbation with weighted historical experience to enhance the directional search capability of the algorithm. Secondly, a cosine-based nonlinear adaptive weight strategy is adopted to dynamically balance global exploration and local exploitation. Finally, a greedy selection strategy is embedded to ensure the monotonically non-deteriorating quality of population solutions. In the experimental section, the performance of the improved algorithm is first verified using benchmark test functions, and then four types of UAV flight path-planning scenarios are constructed in the simulation environment for comparison. The results demonstrate that IROA outperforms ROA, WOA, HHO, DBO, WHO, and other algorithms in terms of optimal value, mean value, and stability indicators. Its convergence speed and optimization accuracy are significantly improved, and high-quality paths can be generated even in obstacle scenarios of varying complexity, which verifies the feasibility of the proposed algorithm for three-dimensional UAV path planning.
Experimental results show that the proposed improved dung beetle optimization (IDBO) algorithm, which integrates multiple coordinated mechanisms to enhance the original dung beetle optimizer, can serve as a competitive optimizer for numerical benchmark problems and offline static 3D UAV path-planning simulations.
To address slow convergence, local optimum stagnation, and multi-objective imbalance problems for unmanned aerial vehicle (UAV) three-dimensional (3D) path planning in complex obstacle environments, an improved adaptive two-stage pigeon swarm optimization (IPIO) algorithm is proposed. Firstly, a hybrid initialization strategy integrating Latin hypercube sampling and obstacle avoidance constraints is adopted to improve initial population diversity and the quality of feasible solutions. Secondly, in the map compass stage, a linearly decreasing adaptive map factor and population diversity-based dynamic perturbation strategy are introduced to balance global exploration and local exploitation while preventing premature convergence. In the landmark stage, an inverse fitness weighting elite center updating mechanism and linearly decreasing elite quantity strategy are designed to enhance the guidance of high-quality individuals and accelerate convergence. A multi-objective fitness function integrating path length, obstacle avoidance safety, and flight smoothness is constructed, whose weight coefficients (ωL=0.3, ωC=0.5, ωS=0.2) are calibrated through parameter-sensitivity analysis and Pareto frontier comparison across six representative weight combinations. Combining ablation validation for each improved module, single-UAV multi-scenario tests, and preliminary multi-UAV trials, these coordinated improvements realize targeted optimization for UAV 3D flight characteristics. Specifically, the preliminary multi-UAV trials involve three UAVs performing independent trajectory planning in shared obstacle environments without explicit inter-UAV collision avoidance constraints, and the reported improvements are based on single-UAV experiments. Finally, comparative experiments are conducted with a standard 100 × 100 × 50 m space, and varying obstacle densities are demonstrated in six diverse 3D test scenarios, where the proposed IPIO achieves an average path length reduction of 12.8% and 15.3% compared to the standard PIO and PSO, respectively. The average fitness improvement is 14.2% over PIO, 16.8% over PSO, 19.5% over GWO, 24.1% over CO, and 38.7% over CS. Key path-quality metrics include a minimum obstacle clearance of 2.37 m, average smoothness cost of 0.34, average convergence time of 0.60 s, and computational cost of O(N*D*MaxIter). Statistical tests confirm that these improvements are significant (p < 0.05) in all tested scenarios. This study presents an efficient and robust algorithm for autonomous three-dimensional path planning of UAVs in complex obstacle environments.
UAV path planning in complex urban environments faces significant challenges due to dense obstacles, narrow corridors, and stringent safety requirements. To address these issues, this paper proposes LLSOA, a modified Seagull Optimization Algorithm that integrates Latin Hypercube Sampling (LHS) for population initialization and Lévy Flight for global search. The key innovation lies in the problem-driven design: LHS ensures uniform coverage in dense urban maps, while Lévy Flight helps escape local optima. Compared with four state-of-the-art swarm intelligence algorithms (DBO, GWO, PIO, and PSO) across four urban scenarios, LLSOA achieves the best comprehensive fitness. Considering multiple constraints including path length, curvature, collision avoidance, and obstacle-avoidance logic, the trajectories generated by LLSOA show competitive overall performance, with no unsafe points recorded in the test scenarios and the best fitness values among the compared algorithms, albeit with a slight trade-off in path length. High-fidelity AirSim simulations with GPS/IMU noise further demonstrate that the planned trajectories remain within engineering acceptable limits. Compared with the noise-free baseline, the maximum trajectory deviation increases by 2.3% and the average deviation increases by 2.8% under high GPS/IMU noise. The main contributions are: (1) a problem-driven LLSOA that combines LHS and Lévy Flight, specifically tailored to dense urban environments; (2) theoretical analysis and simulation verification demonstrating its feasibility for multi-constraint path planning under the tested conditions; (3) high-fidelity (UE+AirSim) validation showing that the generated trajectories retain stability even under realistic sensor noise.
Fangqi Zhang, Yi Hu, Qiang Wang et al.· Drones· 0 citations
The Circle-SPM chaotic map is introduced to optimize the population initialization process, effectively mitigating the premature convergence caused by uneven distribution and a lack of population diversity.
Jian Deng, Honghai Zhang, Ze-Yu Liu et al.· Cluster Computing· 0 citations
A Multi-Strategy Chaotic Enhanced Grey Wolf Optimizer (MSCEGWO) is proposed to address the problem of easily falling into local optima, low computational accuracy, and slow convergence speed in the 3D trajectory planning process of unmanned aerial vehicles using the classical Grey Wolf Optimizer (GWO). This algorithm first employs a tent-logistic hybrid map to generate a diverse initial population, expanding the search space; Then, a nonlinear parameter is adopted to update the algorithm parameters, enhancing the global exploration ability of the algorithm; Finally, the golden sine strategy is introduced to prevent the algorithm from trapping into local optima and facilitate the search for more accurate solutions. The improved algorithm is compared with five mainstream swarm intelligence algorithms on ten benchmark functions to verify its effectiveness. Using a real Digital Elevation Model (DEM) as the test environment, the simulation results of three-dimensional trajectory planning using the improved algorithm and other swarm intelligence algorithms are presented, which demonstrate the superiority of the algorithm in solving practical engineering problems.
