A Multi-Objective Optimization Framework Combining NSGA-II and MOPSO for UAV Path Planning

A multi-strategy improved dung beetle optimization algorithm for UAV path planning

UAV path planning optimization algorithm based on an improved dung beetle optimization algorithm with a mixed strategy

A hybrid improved Grey Wolf optimization algorithm for three dimensional UAV path planning in complex terrain

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.

Three-dimensional path planning for UAVs using a quantum local search-enhanced differential evolution algorithm

This paper introduces a Quantum Local Search Differential Evolution Algorithm (QLSDE) to address path planning for unmanned aerial vehicles (UAVs) in sophisticated environments with multiple threats. First, the path planning problem is transformed into an optimization model by constructing a cost function that incorporates operational requirements and constraints, including UAV feasibility and safety. Subsequently, the QLSDE algorithm efficiently explores the configuration space by leveraging the mapping relationship between particle positions and UAV parameters (velocity, turn angle, and climb/descent angle) to minimize the cost function, thereby deriving the optimal flight path. To evaluate QLSDE's optimization performance, the present paper compared it with several classical and state-of-the-art metaheuristic algorithms (including DE, PSO, GWO, and SaUSDE). Results validated the algorithm's significant optimization capabilities. Furthermore, four benchmark test scenarios were constructed based on real digital elevation model maps. Experimental results demonstrate that QLSDE exhibits clear advantages in most scenarios for UAV path planning problems.

Multi-Objective Trajectory Planning Method for Air–Ground Collaborative Logistics UAVs Under Preemptive Scheduling

A hybrid heuristic population initialization strategy combining emergency-order priority and spatial scanning rules is introduced to increase the proportion of high-quality feasible solutions in the initial population, and the synergistic effects of the four improvement mechanisms effectively enhance the multi-objective optimization performance and the quality of the nondominated solution set.

A Trajectory Planning Method for UAVs in Dynamic Multi-Threat Environments Based on a Dynamic Multi-Objective Crow Search Algorithm

Trajectory planning, which determines a route from a starting position to a target position within a given airspace, is critical to unmanned aerial vehicle (UAV) mission execution. Many existing meta-heuristic approaches to three-dimensional (3D) trajectory planning aggregate competing requirements into a weighted cost and may suffer from limited adaptability when the environment changes. This paper formulates 3D UAV trajectory planning in dynamic multi-threat environments as a dynamic bi-objective optimization problem and proposes a multi-swarm dynamic multi-objective crow search algorithm (MDMCSA). The proposed method organizes objective-oriented swarms within a cooperative search framework and facilitates information exchange through archive sharing, thereby coordinating the search process among different objectives. The memory-time and diverse behavior strategies adjust search behaviors and solution perturbation to balance convergence and diversity. A hybrid change response strategy combines historical information reuse with diversity restoration after dynamic changes. Comparative experiments on dynamic benchmark problems and UAV trajectory planning scenarios demonstrate competitive convergence and adaptation performance, together with a favorable trade-off between solution quality and computational cost. Incremental ablation and parameter-sensitivity analyses further indicate the cumulative benefit of the integrated design and the stable performance of the selected parameter configuration across the tested settings.