Dynamic parameter adaptation in Pareto-Optimal Particle Swarm Optimization for efficient UAV path planning

Efficacious path planning is crucial for the autonomous operations of Unmanned Aerial Vehicles (UAVs) in complex real-world scenarios. The existing path-planning approaches often struggle to balance multiple objectives under dynamic environmental conditions, resulting in suboptimal mission performance. To overcome these limitations, this study proposes an enhanced UAV path-planning algorithm that integrates multiple strategies within a unified framework. The path-planning task is formulated as a multi-objective optimization problem and solved using the Pareto Optimal Particle Swarm Optimization (POPSO) algorithm. The proposed method incorporates hybrid random–deterministic initialization to improve solution diversity, a multi-objective cost function with dynamic constraints to adapt to real-time environmental changes, dynamic updating of PSO parameters for adaptive optimization, and a hybrid Pareto-entropy selection mechanism to balance quality and diversity. Experimental results show that the proposed algorithm achieves enhanced performance in generating a well-distributed set of Pareto-optimal solutions. A comparison of simulations with other state-of-the-art multi-objective methods indicates that the proposed approach improves path efficiency, safety, and adaptability, making it well-suited for complex UAV mission execution.