UAV 3D Path Planning Based on Integrated Particle Swarm Optimization and Artificial Potential Field Method

Safe, efficient, and feasible path planning for unmanned aerial vehicle (UAV) in complex three-dimensional environments remains a critical challenge in intelligent navigation. Although the traditional artificial potential field (APF) method offers high computational efficiency, it is prone to local minima and target inaccessibility in complex environments. To overcome these limitations, this paper proposes a novel 3D path planning approach that integrates an APF with particle swarm optimization (PSO). The method introduces a Gaussian repulsive function to improve obstacle boundary perception and ensure smooth potential field transitions. Combined with a PSO-based optimization of trajectory points, it effectively enhances the algorithm’s ability to escape local minima and improves global path accessibility. To validate the effectiveness of the proposed method, a comprehensive evaluation framework was developed, incorporating key performance metrics such as total path length, average safety distance, and minimum safety distance. Benchmark comparisons were conducted against several advanced path planning algorithms in static, dynamic, and more complex obstacle environments. In addition, a path executability verification framework was introduced, employing multiple flight controllers to perform trajectory tracking simulations and systematically assess control feasibility and adaptability in complex dynamic scenarios. Experimental results show that the proposed method exhibits clear advantages in both path planning quality and practical executability, particularly demonstrating strong adaptability and robustness in complex environments.