Research on UAV path planning based on an improved A* algorithm

Abstract

UAV path planning is a crucial component of autonomous navigation and logistics delivery, and its performance directly affects both operational safety and efficiency. However, the standard A* algorithm often suffers from redundant node expansions and limited path smoothness in cluttered environments, which constrains real-time performance and practical deployability. This study is dedicated to boosting UAV path planning quality and logistics operational efficiency, and therefore puts forward a refined A* algorithm for path optimization. By refining the bidirectional search mechanism, optimizing the heuristic function, and introducing a collinear-node elimination strategy, the proposed approach improves the smoothness of the generated paths, thereby increasing both efficiency and accuracy. Furthermore, a dynamic weighting scheme is incorporated into the bidirectional search framework to adaptively adjust the influence of the heuristic function across different search stages, reducing unnecessary node expansions and shortening planning time. In addition, a correction-factor cost function is designed to fine-tune heuristic guidance, suppress suboptimal solutions during path splicing, and enhance path consistency when the search frontiers from the start and goal points converge. Experimental data demonstrate that the presented algorithm outperforms the conventional A* approach: it shortens the total path length by 7.17% and cuts the path computation time by 21%, alongside generating much smoother flight trajectories.