Research on Path Planning Technology for Unmanned Aerial Vehicles by Integrating Chaotic Bat Algorithm with Artificial Potential Field Algorithm

In the field of autonomous navigation for drones, efficient path planning is the key to achieving safe and fast arrival at the target. This article proposes a hybrid algorithm that combines artificial potential field and chaotic bat algorithm to solve the path planning problem of unmanned aerial vehicles in complex environments. However, when drones use pure APF algorithm for autonomous navigation, they may fall into local minima in some cases, leading to path planning failure. To this end, we introduced the Chaos Bat Algorithm, which is a metaheuristic optimization algorithm based on bat foraging behavior, with good global search ability and the ability to jump out of local optima. In order to further improve the algorithm performance, we applied chaos theory to IBCA, enhancing the exploration and development capabilities of the algorithm. The paper conducted comparative experiments on the proposed fusion algorithm on maps of different complexities, including traditional bat algorithm, hybrid bat algorithm based on differential evolution algorithm (DEBA), and chaotic bat algorithm combined with artificial potential field method (CPFIBA). The comparative experiments showed that the fusion algorithm achieved the expected path length, computation time, and success rate while significantly outperforming other methods. The improved fusion algorithm can effectively overcome local optima of a single algorithm, provide shorter paths, and better flight performance.