A Path Planning Method for Unmanned Aerial Vehicles Based on Improved Artificial Bee Colony Algorithm

With the continuous advancement of UAV applications, UAV flight path planning is a current hot research topic. In this regard, this paper establishes a path planning model for UAV in obstacle environments. On this basis, an improved artificial bee colony algorithm (MABC) is proposed for solving the respective model. The algorithm utilizes a reverse learning approach to optimize the quality of initial solutions. Additionally, it improves the search strategy of employed bees by introducing Levy and Cauchy distributions, thereby enhancing the global optimization capability of the traditional ABC algorithm. Finally, the feasibility of the proposed method is being validated through simulation experiments. Compared to the traditional ABC algorithm, the MABC algorithm reduces the flight distance by approximately 4.6% while meeting the requirements of UAV missions, thereby improving the UAV's flight efficiency and task effectiveness.