To achieve optimal path planning for Automated Guided Vehicles (AGV) in complex and dynamic warehousing environments, an improved artificial bee colony algorithm is proposed. This improvement involves introducing an adaptive k-nearest neighbor search strategy to enhance the search strategy of the original algorithm, utilizing feasible solutions outside the neighborhood and the global optimum to improve the selection strategy, and adjusting the guiding velocity of the global optimum with a dynamic factor β. These enhancements address issues such as premature convergence and low search efficiency in traditional artificial bee colony algorithms. Finally, simulation experiments are conducted using MATLAB software. The simulation results demonstrate that the proposed improved artificial bee colony algorithm is feasible and effective for path planning in warehousing environments.