Minimizing Order Picking Travel Distance using a DNN-Based Method Within a High-Level Storage Warehouse

Abstract

With the rapid growth of e-commerce, the increasing volume of orders and demand for shorter delivery times pose significant challenges to warehouse management, particularly in optimizing high-level storage systems where complex calculations are required. In recent years, deep neural networks (DNNs) have demonstrated remarkable success in pattern recognition and classification, offering a promising avenue for warehouse optimization. This study proposes a novel DNN-based order batching algorithm aimed at minimizing pickers' total travel time in high-level storage systems. The method consists of two stages: in the first stage, a deep neural network is trained to recognize and classify picking route patterns; in the second stage, a Genetic Algorithm (GA) is employed to batch orders within the categories identified by the DNN. Numerical experiments across eight scenarios demonstrate that the proposed DNN-GA method achieves travel distance reductions of up to 34.8% compared to random batching, while traditional GA achieves reductions of up to 10.8%, highlighting the superior efficiency of the proposed approach. Theoretically, this study establishes a foundational framework for utilizing DNNs in order classification, while practically, it demonstrates the potential to reduce warehouse operating costs by optimizing computational resources and minimizing travel distances.