在智能仓库中，人机协作进行订单拣选，涉及模糊的运输和处理时间

《Mathematics》：Human–Robot Collaborative Order Picking in Smart Warehouses with Fuzzy Transportation and Processing Time

　　

[]{}

摘要

1. Robot mobile fulfillment systems (RMFSs), as human–robot collaborative smart warehouses, transform the traditional person-to-goods order picking mode into a goods-to-person mode.
2. Order picking optimization is a core decision-making challenge in RMFSs to improve the system efficiency, which requires optimizing pod selection, robot scheduling, station assignment, and manual picking jointly.
3. Although recent studies have explored integrated operational optimization in RMFSs, most rely on deterministic transportation and processing times, ignoring uncertainties in real-world human–robot collaborations.
4. Jointly optimizing these decisions under uncertain conditions remains challenging.
5. To address this, we developed a model to minimize the overall processing time (makespan) and used an adaptive algorithm based on a large neighborhood search (ALVND) to solve it efficiently.
6. The algorithm employs three-dimensional coupling encoding and multi-stage heuristic decoding methods, as well as a learning-based adaptive operator selection and variable neighborhood search strategy.
7. Extensive experiments proved ALVND’s effectiveness, with objective function values 5.6–25.1% lower than those of competing methods, especially in uncertain human–robot warehouse scenarios.