.png){kind=icon}
Return
Online task assignment in warehouse considering the pickers' dynamic capability: A data-driven optimization approach
.png){kind=icon}
PRE
AI
DOI：10.1016/j.tre.2026.105040.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Dynamic variations in pickers' capability are crucial for task assignment efficiency, yet are often overlooked in research due to the focus on system-level optimization and the complexity of modeling human variability. This paper addresses the problem of order fulfillment task assignment considering the pickers' dynamic capability. A unique feature of the proposed approach is the integration of a data-driven model for characterizing capability with a mixed integer programming optimization model for online task assignment. To solve the model and leverage the pickers' dynamic capability, we developed a variable time window algorithm based on the proportion of available pickers. Numerical experiments are conducted using data obtained from a warehouse located in Southwest China. The results indicate that our approach significantly improves the accuracy of characterizing pickers' capability. Additionally, our model modestly reduces total execution time and achieves a notable improvement of over 20% in labor equilibrium. With the help of our model, the warehouse manager can clearly assess the dynamic variations of pickers' capability and make informed task assignment decisions, ensuring efficient and equitable labor utilization.
Keywords:
Online task assignment
Warehouse
Data-driven
Dynamic capability
Journal
IF:
8.8
Papers:
896
Citations:
2.0W
Organization
Cited Papers
No cited papers available