Year 2025-2028

Supported by the Guangdong Basic and Applied Basic Research Foundation (No. 2025A1515110120).

With the rapid growth of e-commerce and increasing demand for efficient order fulfillment, human-robot collaborative order picking systems have emerged as a promising solution for modern warehouses. By combining human flexibility and decision-making capabilities with robotic efficiency and automation, these systems offer significant potential to improve operational productivity and responsiveness. However, effectively coordinating human workers and robots remains challenging due to dynamic order arrivals, heterogeneous task requirements, varying human performance, and resource constraints.

This project aims to develop a data-driven optimization framework for human-robot collaborative order picking systems. By integrating historical operational data, machine learning, and optimization techniques, the project will investigate intelligent task allocation, human-robot coordination, and real-time scheduling strategies. Particular attention will be given to capturing human behavioral characteristics, predicting operational uncertainties, and developing adaptive decision-making approaches. The expected outcomes include improved picking efficiency, reduced operational costs, balanced human workloads, and enhanced system adaptability, providing both theoretical insights and practical decision-support tools for next-generation intelligent warehousing systems.