Human-machine cooperation: Optimizing layout design and drug retrieval sequencing in automated drug dispensing systems

Automated drug dispensing systems (ADDSs) are increasingly in demand in today's pharmacies, primarily driven by the growing aging population. Recognizing the practical challenges faced by pharmacies implementing ADDSs, this study aims to optimize the layout design and retrieval sequencing issues to enhance the order picking efficiency of ADDSs within a human–machine cooperation environment. In ADDSs, the robotic arm retrieves the drug bin and after that pharmacists need to sort the drug at the Input/output (I/O) points for order picking, which is a human–machine cooperation way. We consider the pharmacists’ stochastic sorting time in the order picking problem. For the various layout designs in ADDSs, we develop dual command retrieval sequencing models with one I/O point layout design and two I/O points layout designs. The successive order arrival and the dual command mode operations make the process intertwined. The proposed models are tested using the pharmacy data. We incorporate the stochastic sorting time of pharmacists to analyze its impact on ADDS performance. Through experimental comparisons of average picking times for prescription orders under various parameters, we demonstrate that the system layout design with two I/O points significantly enhances the efficiency of prescription order fulfillment within a human–machine cooperation environment. Furthermore, our proposed retrieval sequencing method outperforms dynamic programming, greedy, and random strategies in terms of improving prescription order-picking efficiency. Specifically, a comparison is made with the current situation in hospitals as well. By addressing the layout design and sequencing challenges, our research contributes to the field of intelligent warehousing, particularly in smart pharmacies.