A hybrid scheduling and control system architecture for warehouse management

Abstract

In recent years, the hybrid control framework has received attention from the research community. Variations of this control framework are available in the literature. In this paper, a hybrid intelligent agent-based scheduling and control system architecture is presented for an actual industrial warehouse order-picking problem, where goods are stored at multiple locations and the pick location of goods can be selected dynamically in near-real time. The presented architecture includes a higher level optimizer, a middle-level guide agent, and lower level agents. The need for a higher level optimizer and communication between higher and lower level controllers is demonstrated. A mathematical model and a genetic algorithm for the resource assignment problem are presented. Simulation results demonstrating efficiency of the new approach are also presented.