Intelligent agent modeling of an industrial warehousing problem

Abstract

In this paper, we consider 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. We solve the problem using an intelligent agent-based model. The modeling framework is between the two extremes of hierarchical and heterarchical frameworks. It recognizes that horizontal as well as vertical decisions are made between various levels of controllers and that these have to be captured explicitly in the model. Entities (goods or parts) and resources (storage areas and order pickers) are modeled as intelligent agents that function in a co-operative manner so as to accomplish individual as well as system-wide goals. Scheduling and other decisions are taken by these agents in a dynamic real-time fashion based on conditions that exist at the time these decisions are made. To overcome the structural rigidity and lack of flexibility, a negotiation mechanism for real time task allocation is used