Online Planning to Control a Packaging Infeed System

Abstract

In this paper, we investigate a novel application of online planning and scheduling: controlling an automated infeeder for a packaging line of food and consumer packaged goods. In this system, products arrive continuously at high-speed from the end of the production line and need to be arranged into a specific configuration for downstream primary and secondary packaging machines. In collaboration with a domain expert from the packaging industry, we developed an innovative design for a reconfigurable parallel infeed system using a matrix of interchangeable smart belts. We also adapted our online model-based Plantrol planner to this domain. Our planner can control various configurations of the new in-feed system through simulation both in nominal planning and when runtime failures occur. We are also building a small physical prototype to validate the new design and our sofeware framework.