A Supervised Machine Learning Approach for Intelligent Process Automation in Container Logistics

Abstract

Process control in manufacturing industries usually lacks flexibility and adaptability. The process planning is traditionally pursued within the production scheduling and then remains unchanged until a major overhaul is necessary. Consequently, no process knowledge acquired by the machine operators is used to adapt, and thus improve, the process control. In this paper, a fully automated process control solution for container logistics is proposed, which is based on deep neural networks and has been trained from process steering decisions made by employees. Further, a fully automated framework for the labeling of container images is introduced, making use of inherent properties of the logistic process. This allows to automatically generate data sets without the need for manual labeling by an operator.