Autonomous, low-cost sensor module for fill level measurement for a self-learning electronic Kanban system

Abstract

Abstract In the era of digitalization, electronic Kanban (e-Kanban) extends the traditional Kanban with additional data and information sharing that allows for more flexible and optimized inventory planning. The lack of automated fill level measurements for load carriers still hinders the full automation of the process. Our aim is to develop a self-learning e-Kanban system that automatically triggers replenishment orders using machine learning and data from low cost, autonomous sensor modules that measure the fill level of load carriers. This paper explains the concept and presents a first version of the mentioned sensor module that consists of an Intel Realsense sensor and an NVIDIA Jetson Nano. An evaluation is presented as well using small load carriers, which shows the suitability of the proposed method.