The accuracy of inventory records is an essential KPI in the manufacturing industry and in many logistics operations. Currently, the amount of manual workforce needed to maintain high accuracy is relatively high. To establish the location and quantity of products and parts, and to align this information with enterprise resource planning (ERP), typically involves many interfaces which may additionally lead to inconsistencies in the mapping. Therefore, exact inventory recording (and its verification) entails significant overheads in terms of time and money.
Recent technological innovations in drones, computer vision and machine learning present significant optimization potential for inventory management, as they allow for the automatic identification of products in large warehouses, therefore enabling seamless, automated inventory management. In its current incarnation, drone-based inventory management is semi-automatic as it requires a human operator with a line of sight to the drone to ensure safety of operation when the process is carried out during normal operating hours of the warehouse or production floor.
The project SAFE-TRACK, which started in September 2020, investigates how to achieve automated drone-based inventory management, without maintaining line of sight to the drone. This is required to enable flights within operating hours – which means that the drone is collaborating with humans and logistics equipment. Over a period of six months, Area 4.1 (Cognitive Products), TU-Graz (Institute of Computer Graphics and Vision), D-ARIA and Roto Frank Austria will develop and test methods to secure and monitor drone operations in warehouse environments. The methods will be developed in the context of real warehouse inventorying scenarios within Roto Frank Austria and aim to complement D-ARIA’s existing solution for drone-based data acquisition. The project is an important first step towards the autonomous application of drones for continuous inventory management. We are ready to “take off” into a digital future!
