KION Launches Project ARIBIC for Digital Twins of Warehouses

The KION Group and its partners LeddarTech, the Karlsruhe Institute of Technology (KIT), and the STARS Lab at the University of Toronto have launched the research project ‘ARIBIC’. The acronym stands for ‘Artificial Intelligence-Based Indoor Cartography’: continuous evaluation of data is intended to enable the creation of a digital twin of a warehouse or production environment – all in real-time.

(Frankfurt/Main) This project is another step to expand the existing solutions for digital twins as well as simulation and emulation platforms already offered by the KION Group. Both German and Canadian government agencies have been convinced of the potential of the research and are therefore providing project funding. ARIBIC is one of several collaborations that the KION Group has already implemented with various partners.

Driverless transport vehicles are already being used to a significant extent in intralogistics and production facilities. Equipped with modern sensors such as laser scanners and cameras, they safely navigate through shelves, production lines, and warehouses. During operation, they continuously generate a considerable amount of data about the environment in which they operate. However, this data is typically not systematically collected. But what if we could harness the untapped potential of these bits and bytes?

The digital twin of a warehouse is created

Systematic data collection and processing: This is precisely where the ARIBIC research project, driven by STILL, a subsidiary of the KION Group, comes into play. “The data collected by the sensors on the vehicles is used to create high-resolution 3D maps of warehouses or production environments. The goal is to create a digital twin of the environment. This allows us to make the relevant data visible and share it in real-time,” says Dr. Henry Puhl, Chief Technology Officer of the KION Group. “Many companies in the industrial sector still rely on a post-digitalization of their production or warehouses. However, this only provides a small snapshot. The results of ARIBIC will go beyond that, as they will ultimately allow for continuous data evaluation,” says Dr. Joachim Tödter, Senior Director Technology & Innovation at the KION Group.

The data is transmitted from the sensors to the vehicle, processed there, and then sent to the ARIBIC cloud. The advantages are clear: the user receives live information about the position of objects through tracking and tracing. This data then enables, for example, the simulation of vehicle routes and thus improves processes in the warehouse or production. At the same time, these intelligent digital services have the advantage of detecting and reporting anomalies such as blocked pathways. If this is consistently implemented, the entire structure of a warehouse can ultimately be optimized.

“KION is already capable of implementing such techniques today. However, ARIBIC offers us an important advancement in that we can add computer-based perception. This opens the door to many applications, ranging from the more efficient design of flexible automation and mobile robot operations for the warehouse of tomorrow to the inspection and detection of material placement and distribution in the warehouse. This is crucial for optimizing workflows in many logistics operations,” says Hamid Montazeri, Senior Vice President, Software & Digital Solutions Development at KION subsidiary Dematic.

Project partner LeddarTech with deep expertise in sensor technology

The idea for the research project originated in the summer of 2019 in the Technology & Innovation department of the KION Group. For the preparation of the funding application, cross-border partners from industry and research were recruited: LeddarTech, a leading company in environmental sensor solutions for autonomous vehicles and advanced driver assistance systems based in the Canadian province of Quebec, is significantly involved in the project. LeddarTech’s contribution will focus on the sensor system. The Canadian developers will bring their technological expertise in the areas of sensing, perception, and sensor fusion for mobility applications.

“When KION approached us and explained its vision for ARIBIC, it was clear from the beginning that we had to be part of this project,” says Pierre Olivier, Chief Technology Officer of LeddarTech. “It not only allows us to collaborate with an industry leader and two renowned universities, but also presents a perfect opportunity to leverage LeddarTech’s strong expertise in sensor technology, integrating sensor platforms into vehicles, and maximizing the potential of available sensor data.”

Strong collaboration between industry and academia

Research partners include the Karlsruhe Institute of Technology (KIT) and the STARS Lab at the University of Toronto, both leading institutes in the field of artificial intelligence and robotics. As part of the ARIBIC project, the STARS Lab will develop methods for extracting detailed semantic information (object labels) from large 3D maps of warehouse environments. “ARIBIC is a perfect project for us to work with international partners on current research topics and to build new relationships with industry,” says Prof. Jonathan Kelly, head of the STARS Lab.

The Department of Robotics and Interactive Systems at the Institute for Material Handling and Logistics Systems (IFL) at KIT is researching forward-looking robotics solutions with practical benefits for users. The research field includes topics such as mapping and localization of mobile robots, computer vision, automated grasping and placing of various objects, as well as the development of intuitive human-machine interaction. As part of the ARIBIC project, the IFL is focusing on the detection of intralogistics elements in 3D sensor data and the merging of maps in multi-robot scenarios. “We are very much looking forward to the opportunity for international collaboration,” says Prof. Kai Furmans, head of the IFL.

In early 2021, the project was approved by the National Research Council of Canada Industrial Research Assistance Program (NRC IRAP) and the German Federal Ministry for Economic Affairs and Energy (BMWi), securing funding. The project is scheduled to be completed in the fourth quarter of 2023.

Photo: © KION Group