Currently, automated guided vehicles create a static 3D model of their surroundings as they travel through the warehouse. A research program called ARIBIC (Artificial Intelligence-Based Indoor Cartography) aims in real time that adapts to transform this into a dynamic digital twin
When automated guided vehicles (AGVs) navigate through warehouses or production halls, they become data collectors. However, this data is usually deleted immediately. "Ahuge waste," says Bengt Abel, project manager at the forklift manufacturer Still. The international research project aims to develop methods for reusing this information profitably.
The data collected via sensors and cameras can be used in the ARIBIC cloud to create 3D maps of warehouses or production facilities that are always up-to-date. "Using this real-time sensor data, we create a living digital twin of the environment, allowing us everything to display and share outlining the basic concept.
"The sensors detect even the smallest changes and forward them to the platform. In the artificial intelligence-based indoor mapping, these changes, such as a moved shelf or a newly placed pallet, are immediately taken into account and fed back into the system," the expert explained.
The warehouse environment: constantly in motion. Images: Still
High-resolution 3D maps are currently primarily for localization within warehouses. this information can also be used warehouse and factory planning. For example, it clearly shows which areas of the warehouse see high or low traffic, or which aisles are frequently obstructed and thus blocked. With these results, shelves can be moved (initially) virtually, or production areas can be rearranged. Abel explains: "With this new ability to continuously capture the work environment, users can optimally plan and utilize their warehouses and production halls in the future." According to the Still expert, countless other applications are conceivable, building upon the ARIBIC results: "We already have some great ideas. But I'm quite certain that many more will emerge in the future."
launched was The ARIBIC project , involves the Karlsruhe Institute of Technology (KIT), the University of Toronto with its STARS laboratory, and the Canadian sensor manufacturer LeddarTech. The project is funded by the German Federal Ministry for Economic Affairs and Energy (BMWi) and the Industrial Research Assistance Program of the Canadian National Research Council (NRC IRAP). The Hamburg-based intralogistics provider Still will contribute its successful OPX iGo neo model – an autonomous order picker already extensively equipped with sensors and camera technology.
www.still.de
