At LogiMAT (March 11-13), Linde Material Handling will be showcasing, alongside the new E and Xi series electric forklifts, a showcase based on NVIDIA's "Omniverse" AI platform, which uses a digital twin to capture, process and analyze huge amounts of data from warehouse processes in real time.
Just in January, the parent company Kion announced its extensive collaboration with AI market leader NVIDIA and digitalization experts Accenture to take industrial automation to a new level.
On an extension of the Linde MH trade fair stand, a scenario is on display that could be typical for the warehouses of "tomorrow": Manual and automated industrial trucks work together in perfect orchestration using innovative AI technology. This benefits especially operators of large fleets.
“At LogiMAT 2025, we will present our comprehensive Winning Line-up for the challenges of modern logistics: From manual and automated industrial trucks to fully networked safety and energy solutions to the AI-supported warehouse of the future,” said Martin Stadtmüller, Director Marketing Linde Material Handling Germany.
In cooperation with NVIDIA and Accenture, intelligent hardware and software combined with immense computing power ensure that every process in the warehouse becomes transparent and that orders can be processed faster, more securely, and more flexibly through continuous simulation. "Machine learning and neural networks will make the warehouse more efficient. Throughput will increase, manual and automated fleets can be optimized, and personnel can be deployed more efficiently. Ultimately, this will lead to significant cost savings for companies," anticipates Ulrike Just, member of the management board of Linde MH. "As one of the technology and innovation leaders in our industry, we have begun developing AI-based solutions. (...) We are planning pilot projects with our first major customers, as the associated investments will be particularly worthwhile for them."
networked industrial trucks
Linde MH's strategy begins with the networking of its manual industrial trucks. To this end, the intralogistics provider is currently developing a real-time localization system that functions both inside and outside warehouses. It enables seamless location tracking of every vehicle and utilizes ultra-wideband technology for low-infrastructure applications. Drivers receive instructions for navigating the warehouse or are notified of new or modified transport orders via an intelligent display. The system combines location data with vehicle data, such as steering angle. This allows the route to be adjusted in real time if, for example, there is excessive traffic on certain routes, leading to delays.
Not quite so gruesome... Image: NVIDIA
The coordinated collaboration and route optimization between manual and automated material handling equipment (AMRs) places significantly higher demands on computing power due to the increasing complexity. "Coordinating 100 or more vehicles requires a higher-level intelligence and hardware capable of processing such large amounts of data," explains Ron Winkler, Managing Director of the Digital Business Unit at Linde MH. "This is where the AI of the NVIDIA Omniverse platform comes into play. It creates a digital twin of the warehouse, a virtual 1:1 representation of the physical reality." Simulations can be run in fractions of a second within this digital twin. These simulations can be used either to optimize routes and the optimal coordination of AMRs and manual material handling equipment, or to make improvements to existing warehouse layouts.
Data stored digitally
What's special about it: Solutions for changing requirements or problems in the warehouse, such as current order or inventory changes, traffic density in specific warehouse areas, obstacles, or overhanging loads, are captured in real time, simulated in the digital twin, and recalculations are fed back to the vehicle control system – for example, that a late-arriving truck should be unloaded by the nearest forklift with the appropriate equipment. All physical data from industrial trucks (e.g., engine power, steering angle) as well as the infrastructure (e.g., racking locations, travel paths, machine operating times) are digitally stored in the NVIDIA Omniverse platform. The information, which continuously comes from sensors, intelligent vehicle and infrastructure cameras, warehouse management software, and vehicle control systems, is processed in the virtual space.
Intelligent camera systems on the infrastructure, as well as on the manual and automated vehicles, handle the tracking of load carriers, AMRs, and manually driven vehicles, as well as the monitoring of the cargo and storage areas. Their images are directly interpreted and processed by AI.
NVIDIACEO Jensen Huang
Specifically at the trade fair booth: A forklift driver uses his Linde electric forklift to bring goods into the warehouse's pre-zone. From the designated transfer area, a fully automated Linde high-lift pallet truck picks up the pallet and transports it into the warehouse. To seamlessly document and track materials and goods on the Omniverse platform, the manual forklift's mobile intelligent vehicle camera automatically takes a picture of the load when picking up the pallet and saves it to the system. Simultaneously, it detects people and obstacles and immediately adjusts the vehicle's behavior accordingly. The stationary cameras in the warehouse provide the system with information about the occupancy of storage locations and also register potential collisions with people, triggering a reduction in vehicle speed.
Recognizing strange things
But what happens if the forklift driver doesn't place the pallet as precisely on the designated area as an AGV normally requires? The digital twin, using stationary cameras, knows that the pallet has been placed and has forwarded the pick order to the Linde L-MATIC core. Thanks to the intelligent camera of the fully automated AGV, the AI recognizes the tilted pallet and searches for a solution – in this case, the appropriate approach for picking up the load. The same applies if boxes shift or part of the load overhangs. These problems also don't escape the stationary cameras. In this case, the AI would conclude that the goods shouldn't be picked up by an AGV. The Linde L-MATIC core remains stationary, and another transport order can be assigned to it. Instead, the AI has calculated which manually operated vehicle is nearby to take over the order.
“By configuring a digital warehouse model, every conceivable infrastructure and fleet configuration can be simulated in 3D and tested for efficiency,” explains Ron Winkler. “The AI can be continuously trained and refined. This creates the conditions for a warehouse ecosystem that proactively solves challenges and constantly improves.”
At LogiMAT: Hall 10 (Stand B21, B17 and C38)
Loading yard between halls 8 and 10, exhibition grounds between halls 9 and 10
