Germany’s Otto Group is collaborating with Nvidia to improve supply chain operations through intelligent robotics.

This initiative will scale the network-wide deployment of a robotic coordination layer, powered by Nvidia Omniverse libraries and Isaac Sim, across a multitude of Otto Group’s 120 logistics locations.

The goal is to train robots in a simulation environment for intelligent robotic automation, setting an industry benchmark for improved efficiency of logistics operations, scalability and integration.

The robotic coordination layer is seen to be crucial for seamlessly integrating and coordinating diverse robotic systems with existing and new partners. This initiative follows recent investments in logistics and robotics. The Hermes Fulfilment logistics centre in Loehne, Germany, will serve as the first full-scale operational site and blueprint for further roll-outs, with IT services specialist Reply (www.reply.com) having created the digital twin. Following this, Otto Group will develop the layer’s core, including its integration interfaces, and will assume governance.

The robotic coordination layer is an intelligent virtual navigation and communication system designed for all robots in the Otto Group’s logistics centres. Nvidia AI infrastructure, together with its Omniverse libraries and Isaac (developer.nvidia.com/isaac) for AI robotics, provides the foundational infrastructure for digitising and optimising supply chain operations.

This software is available as a single, ready-to-run offering from the Google Cloud Marketplace. By creating physics-based digital twins of Otto Group’s existing distribution and fulfilment centres, Otto can simulate, train and deploy different kinds of robots, including autonomous mobile and stationary robots, faster. This ensures seamless collaboration among robots across the supply chain, aiming to enhance customer experience, optimise peak management and boost overall efficiency.

“More than three years ago we embarked on a journey to deploy AI and robotics in the field of logistics,” said Kay Schiebur from Otto Group (www.ottogroup.com). “Our experiences to date have shown the huge potential for improving efficiency and service. With Nvidia and Reply, we are now ready to take intelligent automation to the next level. This partnership will provide the fundamental structure – a truly innovative way for our robots to communicate – allowing us to quickly scale up robotics in our complex operations, strengthening our leadership in responsible business, especially here in Europe.”

Azita Martin, vice president at Nvidia (www.nvidia.com), added: “Physical AI is redefining what’s possible in supply chain, transforming warehouses from static facilities into dynamic, responsive systems that can adapt in real time. Leveraging Nvidia RTX Pro 6000 and Omniverse on GCP, together with Isaac Sim, Otto Group is training a fleet of robots using physics-based simulation, creating a scalable blueprint for the future of logistics, where fleets of robots and intelligent systems collaborate seamlessly to boost efficiency and drive agility.”

The robotic coordination layer connects robot fleets in the real warehouse to a digital twin that displays the real-time locations and movements of all robots, enabling seamless, interactive control and management of operations. Developed by Reply, this uses reality-capture techniques and post-processing from sensors and cameras mounted on Boston Dynamics’ Spot robot (bostondynamics.com/products/spot/) as it moves through the warehouse. Once established, the digital twin enables virtual reconfiguration of warehouse areas for process optimisation and dynamic simulations to support peak management.

For example, different volume scenarios can be simulated to determine optimal robot and personnel requirements. Concurrently, the layer integrates with robotic fleet management tools and the warehouse management system to coordinate and communicate with various robotic fleets, all visualised and managed within the digital twin.

“Creating a digital twin is more than just mapping a space, it’s about enabling intelligent orchestration at scale,” said Kai Uwe Ernst, executive partner at Reply. “By combining Nvidia’s cutting-edge technologies with our expertise in AI and robotics, we’re laying the foundation for a new standard in robotic coordination. This system will allow different robotic fleets to communicate and collaborate seamlessly, unlocking new levels of efficiency and adaptability in logistics operations.”

The Hermes Fulfilment’s logistics centre in Loehne will serve as the blueprint and first full-scale operational site for this innovation, with plans for the system to be rolled out network-wide. The initial development phase involves an investment in the double-digit million euro range. The long-term vision for the coordination layer is to digitise the entire warehouse ecosystem, a goal enabled by the digital twin created using Nvidia AI infrastructure. It will act as the central operating system, seamlessly connecting, managing, and operating a broad spectrum of assets, from robotic fleets and conventional automation technology to integrated sensors for functions such as pallet size detection and gate control.