A humanoid robot powered by NVIDIA’s physical AI stack has successfully completed autonomous logistics operations at a Siemens electronics factory in Erlangen, Germany.
The deployment forms part of a wider collaboration between UK-based robotics firm Humanoid, Siemens and NVIDIA to develop fully AI-driven, adaptive manufacturing environments.
The first phase of the project, announced in January, saw the Humanoid team built a physical twin to support testing, optimisation and rapid iteration throughout the proof-of-concept.
Now, Humanoid’s HMND 01 Alpha robot has been tested in live factory conditions, where it autonomously carried out tote-handling tasks. The system achieved target throughput rates of up to 60 tote moves per hour, with uptime exceeding eight hours and pick-and-place accuracy surpassing 90%.
The robot integrates with Siemens’ Xcelerator platform, enabling real-time data exchange, synchronised workflows and coordination with other automated systems and human workers.
Humanoid built the system using NVIDIA technologies, including Jetson Thor for edge computing, Isaac Sim for simulation and Isaac Lab for reinforcement learning and policy training. This enabled the company to accelerate development timelines and optimise performance through simulation-led design.
“Our collaboration with Siemens and NVIDIA gives us a powerful advantage by combining NVIDIA’s leading AI infrastructure, simulation tools, and frameworks with Siemens’ deep industrial expertise and integration capabilities,” said Artem Sokolov, CEO and founder of Humanoid. “Together, we’ve proven that humanoid robots are ready for real-world industrial deployment.”
For details on how to enter the 30th Supply Chain Excellence Awards or for sponsorship opportunities, please visit the official website
