UK-designed humanoid performs logistics tasks at Siemens factory
16 April 2026 
Siemens and the UK robot developer Humanoid say they have successfully used Humanoid’s HMND 01 Alpha wheeled robot to perform logistics tasks at Siemens’ electronics factory in Erlangen, Germany. In what they describe as “a landmark milestone in the journey to bring physical AI from vision to industrial reality”, the robot executed tote-handling tasks autonomously – including picking, transporting and placing containers. All of the performance goals were met, including 60 tote moves per hour, an uptime of more than 8 hours, and autonomous pick-and-place success rates above 90%.
The robot incorporates an Nvidia physical AI stack. The trials formed part of Siemens’ and Nvidia’s strategic partnership to build the world’s first fully AI-driven, adaptive manufacturing sites.
According to Siemens, a humanoid robot’s true value is in becoming an integrated, collaborative asset on the shop floor. This involves exchanging real-time data with production systems and other autonomous vehicles, synchronising workflows with other machinery and human operators, and responding dynamically to changing conditions. Without this deep integration, it adds, even the most sophisticated robot would remain isolated.
Siemens provides the critical layer to achieve this through its Xcelerator portfolio, which includes digital twins, AI-enabled perception systems, integrated control and PLC-robot interfaces, as well as fleet management software, industrial communications and high-performance drives. Together, these technologies form the digital backbone and automation infrastructure for humanoid robots to operate efficiently and in concert with the wider factory environment.
London-based Humanoid’s HMND 01 Alpha robot has been designed for industrial environments. It combines an omnidirectional wheeled platform with advanced manipulation capabilities, powered by a proprietary AI framework called KinetIQ. The robot has been engineered to work in human-centric spaces, adapting to diverse tasks and handling complex actions.
The robot’s physical AI stack includes Nvidia’s Jetson Thor for edge computing, Isaac Sim for simulation and Isaac Lab for reinforcement learning and policy training. The result is a said to be a “dramatic” compression of development timelines. Simulation-first hardware design has also allowed the development team to optimise its choice of actuators, joint strength and mass distribution virtually, cutting the time it took to develop a prototype from a typical 18–24 months to just seven months.
“Our mission is to create humanoid robots that perform not only in controlled lab settings, but also in real-world factory environments, handling meaningful industrial tasks,” says Humanoid’s founder and CEO, Artem Sokolov. “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. Together, we’ve proven that humanoid robots are ready for real-world industrial deployment.”
Humanoid’s work with Siemens is latest in a series of collaborations with other companies including Ford, Schaeffler, SAP and Martur Fompak.
According to Siemens, physical AI – the discipline of training intelligent machines to perceive, reason and act in the physical world – is poised to transform how goods are made.
