Bringing physical AI to the factory floor
Siemens and Humanoid have reached a milestone in their work to bring physical AI from vision to industrial reality
Humanoid’s HMND 01 wheeled Alpha humanoid robot, developed using Nvidia's physical AI stack, has been successfully tested in operation at Siemens’ electronics factory in Erlangen, Germany, performing autonomous logistics tasks. This expands on the Siemens and Nvidia strategic partnership to build the world’s first fully AI-driven, adaptive manufacturing sites.
Physical AI in manufacturing
Physical AI could transform how goods are made. Bridging the gap between AI research and the demands of a factory requires a high-performing ecosystem: advanced AI-compute and simulation, a proven robotics platform, and deep industrial automation infrastructure.
The HMND 01 Alpha robot was deployed in Siemens’ logistics operations, where it autonomously executed tote-handling tasks, including picking, transporting, and placing containers for human operators. All target performance metrics were met, including a throughput of 60 tote moves per hour, uptime exceeding eight hours, and autonomous pick-and-place success rates above 90%.
The industrial backbone
A humanoid robot’s value is in becoming a fully integrated, collaborative asset on the shop floor, meaning real-time data exchange with production systems and other Autonomous Guided Vehicles, synchronised workflows with other machinery and human operators, and adaptive behaviour that responds to changing conditions. Without this integration, even the most sophisticated robot remains an isolated feature.
Siemens provides this layer via its Siemens Xcelerator portfolio, which includes a comprehensive digital twin, AI-enabled perception, integrated control, PLC-robot interfaces, fleet management, industrial communication networks, and high-performance drives. These technologies form the digital backbone and automation infrastructure that ensures humanoid robots operate efficiently and within the broader factory environment, resulting in a factory-grade model for deploying humanoids in any industrial setting.
Accelerating intelligence
Humanoid has integrated Nvidia’s full physical AI stack into the HMND 01 platform, including Nvidia Jetson Thor for edge compute, Nvidia Isaac Sim for simulation, and Nvidia Isaac Lab for reinforcement learning and policy training. The result is a compression of development timelines. Simulation-first hardware design also enabled the optimisation of actuator selection, joint strength, and mass distribution virtually, reducing prototype development to seven months.
Deepu Talla, vice president of Robotics and Edge AI at Nvidia, said, “Factories of the future demand robots that can perceive, reason, and adapt autonomously alongside human workers, tackling the labour shortages and operational complexity that traditional automation struggled to handle. With Siemens providing the industrial integration backbone and Humanoid deploying Nvidia's full physical AI stack, from simulation-first training to real-time edge inference, this deployment paves the way for humanoid robots meeting real production targets on a live factory floor."
Building factory-grade humanoids
Humanoid designed the HMND 01 Alpha, a humanoid robot for industrial environments. Combining an omnidirectional wheeled mobility platform with advanced manipulation capabilities, powered by KinetIQ, the HMND 01 is designed to work in human-centric spaces, adapting to diverse tasks and handling complex actions.
Artem Sokolov, CEO and founder of Humanoid, said, “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. 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.”
