Humanoid robot runs factory machines, sorts parts, and scans assets using NVIDIA tech

General-purpose robot for industrial precision

AEON is equipped to handle everything from part manipulation and inspection to asset scanning and operational support.

It’s built to perform tasks typically prone to human error, especially those that involve handling sensitive components or working in dynamic, unpredictable settings.

“Our goal with AEON was to design an intelligent, autonomous humanoid that addresses the real-world challenges industrial leaders have shared with us over the past months,” said Arnaud Robert, president of Hexagon’s robotics division.

The company’s design philosophy focused on combining “advanced mechatronics, multimodal sensor fusion and real-time AI.”

Simulation-trained, factory-ready

To accelerate AEON’s development, Hexagon trained the robot almost entirely in virtual environments using NVIDIA’s Isaac platform.

Through Isaac Sim and Isaac Lab, AEON learned navigation, locomotion, and manipulation skills in simulation before ever touching a factory floor.

This approach allowed AEON to master core movement functions within just two to three weeks, a process that typically takes several months through traditional robotic training methods.

Running on NVIDIA’s robotics stack

At the core of AEON’s performance is NVIDIA’s full-stack robotics infrastructure. The robot runs on Jetson Orin computers for real-time decision-making and will soon be upgraded to NVIDIA’s IGX Thor platform to enable collaborative safety features.

“The age of general-purpose robotics has arrived, due to technological advances in simulation and physical AI,” said Deepu Talla, vice president of robotics and edge AI at NVIDIA.

“Hexagon’s new AEON humanoid embodies the integration of NVIDIA’s three-computer robotics platform and is making a significant leap forward in addressing industry-critical challenges.”

AEON also draws on NVIDIA’s Isaac GR00T foundation model and Mimic tools to learn from human demonstrations and generate synthetic motion data to expand its skillset.

Connecting physical AI to cloud-based collaboration

One of AEON’s standout features is its ability to tie physical data capture to digital platforms.

The robot autonomously scans everything from small parts to full assembly lines, uploading the data to Hexagon’s Reality Cloud Studio via HxDR. There, teams can collaborate using 3D models built in NVIDIA Omniverse.

“AEON’s sophisticated sensor suite enables the integration of reality data capture with NVIDIA Omniverse, streamlining workflows for our customers and moving us closer to making digital twins a mainstream tool for collaboration and innovation,” said Lucas Heinzle, VP of R&D at Hexagon Robotics.

With pilot deployments expected in factories and warehouses, AEON signals a shift toward scalable, simulation-driven automation for the next generation of industrial operations.