Hexagon Collaborates with NVIDIA on New Humanoid AI, AEON

NewsHexagon Collaborates with NVIDIA on New Humanoid AI, AEON

Transforming the Workforce with Robotics: Hexagon’s AEON Enters the Scene

In a world grappling with a significant labor shortage, where 50 million positions remain unfilled across various sectors such as manufacturing and logistics, innovation becomes a critical necessity. Hexagon, a leader in measurement technologies, is stepping up to the challenge by developing humanoid robots to fill this gap. These robots are designed to enhance productivity and efficiency in industries that are heavily dependent on skilled labor.

Bridging the Skills Gap with Robotics

Industries like manufacturing and logistics are heavily reliant on skilled workers to perform tasks that are often prone to human error. One such vital task is reality capture, which involves using high-precision scanners to collect digital data. This data is then used to replicate the real world in simulations, offering significant insights for various applications.

At the recent Hexagon LIVE Global conference, the company’s robotics division unveiled its latest innovation, AEON. This humanoid robot, developed in collaboration with NVIDIA, is engineered to support a wide range of industrial applications. From manipulation and asset inspection to reality capture and operator support, AEON is set to revolutionize the way industries function. Hexagon plans to deploy AEON across multiple sectors including automotive, transportation, aerospace, manufacturing, warehousing, and logistics.

AEON’s Future Applications

AEON is designed with several future applications in mind:

  1. Reality Capture: This involves the automatic planning and scanning of assets, industrial spaces, and environments to generate 3D models. The captured data is crucial for advanced visualization and collaboration, primarily through the Hexagon Digital Reality (HxDR) platform, which powers the Hexagon Reality Cloud Studio (RCS).
  2. Manipulation: AEON is capable of sorting and moving parts in various industrial and manufacturing settings, streamlining operations and reducing the risk of human error.
  3. Part Inspection: The robot can check parts for defects or ensure they adhere to specific standards and specifications, enhancing quality control measures.
  4. Industrial Operations: AEON is also adept at performing highly dexterous technical tasks such as machinery operations, teleoperation, and scanning parts using high-end scanners.

    Deepu Talla, Vice President of Robotics and Edge AI at NVIDIA, emphasized the significance of this development, stating that the age of general-purpose robotics has arrived, thanks to technological advancements in simulation and physical AI. AEON exemplifies the integration of NVIDIA’s three-computer robotics platform, making a substantial leap forward in addressing critical industry challenges.

    Harnessing NVIDIA’s Advanced Technologies

    To bring AEON to life, Hexagon utilized NVIDIA’s sophisticated technology framework, known as the "three computers" for robotics. This framework includes:

    • AI Supercomputers: These are used to train and fine-tune powerful foundation models essential for developing physical AI systems.
    • NVIDIA Omniverse Platform: Running on NVIDIA OVX servers, this platform tests and optimizes models in simulated environments using real and physically-based synthetic data.
    • NVIDIA IGX Thor Robotic Computers: These are essential for running the models once they are developed.

      Hexagon is exploring further possibilities by using NVIDIA accelerated computing to enhance the NVIDIA Isaac GR00T N1.5 open foundation model. This model aims to improve robot reasoning and policies, and the Isaac GR00T-Mimic is used to generate vast amounts of synthetic motion data from a few human demonstrations.

      AEON learns many of its skills through simulations powered by the NVIDIA Isaac platform. Hexagon employs NVIDIA Isaac Sim, a reference robotic simulation application built on Omniverse, to simulate complex robot actions such as navigation, locomotion, and manipulation. These skills are refined using reinforcement learning in NVIDIA Isaac Lab, an open-source framework for robot learning.

      This simulation-first approach has enabled Hexagon to fast-track its robotic development, allowing AEON to master core locomotion skills in just 2-3 weeks, a process that would traditionally take 5-6 months before real-world deployment.

      AEON is also equipped with NVIDIA Jetson Orin onboard computers, allowing it to autonomously move, navigate, and perform tasks in real time. This enhances its speed and accuracy, especially when operating in complex and dynamic environments. Furthermore, Hexagon plans to upgrade AEON with NVIDIA IGX Thor to ensure functional safety for collaborative operation.

      Arnaud Robert, President of Hexagon’s robotics division, highlighted the goal behind AEON’s development: to design an intelligent, autonomous humanoid that addresses the real-world challenges shared by industrial leaders. By leveraging NVIDIA’s full-stack robotics and simulation platforms, Hexagon has delivered a humanoid robot that combines advanced mechatronics, multimodal sensor fusion, and real-time AI.

      Bringing Data to Life Through Reality Capture and Omniverse Integration

      AEON will undergo pilot testing in factories and warehouses, where it will scan everything from small precision parts and automotive components to large assembly lines and storage areas. The captured data will come to life in RCS, a platform that facilitates collaboration, visualization, and sharing of reality-capture data by tapping into HxDR and NVIDIA Omniverse running in the cloud. This approach eliminates the need for local infrastructure.

      Lucas Heinzle, Vice President of Research and Development at Hexagon’s robotics division, noted the advantages of digital twins, which are virtual replicas of physical entities. Although adoption has been challenging in some industries, AEON’s sophisticated sensor suite enables the integration of reality data capture with NVIDIA Omniverse. This streamlines workflows for customers and moves industries closer to making digital twins a mainstream tool for collaboration and innovation.

      What Lies Ahead for AEON?

      Hexagon’s adoption of the OpenUSD framework and development on Omniverse means high-fidelity digital twins can be generated from scanned data. This establishes a data flywheel, a continuous loop of data collection and analysis, to keep training AEON. This initiative with Hexagon is shaping the future of physical AI, offering scalable and efficient solutions to tackle challenges faced by industries reliant on real-world data capture.

      For those interested in learning more about AEON, it’s worth exploring the Hexagon LIVE keynote, presentations, and additional resources that delve into the robot’s capabilities and potential impact on various industries.

      In conclusion, Hexagon’s introduction of the AEON humanoid robot marks a significant milestone in the evolution of robotics and AI. By addressing the pressing issue of labor shortages and enhancing operational efficiency across multiple sectors, AEON is poised to transform the landscape of industrial operations. As technology continues to advance, the integration of robotics like AEON into everyday workflows will become increasingly commonplace, heralding a new era of innovation and productivity.

For more Information, Refer to this article.

Neil S
Neil S
Neil is a highly qualified Technical Writer with an M.Sc(IT) degree and an impressive range of IT and Support certifications including MCSE, CCNA, ACA(Adobe Certified Associates), and PG Dip (IT). With over 10 years of hands-on experience as an IT support engineer across Windows, Mac, iOS, and Linux Server platforms, Neil possesses the expertise to create comprehensive and user-friendly documentation that simplifies complex technical concepts for a wide audience.
Watch & Subscribe Our YouTube Channel
YouTube Subscribe Button

Latest From Hawkdive

You May like these Related Articles

LEAVE A REPLY

Please enter your comment!
Please enter your name here

This site uses Akismet to reduce spam. Learn how your comment data is processed.