OpenUSD Conference Sessions

Join NVIDIA's product leaders and workflow specialists for an interactive discussion on how to get started building with OpenUSD and NVIDIA Omniverse. In either a group or 1:1 setting, discuss your use cases and challenges, get your questions answered, and learn how you can build USD-native applications.

Important: Connect with the Experts sessions are interactive sessions that give you a unique opportunity to meet, in either a group or one-on-one setting, with the minds behind NVIDIA’s products and research to get your questions answered. Attendees can meet with experts on a first-come, first-served basis.

Join our drop-in lab to develop your OpenUSD expertise, supported by on-site experts and guided by our OpenUSD AI tutor. This self-paced experience covers foundational terminology to best practices.

Beginners and experienced developers will gain practical skills through hands-on exercises covering OpenUSD vocabulary, schemas, composition arcs, asset structures, data exchange, and asset modularity.

Discover the power of NVIDIA NIM microservices for real-time guidance, or tap into the expertise of our OpenUSD specialists for in-depth knowledge. By the end of this lab, you’ll be ready to enhance your OpenUSD development and streamline workflows across industries.

Prerequisite(s):

• An understanding of fundamental programming concepts in Python 3 such as functions, loops, dictionaries and arrays and Python 3 related libraries.

In this course, we will be expanding on the concepts of assets from our previous Learn OpenUSD courses and applying them within the domain of robotics. We’ll learn about the benefits of a robot asset structure in OpenUSD and learn best practices by studying the asset structure utilized by the URDF Importer in Isaac Sim. We will gain insights on various optimizations that can be performed on a robot asset and experiment with the different techniques like mesh merging and instancing. Lastly, we will assemble the robot asset and an environment to construct a robot training scene.

Prerequisite(s):

• An understanding of fundamental programming concepts in Python 3 such as functions, loops, dictionaries and arrays and Python 3 related libraries.

This talk explores how Ansys leveraged NVIDIA Omniverse Blueprint for CAE using CUDA, Modulus, and Omniverse for the creation and deployment of digital twins. We'll dive into developing a high-fidelity CFD solver optimized for NVIDIA hardware (Grace, Hopper, Blackwell), enabling fast and accurate physics simulations. We'll then talk about the Integration of NVIDIA Modulus AI framework to easily build customized AI solutions that can improve designer productivity and quickly identify optimal design configurations. Finally, we'll show how we are leveraging Omniverse for real-time, photo-realistic visualization with examples. This combination of hardware and software solutions empowers engineers to build and deploy highly accurate digital twins with unprecedented speed, dramatically shortening product development cycles.

Important: Near capacity, highly suggest arriving early. Attendees are let in on a first-come, first-served basis.