Add RTX Rendering and Sensor Simulation to Your Physical AI App with NVIDIA Omniverse ovrtx

Add RTX rendering and sensor simulation capabilities to an existing physical AI application with the NVIDIA Omniverse ovrtx library, without building a full Omniverse Kit app. In this overview, you’ll walk through the ovrtx library GitHub repo, run the minimal example, connect Python, C, and C++ applications to Omniverse RTX rendering processes, and generate sensor outputs for robotics and synthetic data workflows. You’ll also see how ovrtx skills help AI coding agents understand the library and move from prompt to implementation. What you'll build and explore: 👉 Run the minimal Python example with `uv` in under five minutes 👉 Connect an application to Omniverse RTX rendering and load an OpenUSD scene 👉 Generate camera, lidar, radar, and semantic segmentation outputs for physical AI workflows 👉 Explore tiled rendering, USD material introspection, and Vulkan interop examples 👉 Use ovrtx skills to help AI coding agents understand the library and tested workflows Start Building: 🔗 Explore code examples and skills on GitHub: https://github.com/nvidia-omniverse/ovrtx 🔗 Get started with ovrtx docs and setup: https://nvidia-omniverse.github.io/ovrtx/ About NVIDIA Omniverse: NVIDIA Omniverse™ is a platform that enables developers to easily integrate Universal Scene Description (OpenUSD) and RTX rendering technologies into existing software tools and simulation workflows for building AI systems. Please note that this video is intended for informational purposes only, and should not be treated as a source for official product or company announcements. ⬇️ Get Started → https://nvda.ws/4cZAZO1 👀 Explore OpenUSD → https://nvda.ws/3CeozBQ 👥 Join the Community → https://nvda.ws/3ZMfc6e #OpenUSD #3D #DigitalTwins #NVIDIAOmniverse