TechPrufer
Get started
NVIDIA
NVIDIA logoNVIDIA · Feature trail

Omniverse RTX Sensor Simulation SDK

2 posts · Jul 2026 – Aug 2026

What this trail covers

This feature thread tracks the evolution of integrating NVIDIA Omniverse RTX sensor simulation capabilities into existing applications. Initial efforts focused on providing modular APIs, like ovrtx, within the NVIDIA Agent Toolkit. ovrtx acts as a lightweight C/Python SDK enabling applications to configure render and sensor outputs (camera, lidar, radar) from OpenUSD scenes, step simulation from the app loop, and retrieve output tensors. It integrates with other Omniverse libraries (ovphysx, ovstream, ovstorage, ovstage) for multi-modal simulation and visualization pipelines essential for synthetic data generation, digital twins, and physical AI validation in advanced 3D and industrial domains.

All NVIDIA trails
  1. Scale AV Perception Across Vehicle Platforms with NVIDIA Omniverse NuRec | NVIDIA Technical BlogThis post introduces NVIDIA Omniverse NuRec, a system that reconstructs real-world driving scenes using 3D Gaussian splatting and renders new camera views for target vehicle configurations. It details a workflow for adapting AV perception models to new carlines by pairing reconstructed scenes with target rig configurations, rendering new views, refining frames with NVIDIA Harmonizer, and training perception models on the output. The post also highlights the Physical AI NuRec Dataset and the nurec-skills repository for agent-based workflow automation.
  2. Integrate NVIDIA Omniverse RTX Sensor Simulation Into Existing Apps | NVIDIA Technical BlogThis post details the integration of ovrtx, the RTX sensor simulation library within the NVIDIA Agent Toolkit, into existing application workflows. It outlines a five-step process for developers to bring Omniverse RTX sensor simulation into their applications while maintaining host application control. Key components like the Omniverse RTX Renderer, ovstage, OpenUSD, and RenderProducts/RenderVars are explained. The post provides pseudo-code for integration and highlights examples in PTC Onshape Render Studio and a SimReady Blender workflow, emphasizing the SDK's role in generating camera, lidar, radar, and semantic segmentation outputs from OpenUSD scenes.