TechPrufer
Sign inGet started

Blogs›NVIDIA›Omniverse RTX Sensor Simulation SDK

Omniverse RTX Sensor Simulation SDK

Omniverse RTX Sensor Simulation SDK

1
posts
2026

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) to support production-oriented, multi-modal simulation and visualization pipelines for synthetic data generation, digital twins, and physical AI validation. The core principle is to allow host applications to maintain control over their architecture, UI, data model, and workflow while leveraging RTX-based sensor simulation.

2026

Integrate NVIDIA Omniverse RTX Sensor Simulation Into Existing Apps | NVIDIA Technical Blog

7/20/2026

This post introduces ovrtx, a new modular API within the NVIDIA Agent Toolkit, as a lightweight C/Python SDK for integrating NVIDIA Omniverse RTX sensor simulation (camera, lidar, radar) into existing applications. It details the integration process, which involves creating an ovrtx renderer, loading OpenUSD content, defining RenderProducts and RenderVars, stepping simulation from the application loop, and mapping results back to CPU/GPU memory. The post highlights the use of ovstage for shared USD scene runtime and emphasizes that host applications retain control over the simulation workflow.