NVIDIA-Omniverse/PhysX

NVIDIA PhysX SDK

What it solves

It provides a high-performance framework for simulating physical interactions in real-time, including rigid body dynamics, destruction, and fluids, which is essential for creating realistic virtual environments and robotics simulations.

How it works

The project consists of several integrated components: the core PhysX SDK for real-time physics simulation, the Blast SDK for simulating fractures and destruction, and the Flow SDK for fluid and fire effects. It also includes ovphysx, a C API with Python bindings that enables USD physics simulation and supports DLPack tensor interoperability for data exchange with AI frameworks.

Who it’s for

Developers building real-time simulations, robotics researchers using platforms like Isaac Sim, and creators of interactive 3D environments.

Highlights

  • Real-time simulation: A dedicated SDK for high-speed physics calculations.
  • Specialized simulation libraries: Includes Blast for destruction and Flow for fluids/fire.
  • Python bindings: ovphysx allows for easier integration and Python-based control.
  • Tensor interop: Supports DLPack for efficient data transfer between simulation and AI/ML tensors.

Related

  • Project
    Genesis-Embodied-AI/genesis-world

    A simulation platform for physical AI and robotics that combines a multi-physics engine, photo-realistic rendering, and a cross-platform compiler for scalable research.

  • Project
    google-deepmind/mujoco

    A high-performance physics engine for the fast and accurate simulation of articulated structures, widely used in robotics and machine learning research.

  • Project
    google/brax

    A fast, fully differentiable physics engine written in JAX for large-scale rigid body simulation and reinforcement learning training.

  • Project
    isaac-sim/IsaacSim

    A GPU-accelerated simulation platform for developing, testing, and training AI-powered robots in realistic virtual environments.

  • Project
    umfieldrobotics/OceanSim

    A GPU-accelerated underwater robot perception simulation framework that uses physics-based rendering to model visual and acoustic sensors and reduce the simulation-to-real gap.