Newton Physics Documentation#


Newton is a GPU-accelerated, extensible, and differentiable physics simulation engine designed for robotics, research, and advanced simulation workflows. Built on top of NVIDIA Warp and integrating MuJoCo Warp, Newton provides high-performance simulation, modern Python APIs, and a flexible architecture for both users and developers.

Key Features#

  • GPU-accelerated: Leverages NVIDIA Warp for fast, scalable simulation.

  • Multiple solver implementations - XPBD, VBD, Mujoco, Featherstone, Euler

  • Modular design - Easily extendable with new solvers and components

  • Differentiable: Supports differentiable simulation for machine learning and optimization.

  • Rich Import/Export: Load models from URDF, MJCF, USD, and more.

  • Open Source: Maintained by Disney Research, Google DeepMind, and NVIDIA.

Learn More

For a deep conceptual introduction, see the DeepWiki Newton Physics page.

High-Level Architecture#

        graph TD
A[ModelBuilder] -->|builds| B[Model]
B --> C[State]
C --> D[Solver]
D --> C
B --> F[Renderer]
C --> F
G[Importer] --> A
I[Application] --> A
F --> H[Visualization]

  • ModelBuilder: Constructs models from primitives or imported assets.

  • Model: Encapsulates the physical structure, parameters, and configuration.

  • State: Represents the dynamic state (positions, velocities, etc.).

  • Solver: Advances the simulation by integrating physics.

  • Renderer: Visualizes the simulation in real-time or offline.

  • Importer: Loads models from external formats (URDF, MJCF, USD).