Newton is a high-performance, GPU-accelerated physics simulation engine designed primarily for robotics research, machine learning, and advanced simulation workflows. Built on top of NVIDIA Warp, it leverages GPU parallelism to deliver scalable and efficient simulation environments that support rapid iteration and experimentation. The engine extends previous simulation frameworks by introducing differentiable physics capabilities, allowing it to integrate seamlessly with machine learning models and optimization pipelines. Newton supports OpenUSD for modern 3D scene representation and interoperability, making it suitable for complex simulation ecosystems. It is developed as a Linux Foundation project with contributions from major organizations like NVIDIA, Google DeepMind, and Disney Research, highlighting its relevance in cutting-edge robotics and AI development.
Features
- GPU-accelerated simulation using NVIDIA Warp
- Differentiable physics for machine learning integration
- OpenUSD support for modern 3D scene workflows
- Extensible architecture for custom simulation logic
- Integration with robotics and reinforcement learning frameworks
- Cross-platform support with GPU and CPU execution modes