bulletphysics/bullet3

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

What it solves

Bullet Physics SDK provides a professional-grade toolkit for real-time collision detection and multi-physics simulation. It enables developers to simulate physical interactions in environments used for virtual reality (VR), gaming, visual effects, and robotics.

How it works

Written primarily in C++, the SDK handles the complex mathematics of how objects collide and react physically. It offers a high-performance core that can be extended via Python bindings (PyBullet) for easier integration with machine learning and robotics workflows. For high-performance needs, it includes experimental support for GPGPU execution via OpenCL, allowing collision detection and rigid body dynamics to run directly on the GPU.

Who it’s for

This tool is designed for developers and researchers working in robotics, reinforcement learning, VR, and game development who need a reliable, real-time physics engine.

Highlights

  • Multi-platform support: Works across Windows, Linux, Mac OSX, iOS, and Android.
  • PyBullet bindings: Specialized Python support tailored for reinforcement learning and robotics research.
  • GPU Acceleration: Experimental OpenCL support for executing physics calculations on high-end GPUs.
  • Broad Application: Used for everything from simple game physics to complex humanoid robot simulations.

Related

  • Project
    carla-simulator/carla

    CARLA is an open‑source, Unreal‑Engine‑based autonomous‑driving simulator that provides realistic urban environments, customizable sensor suites, and a Python API for training, testing, and benchmarking self‑driving systems.

  • Project
    pollen-robotics/microduck

    A control system for a tiny biped robot that uses reinforcement learning policies to walk, roll, and interact with its environment.

  • Project
    google-deepmind/mujoco

    MuJoCo is a general-purpose physics engine from Google DeepMind for simulating articulated structures that interact with their environment. It provides a high-performance C API, Python bindings, and interactive 3D visualization, making it a popular tool in robotics and machine learning research.

  • Project
    ArduPilot/ardupilot

    ArduPilot is a comprehensive, open-source autopilot software suite designed to control a wide range of autonomous vehicles, from drones and rovers to submarines.