PyBullet is a Python binding to the Bullet Physics SDK, created by Erwin Coumans in 2016. Bullet is one of the oldest open physics engines — used in AAA games (Grand Theft Auto, Red Dead Redemption), movies (DreamWorks Madagascar, How to Train Your Dragon, Disney's Tangled), and in robotics. PyBullet brings Python's simplicity to this mature technology.
PyBullet features: (1) one-command install via pip install pybullet, (2) all demos run natively in the browser via WebAssembly, (3) URDF/SDF/MJCF support, (4) built-in reference models (KUKA, Franka, Husky, R2D2, Atlas, Cassie, Laikago, Minitaur, quadrupeds, drones), (5) simple API for deep RL (gym-like wrapper), (6) the physics engine runs on CPU — predictable and cheap to launch.
PyBullet dominated learning-based robotics in 2018–2022, used in Stanford CS231n, MIT 6.832, Berkeley CS287, and publications from Google Brain (Quadruped Locomotion, Soft Actor-Critic), DeepMind (a DM Control alternative), and Facebook AI Habitat (early versions). After 2023 it was partly displaced by MuJoCo (precision) and Isaac Lab (GPU scale), but it remains popular for teaching and lightweight projects.
Simulation software is used for modelling, testing, and validating robot behaviours, sensor characteristics, environments, and algorithms without requiring physical hardware. It enables safe, repeatable, and cost-effective development cycles. Common robotics simulators include Gazebo, Isaac Sim (NVIDIA), MuJoCo, PyBullet, and Webots, each offering different trade-offs between physics accuracy, rendering fidelity, and integration with middleware frameworks such as ROS 2.
A Developer Tool is software designed to support the development workflow, including configuration, debugging, testing, monitoring, validation, and integration of robotic and embedded systems. Examples include IDE plugins, visual debuggers, log analysers, hardware-in-the-loop (HIL) test harnesses, and code-generation utilities specific to robotics platforms.
An API Library is a software package that exposes programmatic interfaces for communicating with a device, service, or system. In robotics it typically forms a lightweight integration layer built on top of the manufacturer's official API or an open-source project, abstracting low-level protocol details and providing language-native bindings (Python, C++, Java, etc.).
Robot Control denotes the role of software responsible for motion control, command execution, coordination of actuating elements and the direct operational logic of the robot.
A family of open-source and commercial physics simulators for robotics: Gazebo, Webots, MuJoCo, PyBullet, Isaac Lab, CoppeliaSim, Genesis, and related tools. Common denominator: rigid-body physics engine, URDF/MJCF model support, ROS/ROS 2 integration, sim-to-real transfer.
Google Brain Minitaur (locomotion DRL), Stanford ALOHA early versions, MIT 6.832 (Underactuated Robotics), Berkeley CS287 (Advanced Robotics), Boston Dynamics Spot Mini researcher models, OpenAI Gym Robotics environments (pre-MuJoCo era).
github.com/bulletphysics/bullet3 13k★, pypi.org/project/pybullet 8M+ downloads, > 5000 scientific publications citing PyBullet/Bullet.
Boston Dynamics bipedal humanoid robot. The fully electric generation unveiled in 2024 succeeds the hydraulic Atlas that was retired after more than a decade of research.
Tutor Intelligence industrial robot designed for palletizing, depalletizing and case-picking in warehouses and factories, offered as Robotics-as-a-Service from $14/hr.
Bipedal humanoid robot by Unitree Robotics, designed as a compact research, development, and developer platform.
The lightest of major simulators; runs on Raspberry Pi 4 and budget laptops.
License family: Permissive
Update for Python 3.12, performance fixes.
Apple Silicon (M1) support.
Gym-like API, OpenAI Gym Robotics support.
URDF and SDF support, ready-made KUKA/Franka models.
First public release, integrating Bullet 2.85.
