Search Results for "python physics"

NVIDIA Isaac Sim is a high-fidelity robotics simulation platform built on NVIDIA Omniverse to develop, test, and validate AI-driven robots in physically accurate virtual environments. It supports a wide array of robotics formats (URDF, MJCF, CAD), includes GPU-accelerated physics, and features immersive RTX rendering and multisensory simulation. Realistic physics via GPU-accelerated engines and RTX ray tracing. Multi-sensor simulation (RGB-D cameras, Lidar, Radar, IMU, contact sensors)....

Isaac Lab is an open-source modular robotics learning framework built atop Isaac Sim. It simplifies research workflows across reinforcement learning, imitation learning, and motion planning by offering robust, GPU-accelerated simulation with realistic sensor and physics fidelity—ideal for sim-to-real robot training. Compatible and optimized for use with Isaac Sim versions (e.g., Sim 5.0 and 4.5). GPU-accelerated, high-fidelity physics and sensor simulation suitable for complex learning...

Microduck RL provides reinforcement-learning environments for training behaviors for Pollen Robotics' small bipedal Microduck robot. It is built on mjlab with MuJoCo Warp and trains PPO policies at a 50 Hz control rate. The repository includes tasks for walking, standing up, sitting, kicking, rolling, skating, crouching, and other physical behaviors. Its sim-to-real setup models actuator physics, backlash, domain randomization, and reward design. Trained policies can be exported to ONNX and...

Roboschool is a set of open source robot simulation environments for reinforcement learning, created as an alternative to the Mujoco physics engine. It integrates with OpenAI Gym and provides a variety of continuous control tasks, including humanoid locomotion, quadrupeds, and robotic arms. The library is built on the Bullet Physics engine, making it accessible without the licensing requirements of Mujoco. Roboschool includes training scripts and examples for applying reinforcement learning...

ARS is a physically-accurate robotics simulator written in Python. It's main purpose is to help researchers with to develop mobile manipulators and, in general, any multi-body system. It is open-source, modular, easy to learn and use, and can be a valuable tool in the process of robot design, in the development of control and reasoning algorithms, as well as in teaching and educational activities.

Moved to https://github.com/rdiankov/openrave An open-source, cross-platform, plugin-based robot planning environment for autonomous robotics. Includes services like collision detection, physics, (inverse) kinematics, sensors, robot controls, python bindings, and a network scripting environment.

PyMani is a program for robotic manipulator simulation. Designed for testing manipulator dynamics and as an educational tool for teaching the robotic parameters. This project currently uses Python, VPython, SymPy, PyODE, and wxPython.

A 3D robots simulator written in python. Uses ODE physics and OpenGL/Inventor graphics. A differential wheels robot is provided. There is no user interface but the code is small and is intended to be easily extended for your simulations.

A 2D robotic simulation built on top of the Box2D physics engine. The goal is to make the code ridiculously easy to understand and extend.