DeepMind has opened the source code for the MuJoCo (Multi-Joint dynamics with Contact) engine for simulating physical processes and switched the project to an open development model, which implies the possibility of participation in the development of community representatives. The project is seen as a platform for research and collaboration on new technologies related to the simulation of robots and complex mechanisms. The code is published under the Apache 2.0 license. Linux, Windows and macOS platforms are supported.
MuJoCo is a library that implements an engine for simulating physical processes and modeling articulated structures interacting with the environment, which can be used in the development of robots, biomechanical devices and artificial intelligence systems, as well as in the creation of graphics, animation and computer games. The engine is written in C, does not use dynamic memory allocation, and is optimized for maximum performance.
MuJoCo allows you to manipulate objects at a low level, while providing high precision and extensive modeling capabilities. Models are defined using the MJCF scene description language, which is based on XML and compiled using a special optimizing compiler. In addition to MJCF, the engine supports loading files in the universal URDF format (Unified Robot Description Format). MuJoCo also provides a graphical interface for interactive 3D visualization of the simulation process and rendering of the results using OpenGL.
Key features:
- Simulation in generalized coordinates, excluding the violation of joints.
- Reverse dynamics, determined even in the presence of contact.
- Using convex programming for a unified formulation of constraints in continuous time.
- Ability to set various constraints, including soft touch and dry friction.
- Simulation of particle systems, fabrics, ropes and soft objects.
- Executive elements (actuators), including motors, cylinders, muscles, tendons and crank mechanisms.
- Solvers based on Newton's methods, conjugate gradients and Gauss-Seidel.
- Possibility of using pyramidal or elliptical friction cones.
- Using the choice of numerical integration methods of Euler or Runge-Kutta.
- Multithreaded discretization and approximation by the method of finite differences.
Source: opennet.ru