We have now released v0.3.0! Please use the latest version for the best experience.


Orbit is a unified and modular framework for robot learning that aims to simplify common workflows in robotics research (such as RL, learning from demonstrations, and motion planning). It is built upon NVIDIA Isaac Sim to leverage the latest simulation capabilities for photo-realistic scenes, and fast and efficient simulation. The core objectives of the framework are:

  • Modularity: Easily customize and add new environments, robots, and sensors.

  • Agility: Adapt to the changing needs of the community.

  • Openness: Remain open-sourced to allow the community to contribute and extend the framework.

  • Battery-included: Include a number of environments, sensors, and tasks that are ready to use.

For more information about the framework, please refer to the paper [MYY+23]. For clarifications on NVIDIA Isaac ecosystem, please check out the Frequently Asked Questions section.

Example tasks created using orbit


If you use Orbit in your research, please use the following BibTeX entry:

   author={Mittal, Mayank and Yu, Calvin and Yu, Qinxi and Liu, Jingzhou and Rudin, Nikita and Hoeller, David and Yuan, Jia Lin and Singh, Ritvik and Guo, Yunrong and Mazhar, Hammad and Mandlekar, Ajay and Babich, Buck and State, Gavriel and Hutter, Marco and Garg, Animesh},
   journal={IEEE Robotics and Automation Letters},
   title={Orbit: A Unified Simulation Framework for Interactive Robot Learning Environments},


NVIDIA Isaac Sim is provided under the NVIDIA End User License Agreement. However, the Orbit framework is open-sourced under the BSD-3-Clause license. Please refer to License for more details.

Table of Contents#

Source API

Indices and tables#