OmniDrones is an open-source platform designed for reinforcement learning research on multi-rotor drone systems. Built on Nvidia Isaac Sim, OmniDrones features highly efficient and flxeible simulation that can be adopted for various research purposes. We also provide a suite of benchmark tasks and algorithm baselines to provide preliminary results for subsequent works.
For usage and more details, please refer to the documentation.
Welcome to join our Discord for discussions and questions!
The initial release of OmniDrones is developed based on Isaac Sim 2022.2.0. It can be found at the release branch. The current version is developed based on Isaac Sim 2023.1.0.
Please cite this paper if you use OmniDrones in your work:
@misc{xu2023omnidrones,
title={OmniDrones: An Efficient and Flexible Platform for Reinforcement Learning in Drone Control},
author={Botian Xu and Feng Gao and Chao Yu and Ruize Zhang and Yi Wu and Yu Wang},
year={2023},
eprint={2309.12825},
archivePrefix={arXiv},
primaryClass={cs.RO}
}
Some of the abstractions and implementation was heavily inspired by Isaac Orbit.