Deep Drone Acrobatics (Extended Abstract)

Elia Kaufmann, Antonio Loquercio, René Ranftl, Matthias Müller, Vladlen Koltun, Davide Scaramuzza

IJCAI 2021 pp. 4780-4783

doi:10.24963/IJCAI.2021/650 /ijcai/2021/kaufmann2021ijcai-deep/

Abstract

Acrobatic flight with quadrotors is extremely challenging. Maneuvers such as the loop, matty flip, or barrel roll require high thrust and extreme angular accelerations that push the platform to its limits. Human drone pilots require years of practice to safely master such maneuvers. Yet, a tiny mistake could make the platform lose control, and brutally crash. This short paper describes an approach to safely train acrobatic controllers in simulation and deploy them with no fine-tuning zero-shot transfer on physical quadrotors. The approach uses only onboard sensing and computation.

PDF IJCAI Semantic Scholar

Cite

Text

Kaufmann et al. "Deep Drone Acrobatics (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2021. doi:10.24963/IJCAI.2021/650

Markdown

[Kaufmann et al. "Deep Drone Acrobatics (Extended Abstract)." International Joint Conference on Artificial Intelligence, 2021.](https://mlanthology.org/ijcai/2021/kaufmann2021ijcai-deep/) doi:10.24963/IJCAI.2021/650

BibTeX

@inproceedings{kaufmann2021ijcai-deep,
  title     = {{Deep Drone Acrobatics (Extended Abstract)}},
  author    = {Kaufmann, Elia and Loquercio, Antonio and Ranftl, René and Müller, Matthias and Koltun, Vladlen and Scaramuzza, Davide},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2021},
  pages     = {4780-4783},
  doi       = {10.24963/IJCAI.2021/650},
  url       = {https://mlanthology.org/ijcai/2021/kaufmann2021ijcai-deep/}
}