Metraipolis › archive › dc_ff3259a3ba7c

UWB Meets Crazyflow: Simulating Degraded Feedback at Scale for Aerial Robotics — arXiv:2610.08225

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.08225
License (as archived)
CC0-1.0
Archived
2026-10-07T13:12:19.324Z
SHA-256 of the archived text
10f014c05175dbc628eb988777b0ffcdc04a39112705cfad902952c89112e4a2
Stable URL of this page
https://metraipolis.com/documento/dc_ff3259a3ba7c

How to cite

UWB Meets Crazyflow: Simulating Degraded Feedback at Scale for Aerial Robotics — arXiv:2610.08225 — arXiv (en), https://arxiv.org/abs/2610.08225 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ff3259a3ba7c (Metraipolis archive dc_ff3259a3ba7c, sha256 10f014c05175dbc628eb988777b0ffcdc04a39112705cfad902952c89112e4a2)
BibTeX
@misc{dcff3259a3ba7c,
  title = {UWB Meets Crazyflow: Simulating Degraded Feedback at Scale for Aerial Robotics — arXiv:2610.08225},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.08225},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ff3259a3ba7c; sha256 10f014c05175dbc628eb988777b0ffcdc04a39112705cfad902952c89112e4a2},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.08225. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In this work, we introduce Crazyflow, an accurate, differentiable simulator built on JAX. By leveraging jit compilation via XLA, Crazyflow unifies physics and control into a single differentiable computation graph, enabling massive parallelization on accelerated hardware without sacrificing modeling accuracy. This architecture achieves order-of-magnitude speedups over existing baselines, capable of training deployable reinforcement learning agents in seconds. To highlight its highly modular design, we demonstrate how easily Crazyflow can be extended by integrating a complete, high-fidelity Ultra-Wideband (UWB) and Inertial Measurement Unit (IMU) simulation pipeline coupled with a full-state Extended Kalman Filter (EKF). This capability allows for massive parallel controller evaluation under realistic, degraded state feedback with minimal impact on GPU throughput. By combining speed, accuracy, and extensibility, Crazyflow serves as a foundational tool for the next generation of aerial robotics research.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2610.08225 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T12:42:33.610Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).