Metraipolis › archive › dc_bbb62d51a4fa

Joint Trajectory, Sensing, and Computation Co-Design for UAV-Assisted Federated Edge Vision — arXiv:2611.00790

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.00790
License (as archived)
CC0-1.0
Archived
2026-11-03T18:41:45.778Z
SHA-256 of the archived text
55891b5e870b016f8094c11681696e6f1227b016c2427dc8c19737c5282b8ba6
Stable URL of this page
https://metraipolis.com/documento/dc_bbb62d51a4fa

How to cite

Joint Trajectory, Sensing, and Computation Co-Design for UAV-Assisted Federated Edge Vision — arXiv:2611.00790 — arXiv (en), https://arxiv.org/abs/2611.00790 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bbb62d51a4fa (Metraipolis archive dc_bbb62d51a4fa, sha256 55891b5e870b016f8094c11681696e6f1227b016c2427dc8c19737c5282b8ba6)
BibTeX
@misc{dcbbb62d51a4fa,
  title = {Joint Trajectory, Sensing, and Computation Co-Design for UAV-Assisted Federated Edge Vision — arXiv:2611.00790},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.00790},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bbb62d51a4fa; sha256 55891b5e870b016f8094c11681696e6f1227b016c2427dc8c19737c5282b8ba6},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.00790. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

This paper investigates UAV-assisted federated edge vision for training computationally heavy object detection models. Existing studies treat training data as static, ignoring the tight coupling between dynamic visual sensing and massive in place computational burdens. To minimize the expected training time under battery constraints, we propose a four-phase joint trajectory, sensing, and computation co-design. To mitigate data heterogeneity, we use a uniform sensing probability to translate federated convergence requirements into UAV mobility constraints. Furthermore, a two-layer alternating optimization (AO) algorithm is developed to adaptively determine the local data workload, optimally balancing the required training rounds against in-place computation delays. Simulations validate the superiority of our approach in model convergence and accuracy over baselines.

Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.NI, nuovi lavori del giorno).
Categorie arXiv: Networking and Internet Architecture (cs.NI).
Pagina del lavoro: https://arxiv.org/abs/2611.00790 — 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 2026-11-03T18:13:22.771Z dalla pagina https://arxiv.org/list/cs.NI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).