Metraipolis › archive › dc_f037a951e84e

Audio-based UAV Localization with Adaptive Temporal Correspondence via Reinforcement Learning — arXiv:2609.24218

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.24218
License (as archived)
CC0-1.0
Archived
2026-10-09T22:24:19.743Z
SHA-256 of the archived text
ead3f970445bdbceb3ce91da7bda5cfb793ed1cbdbecab9b9ec89ef2d7ac615f
Stable URL of this page
https://metraipolis.com/documento/dc_f037a951e84e

How to cite

Audio-based UAV Localization with Adaptive Temporal Correspondence via Reinforcement Learning — arXiv:2609.24218 — arXiv (en), https://arxiv.org/abs/2609.24218 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f037a951e84e (Metraipolis archive dc_f037a951e84e, sha256 ead3f970445bdbceb3ce91da7bda5cfb793ed1cbdbecab9b9ec89ef2d7ac615f)
BibTeX
@misc{dcf037a951e84e,
  title = {Audio-based UAV Localization with Adaptive Temporal Correspondence via Reinforcement Learning — arXiv:2609.24218},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24218},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f037a951e84e; sha256 ead3f970445bdbceb3ce91da7bda5cfb793ed1cbdbecab9b9ec89ef2d7ac615f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24218. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Audio-based localization provides a low-cost and illumination-independent sensing solution for anti-UAV early warning. However, existing methods typically rely on a predefined fixed audio segment length, which limits temporal correspondence and creates a trade-off between sufficient acoustic evidence and timely localization. To address this issue, we propose an audio-based localization framework with adaptive temporal correspondence. A probe segment is first used to extract a compact acoustic state that characterizes the reliability and consistency of the observation. Guided by the state, a reinforcement learning controller dynamically determines the required audio window size for each localization decision. The selected audio segment is then processed by a Mamba-based localization network with adaptive temporal feature modulation for 3D position estimation. Extensive experiments demonstrate that our method achieves competitive 3D localization accuracy with substantially reduced temporal correspondence latency compared to SOTA methods and exhibits strong generalization across scenarios.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Sound (cs.SD).
Pagina del lavoro: https://arxiv.org/abs/2609.24218 — 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 2026-10-09T21:59:59.699Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).