Metraipolis › archive › dc_994d59cd037d

Radar-Only Long-Term Beam Prediction in mmWave Vehicular Networks: An Empirical Study of Doppler Input and Cross-Modal Distillation — arXiv:2610.20185

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.20185
License (as archived): CC0-1.0
Archived: 2026-10-15T15:03:30.311Z
SHA-256 of the archived text: 6d358143aabab4542cb84bc0d762a02028c57edd611755dba9dadde9e645a79d
Stable URL of this page: https://metraipolis.com/documento/dc_994d59cd037d

How to cite

Radar-Only Long-Term Beam Prediction in mmWave Vehicular Networks: An Empirical Study of Doppler Input and Cross-Modal Distillation — arXiv:2610.20185 — arXiv (en), https://arxiv.org/abs/2610.20185 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_994d59cd037d (Metraipolis archive dc_994d59cd037d, sha256 6d358143aabab4542cb84bc0d762a02028c57edd611755dba9dadde9e645a79d)

BibTeX

@misc{dc994d59cd037d,
  title = {Radar-Only Long-Term Beam Prediction in mmWave Vehicular Networks: An Empirical Study of Doppler Input and Cross-Modal Distillation — arXiv:2610.20185},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.20185},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_994d59cd037d; sha256 6d358143aabab4542cb84bc0d762a02028c57edd611755dba9dadde9e645a79d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.20185. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Sensing-aided beam prediction could cut the beam-training overhead of millimeter-wave vehicular links, and two design choices could strengthen a radar-only predictor: a Doppler-resolved input and knowledge distilled from a camera during training. We measure what each is worth in received power rather than in top-1 accuracy, whose differences of a few points amount to only tenths of a decibel. We use real DeepSense 6G measurements, mainly at one roadside site, and one convolutional-recurrent predictor family evaluated open-loop up to 0.67 s ahead. Adding a range-Doppler map to the range-angle map lowers the mean beam-selection loss by 0.28 dB (95% bootstrap interval [0.14, 0.41]). The gain comes from the Doppler content, not from the extra input, and replicates, as pre-specified, at a second base station, although holding the last measured beam beats both predictors there. Cross-modal knowledge distillation from a motion-mask vision-radar teacher, by contrast, changes received power by -0.01 dB ([-0.07, +0.06]). The tested teacher, student, fusion and distillation variants show the same null in the metric each was scored on. Where distillation helps, in an exploratory run with few training passes, a radar-only teacher trained on all training passes reproduces most of the gain. For this predictor family and the full training set, the measurable gain at the link comes from Doppler-resolved radar content; no tested route for transferring training-only visual information adds a resolved gain.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv eess.SP, nuovi lavori del giorno).
Categorie arXiv: Signal Processing (eess.SP).
Pagina del lavoro: https://arxiv.org/abs/2610.20185 — 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 2026-10-15T14:07:24.247Z dalla pagina https://arxiv.org/list/eess.SP/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).