Research

Paper

TESTING March 25, 2026

Sensing-Assisted Adaptive Beam Probing with Calibrated Multimodal Priors and Uncertainty-Aware Scheduling

Authors

Abidemi Orimogunje, Vukan Ninkovic, Ognjen Kundacina, Hyunwoo Park, Sunwoo Kim, Dejan Vukobratovic, Evariste Twahirwa, Gaspard Gashema

Abstract

Highly directional mmWave/THz links require rapid beam alignment, yet exhaustive codebook sweeps incur prohibitive training overhead. This letter proposes a sensing-assisted adaptive probing policy that maps multimodal sensing (radar/LiDAR/camera) to a calibrated prior over beams, predicts per-beam reward with a deep Q-ensemble whose disagreement serves as a practical epistemic-uncertainty proxy, and schedules a small probe set using a Prior-Q upper-confidence score. The probing budget is adapted from prior entropy, explicitly coupling sensing confidence to communication overhead, while a margin-based safety rule prevents low signal-to-noise ratio (SNR) locks. Experiments on DeepSense-6G (train: scenarios 42 and 44; test:43) with a 21-beam discrete Fourier transform (DFT) codebook achieve Top-1/Top-3 of 0.81/0.99 with expected beam probe of 2 per sweep and zero observed outages at θ = 0 dB with margin Δ = 3 dB. The results show that multimodal priors with ensemble uncertainty match link quality and improve reliability compared to ablations while cutting overhead with better predictive model.

Metadata

arXiv ID: 2603.24024
Provider: ARXIV
Primary Category: eess.SP
Published: 2026-03-25
Fetched: 2026-03-26 06:02

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.24024v1</id>\n    <title>Sensing-Assisted Adaptive Beam Probing with Calibrated Multimodal Priors and Uncertainty-Aware Scheduling</title>\n    <updated>2026-03-25T07:35:23Z</updated>\n    <link href='https://arxiv.org/abs/2603.24024v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.24024v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Highly directional mmWave/THz links require rapid beam alignment, yet exhaustive codebook sweeps incur prohibitive training overhead. This letter proposes a sensing-assisted adaptive probing policy that maps multimodal sensing (radar/LiDAR/camera) to a calibrated prior over beams, predicts per-beam reward with a deep Q-ensemble whose disagreement serves as a practical epistemic-uncertainty proxy, and schedules a small probe set using a Prior-Q upper-confidence score. The probing budget is adapted from prior entropy, explicitly coupling sensing confidence to communication overhead, while a margin-based safety rule prevents low signal-to-noise ratio (SNR) locks. Experiments on DeepSense-6G (train: scenarios 42 and 44; test:43) with a 21-beam discrete Fourier transform (DFT) codebook achieve Top-1/Top-3 of 0.81/0.99 with expected beam probe of 2 per sweep and zero observed outages at θ = 0 dB with margin Δ = 3 dB. The results show that multimodal priors with ensemble uncertainty match link quality and improve reliability compared to ablations while cutting overhead with better predictive model.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='eess.SP'/>\n    <published>2026-03-25T07:35:23Z</published>\n    <arxiv:comment>5 pages</arxiv:comment>\n    <arxiv:primary_category term='eess.SP'/>\n    <author>\n      <name>Abidemi Orimogunje</name>\n    </author>\n    <author>\n      <name>Vukan Ninkovic</name>\n    </author>\n    <author>\n      <name>Ognjen Kundacina</name>\n    </author>\n    <author>\n      <name>Hyunwoo Park</name>\n    </author>\n    <author>\n      <name>Sunwoo Kim</name>\n    </author>\n    <author>\n      <name>Dejan Vukobratovic</name>\n    </author>\n    <author>\n      <name>Evariste Twahirwa</name>\n    </author>\n    <author>\n      <name>Gaspard Gashema</name>\n    </author>\n  </entry>"
}