Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

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.

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

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.
Paper Structure (22 sections, 15 equations, 3 figures, 3 tables, 1 algorithm)

This paper contains 22 sections, 15 equations, 3 figures, 3 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. System Model and Problem Formulation
  3. SNR proxy and oracle beam
  4. Probing decision, locking rule, and reliability metrics
  5. Problem formulation: overhead-reliability and link-quality trade-off
  6. Proposed Method
  7. Calibrated multimodal prior
  8. Q-ensemble reward prediction and uncertainty
  9. Prior-Q UCB scheduling and adaptive probing
  10. Adaptive probe budget and Safety shield
  11. Computational complexity
  12. Experimental Setup and Evaluation Protocol
  13. Dataset and Split
  14. Training and Inference
  15. Evaluation Metrics
  16. ...and 7 more sections

Figures (3)

  • Figure 1: Empirical CDF of the locked-beam SNR proxy \ref{['eq:snrproxy']} for the proposed adaptive policy on DeepSense-6G scenario 43 ($B{=}21$). Vertical markers denote the mean and the 5th-percentile (p05), illustrating a tight locked-beam SNR distribution under $\mathbb{E}[K_t]\!\approx\!2$ probes per sweep.
  • Figure 2: Ablation at matched probing budget ($K_t{=}2$). Left: locked-beam Top-1/Top-3 accuracy. Right: locked-beam SNR statistics (mean and p05) with reliability indicators (outage at $\theta$ and observed shield activation rate).
  • Figure 3: Modality-dropout robustness on DeepSense-6G scenario 43. Panels (a)–(b) report locked-beam Top-1/Top-3 accuracy across modality subsets; panels (c)–(d) report locked-beam SNR proxy statistics (mean and p05). Adaptive probing mitigates low-confidence sensing states by allocating more probes when the calibrated prior is diffuse, while the probe-and-lock step preserves high locked-beam SNR across settings.