Skip to content
Preprint

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

Oct 2026 · 1 citation · 40 references
Engineering

TL;DR

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.

Abstract

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.

View source

Similar papers

#graph neural networks Open access Oct 2026

SRTRL: Shared Radar-Communication Temporal Representation Learning for Beam Prediction in Vehicular and UAV mmWave Networks

Proactive beam management is essential for high-mobility millimeter-wave communication systems, where transmission latency may cause beams selected from current observations to become mismatched with the optimal beams at future transmission times. This paper investigates radar-only causal multi-horizon proactive beam p...

Gang Wang, Qi-Wu Wu, Li Zhu et al. · 0 citations
Open access 2026

Complex-Valued Hierarchical Fusion Network for Single-Frame Cross-Range Velocity Estimation With Millimeter-Wave MIMO Radar

Conventional frequency-modulated continuous-wave (FMCW) processing directly measures radial velocity but does not provide the cross-range component from a single Doppler peak. This limitation constrains real-time motion sensing in short-range applications, especially in automotive traffic scenarios involving pedestrian...

Bo-Chuan Wu, X. Zhuge · 0 citations
Open access 2026

PGA-TCN: Physics-Guided Attention and Temporal Convolutional Network-Based Millimeter-Wave Radar Ghost Removal

Results demonstrate that PGA-TCN maintains effective ghost recognition capability and cross-scene robustness under challenging indoor radar sensing conditions, providing a lightweight solution for multipath ghost suppression and multiperson point-cloud classification.

Wei Yin, Ling-Feng Shi, Yi-Fan Shi · 0 citations
2026

Prediction-and-Repair OMP for Channel Estimation in RIS-Assisted Slowly Time-Varying Sparse mmWave Channel

Reconfigurable intelligent surfaces (RISs) are a promising technology for sixth-generation (6G) wireless networks. However, the independent mobility of multiple users and inaccurate prior information can cause the propagation of channel estimation errors in RIS-assisted slowly time-varying sparse cascaded channels. By...

Yu-Xiang Deng, Hong-Gui Deng, Vaskar Sen et al. · 0 citations
Open access Oct 2026

Deep Learning-Based Direction-of-Arrival Estimation in Automotive MIMO Radars under Multipath Propagation

Introduction . Today, millimeter-wave radars are a key component of driver-assistance systems. However, in urban scenarios, the performance of conventional methods for estimating the direction of arrival of signals (DOA) is degraded by multipath effects, which can lead to ghost targets. This article describes an alg...

E. V. Lazko, S. A. Popkov, S. Shishanov · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.