SRTRL: Shared Radar-Communication Temporal Representation Learning for Beam Prediction in Vehicular and UAV mmWave Networks.
- 1School of Equipment Management and Support, Engineering University of PAP, Xi'an 710086, China.
- 2Key Laboratory of Counter-Terrorism Command & Information Engineering, Engineering University of PAP, Ministry of Education, Xi'an 710086, China.
- 3School of Information Engineering, Engineering University of PAP, Xi'an 710086, China.
Abstract
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 prediction, aiming to directly rank future communication beams from past radar observations. To this end, we propose Shared-Beam-GCN-TCN, a multi-task framework that learns a shared predictive sensing-communication representation and performs structured decoding in the beam space. Specifically, four consecutive range-angle radar maps are encoded by a frame-wise convolutional neural network and a causal temporal convolutional network to capture short-term motion dynamics. The shared temporal representation is jointly optimized for future beam prediction and short-term radar prediction, encouraging the extraction of predictive sensing dynamics relevant to future communication states. A beam-space graph convolutional decoder then exploits the adjacency structure among 64 beam classes to model correlations between neighboring beams and improve future beam ranking. The framework is evaluated in two high-mobility mmWave communication scenarios, including a trajectory-disjoint DeepSense 6G vehicular scenario and a simulated unmanned aerial vehicle (UAV) scenario. In the vehicular scenario, Shared-Beam-GCN-TCN achieves the best overall performance across different prediction horizons, improving the average Top-3 and Top-5 accuracies by 8.2 and 6.9 percentage points over Seq-CNN-TCN, while reducing the mean beam-index error. In the UAV scenario, the proposed framework achieves an accuracy of 93.4% and a beam-index error of 1.022. These results demonstrate the effectiveness of shared predictive representation learning and structured beam-space decoding for causal multi-horizon beam prediction in high-mobility environments.
Related
- A trust-aware edge-assisted reinforcement learning framework for secure and low-latency vehicular communication
- Tri-Modality Representation Learning for Molecular Property Prediction
- Representation learning for low-data protein fitness prediction using sequence–structure embeddings and graph neural networks
- KT-CBHNET: a spatio-temporal deep learning framework for interpretable ECG signal classification for cardiovascular disease prediction
- Machine learning prediction model for distant metastasis at diagnosis in pediatric neuroblastoma: development, interpretation, and temporal validation
BibTeX
@article{wang2026srtrl,
title = {{SRTRL: Shared Radar-Communication Temporal Representation Learning for Beam Prediction in Vehicular and UAV mmWave Networks.}},
author = {Gang Wang and Qiwu Wu and Li Zhu and Tao Yang and Lingzhi Jiang},
journal = {Sensors (Basel, Switzerland)},
year = {2026},
month = oct,
doi = {10.3390/s26206550},
url = {https://europepmc.org/article/MED/42944413},
note = {CC BY},
}
RIS
TY - JOUR
TI - SRTRL: Shared Radar-Communication Temporal Representation Learning for Beam Prediction in Vehicular and UAV mmWave Networks.
AU - Gang Wang
AU - Qiwu Wu
AU - Li Zhu
AU - Tao Yang
AU - Lingzhi Jiang
PY - 2026
DA - 2026/10/15
JO - Sensors (Basel, Switzerland)
DO - 10.3390/s26206550
UR - https://europepmc.org/article/MED/42944413
AB - 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 prediction, aiming to directly rank future communication beams from past radar observations. To this end, we propose Shared-Beam-GCN-TCN, a multi-task framework that learns a shared predictive sensing-communication representation and performs structured decoding in the beam space. Specifically, four consecutive range-angle radar maps are encoded by a frame-wise convolutional neural network and a causal temporal convolutional network to capture short-term motion dynamics. The shared temporal representation is jointly optimized for future beam prediction and short-term radar prediction, encouraging the extraction of predictive sensing dynamics relevant to future communication states. A beam-space graph convolutional decoder then exploits the adjacency structure among 64 beam classes to model correlations between neighboring beams and improve future beam ranking. The framework is evaluated in two high-mobility mmWave communication scenarios, including a trajectory-disjoint DeepSense 6G vehicular scenario and a simulated unmanned aerial vehicle (UAV) scenario. In the vehicular scenario, Shared-Beam-GCN-TCN achieves the best overall performance across different prediction horizons, improving the average Top-3 and Top-5 accuracies by 8.2 and 6.9 percentage points over Seq-CNN-TCN, while reducing the mean beam-index error. In the UAV scenario, the proposed framework achieves an accuracy of 93.4% and a beam-index error of 1.022. These results demonstrate the effectiveness of shared predictive representation learning and structured beam-space decoding for causal multi-horizon beam prediction in high-mobility environments.
SN - 1424-8220
ER -