Occlusion-Aware Multimodal Beam Prediction and Pose Estimation for mmWave V2I
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866908916075462656 |
|---|---|
| author | Orimogunje, Abidemi Park, Hyunwoo Cha, Kyeong-Ju Orikumhi, Igbafe Kim, Sunwoo Vukobratovic, Dejan |
| author_facet | Orimogunje, Abidemi Park, Hyunwoo Cha, Kyeong-Ju Orikumhi, Igbafe Kim, Sunwoo Vukobratovic, Dejan |
| contents | We propose an occlusion-aware multimodal learning framework that is inspired by simultaneous localization and mapping (SLAM) concepts for trajectory interpretation and pose prediction. Targeting mmWave vehicle-to-infrastructure (V2I) beam management under dynamic blockage, our Transformer-based fusion network ingests synchronized RGB images, LiDAR point clouds, radar range-angle maps, GNSS, and short-term mmWave power history. It jointly predicts the receive beam index, blockage probability, and 2D position using labels automatically derived from 64-beam sweep power vectors, while an offline LiDAR map enables SLAM-style trajectory visualization. On the 60 GHz DeepSense 6G Scenario 31 dataset, the model achieves 50.92\% Top-1 and 86.50\% Top-3 beam accuracy with 0.018 bits/s/Hz spectral-efficiency loss, 63.35\% blocked-class F1, and 1.33m position RMSE. Multimodal fusion outperforms radio-only and strong camera-only baselines, showing the value of coupling perception and communication for future 6G V2I systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_25799 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Occlusion-Aware Multimodal Beam Prediction and Pose Estimation for mmWave V2I Orimogunje, Abidemi Park, Hyunwoo Cha, Kyeong-Ju Orikumhi, Igbafe Kim, Sunwoo Vukobratovic, Dejan Signal Processing We propose an occlusion-aware multimodal learning framework that is inspired by simultaneous localization and mapping (SLAM) concepts for trajectory interpretation and pose prediction. Targeting mmWave vehicle-to-infrastructure (V2I) beam management under dynamic blockage, our Transformer-based fusion network ingests synchronized RGB images, LiDAR point clouds, radar range-angle maps, GNSS, and short-term mmWave power history. It jointly predicts the receive beam index, blockage probability, and 2D position using labels automatically derived from 64-beam sweep power vectors, while an offline LiDAR map enables SLAM-style trajectory visualization. On the 60 GHz DeepSense 6G Scenario 31 dataset, the model achieves 50.92\% Top-1 and 86.50\% Top-3 beam accuracy with 0.018 bits/s/Hz spectral-efficiency loss, 63.35\% blocked-class F1, and 1.33m position RMSE. Multimodal fusion outperforms radio-only and strong camera-only baselines, showing the value of coupling perception and communication for future 6G V2I systems. |
| title | Occlusion-Aware Multimodal Beam Prediction and Pose Estimation for mmWave V2I |
| topic | Signal Processing |
| url | https://arxiv.org/abs/2603.25799 |