# Occlusion-Aware Multimodal Beam Prediction and Pose Estimation for mmWave V2I

arXiv: https://arxiv.org/abs/2603.25799 · HTML: https://mlsanity.com/paper/2603.25799/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Mar 2026.

## Built on by (most cited first, 1 of 1)

- [CM-MAE: A Physics-Guided Cross-Modal Self-Supervised Learning Framework for Vision-Wireless Applications](https://mlsanity.com/paper/2608.15972/) (2026)

## Abstract (arXiv)

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.