Abstract

Context-aware beam management in millimeter-wave (mmWave) wireless communication systems has received increasing attention over the past few years. Machine learning (ML) has played a key role in leveraging different types of context information from the device position and orientation to more ambitious scenarios using RADAR, LIDAR, or camera images. However, most studies in this area consider simplified configurations for user terminals without considering the self-blockage effects owing to the user's hand and body. This paper investigates beam selection on multi-panel devices under realistic self-blockage conditions and proposes context-aware ML methods that exploit the device's position and orientation to recommend the most promising panel and beam configurations. (Read the full version on IEEE Xplore.)

Figures

Bibtex

@article{rezaie2025contextaware,
  title   = {Context-Aware Machine Learning-Based Beam Selection With Multi-Panel Devices in the Presence of Self-Blockage},
  author  = {Rezaie, Sajad and Morais, Jo{\~a}o and Alkhateeb, Ahmed and Mogensen, Preben and Manch{\'o}n, Carles Navarro},
  journal = {IEEE Access},
  year    = {2025},
  url     = {https://ieeexplore.ieee.org/document/10980287}
}