ZTE Communications ›› 2019, Vol. 17 ›› Issue (2): 2-9.DOI: 10.12142/ZTECOM.201902002

• Special Topic • Previous Articles     Next Articles

A Framework for Active Learning of Beam Alignment in Vehicular Millimeter Wave Communications by Onboard Sensors

Z?chmann Erich   

  1. Christian Doppler Laboratory for Dependable Wireless Connectivity for the Society in Motion, Institute of Telecommunications, TU Wien, 1040 Vienna, Austria
  • Received:2019-04-10 Online:2019-06-11 Published:2019-11-14
  • About author:Erich Z?chmann (ezoechma@gmail.com) received all his degrees (B.Sc., Dipl.-Ing, Dr.techn) in electrical engineering from TU Wien, Austria. From 2013 to 2015, he was a project assistant at the Institute of Telecommunications where he co-developed the Vienna LTE-A uplink link level simulator and conducted research on physical layer signal processing for 4G mobile communication systems. From 2015 to 2018 he was involved in experimental characterization and modelling of millimeter wave propagation. From November 2017 until February 2018, he was a visiting scholar at the University of Texas at Austin, USA. Besides wireless propagation, his research interests include physical layer signal processing, array signal processing, compressed sensing, and convex optimization
  • Supported by:
    The work is supported by the Austrian Federal Ministry for Digital and Economic Affairs


Estimating time-selective millimeter wave wireless channels and then deriving the optimum beam alignment for directional antennas is a challenging task. To solve this problem, one can focus on tracking the strongest multipath components (MPCs). Aligning antenna beams with the tracked MPCs increases the channel coherence time by several orders of magnitude. This contribution suggests tracking the MPCs geometrically. The derived geometric tracker is based on algorithms known as Doppler bearing tracking. A recent work on geometric-polar tracking is reformulated into an efficient recursive version. If the relative position of the MPCs is known, all other sensors on board a vehicle, e.g., lidar, radar, and camera, will perform active learning based on their own observed data. By learning the relationship between sensor data and MPCs, onboard sensors can participate in channel tracking. Joint tracking of many integrated sensors will increase the reliability of MPC tracking.

Key words: adaptive filters, autonomous vehicles, directive antennas, doppler measurement, intelligent vehicles, machine learning, millimeter wave communication