TY - GEN
T1 - Vision-Position Multi-Modal Beam Prediction Using Real Millimeter Wave Datasets
AU - Charan, Gouranga
AU - Osman, Tawfik
AU - Hredzak, Andrew
AU - Thawdar, Ngwe
AU - Alkhateeb, Ahmed
N1 - Funding Information:
VIII. ACKNOWLEDGMENT This work was supported in part by the Air Force Research Laboratory Visiting Faculty Research Program SA2020051003-V0224. Approved for public release AFRL-2021-2366.
Publisher Copyright:
© 2022 IEEE.
PY - 2022
Y1 - 2022
N2 - Enabling highly-mobile millimeter wave (mmWave) and terahertz (THz) wireless communication applications requires overcoming the critical challenges associated with the large antenna arrays deployed at these systems. In particular, adjusting the narrow beams of these antenna arrays typically incurs high beam training overhead that scales with the number of antennas. To address these challenges, this paper proposes a multi-modal machine learning based approach that leverages positional and visual (camera) data collected from the wireless communication environment for fast beam prediction. The developed framework has been tested on a real-world vehicular dataset comprising practical GPS, camera, and mmWave beam training data. The results show the proposed approach achieves more than 75% top-1 beam prediction accuracy and close to 100% top-3≈beam prediction accuracy in realistic communication scenarios.
AB - Enabling highly-mobile millimeter wave (mmWave) and terahertz (THz) wireless communication applications requires overcoming the critical challenges associated with the large antenna arrays deployed at these systems. In particular, adjusting the narrow beams of these antenna arrays typically incurs high beam training overhead that scales with the number of antennas. To address these challenges, this paper proposes a multi-modal machine learning based approach that leverages positional and visual (camera) data collected from the wireless communication environment for fast beam prediction. The developed framework has been tested on a real-world vehicular dataset comprising practical GPS, camera, and mmWave beam training data. The results show the proposed approach achieves more than 75% top-1 beam prediction accuracy and close to 100% top-3≈beam prediction accuracy in realistic communication scenarios.
UR - http://www.scopus.com/inward/record.url?scp=85130702969&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85130702969&partnerID=8YFLogxK
U2 - 10.1109/WCNC51071.2022.9771835
DO - 10.1109/WCNC51071.2022.9771835
M3 - Conference contribution
AN - SCOPUS:85130702969
T3 - IEEE Wireless Communications and Networking Conference, WCNC
SP - 2727
EP - 2731
BT - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2022 IEEE Wireless Communications and Networking Conference, WCNC 2022
Y2 - 10 April 2022 through 13 April 2022
ER -