MmWave Vehicular Beam Training with Situational Awareness by Machine Learning

Wang, Yuyang; Klautau, Aldebaro; Ribero, Mónica; Narasimha, Murali; Heath, Robert W.

doi:10.1109/glocomw.2018.8644288

Cited by 38 publications

(24 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A consensus is forming that the out-of-band information from sensors or DSRC is valuable, which can be leveraged to achieve dynamic beam tracking and reduce recovery overhead [37]- [40]. To associate the most appropriate beam pairs, novel schemes like the fingerprint database and machine learning were taken into account [41], [42]. Obviously, these works set up the fundamentals for the practical use of mmWave in vehicular scenarios.…”

Section: A Mmwave Technologies For V2xmentioning

confidence: 99%

Towards Safe Automated Driving: Design of Software-Defined Dynamic MmWave V2X Networks and PoC Implementation

Tao

Fukatsu

et al. 2021

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

Section: A Mmwave Technologies For V2xmentioning

confidence: 99%

Towards Safe Automated Driving: Design of Software-Defined Dynamic MmWave V2X Networks and PoC Implementation

Tao

Fukatsu

et al. 2021

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

“…Nowadays, thanks to the advance of integrated circuits used in mmWave bands [11][12][13], low-cost devices become possible and hence the study on mmWave V2X networks is reinvigorated. Recently, several research efforts have been devoted to exploring such networks [14][15][16][17]. During overtaking, the actual V2V propagation channel for the frequency range from 59.75 to 60.25 GHz was measured in [14].…”

Section: A Related Work and Motivationsmentioning

confidence: 99%

“…Since vehicular radars are also operated in mmWave bands, the authors in [15] proposed an adaptive cruise control mode to enhance mmWave V2X communications by incorporating radar sensing capabilities. Furthermore, machine learning approaches were introduced in [16] to configure beamforming patterns. Note that the average performance of networks is an important metric for designing new protocols [18].…”

Section: A Related Work and Motivationsmentioning

confidence: 99%

Modeling and Analysis of MmWave V2X Networks With Vehicular Platoon Systems

Liu

Deng

et al. 2019

IEEE J. Select. Areas Commun.

Self Cite

View full text Add to dashboard Cite

show abstract

“…Va et al leveraged the position of a vehicle along the past beam measurements to rank desirable pointing directions that can reduce the required beam training based on a popular machine learning method used in recommender systems [41]; moreover, they proposed the utilization of the position of the vehicle to query a multipath fingerprint database that provides prior knowledge of potential pointing directions for reliable beam alignment [42]. In [43], Wang et al also introduced machine learning with the past beam training records for optimal beam pairing by exploiting the locations and sizes of the receiver and its neighboring vehicles.…”

Section: Related Workmentioning

confidence: 99%

Experimental Demonstration of MmWave Vehicle-to-Vehicle Communications Using IEEE 802.11ad

Kim

2019

Sensors

View full text Add to dashboard Cite

Millimeter wave (mmWave) vehicle-to-vehicle (V2V) communications has received significant attention as one of the key applications in 5G technology, which is called as Giga-V2V (GiV2V). The ultra-wide band of the GiV2V allows vehicles to transfer gigabit data within a few seconds, which can achieve platooning of autonomous vehicles. The platooning process requires the rich data of a 4K dash-camera and LiDAR sensors for accurate vehicle control. To achieve this, 3GPP, a global organization of standards that provides specifications for the 5G mobile technology, is developing a new standard for GiV2V technology by extending the existing specification for device-to-device (D2D) communication. Meanwhile, in the last decade, the mmWave spectrum has been used in the wireless local area network (WLAN) for indoor devices, such as home appliances, based on the IEEE 802.11ad (also known as Wireless Gigabit Alliance (WiGig)) technology, which supports gigabit wireless connectivity of approximately 10 m distance in the 60-GHz frequency spectrum. The WiGig technology has been commercialized and used for various applications ranging from Internet access points to set-top boxes for televisions. In this study, we investigated the applicability of the WiGig technology to the GiV2V communications through experiments on a real vehicular testbed. To achieve this, we built a testbed using commercial off-the-shelf WiGig devices and performed experiments to measure inter-vehicle connectivity on a campus and on city roads with different permitted vehicle speeds. The experimental results demonstrate that disconnections occurred frequently due to the short radio range and the connectivity varied with the vehicle speed. However, the instantaneous throughput was sufficient to exchange large data between moving vehicles in different road environments.

show abstract

MmWave Vehicular Beam Training with Situational Awareness by Machine Learning

Cited by 38 publications

References 9 publications

Towards Safe Automated Driving: Design of Software-Defined Dynamic MmWave V2X Networks and PoC Implementation

Towards Safe Automated Driving: Design of Software-Defined Dynamic MmWave V2X Networks and PoC Implementation

Modeling and Analysis of MmWave V2X Networks With Vehicular Platoon Systems

Experimental Demonstration of MmWave Vehicle-to-Vehicle Communications Using IEEE 802.11ad

Contact Info

Product

Resources

About