LiDAR Aided Human Blockage Prediction for 6G

Marasinghe, Dileepa; Rajatheva, Nandana

doi:10.1109/gcwkshps52748.2021.9681949

Cited by 16 publications

(16 citation statements)

References 19 publications

(26 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Given the complex nature of these pre-blockage signatures, we leverage ML (and in particular deep learning models) to utilize them as in [1], [4], [5], [12]- [14], [30]. While the proposed baseline LiDAR methods work well for simple scenarios, complex scenarios such as blockage severity level prediction benefit from more advanced ML-based solutions.…”

Section: ML Based Methodsmentioning

confidence: 99%

Proactively Predicting Dynamic 6G Link Blockages Using LiDAR and In-Band Signatures

Chakrabarti

Alkhateeb

2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

Line-of-sight link blockages represent a key challenge for the reliability and latency of millimeter wave (mmWave) and terahertz (THz) communication networks. To address this challenge, this paper leverages mmWave and LiDAR sensory data to provide awareness about the communication environment and proactively predict dynamic link blockages before they occur. This allows the network to make proactive decisions for hand-off/beam switching, enhancing the network reliability and latency. More specifically, this paper addresses the following key questions: (i) Can we predict a line-of-sight link blockage, before it happens, using in-band mmWave/THz signal and LiDAR sensing data? (ii) Can we also predict when this blockage will occur? (iii) Can we predict the blockage duration? And (iv) can we predict the direction of the moving blockage? For that, we develop machine learning solutions that learn special patterns of the received signal and sensory data, which we call pre-blockage signatures, to infer future blockages. To evaluate the proposed approaches, we build a large-scale real-world dataset that comprises co-existing LiDAR and mmWave communication measurements in outdoor vehicular scenarios. Then, we develop an efficient LiDAR data denoising algorithm that applies some pre-processing to the LiDAR data. Based on the real-world dataset, the developed approaches are shown to achieve above 95% accuracy in predicting blockages occurring within 100 ms and more than 80% prediction accuracy for blockages occurring within one second. Given this future blockage prediction capability, the paper also shows that the developed solutions can achieve an order of magnitude saving in network latency, which further highlights the potential of the developed blockage prediction solutions for wireless networks.

show abstract

Section: ML Based Methodsmentioning

confidence: 99%

Proactively Predicting Dynamic 6G Link Blockages Using LiDAR and In-Band Signatures

Chakrabarti

Alkhateeb

2023

IEEE Open J. Commun. Soc.

View full text Add to dashboard Cite

show abstract

“…1) Learning approach for blockage prediction in RIS-based VLC systems: The idea of communication systems having the ability to predict LoS link blockages such that the transmitter and the RIS can anticipate the blockage and act intelligently is an interesting and innovative concept that requires further investigation. As mentioned in [222], predicting blockage occurrences requires sensing the communication environment to allow for other functionalities such as user positioning. The lack of mathematical models for blockage predictions has motivated researchers to investigate predictors based on machine learning models (e.g., see [223] and references therein).…”

Section: Future Research Directionsmentioning

confidence: 99%

RIS-Assisted Visible Light Communication Systems: A Tutorial

Aboagye¹,

Ndjiongue²,

Ngatched³

et al. 2022

Preprint

View full text Add to dashboard Cite

Recent intensive and extensive development of the fifth-generation (5G) of cellular networks has led to their deployment throughout much of the world. As part of this implementation, one of the challenges that must be addressed is the skip-zone problem, which occurs when objects such as trees, people, animals, and vehicles obstruct the transmission of signals.In free-space optical (FSO) and radio frequency (RF) systems, dead zones are most often caused by buildings and trees, while in visible light communications (VLC), obstructions are caused by individuals moving around a room or objects placed in the room. A signal obstruction can significantly reduce the signal-to-noise ratio in RF and indoor VLC systems, whereas in FSO systems, where the transmitted signals are directional, the obstruction can completely disrupt data transmission. Therefore, the skipzone dilemma must be resolved to ensure the smooth and efficient operation of 5G and beyond networks. By placing a relay between a transmitter and a receiver, the effects of obstacles can be mitigated. As a result, the signal from the transmitter will reach the receiver. In recent years, reconfigurable intelligent surfaces (RISs) that are more efficient than relays have become widely accepted as a method of mitigating skip-zones and providing reconfigurable radio environments. However, there have been limited studies on RISs for optical wireless communication (OWC) systems. Through the RIS technology, OWC and RF communication channels can be reconfigured. This paper aims to provide a comprehensive tutorial on indoor VLC systems utilizing RIS technology. The article discusses the basics of VLC and RISs and reintroduces RISs for OWC systems, focusing on RIS-assisted indoor VLC systems. We also provide a comprehensive overview of optical RISs and examine the differences between optical RISs, RF-RISs, and optical relays. Furthermore, we discuss in detail how RISs can be used to overcome line-of-sight blockages and the device orientation issue in VLC systems while revealing key challenges such as RIS element orientation design, RIS elements to access point/user assignment design, and RIS array positioning design problems that need to be studied. Moreover, we discuss and propose several research problems on integrating optical RISs with other emerging technologies, including non-orthogonal multiple access, multiple-input multiple-output systems, physical layer security, and simultaneous lightwave and power transfer in VLC systems. Finally, we highlight other important research directions that can further improve the performance of RISassisted VLC systems.

show abstract

“…At the time of operation, the central unit creates a combined 3D point cloud c t of the total area covered by the sensors using the relative 3D transformation matrices [13] with a rate of f l synchronized with the output rates of the sensors. This input LiDAR point cloud c t is processed based on the method proposed in [14] adapted for static sensors which was also used in our prior work in [6]. When c t becomes available, the algorithm first subtracts c 0 from c t to isolate the foreground points.…”

Section: A System Modelmentioning

confidence: 99%

“…Motivated by these factors and the ability to provide detailed yet privacy-persevered data, we employ LiDAR as the sensing modality in this work. We consider an infrastructuremounted LiDAR system following our previous works [4], [5], [6] for beam prediction assisting a 5G NR system. We focus on predicting the future downlink beams while reducing the frequency of the beam reports, thus reducing the resource usage for beam measurements.…”

Section: Introductionmentioning

confidence: 99%

LiDAR aided Wireless Networks - Beam Prediction for 5G

Marasinghe

Jayaweera

Rajatheva

et al. 2022

2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall)

Self Cite

View full text Add to dashboard Cite

5G New Radio (NR) mmWave operates with narrow beams. Beam-based connections require careful management of beams to ensure a reliable connection, specially when the user has mobility. 5G NR beam management achieve this, at the expense of periodic reporting with increased overheads and resource usage. Concurrently, recent interest in sensing for assisting wireless systems provides an opportunity to extract situational awareness information which can aid in proactive decisions for the network. In this work, we utilize an infrastructure-mounted light detection and ranging (LiDAR) sensor system simultaneously operating with the wireless system to predict future beam decisions. A recurrent neural network (RNN) based learning model is proposed for the beam prediction, employing tracking information of users facilitated by the LiDARs and beam sequence information from the wireless system. Furthermore, a method for predictive beam management with increased periodicity of the reporting mechanism and aperiodic reporting is analyzed. The results for the considered scenario reveal 86.8% of the resources can be saved compared to the conventional beam reporting procedure, while achieving an 88.7% accuracy for optimal beam decisions.

show abstract

LiDAR Aided Human Blockage Prediction for 6G

Cited by 16 publications

References 19 publications

Proactively Predicting Dynamic 6G Link Blockages Using LiDAR and In-Band Signatures

Proactively Predicting Dynamic 6G Link Blockages Using LiDAR and In-Band Signatures

RIS-Assisted Visible Light Communication Systems: A Tutorial

LiDAR aided Wireless Networks - Beam Prediction for 5G

Contact Info

Product

Resources

About