The recent trends in wireless communication, fueled by the demand for lower latency and higher bandwidth, have caused the migration of users from lower frequencies to higher frequencies, i.e., from 2.5GHz to millimeter wave. However, the migration to higher frequencies has its challenges. The sensitivity to blockages is a key challenge for millimeter wave and terahertz networks in 5G and beyond. Since these networks mainly rely on line-of-sight (LOS) links, sudden link blockages highly threaten the reliability of such networks. Further, when the LOS link is blocked, the network typically needs to hand off the user to another LOS basestation, which may incur critical time latency, especially if a search over a large codebook of narrow beams is needed. A promising way to tackle the reliability and latency challenges lies in enabling proaction in wireless networks. Proaction allows the network to anticipate future blockages, especially dynamic blockages, and initiate user hand-off beforehand. This thesis presents a complete machine learning framework for enabling proaction in wireless networks relying on the multi-modal 3D LiDAR(Light Detection and Ranging) point cloud and position data. In particular, the paper proposes a sensing-aided wireless communication solution that utilizes bimodal machine learning to predict the user link status. This is mainly achieved via a deep learning algorithm that learns from LiDAR point-cloud and position data to distinguish between LOS and NLOS(non line-of-sight) links. The algorithm is evaluated on the multi-modal wireless Communication Dataset DeepSense6G dataset. It is a time-synchronized collection of data from various sensors such as millimeter wave power, position, camera, radar, and LiDAR. Experimental results indicate that the algorithm can accurately predict link status with 87% accuracy. This highlights a promising direction for enabling high reliability and low latency in future wireless networks.

Terahertz (THz) waves (300 GHz to 10 THz) constitute the least studied part of the electromagnetic (EM) spectrum with unique propagation properties that make them attractive to emerging sensing and imaging application. As opposed to optical signals, THz waves can penetrate several non-metallic materials (e.g., plastic, wood, and thin tissues), thus enabling several applications in security monitoring, non-destructive evaluation, and biometrics. Additionally, THz waves scatter on most surfaces distinctively compared with lower/higher frequencies (e.g., microwave/optical bands). Therefore, based on these two interesting THz wave propagation properties, namely penetration and scattering, I worked on THz imaging methods that explore non-line-of-sight (NLoS) information. First, I use a THz microscopy method to probe the fingertips as a new technique for fingerprint scanning. Due to the wave penetration in the THz range, I can exploit sub-skin traits not visible with current approaches to obtain a more robust and secure fingerprint scanning method. I also fabricated fingerprint spoofs using latex to compare the imaging results between real and fake fingers. Next, I focus on THz imaging hardware topologies and algorithms for longer-distance imaging applications. As such, I compare the imaging performance of dense and sparse antenna arrays through simulations and measurements. I show that sparse arrays with nonuniform amplitudes can provide lower side lobes in the images. Besides, although sparse arrays feature a much smaller total number of elements, dense arrays have advantages when imaging scenarios with multiple objects. Afterward, I propose a THz imaging method to see around obstacles/corners. THz waves’ unique scattering properties are helpful to implement around-the-corner imaging. I carried out both simulations and measurements in various scenarios to validate the proposed method. The results indicate that THz waves can reveal the hidden scene with centimeter-scale resolution using proper rough surfaces and moderately sized apertures. Moreover, I demonstrate that this imaging technique can benefit simultaneous localization and mapping (SLAM) in future communication systems. NLoS images enable accurate localization of blocked users, hence increasing the link robustness. I present both simulation and measurement results to validate this SLAM method. I also show that better localization accuracy is achieved when the user's antenna is omnidirectional rather than directional.

Every communication system has a receiver and a transmitter. Irrespective if it is wired or wireless.The future of wireless communication consists of a massive number of transmitters and receivers. The question arises, can we use computer vision to help wireless communication? To satisfy the high data requirement, a large number of antennas are required. The devices that employ large-antenna arrays have other sensors such as RGB camera, depth camera, or LiDAR sensors.These vision sensors help us overcome the non-trivial wireless communication challenges, such as beam blockage prediction and hand-over prediction.This is further motivated by the recent advances in deep learning and computer vision that can extract high-level semantics from complex visual scenes, and the increasing interest of leveraging machine/deep learning tools in wireless communication problems.[1] <br/><br/>The research was focused solely based on technology like 3D cameras,object detection and object tracking using Computer vision and compression techniques. The main objective of using computer vision was to make Milli-meter Wave communication more robust, and to collect more data for the machine learning algorithms. Pre-build lossless and lossy compression algorithms, such as FFMPEG, were used in the research. An algorithm was developed that could use 3D cameras and machine learning models such as YOLOV3, to track moving objects using servo motors and low powered computers like the raspberry pi or the Jetson Nano. In other words, the receiver could track the highly mobile transmitter in 1 dimension using a 3D camera. Not only that, during the research, the transmitter was loaded on a DJI M600 pro drone, and then machine learning and object tracking was used to track the highly mobile drone. In order to build this machine learning model and object tracker, collecting data like depth, RGB images and position coordinates were the first yet the most important step. GPS coordinates from the DJI M600 were also pulled and were successfully plotted on google earth. This proved to be very useful during data collection using a drone and for the future applications of position estimation for a drone using machine learning. <br/><br/>Initially, images were taken from transmitter camera every second,and those frames were then converted to a text file containing hex-decimal values. Each text file was then transmitted from the transmitter to receiver, and on the receiver side, a python code converted the hex-decimal to JPG. This would give an efect of real time video transmission. However, towards the end of the research, an industry standard, real time video was streamed using pre-built FFMPEG modules, GNU radio and Universal Software Radio Peripheral (USRP). The transmitter camera was a PI-camera. More details will be discussed as we further dive deep into this research report.

Constant false alarm rate is one of the essential algorithms in a RADAR detection system. It allows the RADAR system to dynamically set thresholds based on the data power level to distinguish targets with interfering noise and clutters.

To have a better acknowledgment of constant false alarm rate approaches performance, three clutter models, Gamma, Weibull, and Log-normal, have been introduced to evaluate the detection's capability of each constant false alarm rate algorithm.

The order statistical constant false alarm rate approach outperforms other conventional constant false alarm rate methods, especially in clutter evolved environments. However, this method requires high power consumption due to repeat sorting.
In the automotive RADAR system, the computational complexity of algorithms is essential because this system is in real-time. Therefore, the algorithms must be fast and efficient to ensure low power consumption and processing time.

The reduced computational complexity implementations of cell-averaging and order statistic constant false alarm rate were explored. Their big O and processing time has been reduced.

Unmanned aerial systems (UASs) have recently enabled novel applications such as passenger transport and package delivery, but are increasingly vulnerable to cyberattack and therefore difficult to certify. Legacy systems such as GPS provide these capabilities extremely well, but are sensitive to spoofing and hijacking. An alternative intelligent transport system (ITS) was developed that provides highly secure communications, positioning, and timing synchronization services to networks of cooperative RF users, termed Communications and High-Precision Positioning (CHP2) system. This technology was implemented on consumer-off-the-shelf (COTS) hardware and it offers rapid (<100 ms) and precise (<5 cm) positioning capabilities in over-the-air experiments using flexible ground stations and UAS platforms using limited bandwidth (10 MHz). In this study, CHP2 is considered in the context of safety-critical and resource limited transport applications and urban air mobility. The two-way ranging (TWR) protocol over a joint positioning-communications waveform enables distributed coherence and time-of-flight(ToF) estimation. In a multi-antenna setup, the cross-platform ranging on participating nodes in the network translate to precise target location and orientation. In the current form, CHP2 necessitates a cooperative timing exchange at regular intervals. Dynamic resource management supports higher user densities by constantly renegotiating spectral access depending on need and opportunity. With these novel contributions to the field of integrated positioning and communications, CHP2 is a suitable candidate to provide both communications, navigation, and surveillance (CNS) and alternative positioning, navigation, and timing (APNT) services for high density safety-critical transport applications on a variety of vehicular platforms.

The recent increase in users of cellular networks necessitates the use of new technologies to meet this demand. Massive multiple input multiple output (MIMO) communication systems have great potential for increasing the network capacity of the emerging 5G+ cellular networks. However, leveraging the multiplexing and beamforming gains from these large-scale MIMO systems requires the channel knowlege between each antenna and each user. Obtaining channel information on such a massive scale is not feasible with the current technology available due to the complexity of such large systems. Recent research shows that deep learning methods can lead to interesting gains for massive MIMO systems by mapping the channel information from the uplink frequency band to the channel information for the downlink frequency band as well as between antennas at nearby locations. This thesis presents the research to develop a deep learning based channel mapping proof-of-concept prototype.



Due to deep neural networks' need of large training sets for accurate performance, this thesis outlines the design and implementation of an autonomous channel measurement system to analyze the performance of the proposed deep learning based channel mapping concept. This system obtains channel magnitude measurements from eight antennas autonomously using a mobile robot carrying a transmitter which receives wireless commands from the central computer connected to the static receiver system. The developed autonomous channel measurement system is capable of obtaining accurate and repeatable channel magnitude measurements. It is shown that the proposed deep learning based channel mapping system accurately predicts channel information containing few multi-path effects.

Within the near future, a vast demand for autonomous vehicular techniques can be forecast on both aviation and ground platforms, including autonomous driving, automatic landing, air traffic management. These techniques usually rely on the positioning system and the communication system independently, where it potentially causes spectrum congestion. Inspired by the spectrum sharing technique, Communications and High-Precision Positioning (CHP2) system is invented to provide a high precision position service (precision ~1cm) while performing the communication task simultaneously under the same spectrum. CHP2 system is implemented on the consumer-off-the-shelf (COTS) software-defined radio (SDR) platform with customized hardware. Taking the advantages of the SDR platform, the completed baseband processing chain, time-of-arrival estimation (ToA), time-of-flight estimation (ToF) are mathematically modeled and then implemented onto the system-on-chip (SoC) system. Due to the compact size and cost economy, the CHP2 system can be installed on different aerial or ground platforms enabling a high-mobile and reconfigurable network.

In this dissertation report, the implementation procedure of the CHP2 system is discussed in detail. It mainly focuses on the system construction on the Xilinx Ultrascale+ SoC platform. The CHP2 waveform design, ToA solution, and timing exchanging algorithms are also introduced. Finally, several in-lab tests and over-the-air demonstrations are conducted. The demonstration shows the best ranging performance achieves the ~1 cm standard deviation and 10Hz refreshing rate of estimation by using a 10MHz narrow-band signal over 915MHz (US ISM) or 783MHz (EU Licensed) carrier frequency.

Object localization is used to determine the location of a device, an important aspect of applications ranging from autonomous driving to augmented reality. Commonly-used localization techniques include global positioning systems (GPS), simultaneous localization and mapping (SLAM), and positional tracking, but all of these methodologies have drawbacks, especially in high traffic indoor or urban environments. Using recent improvements in the field of machine learning, this project proposes a new method of localization using networks with several wireless transceivers and implemented without heavy computational loads or high costs. This project aims to build a proof-of-concept prototype and demonstrate that the proposed technique is feasible and accurate.

Modern communication networks heavily depend upon an estimate of the communication channel, which represents the distortions that a transmitted signal takes as it moves towards a receiver. A channel can become quite complicated due to signal reflections, delays, and other undesirable effects and, as a result, varies significantly with each different location. This localization system seeks to take advantage of this distinctness by feeding channel information into a machine learning algorithm, which will be trained to associate channels with their respective locations. A device in need of localization would then only need to calculate a channel estimate and pose it to this algorithm to obtain its location.

As an additional step, the effect of location noise is investigated in this report. Once the localization system described above demonstrates promising results, the team demonstrates that the system is robust to noise on its location labels. In doing so, the team demonstrates that this system could be implemented in a continued learning environment, in which some user agents report their estimated (noisy) location over a wireless communication network, such that the model can be implemented in an environment without extensive data collection prior to release.

Limited spectral access motivates technologies that adapt to diminishing resources and increasingly cluttered environments. A joint positioning-communications system is designed and implemented on \acf{COTS} hardware. This system enables simultaneous positioning of, and communications between, nodes in a distributed network of base-stations and unmanned aerial systems (UASs). This technology offers extreme ranging precision ($<$ 5 cm) with minimal bandwidth (10 MHz), a secure communications link to protect against cyberattacks, a small form factor that enables integration into numerous platforms, and minimal resource consumption which supports high-density networks. The positioning and communications tasks are performed simultaneously with a single, co-use waveform, which efficiently utilizes limited resources and supports higher user densities. The positioning task uses a cooperative, point-to-point synchronization protocol to estimate the relative position and orientation of all users within the network. The communications task distributes positioning information between users and secures the positioning task against cyberattacks. This high-performance system is enabled by advanced time-of-arrival estimation techniques and a modern phase-accurate distributed coherence synchronization algorithm. This technology may be installed in ground-stations, ground vehicles, unmanned aerial systems, and airborne vehicles, enabling a highly-mobile, re-configurable network with numerous applications.

The objective of this work is to design a novel method for imaging targets and scenes which are not directly visible to the observer. The unique scattering properties of terahertz (THz) waves can turn most building surfaces into mirrors, thus allowing someone to see around corners and various occlusions. In the visible regime, most surfaces are very rough compared to the wavelength. As a result, the spatial coherency of reflected signals is lost, and the geometry of the objects where the light bounced on cannot be retrieved. Interestingly, the roughness of most surfaces is comparable to the wavelengths at lower frequencies (100 GHz – 10 THz) without significantly disturbing the wavefront of the scattered signals, behaving approximately as mirrors. Additionally, this electrically small roughness is beneficial because it can be used by the THz imaging system to locate the pose (location and orientation) of the mirror surfaces, thus enabling the reconstruction of both line-of-sight (LoS) and non-line-of-sight (NLoS) objects.

Back-propagation imaging methods are modified to reconstruct the image of the 2-D scenario (range, cross-range). The reflected signal from the target is collected using a SAR (Synthetic Aperture Radar) set-up in a lab environment. This imaging technique is verified using both full-wave 3-D numerical analysis models and lab experiments.

The novel imaging approach of non-line-of-sight-imaging could enable novel applications in rescue and surveillance missions, highly accurate localization methods, and improve channel estimation in mmWave and sub-mmWave wireless communication systems.