skip to main content


Title: A Machine Learning Solution for Beam Tracking in mmWave Systems
Utilizing millimeter-wave (mmWave) frequencies for wireless communication in mobile systems is challenging since it requires continuous tracking of the beam direction. Recently, beam tracking techniques based on channel sparsity and/or Kalman filter-based techniques were proposed where the solutions use assumptions regarding the environment and device mobility that may not hold in practical scenarios. In this paper, we explore a machine learning-based approach to track the angle of arrival (AoA) for specific paths in realistic scenarios. In particular, we use a recurrent neural network (R-NN) structure with a modified cost function to track the AoA. We propose methods to train the network in sequential data, and study the performance of our proposed solution in comparison to an extended Kalman filter based solution in a realistic mmWave scenario based on stochastic channel model from the QuaDRiGa framework. Results show that our proposed solution outperforms an extended Kalman filter-based method by reducing the AoA outage probability, and thus reducing the need for frequent beam search.  more » « less
Award ID(s):
1618078
NSF-PAR ID:
10165865
Author(s) / Creator(s):
; ;
Date Published:
Journal Name:
2019 53rd Asilomar Conference on Signals, Systems, and Computers
Page Range / eLocation ID:
173 to 177
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. This paper presents a novel method for pedestrian detection and tracking by fusing camera and LiDAR sensor data. To deal with the challenges associated with the autonomous driving scenarios, an integrated tracking and detection framework is proposed. The detection phase is performed by converting LiDAR streams to computationally tractable depth images, and then, a deep neural network is developed to identify pedestrian candidates both in RGB and depth images. To provide accurate information, the detection phase is further enhanced by fusing multi-modal sensor information using the Kalman filter. The tracking phase is a combination of the Kalman filter prediction and an optical flow algorithm to track multiple pedestrians in a scene. We evaluate our framework on a real public driving dataset. Experimental results demonstrate that the proposed method achieves significant performance improvement over a baseline method that solely uses image-based pedestrian detection. 
    more » « less
  2. This paper presents a novel reconfigurable intel-ligent surface (RIS)-based localization approach for mobile user equipment (UE) in a millimeter-wave uplink cellular environment. The proposed approach develops a measurement engine that employs a state-of-the-art carrier-aided code-phase-based navigation receiver and incorporates a passive correlation-based angle-locked loop (ALL) for TOA and AOA estimation. An extended Kalman filter (EKF)-based RIS-aided navigation framework is deployed, providing accurate 3D position and velocity estimates for the mobile UEs utilizing the RIS-based navigation observables, which are then leveraged to optimize the RIS phase profile to maximize the signal-to-noise ratio (SNR) for the various UEs. Finally, the paper demonstrates the accuracy of the navigation solution through extensive Monte Carlo simu-lations that encompass different scenarios involving pedestrians, ground vehicles, and unmanned aerial vehicles (UAVs), These simulations emphasize the utility of our proposed approach in delivering sub-meter and meter-level posltioning accuracies. 
    more » « less
  3. null (Ed.)
    Localization is one of the most interesting topics related to the promising millimeter wave (mmWave) technology. In this paper, we investigate joint channel estimation and localization for a cooperative mmWave system with several receivers. Due to the strong line-of-sight path common to mmWave channels, one can localize the position of the user by exploiting the signal's angle-of-arrival (AoA). Leveraging a variational Bayesian approach, we obtain soft information about the AoA for each receiver. We then use the soft AoA information and geometrical constraints to localize the position of the user and further improve the channel estimation performance. Numerical results show that the proposed algorithm has centimeter-level localization accuracy for an outdoor scene. In addition, the proposed algorithm provides 1-3 dB of gain for channel estimation by exploiting the correlation among the receiver channels depending on the availability of prior information about the path loss model. 
    more » « less
  4. In this research, a Kalman filter-based Z-source inverter is proposed with an enhanced control algorithm for Maximum Power Pointer Tracking(MPPT) and this capacitor voltage stabilization. By implementing Unified Linear Kalman Filter Algorithm with Capacitor Voltage Control (CVC) algorithm for the Z-source inverter, the Kalman Filter can track Maximum Power Point (MPP) faster than traditional algorithm such as Perturb and Observation (P&O) algorithm, that has a minimum impact on rapidly changing atmospheric conditions. Thus, by using the Integrated Kalman Filter and CVC algorithm we can achieve faster, effective and capacitor voltage regulation at the same time. The effectiveness of this proposed Kalman Filter with CVC Algorithm for Z-source inverter is validated in MATLAB/Simulink and a hardware prototype has been built to verify the simulation and theoretical results. 
    more » « less
  5. Low overhead channel estimation based on compressive sensing (CS) has been widely investigated for hybrid wideband millimeter wave (mmWave) multiple-input multiple-output (MIMO) systems. The channel sparsifying dictionaries used in prior work are built from ideal array response vectors evaluated on discrete angles of arrival/departure. In addition, these dictionaries are assumed to be the same for all subcarriers, without considering the impacts of hardware impairments and beam squint. In this manuscript, we derive a general channel and signal model that explicitly incorporates the impacts of hardware impairments, practical pulse shaping functions, and beam squint, overcoming the limitations of mmWave MIMO channel and signal models commonly used in previous work. Then, we propose a dictionary learning (DL) algorithm to obtain the sparsifying dictionaries embedding hardware impairments, by considering the effect of beam squint without introducing it into the learning process. We also design a novel CS channel estimation algorithm under beam squint and hardware impairments, where the channel structures at different subcarriers are exploited to enable channel parameter estimation with low complexity and high accuracy. Numerical results demonstrate the effectiveness of the proposed DL and channel estimation strategy when applied to realistic mmWave channels. 
    more » « less