Robust ToA-Estimation using Convolutional Neural Networks on Randomized Channel Models

Feigl T, Eberlein E, Kram S (2021)

Publication Language: English

Publication Type: Conference contribution, Conference Contribution

Publication year: 2021

Publisher: IEEE Xplore

Pages Range: 1-8

Conference Proceedings Title: Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN 2021)

Event location: Lloret de Mar, Spain ES

DOI: 10.1109/IPIN51156.2021.9662625

Abstract

Many radio-based positioning systems use time-of-arrival (ToA). We obtain it from the first and direct path of arrival (FDPoA) in a corresponding set of multipath components (MPC) of the underlying channel state information (CSI). While detection of the FDPoA under Line-of-Sight (LoS) is simple, itis prone to errors in environments with specular and diffuse reflections, as well as nonlinear diffraction, absorption, and transmission of a signal. Such Obstructed- or Non-Line-of-Sight (OLoS, NLoS) situations lead to incorrect FDPoA and consequently to incorrect ToA estimates and inaccurate positions. State-of-the-art estimators suffer from a high computing effort and most of them fail at low signal-to-noise ratios (SNRs).

We propose a deep learning (DL) approach to identify optimal FDPoAs as ToA directly from the raw CSI. Our 1D Convolutional Neural Network (CNN) learns the spatial distribution of MPCs of the CSI to predict correct estimates of the ToA. To train our DL model, we use QuaDRiGa to generate datasets with CIRs and ground truth ToAs for realistic 5G channel models. We found that Delay Spread (DS), k-Factor (kF), and SNR are appropriate metrics to cover most LoS-NLoS constellations in realistic datasets. We compare our DL model with the state-of-the-art estimators such as threshold (PEAK), inflection point (IFP), MUSIC, and DL and show that we consistently outperform them by about 17 % for SNRs below -10dB.

Authors with CRIS profile

Tobias Feigl Lehrstuhl für Informatik 2 (Programmiersysteme) Christopher Mutschler
Sebastian Kram Lehrstuhl für Informationstechnik mit dem Schwerpunkt Kommunikationselektronik (Stiftungslehrstuhl)

Related research project(s)

Recurrent Neuronal Networks (RNNs) for Real-Time Estimation of Nonlinear Motion Models (RuNN) Oct. 1, 2017 - March 31, 2021

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Feigl, T., Eberlein, E., & Kram, S. (2021). Robust ToA-Estimation using Convolutional Neural Networks on Randomized Channel Models. In Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN 2021) (pp. 1-8). Lloret de Mar, Spain, ES: IEEE Xplore.

MLA:

Feigl, Tobias, Ernst Eberlein, and Sebastian Kram. "Robust ToA-Estimation using Convolutional Neural Networks on Randomized Channel Models." Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN 2021), Lloret de Mar, Spain IEEE Xplore, 2021. 1-8.

BibTeX: Download