期刊
IEEE SENSORS JOURNAL
卷 22, 期 6, 页码 5133-5140出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/JSEN.2021.3101933
关键词
Feature extraction; Location awareness; Sensors; Reliability; Training; Support vector machines; Receivers; NLOS identification; NLOS mitigation; channel quality estimation; CIR; UWB; deep learning; VAE
资金
- Bavarian Ministry of Economic Affairs, Infrastructure, Energy and Technology as part of the Bavarian Projects Leistungszentrum Elektroniksysteme (LZE)
- Center for AnalyticsData-Applications (ADA-Center)
This study proposes the use of generative deep learning models for detecting anomalous signals that negatively affect RF-based localization performance and mitigating the introduced errors. By predicting anomaly scores for channel impulse responses, using a Variational Autoencoder, this method demonstrates good generalization in different environments and shows improved tracking performance by integrating the anomaly scores into a Kalman filter.
Radio frequency (RF)-based localization yields centimeter-accurate positions under mild propagation conditions. However, propagation conditions predominant in indoor environments (e.g. industrial production) are often challenging as signal blockage, diffraction and dense multipath lead to errors in the time of flight (TOF) estimation and hence to a degraded localization accuracy. A major topic in high-precision RF-based localization is the identification of such anomalous signals that negatively affect the localization performance, and to mitigate the errors introduced by them. As such signal and error characteristics depend on the environment, data-driven approaches have shown to be promising. However, there is a trade-off to a bad generalization and a need for an extensive and time-consuming recording of training data associated with it. We propose to use generative deep learning models for out-of-distribution detection based on channel impulse responses (CIRs). We use a Variational Autoencoder (VAE) to predict an anomaly score for the channel of a TOF-based Ultra-wideband (UWB) system. Our experiments show that a VAE trained only on line-of-sight (LOS) training data generalizes well to new environments and detects non-line-of-sight CIRs with an accuracy of 85%. We also show that integrating our anomaly score into a TOF-based extended Kalman filter (EKF) improves tracking performance by over 25%.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据