Map-assisted TDOA Localization Enhancement Based On CNN

TL;DR

This paper introduces a CNN-based method that uses map features to predict and correct NLOS-induced localization errors, significantly improving TDOA accuracy in urban environments.

Contribution

It develops a novel CNN-based error prediction and compensation scheme leveraging map features to enhance TDOA localization accuracy under NLOS conditions.

Findings

CNN models achieve high prediction accuracy for localization errors.

Error compensation improves TDOA accuracy by approximately 75%.

The approach demonstrates strong potential for urban localization enhancement.

Abstract

For signal processing related to localization technologies, non line of sight (NLOS) multipaths have a significant impact on the localization error level. This study proposes a localization correction method based on convolution neural network (CNN), which extracts obstacle features from maps to predict the localization errors caused by NLOS effects. A novel compensation scheme is developed and structured around the localization error in terms of distance and azimuth angle predicted by the CNN. Four prediction tasks are executed over different building distributions within the maps for typical urban scenario, resulting in CNN models with high prediction accuracy. Finally, a thorough comparison of the accuracy performance between the time difference of arrival (TDOA) localization algorithm and the results after the error compensation reveals that, generally, the CNN prediction approach demonstrates great localization error correction performance, improving TDOA accuracy by 75%. It can be observed that the powerful feature extraction capability of CNN can be exploited by processing surrounding maps to predict the localization error distribution, showing great potential for further enhancement of TDOA performance under challenging scenarios with rich multipath propagation.