Real-time Outdoor Localization Using Radio Maps: A Deep Learning Approach

This paper deals with the problem of localization in a cellular network in a dense urban scenario. Global Navigation Satellite Systems typically perform poorly in urban environments, where the likelihood of line-of-sight conditions between the devices and the satellites is low, and thus alternative localization methods are required for good accuracy. We present LocUNet: A fully convolutional, end-to-end trained neural network for the localization task, which merely depends on the received signal strengths (RSS) from Base Stations (BSs).In a wireless network, user devices scan the base station beacon slots and identify the few strongest base station signals for handover and user-base station association purposes. In the proposed method, the user to be localized simply reports such received signal strengths to a central processing unit, which may be located in the cloud. Alternatively, the localization can be performed locally at the user. Using the pathloss radio map estimations and the RSS measurements, LocUNet can localize users with state-of-the-art accuracy and enjoys high robustness to inaccuracies in the estimations of the radio maps. The proposed method does not require pre-sampling of the environment; and is suitable for real-time applications, thanks to the RadioUNet, a neural network-based radio map estimator. Moreover, two novel datasets that allow for numerical evaluations of RSS and ToA methods in realistic urban environments are presented and set publicly available for the use of research community. By using these datasets, we also provided a fair comparison of state-of-the-art RSS and ToA-based methods in the dense urban scenario, LocUNet outperforming all the compared methods.