Poster: RSSI-Based Pedestrian Localization Using Artificial Neural Networks

Abstract

Pedestrians are particularly vulnerable traffic participants and, therefore, accurate localization and reliable communication between them and vehicles are of utmost importance to ensure their safety. A common method to determine distances between mobile devices is to use radio frequency (RF) based ranging. In this paper, we rely on the commonly used Received Signal Strength Indicator (RSSI) as the primary parameter for ranging and pedestrian localization. We use artificial neural networks to improve the performance of pedestrian localization by adding contextual information of the vehicular environment, such as vehicle velocity and direction to address the RF-based ranging challenges (i.e., multipath fading and shadowing). We show that the proposed scheme can improve the reliability and accuracy of RSSI-based ranging.