Collaborative Indoor Positioning by Localization Comparison at an Encounter Position

Abstract

With the widespread use of smartphones, there is a surging demand for localization in indoor environments. The main challenges are the requirement of special equipment (e.g., a map database and Wi-Fi access points) and error accumulation for indoor localization. In this paper, we propose a novel collaborative indoor positioning method to reduce error accumulation. Estimated positions are corrected using the collaborator’s positions when an encounter is detected by communication based on Bluetooth Low Energy (BLE). In addition, a map is obtained by taking photos of information boards. Therefore, the proposed method needs smartphones only; other equipment is not required. We obtained an accurate localization comparison using a machine learning model. The experimental results showed that the proposed method achieved reliable encounter communication in eight facilities. The collaborative localization method successfully enhanced position estimations. Specifically, the proposed method outperformed the existing baseline method by 13.0% in accuracy of indoor positioning.