Accurate indoor navigation system using human-item spatial relation

Indoor navigation has received much attention by both industry and academia in recent years. To locate users, a number of existing methods use various localization algorithms in combination with an indoor map, which require expensive infrastructures deployed in advance. In this study, we propose the use of existing indoor objects with attached RFID tags and a reader to navigate users to their destinations, without the need for any additional hardware. The key insight upon which our proposal is based is that a person's movement has an impact on the frequency shift values collected from indoor objects when they near a tag. We leverage this local human-item spatial relation to infer the user's position and then navigate the user to the desired destination step by step. We implement a prototype navigation system, called RollCaller, and conduct a comprehensive range of experiments to examine its performance.