HF RFID-based Book Localization via Mobile Scanning

Shelf scanning is one of the most important processes for inventory management in a library, which is able to help library users find the misplaced books and pinpoint where they are. Traditional solutions suffer from intensive manual labor, long scanning delay, or high-cost infrastructure renewal, which is a great barrier to commercial adoption. In this paper, we propose an HF RFID system that can perform the shelf scanning automatically by combining robotics and RFID technology, where the mobile robot is used for replacing the library staff and the RFID is for locating the tagged books on the bookshelves. The biggest challenge is that the commodity HF RFID device cannot capture RF phase, which is a fine-grained metric with high resolution for locating. To address this problem, we break down the task of localization into two stages, tier-level localization and order estimation, and use fuzzy logic to model and estimate the tagged book’s position. We implement the system and deploy it into four libraries for practical use. Long-term extensive experimental results demonstrate that our system provides a finegrained book localization with an accuracy of a few centimeters.