Pragmatic Indoor Localization with Quantum Computing

WiFi RSSI fingerprinting is a cost-effective indoor localization technique leveraging existing infrastructure, but it suffers from time-varying signal fluctuations that degrade accuracy. This paper proposes a quantum-enhanced fingerprinting approach using a Swap Test for cosine similarity and a quantum oracle that encodes offline fingerprints in superposition for parallel comparison with online measurements. To mitigate RSSI noise, we introduce a PCA-based preprocessing that projects RSSI data into a lower-dimensional subspace, maximizing the angular separation of fingerprints and improving classification. Experiments on a Qiskit simulator demonstrate that our quantum fingerprinting method achieves improved localization accuracy as the number of measurement shots increases, leveraging quantum parallelism. To our knowledge, this is the first detailed implementation of quantum fingerprinting for indoor localization in Qiskit, laying the foundation for quantum-based positioning.