Interpretable Physics-Informed WiFi Indoor Localization: Learning an Effective Access Point Geometry and Using It to Prune

License: See LICENSE file · Updated 2026-09-26
My rating

The paper proposes a hierarchical deep learning framework for WiFi fingerprint-based indoor localization. It jointly predicts user location and learns an effective geometry for the surrounding access points. Physics-informed decoders infer this geometry directly from RSSI measurements and labeled user positions without requiring the true access-point geometry.

Tags: