GPS-Free Geolocation Based on LoRa

In WSN/IoT, the localization of nodes are essential to long-running applications for accurate environment monitoring and detection of important events, often covering a large area in the field. Due to the lower time resolution of typical WSN/IoT platforms (e.g., 1 microsecond for ESP32), ranging-based localization techniques cannot provide spatial resolution better than ~300 meters. Location fingerprinting techniques based on received signal strengths, too, suffer from various scattering issues, resulting in lower performance. In this project, we are to investigate hybrid localization techniques based on both ranging and location fingerprinting, where the lower spatial resolution from ranging could be improved by (1) a newly-proposed "multiple two-way message exchanges" scheme and (2) location fingerprinting based on received signal strengths and a time series of measurement data like the arrival times of periodic beacons. We will carry out experiments on a LoRa testbed to demonstrate the feasibility of GPS-free geolocation based on the hybrid localization techniques.

We are to investigate hybrid localization techniques based on both ranging and location fingerprinting in the context of GPS-free geolocation based on LoRa. The key research questions are:

• Can the newly-proposed "multiple two-way message exchanges" scheme address the issue of the lower spatial resolution from ranging?
• Can the time series of periodic beacon arrival times provide characteristics unique to its measurement location (i.e., the distance between the sender and the receiver of beacons)?

• Xi'an Jiaotong-Liverpool University Summer Undergraduate Research Fellowships (SURF) programme (under grant SURF-2025-0217).

• Jun./2025–Aug./2025 (10 weeks)

• To be added…

1. Chaojie Gu, Linshan Jiang, and Rui Tan, "LoRa-based localization: Opportunities and challenges," Proc. EWSN'19, Beijing, China, Mar. 2019, pp. 413–419.
2. Jonas Danebjer and Valthor Halldórsson, "A Hybrid Approach to GPS-Free Geolocationover LoRa," Master's thesis, Department of Electrical and Information Technology, Lund University, Sep. 2018.
3. D. Merhej, I. Ahriz, L. Zerioul, S. Garcia, and M. Terré, "Joint RSS and ranging fingerprint for LoRa indoor localization," Proc. WCNC 2024, Dubai, United Arab Emirates, 2024, pp. 1–6.
4. B. C. Fargas and M. N. Petersen, "GPS-free geolocation using LoRa in low-power WANs," Proc. GIoTS 2017, Geneva, Switzerland, 2017, pp. 1–6.

• XJTLU PGRS1912001: Scalable and Energy-Efficient Multi-Building and Multi-Floor Indoor Localisation/Navigation based on Deep Neural Networks with a Multivariate Database
• XJTLU KSF-E-25: Feasibility Study of XJTLU Campus-Wide Indoor Localization System Based on Deep Neural Networks
• XJTLU SURF-2024-0311: Indoor Localization Based on Multi-Sensor Fusion Databases
• XJTLU SURF-2023-0135: Multi-Building, Multi-Floor Time-Varying Indoor Localization Database for XJTLU Campus
• XJTLU SURF-2022076: Scalable Representation of RSSIs for Multi-Building and Multi-Floor Indoor Localization Based on Deep Neural Networks
• XJTLU SURF-201913: Analysis of XJTLUIndoorLoc Multivariate Dataset for DNN-Based Indoor Localization
• XJTLU SURF-201830: Trajectory Estimation of Mobile Users/Devices based on Wi-Fi Fingerprinting and Deep Neural Networks
• XJTLU SURF-201739: Indoor Localisation Based on Wi-Fi Fingerprinting with Fuzzy Sets
• XJTLU RISGC-2017-4: Feasibility Assessment and Roadmap for XJTLU Campus Information and Visitor Service System as A Test Bed for Large-Scale Location-Aware Services in SIP