Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Passive Indoor Localization with WiFi Fingerprints

Minh Tu Hoang, Brosnan Yuen, Kai Ren, Ahmed Elmoogy, Xiaodai Dong, Tao Lu, Hung Le Nguyen Robert Westendorp, Kishore Reddy Tarimala

TL;DR

The paper tackles passive indoor WiFi localization by exploiting RSSI and CSI fingerprints collected at WiFi routers, eliminating the need for software on mobile devices. It introduces RTS/CTS-assisted data augmentation for inactive phones and a two-stage fusion of RSSI and CSI for active phones, applying kernel-density SSP and P-MIMO LSTM to model fingerprints and trajectories. Extensive autonomous-robot experiments in office and home settings demonstrate localization errors of about $0.8$ m when active and $1.5$ m when inactive, with robustness to device heterogeneity and MAC randomization challenges. This work offers a practical, scalable passive localization solution that leverages existing WiFi infrastructure for high-precision indoor positioning without client-side software installation.

Abstract

This paper proposes passive WiFi indoor localization. Instead of using WiFi signals received by mobile devices as fingerprints, we use signals received by routers to locate the mobile carrier. Consequently, software installation on the mobile device is not required. To resolve the data insufficiency problem, flow control signals such as request to send (RTS) and clear to send (CTS) are utilized. In our model, received signal strength indicator (RSSI) and channel state information (CSI) are used as fingerprints for several algorithms, including deterministic, probabilistic and neural networks localization algorithms. We further investigated localization algorithms performance through extensive on-site experiments with various models of phones at hundreds of testing locations. We demonstrate that our passive scheme achieves an average localization error of 0.8 m when the phone is actively transmitting data frames and 1.5 m when it is not transmitting data frames.

Passive Indoor Localization with WiFi Fingerprints

TL;DR

The paper tackles passive indoor WiFi localization by exploiting RSSI and CSI fingerprints collected at WiFi routers, eliminating the need for software on mobile devices. It introduces RTS/CTS-assisted data augmentation for inactive phones and a two-stage fusion of RSSI and CSI for active phones, applying kernel-density SSP and P-MIMO LSTM to model fingerprints and trajectories. Extensive autonomous-robot experiments in office and home settings demonstrate localization errors of about m when active and m when inactive, with robustness to device heterogeneity and MAC randomization challenges. This work offers a practical, scalable passive localization solution that leverages existing WiFi infrastructure for high-precision indoor positioning without client-side software installation.

Abstract

This paper proposes passive WiFi indoor localization. Instead of using WiFi signals received by mobile devices as fingerprints, we use signals received by routers to locate the mobile carrier. Consequently, software installation on the mobile device is not required. To resolve the data insufficiency problem, flow control signals such as request to send (RTS) and clear to send (CTS) are utilized. In our model, received signal strength indicator (RSSI) and channel state information (CSI) are used as fingerprints for several algorithms, including deterministic, probabilistic and neural networks localization algorithms. We further investigated localization algorithms performance through extensive on-site experiments with various models of phones at hundreds of testing locations. We demonstrate that our passive scheme achieves an average localization error of 0.8 m when the phone is actively transmitting data frames and 1.5 m when it is not transmitting data frames.
Paper Structure (18 sections, 2 equations, 7 figures, 3 tables)

This paper contains 18 sections, 2 equations, 7 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related work
  3. Indoor Localization Algorithms
  4. Device Heterogeneity
  5. Proposed Passive Localization System
  6. Inactive Phone Localization
  7. Active Phone Localization
  8. Localization Algorithms
  9. Inactive Phone Localization
  10. Active Phone Localization
  11. Database And Experiments
  12. Results And Discussions
  13. Device Heterogeneity
  14. MAC Randomization
  15. Antenna Orientation
  16. ...and 3 more sections

Figures (7)

  • Figure 1: Proposed Localization Process
  • Figure 2: Data transmission scheme when: (a) the phone is inactive and the RTS/CTS mechanism is executed, (b) the phone is actively exchanging data frames with the AP, (c) the phone's transmitted packets are plotted over time while the phone is inactive, (d) the phone's transmitted packets are plotted over time while the phone is responding to RTS/CTS packets and is not connected to anything, (e) the cumulative distribution functions of the Samsung Galaxy S6's transmitted packets are plotted over time, and (f) PDF of RSSI for various devices: Nexus 5 (blue star), Samsung S6 (green square), iPhone X (black triangle), and the overall PDF (red circle) at a fixed location.
  • Figure 3: CSI from a Samsung Galaxy S6 phone at 2 fixed locations (a) CSI amplitude images. (b) CSI phase difference.
  • Figure 4: (a) Office experiment floor map. (b) Home experiment floor map. (c) RSSI heat map of office experiment. (d) RSSI heat map of home experiment.
  • Figure 5: Number of received RSSI packets from different phones.
  • ...and 2 more figures