Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Environment-Aware Indoor LoRaWAN Ranging Using Path Loss Model Inversion and Adaptive RSSI Filtering

Nahshon Mokua Obiri, Kristof Van Laerhoven

TL;DR

This work tackles indoor LoRaWAN ranging with a single gateway by addressing non-stationary RSSI attenuation from multipath, occupancy, and micro-climate dynamics. It combines an environment-aware multi-wall path loss model (MWM-EP) with a forward-only Kalman RSSI prefilter, enabling deterministic distance inversion and robust per-packet estimates. On a year-long office dataset with over 2 million uplinks, the approach achieves a mean absolute error of $4.74\,\mathrm{m}$ and RMSE of $6.76\,\mathrm{m}$, substantially outperforming the COST-231 multi-wall baseline and its environment-augmented variant, while reducing RSSI volatility by $43.29\%$. The method remains interpretable and computationally light ($O(1)$ per packet), offering a strong building block for multi-gateway localization and guiding future validation across diverse sites and deployment scenarios.

Abstract

Achieving sub-10 m indoor ranging with LoRaWAN is difficult because multipath, human blockage, and micro-climate dynamics induce non-stationary attenuation in received signal strength indicator (RSSI) measurements. We present a lightweight, interpretable pipeline that couples an environment-aware multi-wall path loss model with a forward-only, innovation-driven Kalman prefilter for RSSI. The model augments distance and wall terms with frequency, signal-to-noise ratio (SNR), and co-located environmental covariates (temperature, relative humidity, carbon dioxide, particulate matter, and barometric pressure), and is inverted deterministically for distance estimation. On a one-year single-gateway office dataset comprising over 2 million uplinks, the approach attains a mean absolute error (MAE) of 4.74 m and a root mean square error (RMSE) of 6.76 m in distance estimation, improving over a COST-231 multi-wall baseline (12.07 m MAE) and its environment-augmented variant (7.76 m MAE. Filtering reduces RSSI volatility from 10.33 to 5.43 dB and halves path loss error to 5.35 dB while raising R-squared from 0.82 to 0.89. The result is a single-anchor LoRaWAN ranging method with constant per-packet cost that is accurate, robust, and interpretable, providing a strong building block for multi-gateway localization.

Environment-Aware Indoor LoRaWAN Ranging Using Path Loss Model Inversion and Adaptive RSSI Filtering

TL;DR

This work tackles indoor LoRaWAN ranging with a single gateway by addressing non-stationary RSSI attenuation from multipath, occupancy, and micro-climate dynamics. It combines an environment-aware multi-wall path loss model (MWM-EP) with a forward-only Kalman RSSI prefilter, enabling deterministic distance inversion and robust per-packet estimates. On a year-long office dataset with over 2 million uplinks, the approach achieves a mean absolute error of and RMSE of , substantially outperforming the COST-231 multi-wall baseline and its environment-augmented variant, while reducing RSSI volatility by . The method remains interpretable and computationally light ( per packet), offering a strong building block for multi-gateway localization and guiding future validation across diverse sites and deployment scenarios.

Abstract

Achieving sub-10 m indoor ranging with LoRaWAN is difficult because multipath, human blockage, and micro-climate dynamics induce non-stationary attenuation in received signal strength indicator (RSSI) measurements. We present a lightweight, interpretable pipeline that couples an environment-aware multi-wall path loss model with a forward-only, innovation-driven Kalman prefilter for RSSI. The model augments distance and wall terms with frequency, signal-to-noise ratio (SNR), and co-located environmental covariates (temperature, relative humidity, carbon dioxide, particulate matter, and barometric pressure), and is inverted deterministically for distance estimation. On a one-year single-gateway office dataset comprising over 2 million uplinks, the approach attains a mean absolute error (MAE) of 4.74 m and a root mean square error (RMSE) of 6.76 m in distance estimation, improving over a COST-231 multi-wall baseline (12.07 m MAE) and its environment-augmented variant (7.76 m MAE. Filtering reduces RSSI volatility from 10.33 to 5.43 dB and halves path loss error to 5.35 dB while raising R-squared from 0.82 to 0.89. The result is a single-anchor LoRaWAN ranging method with constant per-packet cost that is accurate, robust, and interpretable, providing a strong building block for multi-gateway localization.
Paper Structure (11 sections, 1 equation, 4 figures, 1 table)

This paper contains 11 sections, 1 equation, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Design and Methodology
  3. Data Collection Campaign
  4. Kalman Filtering for RSSI Refinement
  5. Environment-Aware Path Loss Modeling
  6. Deterministic Distance Estimation
  7. Evaluation Results and Discussion
  8. Kalman Filtering Performance
  9. Path Loss Modeling Evaluation
  10. Distance Estimation Analysis
  11. Conclusion, Limitations and Future Outlook

Figures (4)

  • Figure 1: Data campaign design and deployment: (a) indoor gateway (GW), (b) sensor network, (c) fabricated end nodes (EN0–EN5).
  • Figure 2: Comparison of predicted and actual path loss for the MWM, MWM-EP, and MWM-EP-KF models with (a) measured and (b) filtered RSSI.
  • Figure 3: Distance estimation error comparison across models: (a) RMSE, (b) MAE, (c) median absolute error, and (d) empirical cumulative distribution error (CDE).
  • Figure 4: Relative error distributions per device for the MWM, the MWM-EP, and the MWM-EP-KF. Whiskers extend to $1.5\times\mathrm{IQR}$.