Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

KD-EKF: Knowledge-Distilled Adaptive Covariance EKF for Robust UWB/PDR Indoor Localization

Kyeonghyun Yoo, Wooyong Jung, Namkyung Yoon, Sangmin Lee, Sanghong Kim, Hwangnam Kim

Abstract

Ultra-wideband (UWB) indoor localization provides centimeter-level accuracy and low latency, but its measurement reliability degrades severely under Non-Line-of-Sight (NLOS) conditions, leading to meter-scale ranging errors and inconsistent uncertainty characteristics. Inertial Measurement Unit (IMU)-based Pedestrian Dead Reckoning (PDR) complements UWB by providing infrastructure-free motion estimation; however, its error accumulates nonlinearly over time due to bias and noise propagation. Fusion methods based on Extended Kalman Filters (EKF) and Particle Filters (PF) can improve average localization accuracy through probabilistic state estimation. However, these approaches typically rely on manually tuned measurement covariances. Such fixed or heuristically tuned parameters are hard to sustain across varying indoor layouts, NLOS ratios, and motion patterns, leading to limited robustness and poor generalization of measurement uncertainty modeling in heterogeneous environments. To address this limitation, this work proposes an adaptive measurement covariance scaling framework in which reliability cues are learned from historical UWB/PDR trajectories. A large teacher model is employed offline to generate temporally consistent next-position predictions from structured UWB/PDR sequences, and this behavior is distilled into a lightweight student model suitable for real-time deployment. The student model continuously regulates EKF measurement covariances based on prediction residuals, enabling environment-aware fusion without manual re-tuning. Experimental results demonstrate that the proposed KD-EKF framework significantly reduces localization error, suppresses error spikes during Line-of-Sight (LOS)/NLOS transitions, and mitigates long-term drift compared to fixed-parameter EKF, thereby improving measurement robustness across diverse indoor environments.

KD-EKF: Knowledge-Distilled Adaptive Covariance EKF for Robust UWB/PDR Indoor Localization

Abstract

Ultra-wideband (UWB) indoor localization provides centimeter-level accuracy and low latency, but its measurement reliability degrades severely under Non-Line-of-Sight (NLOS) conditions, leading to meter-scale ranging errors and inconsistent uncertainty characteristics. Inertial Measurement Unit (IMU)-based Pedestrian Dead Reckoning (PDR) complements UWB by providing infrastructure-free motion estimation; however, its error accumulates nonlinearly over time due to bias and noise propagation. Fusion methods based on Extended Kalman Filters (EKF) and Particle Filters (PF) can improve average localization accuracy through probabilistic state estimation. However, these approaches typically rely on manually tuned measurement covariances. Such fixed or heuristically tuned parameters are hard to sustain across varying indoor layouts, NLOS ratios, and motion patterns, leading to limited robustness and poor generalization of measurement uncertainty modeling in heterogeneous environments. To address this limitation, this work proposes an adaptive measurement covariance scaling framework in which reliability cues are learned from historical UWB/PDR trajectories. A large teacher model is employed offline to generate temporally consistent next-position predictions from structured UWB/PDR sequences, and this behavior is distilled into a lightweight student model suitable for real-time deployment. The student model continuously regulates EKF measurement covariances based on prediction residuals, enabling environment-aware fusion without manual re-tuning. Experimental results demonstrate that the proposed KD-EKF framework significantly reduces localization error, suppresses error spikes during Line-of-Sight (LOS)/NLOS transitions, and mitigates long-term drift compared to fixed-parameter EKF, thereby improving measurement robustness across diverse indoor environments.
Paper Structure (22 sections, 8 equations, 7 figures, 5 tables, 1 algorithm)

This paper contains 22 sections, 8 equations, 7 figures, 5 tables, 1 algorithm.

Table of Contents

  1. Introduction
  2. Related Work
  3. System Design
  4. UWB Positioning using DS-TWR Trilateration
  5. PDR using Chest-Mounted IMU
  6. Offline Stage: LLM Teacher-Student Knowledge Distillation
  7. Teacher LLM for Position Regression
  8. Knowledge Distillation
  9. Lightweight Student Model
  10. Online Stage: Error-Based Adaptive Sensor Fusion
  11. Evaluation
  12. Experimental Setup
  13. Prompt-Based Position Regression Performance and Knowledge Distillation Effect
  14. Teacher-Student Inference Latency and Throughput Comparison
  15. KD-EKF Localization Performance Under LOS/NLOS Variations
  16. ...and 7 more sections

Figures (7)

  • Figure 1: Two-stage system overview of the proposed KD–EKF hybrid localization framework.
  • Figure 2: Floor plans and experimental trajectories used in the evaluation. Green areas denote LOS areas covered by UWB anchors, while orange areas indicate NLOS areas without anchor coverage. Experiment 1 represents a short-range environment with separated LOS/NLOS segments, whereas Experiment 2 corresponds to a closed rectangular corridor with repeated LOS/NLOS transitions.
  • Figure 3: Experimental hardware configuration. (a) Mobile tag device integrating a Raspberry Pi, a DWM1000 UWB module, and an IMU sensor for PDR preprocessing. (b) Fixed UWB anchor device based on the DWM1000 module deployed in LOS areas.
  • Figure 4: CDF of Absolute Trajectory Error (ATE)
  • Figure 5: Comparison of estimated trajectories for Experiment 1 in a short-range environment with mixed LOS/NLOS conditions.
  • ...and 2 more figures