Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Train Localization During GNSS Outages: A Minimalist Approach Using Track Geometry And IMU Sensor Data

Wendi Löffler, Mats Bengtsson

TL;DR

The paper addresses reliable train localization under GNSS outages by proposing a map-constrained particle filter that fuses a minimalist IMU sensor suite with a discrete track map treated as a Look-Up Table. By reducing the state to a 1D distance along the track, the method projects into 2D map coordinates via the LUT and uses curvature-enhanced observations to update the filter, with IMU processing and ZVU to curb drift. On the WinterRailDataSetOctober2018, the approach achieves robust positioning during outages (absolute errors below 10 m in the tested scenarios) and outperforms a map-enabled EKF (EKFMM) in outage conditions, especially on curved sections where the track geometry provides strong constraints. The solution offers a practical, computationally light redundancy to existing GNSS/IMU systems, and can be extended as a complementary component in more comprehensive rail localization frameworks. Future work includes broader scenario testing and refined bias correction to bolster stand-alone applicability.

Abstract

Train localization during Global Navigation Satellite Systems (GNSS) outages presents challenges for ensuring failsafe and accurate positioning in railway networks. This paper proposes a minimalist approach exploiting track geometry and Inertial Measurement Unit (IMU) sensor data. By integrating a discrete track map as a Look-Up Table (LUT) into a Particle Filter (PF) based solution, accurate train positioning is achieved with only an IMU sensor and track map data. The approach is tested on an open railway positioning data set, showing that accurate positioning (absolute errors below 10 m) can be maintained during GNSS outages up to 30 s in the given data. We simulate outages on different track segments and show that accurate positioning is reached during track curves and curvy railway lines. The approach can be used as a redundant complement to established positioning solutions to increase the position estimate's reliability and robustness.

Train Localization During GNSS Outages: A Minimalist Approach Using Track Geometry And IMU Sensor Data

TL;DR

The paper addresses reliable train localization under GNSS outages by proposing a map-constrained particle filter that fuses a minimalist IMU sensor suite with a discrete track map treated as a Look-Up Table. By reducing the state to a 1D distance along the track, the method projects into 2D map coordinates via the LUT and uses curvature-enhanced observations to update the filter, with IMU processing and ZVU to curb drift. On the WinterRailDataSetOctober2018, the approach achieves robust positioning during outages (absolute errors below 10 m in the tested scenarios) and outperforms a map-enabled EKF (EKFMM) in outage conditions, especially on curved sections where the track geometry provides strong constraints. The solution offers a practical, computationally light redundancy to existing GNSS/IMU systems, and can be extended as a complementary component in more comprehensive rail localization frameworks. Future work includes broader scenario testing and refined bias correction to bolster stand-alone applicability.

Abstract

Train localization during Global Navigation Satellite Systems (GNSS) outages presents challenges for ensuring failsafe and accurate positioning in railway networks. This paper proposes a minimalist approach exploiting track geometry and Inertial Measurement Unit (IMU) sensor data. By integrating a discrete track map as a Look-Up Table (LUT) into a Particle Filter (PF) based solution, accurate train positioning is achieved with only an IMU sensor and track map data. The approach is tested on an open railway positioning data set, showing that accurate positioning (absolute errors below 10 m) can be maintained during GNSS outages up to 30 s in the given data. We simulate outages on different track segments and show that accurate positioning is reached during track curves and curvy railway lines. The approach can be used as a redundant complement to established positioning solutions to increase the position estimate's reliability and robustness.
Paper Structure (13 sections, 19 equations, 10 figures, 1 table, 1 algorithm)

This paper contains 13 sections, 19 equations, 10 figures, 1 table, 1 algorithm.

Table of Contents

  1. Introduction
  2. Enhanced geometric track map and track constraint formulation
  3. Derivation of map curvature
  4. Map Matching and interpolation of map data
  5. Map-constrained particle filter
  6. Dynamic Motion Model
  7. Observation Model
  8. IMU Processing
  9. Complete Particle Filter Setup
  10. Experimental Results
  11. Evaluation using experimental data
  12. Indefinite GNSS outage on different track characteristics
  13. Conclusion

Figures (10)

  • Figure 1: Considered set up in this paper. Our proposed solution exploits an IMU and a track map.
  • Figure 2: Visualization of variables stored from the track map
  • Figure 3: Overview of complete algorithm
  • Figure 4: Visualization of observation model
  • Figure 5: Comparison of different methods during a short GNSS outage
  • ...and 5 more figures