Abstract

Robot localization inside tunnels is a challenging task due to the special conditions of these environments. The GPS-denied nature of these scenarios, coupled with the low visibility, slippery and irregular surfaces, and lack of distinguishable visual and structural features, make traditional robotics methods based on cameras, lasers, or wheel encoders unreliable. Fortunately, tunnels provide other types of valuable information that can be used for localization purposes. On the one hand, radio frequency signal propagation in these types of scenarios shows a predictable periodic structure (periodic fadings) under certain settings, and on the other hand, tunnels present structural characteristics (e.g., galleries, emergency shelters) that must comply with safety regulations. The solution presented in this paper consists of detecting both types of features to be introduced as discrete sources of information in an alternative graph-based localization approach. The results obtained from experiments conducted in a real tunnel demonstrate the validity and suitability of the proposed system for inspection applications.

Highlights

  • Long road and railway tunnels are important structures that facilitate communication and play a decisive role in the functioning and development of regional economies

  • When the vehicle reached the area of the periodic fadings, some odometry error was accumulated as shown Figure 13b, where the radio frequency (RF) real values are represented with respect to the position estimated by the odometry

  • We have presented a graph-based localization approach for tunnel-like environments using different sources of information, including odometry data, absolute positions provided by an RF signal minima detector based on a theoretical fadings model acting as an RF map, and the absolute positions provided by a gallery detector

Read more

Summary

Introduction

Long road and railway tunnels (over 500 m) are important structures that facilitate communication and play a decisive role in the functioning and development of regional economies. As can be extracted from the Directive, many of them are pseudo-periodic along the longitudinal dimension In view of the latter, we propose the complementary use of structural characteristics originating from the safety regulations to increase localization accuracy using only fadings. The superposition of the modes will take place with different relative phases in different positions within the guide, producing constructive interference if both modes are in phase and destructive interference if the relative phase differs by an odd π multiple This gives rise to a periodic fading structure of the RF power inside the waveguide. The total electromagnetic field, which represents the propagation model, will be the superposition of all the propagation modes (see [1] for a complete 3D fadings structure analysis in tunnels) With this approximation, the obtained theoretical propagation model closely matches the experimental data. The similarity between both signals (Figure 3c) in the far sector is sufficient to make us consider them useful for localization purposes, using the propagation model as a position reference

Graph-Based Localization
The Canfranc Tunnel and Experiments Setup
Localization
Transverse Localization in a Tunnel
Longitudinal Localization in a Tunnel
Discrete Features Detection
Emergency Gallery Detection
Pattern Matching Gallery Detection
Generic Gallery Detection
RF Signal Fading Detection
Multi-Sensor Graph-Based Localization
Management of RF Fadings Minima Detection in the Pose Graph
Management of Gallery Detection in the Pose Graph
Experimental Results
Algorithm Implementation
Pattern-Based Gallery Detection
Graph-Based Localization Results
Graph-Based Localization Performance Evaluation
Conclusions
Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.