ITSC 2024 Paper Abstract

Close

Paper ThAT17.5

Wang, Siqi (Beijing Jiaotong University), Liu, Jiang (Beijing Jiaotong University), Cai, Baigen (Beijing Jiaotong University), Wang, Jian (Beijing Jiaotong University), Lu, Debiao (Beijing Jiaotong University)

GNSS Spoofing Detection and Elimination for Resilient Train Positioning Using Spiking Neural Network and Compressed Sensing

Scheduled for presentation during the Poster Session "Accurate Positioning and Localization" (ThAT17), Thursday, September 26, 2024, 10:30−12:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on December 26, 2024

Keywords Accurate Global Positioning

Abstract

The Global Navigation Satellite System (GNSS) technology has received considerable attention in railway train positioning because of the high autonomy of train-borne system. However, performance of GNSS-based train positioning may be greatly affected by GNSS spoofing attacks under complicated operation conditions. In order to mitigate the effects of spoofing on positioning and achieve a trustworthy estimation of the train position, this paper proposes a resilient positioning solution. In the proposed solution, anti-spoofing is realized by spoofing detection using the Spiking Neural Network (SNN), signal parameter estimation through Compressed Sensing (CS)-based sparse reconstruction, and recognition of the spoofing/authentic signals with odometer/trackmap-aided train location prediction. By re-constructing and removing the spoofing signal, and re-tracking the recovered spoofing-free signal, performance of the train position determination can be guaranteed. The proposed solution is assessed through tests under specific GNSS spoofing-injected scenarios. The results demonstrate that the proposed solution can effectively mitigate the negative effects of spoofing on position estimation, and improve the positioning accuracy and availability under spoofing attack conditions.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-12-26  06:32:55 PST  Terms of use