Enconv1d Model Based on Pseudolite System for Long-Tunnel Positioning

Pseudolite positioning systems offer precise localization when GPS signals are unavailable, advancing the development of intelligent transportation systems. However, in confined indoor environments such as kilometer-long tunnels, where vehicles move at high speeds, traditional pseudolite algorithms struggle to establish accurate physical models linking signals to spatial domains. This study introduces a deep learning-based pseudolite positioning algorithm leveraging a spatio-temporal fusion framework to address challenges such as signal attenuation, multipath effects, and non-line-of-sight (NLOS) effects. The Enconv1d model we developed is based on the spatio-temporal characteristics of the pseudolite observation signals. The model employs the encoder module from the Transformer to capture multi-step time constraints while introducing a multi-scale one-dimensional convolutional neural network module (1D CNN) to assist the encoder module in learning spatial features and finally outputs the localization results of the Enconv1d model after the dense layer integration. Four experimental tests in a 4.6 km long real-world tunnel demonstrate that the proposed framework delivers continuous decimeter-level positioning accuracy.