pyrtklib: An open-source package for tightly coupled deep learning and GNSS integration for positioning in urban canyons

TL;DR

Comparative analyses demonstrate that the proposed innovative indirect training approach using deep learning to optimize both pseudorange bias and weight estimation surpasses established tools like goGPS and RTKLIB in positioning accuracy, marking a significant advancement in the field.

Abstract

Artificial intelligence (AI) is revolutionizing numerous fields, with increasing applications in Global Navigation Satellite Systems (GNSS) positioning algorithms in intelligent transportation systems (ITS) via deep learning. However, a significant technological disparity exists as traditional GNSS algorithms are often developed in Fortran or C, contrasting with the Python-based implementation prevalent in deep learning tools. To address this discrepancy, this paper introduces pyrtklib, a Python binding for the widely utilized open-source GNSS tool, RTKLIB. This binding makes all RTKLIB functionalities accessible in Python, facilitating seamless integration. Moreover, we present a deep learning subsystem under pyrtklib, which is a novel deep learning framework that leverages pyrtklib to accurately predict weights and biases within the GNSS positioning process. The use of pyrtklib enables developers to easily and quickly prototype and implement deep learning-aided GNSS algorithms, showcasing its potential to enhance positioning accuracy significantly.

Figures (7)

• Figure 1: The detailed structure of the bias network and weight network.
• Figure 2: The loss curves of bias and weight network training process. The blue curve is the mean position loss of the bias network and the green curve is for weight network.
• Figure 3: The boxplot for 3D error of the compared methods on the three datasets.
• Figure 4: The detailed 3D error of the compared methods on the three datasets.
• Figure 5: The trajectory and ground truth of the compared methods on the three datasets.