Open AccessVehicle Location Algorithm Based on Federated Learning and Smart Phone in GNSS Low Sampling Rate Scene
Author(s) -
Wenbiao Guo,
Hang Li,
Feng Yin,
Bo Ai
Publication year - 2021
Publication title -
journal of physics. conference series
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.21
H-Index - 85
eISSN - 1742-6596
pISSN - 1742-6588
DOI - 10.1088/1742-6596/2066/1/012052
Subject(s) - gnss applications , computer science , satellite system , real time computing , global positioning system , precise point positioning , algorithm , positioning system , sensor fusion , positioning technology , inertial navigation system , phone , artificial intelligence , engineering , telecommunications , inertial frame of reference , linguistics , philosophy , physics , structural engineering , quantum mechanics , node (physics)
In the existing vehicle positioning system based on Global Navigation Satellite System/Inertial Navigation System (GNSS/INS), when the GNSS signal is lost, the error accumulated by using only the INS will damage the positioning accuracy. In order to improve the accuracy, this paper proposed a positioning method based on data-driven and learning models, which utilized distributed data sets to collaboratively construct accurate positioning models through federated fusion algorithms without sacrificing user privacy. In the field scenarios of IID and Non-IID types, this paper compared the performance of INS and the existing two typical methods, DeepSense and PVAUA, it is verified that the two federated learning algorithm models constructed had higher positioning accuracy in different scenarios and different GNSS signal loss durations. The results were analyzed.