2nd Place Winner of the Smartphone Decimeter Challenge: Improving Smartphone GNSS Positioning Using Gradient Descent Method

Shubin Dai

Abstract:	Smartphone’s GNSS chipsets provide raw measurements, which can be used to compute the smartphone’s position. Current mobile phones only offer 3-5 meters of positioning accuracy, to seek advanced research in smartphone GNSS positioning accuracy and help people better navigate the world around them, Google smartphone decimeter challenge 2022(GSDC2022) (kaggle, 2022) was held. The main challenge of this competition is the quality of the data, which make current existing algorithms hard to get good results on it. In this paper, we present global optimization method by using gradient descent, taking pseudorange, pseudorange rate, accumulate carrier phase (ADR) , phone speed and acceleration constraints of every time epoch on a track into account, it shows superiority over other methods such as precise point positioning and real-time kinematic. The final score of this solution is 1.499 on private leaderboard which was the second place in GSDC2022(kaggle, 2022).
Published in:	Proceedings of the 35th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2022) September 19 - 23, 2022 Hyatt Regency Denver Denver, Colorado
Pages:	2321 - 2328
Cite this article:	Dai, Shubin, "2nd Place Winner of the Smartphone Decimeter Challenge: Improving Smartphone GNSS Positioning Using Gradient Descent Method," Proceedings of the 35th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2022), Denver, Colorado, September 2022, pp. 2321-2328. https://doi.org/10.33012/2022.18380
Full Paper:	ION Members/Non-Members: 1 Download Credit Sign In