Tampere University of Technology

TUTCRIS Research Portal

Improvement of GPS and BeiDou extended orbit predictions with CNNs

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Standard

Improvement of GPS and BeiDou extended orbit predictions with CNNs. / Pihlajasalo, Jaakko; Leppäkoski, Helena; Ali-Löytty, Simo; Piché, Robert.

26th European Navigation Conference, ENC 2018: Gothenburg, Sweden, 14-17 May, 2018. IEEE, 2018. p. 54-59 8433244.

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

Harvard

Pihlajasalo, J, Leppäkoski, H, Ali-Löytty, S & Piché, R 2018, Improvement of GPS and BeiDou extended orbit predictions with CNNs. in 26th European Navigation Conference, ENC 2018: Gothenburg, Sweden, 14-17 May, 2018., 8433244, IEEE, pp. 54-59, European Navigation Conference, 20/09/18. https://doi.org/10.1109/EURONAV.2018.8433244

APA

Pihlajasalo, J., Leppäkoski, H., Ali-Löytty, S., & Piché, R. (2018). Improvement of GPS and BeiDou extended orbit predictions with CNNs. In 26th European Navigation Conference, ENC 2018: Gothenburg, Sweden, 14-17 May, 2018 (pp. 54-59). [8433244] IEEE. https://doi.org/10.1109/EURONAV.2018.8433244

Vancouver

Pihlajasalo J, Leppäkoski H, Ali-Löytty S, Piché R. Improvement of GPS and BeiDou extended orbit predictions with CNNs. In 26th European Navigation Conference, ENC 2018: Gothenburg, Sweden, 14-17 May, 2018. IEEE. 2018. p. 54-59. 8433244 https://doi.org/10.1109/EURONAV.2018.8433244

Author

Pihlajasalo, Jaakko ; Leppäkoski, Helena ; Ali-Löytty, Simo ; Piché, Robert. / Improvement of GPS and BeiDou extended orbit predictions with CNNs. 26th European Navigation Conference, ENC 2018: Gothenburg, Sweden, 14-17 May, 2018. IEEE, 2018. pp. 54-59

Bibtex - Download

@inproceedings{3af966d1d4d942719539583151708b0f,
title = "Improvement of GPS and BeiDou extended orbit predictions with CNNs",
abstract = "This paper presents a method for improving the accuracy of extended GNSS satellite orbit predictions with convolutional neural networks (CNN). Satellite orbit predictions are used in self-assisted GNSS to reduce the Time to First Fix of a satellite positioning device. We describe the models we use to predict the satellite orbit and present the improvement method that uses CNN. The CNN estimates future prediction errors of our model and these estimates are used to correct our orbit predictions. We also describe how the neural network can be implemented into our prediction algorithm. In tests with GPS and BeiDou data, the method significantly improves orbit prediction accuracy. For example, the 68{\%} error quantile of 7 day orbit prediction errors of GPS satellites was reduced by 45{\%} on average.",
author = "Jaakko Pihlajasalo and Helena Lepp{\"a}koski and Simo Ali-L{\"o}ytty and Robert Pich{\'e}",
note = "INT=mat,{"}Jaakko Pihlajasalo{"}",
year = "2018",
month = "8",
day = "10",
doi = "10.1109/EURONAV.2018.8433244",
language = "English",
isbn = "9781538649626",
pages = "54--59",
booktitle = "26th European Navigation Conference, ENC 2018",
publisher = "IEEE",

}

RIS (suitable for import to EndNote) - Download

TY - GEN

T1 - Improvement of GPS and BeiDou extended orbit predictions with CNNs

AU - Pihlajasalo, Jaakko

AU - Leppäkoski, Helena

AU - Ali-Löytty, Simo

AU - Piché, Robert

N1 - INT=mat,"Jaakko Pihlajasalo"

PY - 2018/8/10

Y1 - 2018/8/10

N2 - This paper presents a method for improving the accuracy of extended GNSS satellite orbit predictions with convolutional neural networks (CNN). Satellite orbit predictions are used in self-assisted GNSS to reduce the Time to First Fix of a satellite positioning device. We describe the models we use to predict the satellite orbit and present the improvement method that uses CNN. The CNN estimates future prediction errors of our model and these estimates are used to correct our orbit predictions. We also describe how the neural network can be implemented into our prediction algorithm. In tests with GPS and BeiDou data, the method significantly improves orbit prediction accuracy. For example, the 68% error quantile of 7 day orbit prediction errors of GPS satellites was reduced by 45% on average.

AB - This paper presents a method for improving the accuracy of extended GNSS satellite orbit predictions with convolutional neural networks (CNN). Satellite orbit predictions are used in self-assisted GNSS to reduce the Time to First Fix of a satellite positioning device. We describe the models we use to predict the satellite orbit and present the improvement method that uses CNN. The CNN estimates future prediction errors of our model and these estimates are used to correct our orbit predictions. We also describe how the neural network can be implemented into our prediction algorithm. In tests with GPS and BeiDou data, the method significantly improves orbit prediction accuracy. For example, the 68% error quantile of 7 day orbit prediction errors of GPS satellites was reduced by 45% on average.

U2 - 10.1109/EURONAV.2018.8433244

DO - 10.1109/EURONAV.2018.8433244

M3 - Conference contribution

SN - 9781538649626

SP - 54

EP - 59

BT - 26th European Navigation Conference, ENC 2018

PB - IEEE

ER -