Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
169 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

GNSS Positioning using Cost Function Regulated Multilateration and Graph Neural Networks (2402.18630v1)

Published 28 Feb 2024 in cs.LG and eess.SP

Abstract: In urban environments, where line-of-sight signals from GNSS satellites are frequently blocked by high-rise objects, GNSS receivers are subject to large errors in measuring satellite ranges. Heuristic methods are commonly used to estimate these errors and reduce the impact of noisy measurements on localization accuracy. In our work, we replace these error estimation heuristics with a deep learning model based on Graph Neural Networks. Additionally, by analyzing the cost function of the multilateration process, we derive an optimal method to utilize the estimated errors. Our approach guarantees that the multilateration converges to the receiver's location as the error estimation accuracy increases. We evaluate our solution on a real-world dataset containing more than 100k GNSS epochs, collected from multiple cities with diverse characteristics. The empirical results show improvements from 40% to 80% in the horizontal localization error against recent deep learning baselines as well as classical localization approaches.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (36)
  1. Gnss positioning accuracy enhancement based on robust statistical mm estimation theory for ground vehicles in challenging environments. Applied sciences, 8(6):876.
  2. Betz, J. W. (2021). Fundamentals of satellite-based navigation and timing. In Morton, Y. J., van Diggelen, F., Spilker Jr, J. J., Parkinson, B. W., Lo, S., and Gao, G. E., editors, Position, navigation, and timing technologies in the 21st century: Integrated satellite navigation, sensor systems, and civil applications, volume 1. John Wiley & Sons.
  3. Gps meteorology: Mapping zenith wet delays onto precipitable water. Journal of Applied Meteorology (1988-2005), pages 379–386.
  4. Sagnac effect and set error based pseudorange modeling for gps applications. Procedia Computer Science, 87:172–177.
  5. Geometric deep learning: Grids, groups, graphs, geodesics, and gauges. arXiv preprint arXiv:2104.13478.
  6. A note on over-smoothing for graph neural networks. arXiv preprint arXiv:2006.13318.
  7. Machine learning correction for improved pvt accuracy. In Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), pages 3392–3401.
  8. Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In Proceedings of the AAAI conference on artificial intelligence, volume 34, pages 3438–3445.
  9. Neural message passing for quantum chemistry. In International conference on machine learning, pages 1263–1272. PMLR.
  10. Height aiding, c/n0 weighting and consistency checking for gnss nlos and multipath mitigation in urban areas. The Journal of Navigation, 66(5):653–669.
  11. A novel self-learning gnss/ins integrated navigation method. In Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), pages 168–179.
  12. Designing deep neural networks for sequential gnss positioning. In Proceedings of the 35th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2022), pages 1209–1219.
  13. Inductive representation learning on large graphs. Advances in neural information processing systems, 30.
  14. Precise positioning with machine learning based kalman filter using gnss/imu measurements from android smartphone. In Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), pages 3094–3102.
  15. Variances of gps phase observations: the sigma-ε𝜀\varepsilonitalic_ε model. GPS solutions, 2:35–43.
  16. Long short-term memory. Neural computation, 9(8):1735–1780.
  17. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, pages 448–456. pmlr.
  18. Improving gnss positioning using neural-network-based corrections. NAVIGATION: Journal of the Institute of Navigation, 69(4).
  19. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980.
  20. Semi-supervised classification with graph convolutional networks. arXiv preprint arXiv:1609.02907.
  21. Klobuchar, J. A. (1987). Ionospheric time-delay algorithm for single-frequency gps users. IEEE Transactions on aerospace and electronic systems, (3):325–331.
  22. Rectifier nonlinearities improve neural network acoustic models. In Proc. icml, volume 30, page 3. Atlanta, Georgia, USA.
  23. Learning gnss positioning corrections for smartphones using graph convolution neural networks. In Proceedings of the 35th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2022), pages 2215–2225.
  24. Fundamentals of inertial navigation, satellite-based positioning and their integration. Springer Science & Business Media.
  25. The graph neural network model. IEEE transactions on neural networks, 20(1):61–80.
  26. Improving precision gnss positioning and navigation accuracy on smartphones using machine learning. In Proceedings of the 34th International Technical Meeting of the Satellite Division of The Institute of Navigation (ION GNSS+ 2021), pages 3081–3093.
  27. Nlos multipath classification of gnss signal correlation output using machine learning. Sensors, 21(7):2503.
  28. Reliable urban canyon navigation solution in gps and glonass integrated receiver using improved fuzzy weighted least-square method. Wireless Personal Communications, 94:3181–3196.
  29. Graph attention networks. arXiv preprint arXiv:1710.10903.
  30. Weighted dop with consideration on elevation-dependent range errors of gnss satellites. IEEE Transactions on Instrumentation and Measurement, 61(12):3241–3250.
  31. A comprehensive survey on graph neural networks. IEEE transactions on neural networks and learning systems, 32(1):4–24.
  32. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826.
  33. Graphrnn: Generating realistic graphs with deep auto-regressive models. In International conference on machine learning, pages 5708–5717. PMLR.
  34. Deep sets. Advances in neural information processing systems, 30.
  35. Prediction on the urban gnss measurement uncertainty based on deep learning networks with long short-term memory. IEEE Sensors Journal, 21(18):20563–20577.
  36. Graph neural networks: A review of methods and applications. AI open, 1:57–81.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now