A Novel FECAM-iTransformer Algorithm for Assisting INS/GNSS Navigation System during GNSS Outages
Source abstract
Abstract
In the field of navigation and positioning, the inertial navigation system (INS)/global navigation satellite system (GNSS) integrated navigation system is known for providing stable and high-precision navigation services for vehicles. However, in extreme scenarios where GNSS navigation data are completely interrupted, the positioning accuracy of these integrated systems declines sharply. While there has been considerable research into using neural networks to replace the GNSS signal output during such interruptions, these approaches often lack targeted modeling of sensor information, resulting in poor navigation stability. In this study, we propose an integrated navigation system assisted by a novel neural network: an inverted-Transformer (iTransformer) and the application of a frequency-enhanced channel attention mechanism (FECAM) to enhance its performance, called an INS/FECAM-iTransformer integrated navigation system. The key advantage of this system lies in its ability to simultaneously extract features from both the time and frequency domains and capture the variable correlations among multi-channel measurements, thereby enhancing the modeling capabilities for sensor data. In the experimental part, a public dataset and a private dataset are used for testing. The best experimental results show that compared to a pure INS inertial navigation system, the position error of the INS/FECAM-iTransformer integrated navigation system reduces by up to 99.9%. Compared to the INS/LSTM (long short-term memory) and INS/GRU (gated recurrent unit) integrated navigation systems, the position error of the proposed method decreases by up to 82.4% and 78.2%, respectively. The proposed approach offers significantly higher navigation accuracy and stability.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Inertial Sensor and Navigation
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Engineering, Shanghai Ocean University, No. 999 Hucheng Ring Road, Shanghai 201306, China
Funding
National Key Research and Development Program of China: Design and Development of High Performance Marine Electric Field Sensor
References (36)
Show source-provided references
1. PNT intelligent services
2. Groves, P.D., Wang, L., Walter, D., Martin, H., Voutsis, K., and Jiang, Z. (2014, January 5–8). The four key challenges of advanced multisensor navigation and positioning. Proceedings of the 2014 IEEE/ION Position, Location and Navigation Symposium—PLANS 2014, Monterey, CA, USA.10.1109/PLANS.2014.6851443 ↗
3. A Robust In-Motion Optimization-Based Alignment for SINS/GPS Integration10.1109/TITS.2020.3044084 ↗
4. An inertial and global positioning system based algorithm for ownship navigation10.1504/IJSNET.2021.119487 ↗
5. Vehicle Ego-Localization Based on Streetscape Image Database Under Blind Area of Global Positioning System10.1007/s12204-018-2008-8 ↗
6. Multi-sensor fusion methodology for enhanced land vehicle positioning10.1016/j.inffus.2018.04.006 ↗
7. A novel hybrid approach based-SRG model for vehicle position prediction in multi-GPS outage conditions10.1016/j.inffus.2017.07.002 ↗
8. Adaptive Fuzzy Prediction of Low-Cost Inertial-Based Positioning Errors10.1109/TFUZZ.2006.889936 ↗
9. Gao, J., Li, K., and Chen, J. (2020). Research on the Integrated Navigation Technology of SINS with Couple Odometers for Land Vehicles. Sensors, 20.10.3390/s20020546 ↗
10. An adaptive interactive multi-model navigation method based on UUV10.1016/j.oceaneng.2022.113217 ↗
11. Online Calibration Method of DVL Error Based on Improved Integrated Navigation Model10.1109/JSEN.2022.3208327 ↗
12. Improved Gaussian process regression-based method to bridge GPS outages in INS/GPS integrated navigation systems10.1016/j.measurement.2024.114432 ↗
13. Jwo, D.-J., Biswal, A., and Mir, I.A. (2023). Artificial Neural Networks for Navigation Systems: A Review of Recent Research. Appl. Sci., 13.10.3390/app13074475 ↗
14. Online INS/GPS integration with a radial basis function neural network10.1109/MAES.2005.1412121 ↗
15. Sensor Integration for Satellite-Based Vehicular Navigation Using Neural Networks10.1109/TNN.2006.890811 ↗
16. GA-SVR and Pseudo-position-aided GPS/INS Integration during GPS Outage10.1017/S037346331500003X ↗
17. Fang, W., Jiang, J., Lu, S., Gong, Y., Tao, Y., Tang, Y., Yan, P., Luo, H., and Liu, J. (2020). A LSTM Algorithm Estimating Pseudo Measurements for Aiding INS during GNSS Signal Outages. Remote Sens., 12.10.3390/rs12020256 ↗
18. A GNSS/INS Integrated Navigation Compensation Method Based on CNN–GRU + IRAKF Hybrid Model During GNSS Outages
19. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, Ł., and Polosukhin, I. (2017, January 4–9). Attention is all you need. Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017), Long Beach, CA, USA.
20. Wang, H., Tang, F., Wei, J., Zhu, B., Wang, Y., and Zhang, K. (2024). Online Semi-supervised Transformer for Resilient Vehicle GNSS/INS Navigation. IEEE Trans. Veh. Technol., 1–16. early access.10.1109/TVT.2024.3422680 ↗
21. An Adaptive Integrated Positioning Method for Urban Vehicles Based on Multitask Heterogeneous Deep Learning During GNSS Outages10.1109/JSEN.2023.3302796 ↗
22. Long Short-Term Memory10.1162/neco.1997.9.8.1735 ↗
23. Chung, J., Gulcehre, C., Cho, K., and Bengio, Y. (2014). Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling. arXiv.
24. Kim, T., Kim, J., Tae, Y., Park, C., Choi, J., and Choo, J. (2022, January 25–29). Reversible Instance Normalization for Accurate Time-Series Forecasting against Distribution Shift. Proceedings of the International Conference on Learning Representations, Online. Available online: https://api.semanticscholar.org/CorpusID:251647808.
25. Liu, Y., Hu, T., Zhang, H., Wu, H., Wang, S., Ma, L., and Long, M.J.A. (2024, January 7–11). iTransformer: Inverted Transformers Are Effective for Time Series Forecasting. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria.
26. System noise variance matrix adaptive Kalman filter method for AUV INS/DVL navigation system10.1016/j.oceaneng.2022.113269 ↗
27. Zihajehzadeh, S., and Park, E.J. (2017, January 11–15). A Gaussian process regression model for walking speed estimation using a head-worn IMU. Proceedings of the 2017 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).10.1109/EMBC.2017.8037326 ↗
28. Bolotin, Y., and Savin, V. (2023). Turntable IMU Calibration Algorithm Based on the Fourier Transform Technique. Sensing, 23.10.3390/s23021045 ↗
29. Lee-Thorp, J., Ainslie, J., Eckstein, I., and Ontañón, S.J.A. (2022, January 10–15). FNet: Mixing Tokens with Fourier Transforms. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL 2022), Seattle, WA, USA.10.18653/v1/2022.naacl-main.319 ↗
30. Zhou, T., Ma, Z., Wen, Q., Wang, X., Sun, L., and Jin, R.J.A. (2022, January 17–23). FEDformer: Frequency Enhanced Decomposed Transformer for Long-term Series Forecasting. Proceedings of the 39th International Conference on Machine Learning (ICML 2022), Baltimore, Maryland.
31. Xu, Z., Zeng, A., and Xu, Q. (2024, January 7–11). FITS: Modeling Time Series with 10k Parameters. Proceedings of the Twelfth International Conference on Learning Representations (ICLR 2024), Vienna, Austria.
32. FECAM: Frequency enhanced channel attention mechanism for time series forecasting10.1016/j.aei.2023.102158 ↗
33. Zhao, S., Zhou, Y., and Huang, T. (2022). A Novel Method for AI-Assisted INS/GNSS Navigation System Based on CNN-GRU and CKF during GNSS Outage. Remote Sens., 14.10.3390/rs14184494 ↗
34. Tamer, B. (2001). A New Approach to Linear Filtering and Prediction Problems. Control Theory: Twenty-Five Seminal Papers (1932–1981), IEEE.
35. Vision-aided inertial navigation for pin-point landing using observations of mapped landmarks10.1002/rob.20189 ↗
36. Dual-optimization for a MEMS-INS/GPS system during GPS outages based on the cubature Kalman filter and neural networks10.1016/j.ymssp.2019.07.003 ↗