Position Accuracy Improvement of the Inertial Navigation System using LSTM Algorithm without GNSS Signals

Majlesi Journal of Electrical Engineering

مقاله 5، دوره 18، شماره 1، خرداد 2024، صفحه 45-53   

نوع مقاله: Reseach Article

شناسه دیجیتال (DOI): 10.30486/mjee.2023.1992635.1192

نویسندگان

Mohammad Sabzevari¹؛ Masoudreza Aghabozorgi Sahaf^{* 2}

¹Electrical Engineering Department, Yazd university, Yazd, IRAN

²Electrical Engineering Department, Yazd University, Yazd, Iran.

چکیده

Currently, satellite navigation systems on cars provide a promising means of making these vehicles unmanned in the future. There is a common problem with these systems due to the unavailability of satellite signals in tunnels, forests, and noisy areas. One of the methods used to solve this problem is by using inertial navigation systems as an auxiliary system. This system works by modeling errors and correcting them when GNSS signals are absent. A number of methods are available for error modeling such as Kalman filters, neural networks, and so on, each of which has its own advantages and disadvantages. The error of inertial navigation is modeled using LSTM deep neural networks in this article. In this neural network, the relationship between current and past data is modeled as long as the GNSS satellite signal is available to improve the output position of the inertial navigation system when the GNSS satellite signal can no longer be received. The proposed method has been tested on real car driving data, and the calculated position from the inertial navigation system in four maneuvers has been compared with the Extended Kalman Filter method outputs. According to the results of the experiments, the proposed algorithm has improved the position estimation by 60% on average during 30, 60, and 120 seconds without GNSS signals, compared to the inertial navigation system based on Extended Kalman filter.

کلیدواژه‌ها

Inertial Navigation System؛ GNSS؛ LSTM؛ Deep learning؛ Extended Kalman Filter؛ IMU

مراجع

• Delobel, R. Aufrere, C. Debain, R. Chapuis, and T. Chateau, “A realtimemap refinement method using a multi-sensor localization framework,”IEEE Trans. Intell. Transp. Syst., Vol. 20, No. 5, pp. 1644–1658, May 2019.
• Zhang and N. Masoud, “Increasing GPS localization accuracy withreinforcementlearning,”IEEE Trans. Intell. Transp. Syst., Vol. 22, No. 5,pp. 2615–2626, May 2021.
• Wang, Y.Dong, Z. Li, Q. Li, and J. Wu,“Constrained MEMS-basedGNSS/INS tightly coupled system with robust Kalman filter for accurateland vehicular navigation,”IEEE Trans. Instrum. Meas., Vol. 69, No. 7,pp. 5138–5148, Jul. 2020.
• K. Suhr, J. Jang, D. Min, and H. G. Jung, “Sensor fusion-based lowcostvehicle localization system for complex urban environments,”IEEETrans. Intell. Transp. Syst., Vol. 18, No. 5, pp. 1078–1086, May 2017.
• Li and L. Chang, “MEKF With Navigation Frame Attitude Error Parameterization for INS/GPS, ”in IEEE Sensors Journal, Vol. 20, No. 3, pp. 1536-1549, 2020.
• Ryu, J.Kang and D. Lee, “Performance Comparison between EKF and UKF in GPS/INS Low Observability Conditions, ”21st International Conference on Control, Automation and Systems (ICCAS), Korea, pp. 1911-1916, 2021.
• Benzerrouk, R. Landry, V. Nebylov and A. Nebylov,“Robust INS/GPS Coupled Navigation Based on Minimum Error Entropy Kalman Filtering, ”27th Saint Petersburg International Conference on Integrated Navigation Systems (ICINS), Russia, pp. 1-4, 2020.
• Guangcai, X. Xu, and T. Zhang, “M-M estimation based robustcubatureKalman filter for INS/GPS integrated navigation system,”IEEE Trans. Instrum. Meas.,Vol. 70, 2021,
• S.Arulampalam and et al., “A tutorial on particle filters for online nonlinear/non-Gaussian Bayesiantracking, ”IEEE Transactions on signal processing, pp.174-188,2002.
• Alspach, H.Sorenson,“NonlinearBayesian estimation using Gaussian sum approximations,”IEEEtransactions on automatic control, pp. 439-448, 1972.
• Andrei and M. Hever, “Q-Learning Model Covariance Adaptation of Rao-Blackwellized Particle Filtering in Airborne Geomagnetic Navigation,”IEEE/ION Position, Location and Navigation Symposium (PLANS), Monterey, CA, USA, pp. 143-149, 2023.
• Sharaf, R.; Noureldin, A. “Sensor integration for satellite-based vehicular navigation using neural networks, ”IEEE Trans. Neural Netw.,V 18, pp. 589–594,2017.
• W.Chiang, A.Noureldin and N.El-Sheimy, “Multi-sensors integration using neuron computing for land vehicle navigation, ”GPS Solution, Vol. 6, No. 3, pp. 209–218, 2003.
• Forrest, T. Spracklen, and N. Ryan, “An inertial navigation data fusion system employing an artificial neural network as the data integrator,” in Proc. ION NTM, Anaheim, CA, pp. 153–158, 2000.
• Toth, D.A.Grejner-Brzezinska and S.Moafipoor, “Pedestrian Tracking and Navigation Using Neural Networks and Fuzzy Logic, ”IEEE International Symposium on Intelligent Signal Processing, Alcala de Henares, Spain, pp. 1–6, 2007.
• Noureldin, A.ElShafie, M.Bayoumi, “GPS/INS Integration Utilizing Dynamic Neural Networks for Vehicular Navigation, ”Inf. Fusion, pp.48–57, 2011.
• El-Sheimy, N.; Chiang, K.-W.; Noureldin, A,“The utilization of artificial neural networks for multisensor system integration in navigation and positioning instruments, ”IEEE Trans. Instrum. Meas.,V 55, pp.1606–1615, 2006.
• Liu and G. Guo, “Vehicle Localization During GPS Outages With Extended Kalman Filter and Deep Learning, ” in IEEE Transactions on Instrumentation and Measurement, Vol. 70, pp. 1-10, 2021.
• Hosseinyalamdary, “Deep Kalman Filter: Simultaneous Multi-Sensor Integration and Modelling;A GNSS/IMU Case Study, ” sensors, 2018.
• Chang, L. Zhang, L. -T. Hsu, B. Xu, F. Huang and D. Xu, “Analytic Models of a Loosely Coupled GNSS/INS/LiDAR Kalman Filter Considering Update Frequency Under a Spoofing Attack, ” in IEEE Sensors Journal, Vol. 22, No. 23, pp. 23341-23355, 2022.
• Fang et al., “A LSTM algorithm estimating pseudo measurements for aiding INS during GNSS signal outages,”Remote Sens., Vol. 12, No. 2, p. 256, Jan. 2020.
• Xingjian, S.H.I,“Convolutional LSTM network: A machine learning approach for precipitation nowcasting, ” Neural Inf. Process. Syst. Vol. 28, pp. 802–810, 2015.
• Ma, H. Liu, C. Peng, and T. Qiu, “Unauthorized broadcasting identification: A deep LSTM recurrent learning approach,”IEEETrans.Instrum. Meas., Vol. 69, No. 9, pp. 5981–5983, 2020.