Abstract
In recent years, aided navigation systems through combining inertial navigation system (INS) with global navigation satellite system (GNSS) have been widely applied to enhance the position, velocity, and attitude information of autonomous vehicles. In order to gain the accuracy of the aided INS/GNSS in GNSS gap intervals, a heuristic neural network structure based on the recurrent fuzzy wavelet neural network (RFWNN) is applicable for INS velocity and position error compensation purpose. During frequent access to GNSS data, the RFWNN should be trained as a highly precise prediction model equipped with the Kalman filter algorithm. Therefore, the INS velocity and position error data are obtainable along with the lost intervals of GNSS signals. For performance assessment of the proposed RFWNN-aided INS/GNSS, real flight test data of a small commercial unmanned aerial vehicle (UAV) were conducted. A comparison of test results shows that the proposed NN algorithm could efficiently provide high-accuracy corrections on the INS velocity and position information during GNSS outages.
Similar content being viewed by others
References
Abdel-Hamid W, Noureldin A, El-Sheimy N (2007) Adaptive fuzzy prediction of low-cost inertial-based positioning errors. IEEE Trans Fuzzy Syst 15(3):519–529
Ahjebory KM, Ismaeel SA, Alqaissi AM (2009) Implementation of an intelligent SINS navigator based on ANFIS. In: 2009 6th international multi-conference on systems signals and devices pp 1–7
Bo F, Li L, Jiuhong B (2013) GNSS/INS/speed log integrated navigation system based on MAKF and priori velocity information. In: 2013 IEEE international conference on information and automation (ICIA) Aug 26–28, pp 54–58
Chen X, Shen C, Zhang W-b, Tomizuka M, Xu Y, Chiu K (2013) Novel hybrid of strong tracking Kalman filter and wavelet neural network for GNSS/INS during GNSS outages. Measurement 46(10):3847–3854
Chen S-Y, Hung Y-C, Hung Y-H, Wu C-H (2016) Application of a recurrent wavelet fuzzy-neural network in the positioning control of a magnetic-bearing mechanism. Comput Electr Eng 54:147–158
Chiang K-W, Noureldin A, El-Sheimy N (2003) Multisensor integration using neuron computing for land-vehicle navigation. GPS Solut 6(4):209–218
El Shafie A, Hussain A, Noureldin A (2009) ANFIS-based model for real-time INS/GNSS data fusion for vehicular navigation system. In: 2009 IEEE international conference on computer technology and development, pp 278–282
Enkhtur M, Cho SY, Kim KH (2013) Modified unscented Kalman filter for a multirate INS/GNSS integrated navigation system. ETRI J 35(5):943–946
Gongming W, Wenjing L, Junfei Q, Guandi W (2017) Nonlinear system identification using deep belief network based on PLSR. In: 2017 IEEE 36th Chinese control conference (CCC), pp 10807–10812
Malleswaran M, Vaidehi V, Sivasankari N (2014) A novel approach to the integration of GNSS and INS using recurrent neural networks with evolutionary optimization techniques. Aerosp Sci Technol 32(1):169–179
Mohinder SG, Lawrence RW, Angus PA (2001) Global positioning systems, inertial navigation, and integration. Wiley, Hoboken
Nassar S, Schwarz KP, EL-Sheimy N, Noureldin A (2004) Modeling inertial sensor errors using autoregressive (AR) models. Navigation 51(4):259–268
Noureldin A, Osman A, El-Sheimy N (2003) A neuro-wavelet method for multi-sensor system integration for vehicular navigation. Meas Sci Technol 15(2):404–412
Noureldin A, El-Shafie A, Bayoumi M (2011) GNSS/INS integration utilizing dynamic neural networks for vehicular navigation. Inf Fusion 12(1):48–57
Nourmohammadi H, Keighobadi J (2018) Fuzzy adaptive integration scheme for low-cost SINS/GNSS navigation system. Mech Syst Signal Process 99:434–449
Petersen CD, Fraanje R, Cazzolato BS, Zander AC, Hansen CH (2008) A Kalman filter approach to virtual sensing for active noise control. Mech Syst Signal Process 22(2):490–508
Rogers RM (2007) Applied mathematics in integrated navigation systems. American Institute of Aeronautics and Astronautics, Reston
Sharaf R, Noureldin A, Osman A, El-Sheimy N (2005) Online INS/GNSS integration with a radial basis function neural network. IEEE Aerosp Electron Syst Mag 20(3):8–14
Sharaf R, Taha MR, Tarbouchi M, Noureldin A (2007) Merits and limitations of using fuzzy inference system for temporal integration of INS/GNSS in vehicular navigation. Soft Comput 11(9):889–900
TeKnol Ltd (2011) COMPANAV2‚ integrated MEMS INS/GPS system for aviation applications. Available at http://www.teknol.ru/pdf/en/CN-2_overview_en.pdf
Wai R-J, Liu C-M (2009) Design of dynamic petri recurrent fuzzy neural network and its application to path-tracking control of nonholonomic mobile robot. IEEE Trans Ind Electron 56(7):2667–2683
Walchko KJ, Nechyba MC, Schwartz E, Arroyo A (2003) Embedded low cost inertial navigation system. Florida conference on recent advances in robotics. FAU, Dania Beach, pp 8–15
Xu Z, Li Y, Rizos C, Xu X (2010) Novel hybrid of LS-SVM and Kalman filter for GNSS/INS integration. J Navig 63(2):289–299
Zhang Q (1997) Using wavelet network in nonparametric estimation. IEEE Trans Neural Netw 8(2):227–236
Zhang T, Xu X (2012) A new method of seamless land navigation for GNSS/INS integrated system. Measurement 45(4):691–701
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Doostdar, P., Keighobadi, J. & Hamed, M.A. INS/GNSS integration using recurrent fuzzy wavelet neural networks. GPS Solut 24, 29 (2020). https://doi.org/10.1007/s10291-019-0942-z
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10291-019-0942-z