A Novel Hybrid Fusion Algorithm for Low-Cost GPS/INS Integrated Navigation System During GPS Outages

It is the main challenge for Global Positioning System (GPS)/Inertial Navigation System (INS) to achieve reliable and low-cost positioning solutions during GPS outages. A new GPS/INS hybrid method is proposed to bridge GPS outages. Firstly, a data pre-processing algorithm based on empirical mode decomposition (EMD) for wavelet de-noising is developed to reduce the uncertain noise of IMU raw measurements and provide accurate information for subsequent GPS/INS data fusion and training samples. Then, the interactive multi-model extended Kalman filter(IMM-EKF) algorithm is proposed to improve the robustness of Kalman filter output and the accuracy of model training target output. Finally, a new intelligent structure of GPS/INS based on Extreme Learning Machine (ELM) is proposed. When the GPS is available, the IMM-EKF is used to fuse the GPS and de-noised INS data, and the de-noised INS data and the outputs of IMM-EKF are used to train the ELM. During GPS outages, the ELM is used to predict and correct the INS position error. In order to evaluate the effectiveness of the proposed method, 3 tests were performed in the actual field test. The comparison results show that the proposed fusion method can significantly improve the accuracy and reliability of positioning during GPS outages.

[1]  Prabir Bhattacharya,et al.  Dempster Shafer neural network algorithm for land vehicle navigation application , 2013, Inf. Sci..

[2]  Jingjing Li,et al.  An adaptive navigation method for a small unmanned aerial rotorcraft under complex environment , 2013 .

[3]  Masayoshi Tomizuka,et al.  Novel hybrid of strong tracking Kalman filter and wavelet neural network for GPS/INS during GPS outages , 2013 .

[4]  Prabir Bhattacharya,et al.  A novel hybrid fusion algorithm to bridge the period of GPS outages using low-cost INS , 2014, Expert Syst. Appl..

[5]  Ming Liu,et al.  GNSS/MEMS IMU ultra‐tightly integrated navigation system based on dual‐loop NCO control method and cascaded channel filters , 2018, IET Radar, Sonar & Navigation.

[6]  Bo Wang,et al.  INS/DVL/PS Tightly Coupled Underwater Navigation Method With Limited DVL Measurements , 2018, IEEE Sensors Journal.

[7]  Peng Jiao.  Study of the influence of transition IMF on EMD do-noising and the improved algorithm , 2013 .

[8]  Rudolph van der Merwe,et al.  The square-root unscented Kalman filter for state and parameter-estimation , 2001, 2001 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings (Cat. No.01CH37221).

[9]  Mohammad Reza Mosavi,et al.  A wavelet-extreme learning machine for low-cost INS/GPS navigation system in high-speed applications , 2017, GPS Solutions.

[10]  V. Vaidehi,et al.  A novel approach to the integration of GPS and INS using recurrent neural networks with evolutionary optimization techniques , 2014 .

[11]  Hong Wang,et al.  A low-cost INS/GPS integration methodology based on random forest regression , 2013, Expert Syst. Appl..

[12]  Lei Wang,et al.  Enhanced Multi-sensor Data Fusion Methodology based on Multiple Model Estimation for Integrated Navigation System , 2018 .

[13]  Xu Li,et al.  Enhancing Localization Accuracy of MEMS-INS/GPS/In-Vehicle Sensors Integration During GPS Outages , 2018, IEEE Transactions on Instrumentation and Measurement.

[14]  Fabio Dovis,et al.  A Comparison between Different Error Modeling of MEMS Applied to GPS/INS Integrated Systems , 2013, Sensors.

[15]  Aboelmagd Noureldin,et al.  Integrated Indoor Navigation System for Ground Vehicles With Automatic 3-D Alignment and Position Initialization , 2015, IEEE Transactions on Vehicular Technology.

[16]  Xiaosu Xu,et al.  A hybrid fusion algorithm for GPS/INS integration during GPS outages , 2017 .

[17]  Jian Wang,et al.  GPS/BDS/INS tightly coupled integration accuracy improvement using an improved adaptive interacting multiple model with classified measurement update , 2017 .

[18]  Li Yong-long.  Gear fault pattern identification and diagnosis using Time-Frequency Analysis and wavelet threshold de-noising based on EMD , 2012 .

[19]  Mosbeh R. Kaloop,et al.  Multi input–single output models identification of tower bridge movements using GPS monitoring system , 2014 .

[20]  Aboelmagd Noureldin,et al.  GPS/INS integration utilizing dynamic neural networks for vehicular navigation , 2011, Inf. Fusion.

[21]  Jongwoo An,et al.  Robust Navigational System for a Transporter Using GPS/INS Fusion , 2018, IEEE Transactions on Industrial Electronics.

[22]  Chee Kheong Siew,et al.  Extreme learning machine: Theory and applications , 2006, Neurocomputing.

[23]  Simon Washington,et al.  Shortest path and vehicle trajectory aided map-matching for low frequency GPS data , 2015 .

[24]  Bin Li,et al.  Multi-sensor fusion methodology for enhanced land vehicle positioning , 2019, Inf. Fusion.

[25]  Jing Li,et al.  Improving positioning accuracy of vehicular navigation system during GPS outages utilizing ensemble learning algorithm , 2017, Inf. Fusion.

[26]  Chong Shen,et al.  Hybrid Algorithm Based on MDF-CKF and RF for GPS/INS System During GPS Outages (April 2018) , 2018, IEEE Access.

[27]  Fernando Puente León,et al.  Information fusion for automotive applications - An overview , 2011, Inf. Fusion.

[28]  Jamshaid Ali,et al.  An Adaptive & Fault Tolerant SINS/GPS Integrated Navigation Scheme Robustified against Slowly Growing Errors in GPS Updates , 2013 .

[29]  Fan-Ren Chang,et al.  A Solution to the Ill-Conditioned GPS Positioning Problem in an Urban Environment , 2009, IEEE Transactions on Intelligent Transportation Systems.