GNSS multipath detection using a machine learning approach

Insufficient localization accuracy of global navigation satellite system (GNSS) receivers is one of the challenges to implement advanced intelligent transportation system in highly urbanized areas. Multipath and non-line-of-sight (NLOS) effects strongly deteriorate GNSS positioning performance. This paper aims to train a classifier by supervised machine learning to separate the type of GNSS pseudorange measurement into three categories, clean, multipath and NLOS. Several features obtained or calculated from the GNSS raw data are evaluated. This paper also proposes a new feature to indicate the consistency between measurements of pseudorange and Doppler shift. According to the experiment result, about 75% of classification accuracy can be achieved using a support vector machine (SVM) classifier trained by the proposed feature and received signal strength.

[1]  Nobuaki Kubo,et al.  Multipath mitigation and NLOS detection using vector tracking in urban environments , 2015, GPS Solutions.

[2]  Miguel Ortiz,et al.  About Non-Line-Of-Sight Satellite Detection and Exclusion in a 3D Map-Aided Localization Algorithm , 2013, Sensors.

[3]  Li-Ta Hsu,et al.  Evaluation of Multi-GNSSs and GPS with 3D Map Methods for Pedestrian Positioning in an Urban Canyon Environment , 2015, IEICE Trans. Fundam. Electron. Commun. Comput. Sci..

[4]  Li-Ta Hsu,et al.  Urban Pedestrian Navigation Using Smartphone-Based Dead Reckoning and 3-D Map-Aided GNSS , 2016, IEEE Sensors Journal.

[5]  Chen-Ying Kao,et al.  Sequential Quadratic Method for GPS NLOS Positioning in Urban Canyon Envi-ronments , 2013 .

[6]  Li-Ta Hsu,et al.  GNSS/Onboard Inertial Sensor Integration With the Aid of 3-D Building Map for Lane-Level Vehicle Self-Localization in Urban Canyon , 2016, IEEE Transactions on Vehicular Technology.

[7]  Ian McLoughlin,et al.  GPS multipath mitigation: a nonlinear regression approach , 2013, GPS Solutions.

[8]  Per Enge,et al.  Fundamentals Of Signal Tracking Theory , 1996 .

[9]  Miguel Ortiz,et al.  Assessment of end-to-end performances of a GNSS-based road user charging system based on IFSTTAR-GEOLOC and Q-Free cooperation , 2016, 2016 European Navigation Conference (ENC).

[10]  Antonio F. Gómez-Skarmeta,et al.  GNSS Autonomous Localization: NLOS Satellite Detection Based on 3-D Maps , 2014, IEEE Robotics & Automation Magazine.

[11]  Nobuaki Kubo,et al.  Correcting GNSS Multipath Errors Using a 3D Surface Model and Particle Filter , 2013 .

[12]  Chao Wei,et al.  Efficient Traffic State Estimation for Large-Scale Urban Road Networks , 2013, IEEE Transactions on Intelligent Transportation Systems.

[13]  Moe Z. Win,et al.  A Machine Learning Approach to Ranging Error Mitigation for UWB Localization , 2012, IEEE Transactions on Communications.

[14]  Tsung-Ming Chen,et al.  The Performance Analysis of a Real-Time Integrated INS / GPS Vehicle Navigation System with Abnormal GPS Measurement Elimination , 2014 .

[15]  Werner Gurtner,et al.  RINEX : The Receiver · ! Independent Exchange Format 1 , 2022 .

[16]  Lei Wang,et al.  Urban Positioning on a Smartphone: Real-time Shadow Matching Using GNSS and 3D City Models , 2013 .

[17]  P. Groves.  Shadow Matching: A New GNSS Positioning Technique for Urban Canyons , 2011, Journal of Navigation.

[18]  M. Zhodzishsky,et al.  The Mitigation of Multipath Errors by Strobe Correlators in GPS/GLONASS Receivers , 1998, GPS Solutions.

[19]  Roi Yozevitch,et al.  A Robust GNSS LOS/NLOS Signal Classifier , 2016 .

[20]  Fawzi Nashashibi,et al.  Fusion of Perception and V2P Communication Systems for the Safety of Vulnerable Road Users , 2017, IEEE Transactions on Intelligent Transportation Systems.

[21]  Paul Cross,et al.  Development and testing of a new ray-tracing approach to GNSS carrier-phase multipath modelling , 2007 .

[22]  João Barros,et al.  Neighbor-Aided Localization in Vehicular Networks , 2017, IEEE Transactions on Intelligent Transportation Systems.

[23]  Shaojun Feng,et al.  An integrated solution for lane level irregular driving detection on highways , 2015 .

[24]  Otman A. Basir,et al.  GPS Localization Accuracy Classification: A Context-Based Approach , 2013, IEEE Transactions on Intelligent Transportation Systems.

[25]  Monsak Socharoentum,et al.  A Machine Learning Approach to Detect Non-Line of Sight Satellites in Nav2 Nav , 2014 .

[26]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[27]  Nobuaki Kubo,et al.  A Unique Approach to Strong Multipath Mitigation in Dense Urban Areas , 2015 .

[28]  T.A. Rahman,et al.  Intelligent Fleet Management System with Concurrent GPS & GSM Real-Time Positioning Technology , 2007, 2007 7th International Conference on ITS Telecommunications.

[29]  Agus Budiyono,et al.  Principles of GNSS, Inertial, and Multi-sensor Integrated Navigation Systems , 2012 .

[30]  Negin Sokhandan,et al.  GNSS Multipath Mitigation using Low Complexity Adaptive Equalization Algorithms , 2014 .

[31]  Paul D. Groves,et al.  NLOS GPS signal detection using a dual-polarisation antenna , 2012, GPS Solutions.

[32]  S. Miquel,et al.  A New Modeling Based on Urban Trenches to Improve GNSS Positioning Quality of Service in Cities , 2013, IEEE Intelligent Transportation Systems Magazine.

[33]  Li-Ta Hsu,et al.  GPS Error Correction With Pseudorange Evaluation Using Three-Dimensional Maps , 2015, IEEE Transactions on Intelligent Transportation Systems.

[34]  Nobuaki Kubo,et al.  Multiple Faulty GNSS Measurement Exclusion Based on Consistency Check in Urban Canyons , 2017, IEEE Sensors Journal.