Multi-sensor fusion methodology for enhanced land vehicle positioning

Abstract It is a main challenge for land vehicles to achieve reliable and low-cost navigation solution in various situations, especially when Global Positioning System (GPS) is not available. To address this challenge, we propose an enhanced multi-sensor fusion methodology to fuse the information from low-cost GPS, MEMS Inertial Measurement Unit (IMU), and digital compass in this paper. First, a key data preprocessing algorithm based on Empirical Mode Decomposition (EMD) interval threshold filter is developed to remove the noises in inertial sensors so as to offer more accurate information for subsequent modeling. Then, a Least-Squares Support Vector Machine (LSSVM)-based nonlinear autoregressive with exogenous input (NARX) model (LSSVM-NARX) is designed and augmented with Kalman filter (KF) to construct a novel LSSVM-NARX/KF hybrid strategy. In case of GPS outages, the recently updated LSSVM-NARX is adopted to predict and compensate for the INS position errors. Finally, the performance of proposed methodology was evaluated with real-world data collected in urban settings including typical driving maneuvers. The results indicate that the proposed methodology can achieve remarkable enhancement in positioning accuracy in GPS-denied environments.