A Hybrid RISS/GNSS Method During GNSS Outage in the Land Vehicle Navigation System

Abstract

The integrated navigation system of an inertial navigation system (INS) and a global navigation satellite system (GNSS) is a standard solution in land vehicle navigation applications. Considering a low-cost solution, the reduced inertial sensor system (RISS) is adopted in place of INS to provide better navigation performance for land vehicles with fewer inertial sensors and lower computations. However, low-cost sensors can quickly deteriorate the navigation solution during GNSS outage. Hence, a novel RISS /GNSS method with the assistance of the long short-term memory (LSTM) neural network (NN), which has the ability of adaptive memorizing, is proposed to bridge GNSS outage by means of data fusion. In addition, zero-velocity detection is applied to advance the navigation performance provided by the LSTM algorithm during GNSS outage. We examined the performance of this method by using real road test experiments in a land vehicle equipped with GNSS receivers and inertial sensors in addition to a high-end GNSS /INS to provide the reference solution. During 300-s GNSS outage, the experimental results illustrate that this hybrid method based on the LSTM algorithm can enhance the navigation accuracy by 50% when compared with the standalone RISS algorithm, and provide 30% improvements in comparison with the nonlinear autoregressive with exogenous input (NARX) algorithm.