A novel approach for aiding unscented Kalman filter for bridging GNSS outages in integrated navigation systems

Abstract Aiming to improve the position and velocity precision of INS/GNSS system during GNSS outages, a novel that combines unscented Kalman filter (UKF) nonlinear autoregressive neural networks with external inputs (NARX) is proposed. The NARX-based module utilized predict measurement updates UKF outages. A new offline approach for selecting optimal NARX suggested tested. This based on mutual information (MI) theory identifying influence each outputs (the UKF) lag-space estimation (LSE) investigating dependency these past values outputs. performance proposed verified experimentally using real dataset. comparison results indicate NARX-aided outperforms other methods use different input configurations networks.