An Intelligent Adaptive Kalman Filter for Integrated Navigation Systems

This paper presents an intelligent adaptive Kalman filter based on deep neural network and fuzzy logic for integrated navigation systems. The highlight is that the process noise covariance is obtained by analyzing inertial sensors' output sequence rather than based on auxiliary measurements. Such novel method realizes the decoupling estimation of process noise covariance and measurement noise covariance, and the sequence-to-sequence process of sensors analyzer gains high real-time performance. The model of sensors analyzer is constructed and an incremental subset training method is proposed. The effects of noise covariance error are analyzed. A numerical experiment is conducted, which shows promising accuracy and robustness improvement of the proposed method.

Abstract licence: CC BY-NC-ND

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.