To satisfy the increasing demands of the accuracy for the human localization, in this work, we propose a pedestrian tracking method by tightly coupling recent inertial navigation system–based and ultra-wideband–based measurements. In this mode, the difference between the distances derived from the inertial navigation system–based and ultra-wideband–based system is used as the observation of the data fusion filter. Moreover, in order to improve the performance of the extended finite impulse response filter, which depends on the averaging horizon ([Formula: see text]) when the error state vector ([Formula: see text]) is determined due to the model, the extended finite impulse response filter bank is employed to be the fusion center for pedestrian tracking, which used the Mahalanobis distance to find the optimal [Formula: see text] at each time index [Formula: see text]. Test experiments illustrate that the extended finite impulse response filter bank–based tightly coupled inertial navigation system/ultra-wideband–integrated method is able to achieve real-time estimation, and its accuracy is similar to the extended finite impulse response with the ideal [Formula: see text] which is calculated off-line.
An Outlier Robust Finite Impulse Response Filter With Maximum Correntropy
