Zero velocity update is a common and efficient approach to bound the accumulated error growth for footmounted inertial navigation system. Thus a robust zero velocity detector (ZVD) for all kinds of locomotion is needed for high accuracy pedestrian navigation systems. In this paper, we investigate twomachine learning-basedZVDs: Histogrambased Gradient Boosting (HGB) and Random Forest (RF), aiming at adapting to different motion types while reducing the computation costs compared to the deep learningbased detectors. A complete data pre-processing procedure, including a feature engineering study and data augmentation techniques, is proposed. A motion classifier based on HGB is used to distinguish ?single support? and ?double float? motions. This concept is different from the traditional locomotion classification (walking, running, stair climbing) since it merges similar motions into the same class. The proposed ZVDs are evaluated with inertial data collected by two subjects over a 1.8 km indoor/outdoor pathwith differentmotions and speeds. The results showthatwithout huge training dataset, these two machine learning-based ZVDs achieve better performances (55 cm positioning accuracy) and lower computational costs than the two deep learning-based Long Short-TermMemory methods (1.21 m positioning accuracy).