Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter
For robotics and AR/VR applications requiring accurate pose tracking, this method improves upon standard Kalman filters by better handling directional uncertainty.
The paper introduces the ensemble directional Kalman filter (EnDKF) for pose tracking, which jointly estimates position and attitude using directional statistics. Experiments show significant error reduction over using raw measurements in synthetic and head-tracking scenarios.
This paper introduces the ensemble directional Kalman filter (EnDKF), an ensemble-based Kalman filtering approach for pose tracking that jointly estimates an object's position and attitude using ideas from directional statistics. The EnDKF integrates a unit-quaternion attitude representation to move beyond canonical Kalman filter mean and covariance assumptions that poorly capture directional uncertainty. Experiments on a synthetic constant-velocity constant-angular-velocity system and a digital-twin head-tracking scenario using the FoundationPose algorithm demonstrate a significant reduction in error as opposed to merely using measurements.