Pose Tracking with a Foundation Pose Model and an Ensemble Directional Kalman Filter

TL;DR

This paper presents the ensemble directional Kalman filter (EnDKF), a novel pose tracking method that improves accuracy by integrating directional statistics and quaternion representations, validated on synthetic and head-tracking scenarios.

Contribution

The paper introduces EnDKF, combining ensemble Kalman filtering with directional statistics and quaternion attitude representation for enhanced pose tracking accuracy.

Findings

EnDKF significantly reduces pose estimation error compared to measurement-only methods.

Experiments on synthetic and head-tracking scenarios demonstrate improved robustness and accuracy.

The approach effectively captures directional uncertainty in pose estimation.

Abstract

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.