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

2026-05-04

AI Summary

This work addresses the limitations of traditional Kalman filtering in accurately modeling uncertainty in pose orientation by proposing a joint estimation framework that integrates FoundationPose with an Ensemble Directional Kalman Filter (EnDKF). The method represents pose using unit quaternions and incorporates directional statistics to overcome the conventional assumptions of Gaussianity and linear covariance propagation inherent in standard filters. Experimental results demonstrate that the proposed approach significantly reduces both positional and orientational tracking errors on synthetic datasets and in digital twin head-tracking tasks, outperforming baseline methods that rely solely on raw observations.

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.

Problem

• pose tracking
• directional uncertainty
• Kalman filter
• attitude estimation
• object pose

Innovation

• Ensemble Directional Kalman Filter
• Pose Tracking
• Directional Statistics
• Unit Quaternion
• FoundationPose