Temporally Consistent Object 6D Pose Estimation for Robot Control

TL;DR

This paper introduces a factor graph method to improve the temporal consistency and robustness of 6D object pose estimation from single-view RGB images for robot control applications.

Contribution

It develops an online optimization approach that incorporates object motion models and measurement uncertainty to enhance pose estimation stability.

Findings

Significantly improves pose estimation accuracy on benchmarks.

Demonstrates stable robot control using the proposed method.

Effective outlier rejection and smoothing enhance results.

Abstract

Single-view RGB object pose estimators have reached a level of precision and efficiency that makes them good candidates for vision-based robot control. However, off-the-shelf methods lack temporal consistency and robustness that are mandatory for a stable feedback control. In this work, we develop a factor graph approach to enforce temporal consistency of the object pose estimates. In particular, the proposed approach: (i) incorporates object motion models, (ii) explicitly estimates the object pose measurement uncertainty, and (iii) integrates the above two components in an online optimization-based estimator. We demonstrate that with appropriate outlier rejection and smoothing using the proposed factor graph approach, we can significantly improve the results on standardized pose estimation benchmarks. We experimentally validate the stability of the proposed approach for a feedback-based robot control task in which the object is tracked by the camera attached to a torque controlled manipulator.