Temporally Consistent Object 6D Pose Estimation for Robot Control
Kateryna Zorina, Vojtech Priban, Mederic Fourmy, Josef Sivic, Vladimir Petrik
TLDR
A factor graph approach enhances temporal consistency and robustness for 6D object pose estimation in robot control.
Key contributions
- Develops a factor graph for temporal 6D object pose consistency.
- Incorporates object motion models and estimates pose uncertainty.
- Integrates these components into an online optimization-based estimator.
- Significantly improves benchmark results and robot control stability.
Why it matters
Off-the-shelf pose estimators lack temporal consistency and robustness for stable robot control. This work addresses these critical gaps by enforcing temporal consistency. It enables more reliable and precise vision-based robot manipulation.
Original 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.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.