Temporally Consistent Object 6D Pose Estimation for Robot Control
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866918481486675968 |
|---|---|
| author | Zorina, Kateryna Priban, Vojtech Fourmy, Mederic Sivic, Josef Petrik, Vladimir |
| author_facet | Zorina, Kateryna Priban, Vojtech Fourmy, Mederic Sivic, Josef Petrik, Vladimir |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_02708 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Temporally Consistent Object 6D Pose Estimation for Robot Control Zorina, Kateryna Priban, Vojtech Fourmy, Mederic Sivic, Josef Petrik, Vladimir Robotics Computer Vision and Pattern Recognition I.2.9; I.2.10; I.4.8 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. |
| title | Temporally Consistent Object 6D Pose Estimation for Robot Control |
| topic | Robotics Computer Vision and Pattern Recognition I.2.9; I.2.10; I.4.8 |
| url | https://arxiv.org/abs/2605.02708 |