Tracing Back Error Sources to Explain and Mitigate Pose Estimation Failures
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_ | 1866914365294247936 |
|---|---|
| author | Schneider, Loris Shi, Yitian Wolf, Rosa Brenner, Carolin Triebel, Rudolph Rayyes, Rania |
| author_facet | Schneider, Loris Shi, Yitian Wolf, Rosa Brenner, Carolin Triebel, Rudolph Rayyes, Rania |
| contents | Robust estimation of object poses in robotic manipulation is often addressed using foundational general estimators, that aim to handle diverse error sources naively within a single model. Still, they struggle due to environmental uncertainties, while requiring long inference times and heavy computation. In contrast, we propose a modular, uncertainty-aware framework that attributes pose estimation errors to specific error sources and applies targeted mitigation strategies only when necessary. Instantiated with Iterative Closest Point (ICP) as a simple and lightweight pose estimator, we leverage our framework for real-world robotic grasping tasks. By decomposing pose estimation into failure detection, error attribution, and targeted recovery, we significantly improve the robustness of ICP and achieve competitive performance compared to foundation models, while relying on a substantially simpler and faster pose estimator. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_02881 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Tracing Back Error Sources to Explain and Mitigate Pose Estimation Failures Schneider, Loris Shi, Yitian Wolf, Rosa Brenner, Carolin Triebel, Rudolph Rayyes, Rania Robotics Robust estimation of object poses in robotic manipulation is often addressed using foundational general estimators, that aim to handle diverse error sources naively within a single model. Still, they struggle due to environmental uncertainties, while requiring long inference times and heavy computation. In contrast, we propose a modular, uncertainty-aware framework that attributes pose estimation errors to specific error sources and applies targeted mitigation strategies only when necessary. Instantiated with Iterative Closest Point (ICP) as a simple and lightweight pose estimator, we leverage our framework for real-world robotic grasping tasks. By decomposing pose estimation into failure detection, error attribution, and targeted recovery, we significantly improve the robustness of ICP and achieve competitive performance compared to foundation models, while relying on a substantially simpler and faster pose estimator. |
| title | Tracing Back Error Sources to Explain and Mitigate Pose Estimation Failures |
| topic | Robotics |
| url | https://arxiv.org/abs/2603.02881 |