Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866913913519472640 |
|---|---|
| author | Joyce, Eric C. Zhao, Qianwen Burgdorfer, Nathaniel Wang, Long Mordohai, Philippos |
| author_facet | Joyce, Eric C. Zhao, Qianwen Burgdorfer, Nathaniel Wang, Long Mordohai, Philippos |
| contents | Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_20045 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception Joyce, Eric C. Zhao, Qianwen Burgdorfer, Nathaniel Wang, Long Mordohai, Philippos Robotics Computer Vision and Pattern Recognition Deep object pose estimators are notoriously overconfident. A grasping agent that both estimates the 6-DoF pose of a target object and predicts the uncertainty of its own estimate could avoid task failure by choosing not to act under high uncertainty. Even though object pose estimation improves and uncertainty quantification research continues to make strides, few studies have connected them to the downstream task of robotic grasping. We propose a method for training lightweight, deep networks to predict whether a grasp guided by an image-based pose estimate will succeed before that grasp is attempted. We generate training data for our networks via object pose estimation on real images and simulated grasping. We also find that, despite high object variability in grasping trials, networks benefit from training on all objects jointly, suggesting that a diverse variety of objects can nevertheless contribute to the same goal. |
| title | Consensus-Driven Uncertainty for Robotic Grasping based on RGB Perception |
| topic | Robotics Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2506.20045 |