JENGA: Object selection and pose estimation for robotic grasping from a stack

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Jeevanandam, Sai Srinivas, Inuganti, Sandeep, Govil, Shreedhar, Stricker, Didier, Rambach, Jason
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911007436177408
author Jeevanandam, Sai Srinivas
Inuganti, Sandeep
Govil, Shreedhar
Stricker, Didier
Rambach, Jason
author_facet Jeevanandam, Sai Srinivas
Inuganti, Sandeep
Govil, Shreedhar
Stricker, Didier
Rambach, Jason
contents Vision-based robotic object grasping is typically investigated in the context of isolated objects or unstructured object sets in bin picking scenarios. However, there are several settings, such as construction or warehouse automation, where a robot needs to interact with a structured object formation such as a stack. In this context, we define the problem of selecting suitable objects for grasping along with estimating an accurate 6DoF pose of these objects. To address this problem, we propose a camera-IMU based approach that prioritizes unobstructed objects on the higher layers of stacks and introduce a dataset for benchmarking and evaluation, along with a suitable evaluation metric that combines object selection with pose accuracy. Experimental results show that although our method can perform quite well, this is a challenging problem if a completely error-free solution is needed. Finally, we show results from the deployment of our method for a brick-picking application in a construction scenario.
format Preprint
id arxiv_https___arxiv_org_abs_2506_13425
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle JENGA: Object selection and pose estimation for robotic grasping from a stack
Jeevanandam, Sai Srinivas
Inuganti, Sandeep
Govil, Shreedhar
Stricker, Didier
Rambach, Jason
Robotics
Computer Vision and Pattern Recognition
Vision-based robotic object grasping is typically investigated in the context of isolated objects or unstructured object sets in bin picking scenarios. However, there are several settings, such as construction or warehouse automation, where a robot needs to interact with a structured object formation such as a stack. In this context, we define the problem of selecting suitable objects for grasping along with estimating an accurate 6DoF pose of these objects. To address this problem, we propose a camera-IMU based approach that prioritizes unobstructed objects on the higher layers of stacks and introduce a dataset for benchmarking and evaluation, along with a suitable evaluation metric that combines object selection with pose accuracy. Experimental results show that although our method can perform quite well, this is a challenging problem if a completely error-free solution is needed. Finally, we show results from the deployment of our method for a brick-picking application in a construction scenario.
title JENGA: Object selection and pose estimation for robotic grasping from a stack
topic Robotics
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.13425