Grasping Partially Occluded Objects Using Autoencoder-Based Point Cloud Inpainting

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Koebler, Alexander, Gross, Ralf, Buettner, Florian, Thon, Ingo
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929762095595520
author Koebler, Alexander
Gross, Ralf
Buettner, Florian
Thon, Ingo
author_facet Koebler, Alexander
Gross, Ralf
Buettner, Florian
Thon, Ingo
contents Flexible industrial production systems will play a central role in the future of manufacturing due to higher product individualization and customization. A key component in such systems is the robotic grasping of known or unknown objects in random positions. Real-world applications often come with challenges that might not be considered in grasping solutions tested in simulation or lab settings. Partial occlusion of the target object is the most prominent. Examples of occlusion can be supporting structures in the camera's field of view, sensor imprecision, or parts occluding each other due to the production process. In all these cases, the resulting lack of information leads to shortcomings in calculating grasping points. In this paper, we present an algorithm to reconstruct the missing information. Our inpainting solution facilitates the real-world utilization of robust object matching approaches for grasping point calculation. We demonstrate the benefit of our solution by enabling an existing grasping system embedded in a real-world industrial application to handle occlusions in the input. With our solution, we drastically decrease the number of objects discarded by the process.
format Preprint
id arxiv_https___arxiv_org_abs_2503_12549
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Grasping Partially Occluded Objects Using Autoencoder-Based Point Cloud Inpainting
Koebler, Alexander
Gross, Ralf
Buettner, Florian
Thon, Ingo
Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
Flexible industrial production systems will play a central role in the future of manufacturing due to higher product individualization and customization. A key component in such systems is the robotic grasping of known or unknown objects in random positions. Real-world applications often come with challenges that might not be considered in grasping solutions tested in simulation or lab settings. Partial occlusion of the target object is the most prominent. Examples of occlusion can be supporting structures in the camera's field of view, sensor imprecision, or parts occluding each other due to the production process. In all these cases, the resulting lack of information leads to shortcomings in calculating grasping points. In this paper, we present an algorithm to reconstruct the missing information. Our inpainting solution facilitates the real-world utilization of robust object matching approaches for grasping point calculation. We demonstrate the benefit of our solution by enabling an existing grasping system embedded in a real-world industrial application to handle occlusions in the input. With our solution, we drastically decrease the number of objects discarded by the process.
title Grasping Partially Occluded Objects Using Autoencoder-Based Point Cloud Inpainting
topic Robotics
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2503.12549