Evaluation metric for instance segmentation in robotic grasping of deformable linear objects

Jonas Dirr, Andre Siepmann, Daniel Gebauer, Rüdiger Daub

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations

Abstract

Automating the assembly and handling of deformable linear objects requires their robust detection. This paper introduces a new evaluation metric for the results from instance segmentation. The metric enables estimating the proportion of valid grasp poses and graspable objects for specific gripper models. The results demonstrate that masks with similar scores in area-based metrics can have different grasp pose validity outcomes. In addition, it is indicated that when handling deformable linear objects with a vacuum gripper, it is possible to achieve a grasp precision and grasp recall of about 90 %.

Original languageEnglish
Pages (from-to)726-731
Number of pages6
JournalProcedia CIRP
Volume120
DOIs
StatePublished - 2023
Event56th CIRP International Conference on Manufacturing Systems, CIRP CMS 2023 - Cape Town, South Africa
Duration: 24 Oct 202326 Oct 2023

Keywords

  • Deformable one-dimensional objects
  • cable
  • grasp precision
  • grasp recall
  • wire

Fingerprint

Dive into the research topics of 'Evaluation metric for instance segmentation in robotic grasping of deformable linear objects'. Together they form a unique fingerprint.

Cite this