File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: Vision-based Six-Dimensional Peg-in-Hole for Practical Connector Insertion

TitleVision-based Six-Dimensional Peg-in-Hole for Practical Connector Insertion
Authors
Issue Date29-May-2023
Abstract

We study six-dimensional (6D) perceptive peg-in-hole problem for practical connector insertion task in this paper. To enable the manipulator system to handle different types of pegs in complex environment, we develop a perceptive robotic assembly system that utilizes an in-hand RGB-D camera for peg-in-hole with multiple types of pegs. The proposed framework addresses the critical hole detection and pose estimation problem through combining the learning-based detection with model-based pose estimation strategies. By exploiting the structure of the peg-in-hole task, we consider a rectangle-shape based characterization for modeling the candidate socket. Such a characterization allows us to design simple learning-based methods to detect and estimate the 6D pose of the target socket that balances between processing speed and accuracy. To validate our method, we test the performance of the proposed perceptive peg-in-hole solution using a KUKA iiwa7 robotic arm to accomplish the socket insertion task with two types of practical sockets (RJ45/HDMI). Without the need of additional search, our method achieves an acceptable success rate in the connector insertion tasks. The results confirm the reliability of our method and show that our method is suitable for real world application.


Persistent Identifierhttp://hdl.handle.net/10722/333847
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorZhang, Kun-
dc.contributor.authorWang, Chen-
dc.contributor.authorChen, Hua-
dc.contributor.authorPan, Jia-
dc.contributor.authorWang, Michael, Yu-
dc.contributor.authorZhang, Wei-
dc.date.accessioned2023-10-06T08:39:34Z-
dc.date.available2023-10-06T08:39:34Z-
dc.date.issued2023-05-29-
dc.identifier.urihttp://hdl.handle.net/10722/333847-
dc.description.abstract<p>We study six-dimensional (6D) perceptive peg-in-hole problem for practical connector insertion task in this paper. To enable the manipulator system to handle different types of pegs in complex environment, we develop a perceptive robotic assembly system that utilizes an in-hand RGB-D camera for peg-in-hole with multiple types of pegs. The proposed framework addresses the critical hole detection and pose estimation problem through combining the learning-based detection with model-based pose estimation strategies. By exploiting the structure of the peg-in-hole task, we consider a rectangle-shape based characterization for modeling the candidate socket. Such a characterization allows us to design simple learning-based methods to detect and estimate the 6D pose of the target socket that balances between processing speed and accuracy. To validate our method, we test the performance of the proposed perceptive peg-in-hole solution using a KUKA iiwa7 robotic arm to accomplish the socket insertion task with two types of practical sockets (RJ45/HDMI). Without the need of additional search, our method achieves an acceptable success rate in the connector insertion tasks. The results confirm the reliability of our method and show that our method is suitable for real world application.<br></p>-
dc.languageeng-
dc.relation.ispartof2023 IEEE International Conference on Robotics and Automation (ICRA2023) (29/05/2023-02/06/2023, London)-
dc.titleVision-based Six-Dimensional Peg-in-Hole for Practical Connector Insertion-
dc.typeConference_Paper-
dc.identifier.doi10.1109/ICRA48891.2023.10161116-
dc.identifier.scopuseid_2-s2.0-85168692171-
dc.identifier.volume2023-May-
dc.identifier.spage1771-
dc.identifier.epage1777-
dc.identifier.isiWOS:001036713001084-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats