Skip to main navigation Skip to search Skip to main content

Target-driven Object Grasping Method for Mobile Manipulator in Clutter

  • Xinkai Yu
  • , Yongzhuo Gao*
  • , Wei Dong
  • , Mingyang Li
  • , Huajian Liu
  • , Chao Wang
  • *Corresponding author for this work
  • Harbin Institute of Technology
  • CAS - Beijing Institute of Control Engineering

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

The demand for mobile manipulator in the military field is strong, but there is no product that can achieve autonomous grasping in a cluttered environment. In this paper, a target-driven grasp pose detection algorithm is proposed, which can be used to detect the grasp pose of a specified target object in a cluttered environment. After that, based on the lightweight requirements of the military, a mobile manipulator platform is built, and the forward and inverse kinematics model of the mobile manipulator is established. At the same time, a vehicle-arm coordination algorithm is designed to make the grasping efficiency higher. Finally, we use the mobile manipulator to perform autonomous grasping in a cluttered environment to verify the system functionality.

Original languageEnglish
Title of host publicationProceedings of 2022 IEEE International Conference on Unmanned Systems, ICUS 2022
EditorsRong Song
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages980-985
Number of pages6
ISBN (Electronic)9781665484565
DOIs
StatePublished - 2022
Event2022 IEEE International Conference on Unmanned Systems, ICUS 2022 - Guangzhou, China
Duration: 28 Oct 202230 Oct 2022

Publication series

NameProceedings of 2022 IEEE International Conference on Unmanned Systems, ICUS 2022

Conference

Conference2022 IEEE International Conference on Unmanned Systems, ICUS 2022
Country/TerritoryChina
CityGuangzhou
Period28/10/2230/10/22

Keywords

  • autonomous grasping
  • grasp pose detection
  • mobile manipulator
  • target-driven
  • vehicle-arm coordination

Fingerprint

Dive into the research topics of 'Target-driven Object Grasping Method for Mobile Manipulator in Clutter'. Together they form a unique fingerprint.

Cite this