Skip to main navigation Skip to search Skip to main content

An Automatic Robotic End-Effector System Based on Visual Detection

  • Junyuan Tao
  • , Bin Wang*
  • , Shuai Yang
  • , Qifan Duan
  • , Baoxu Feng
  • *Corresponding author for this work

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

Abstract

According to the problem that a traditional end-effector is fixed to the wrist of a robotic arm and cannot be replaced autonomously, this paper designs a robotic end-effector system that can perform multiple tasks for manipulation robots. The system consists of a tool changer and three operating tools. The advantage of the end-effector is that the motor driving module of operating tools is reduced, and the driving torque is provided by the tool changer. So the size and weight of the operating tool are small and the structure is simple. In order to realize autonomous tool change, a new visual identification marker is designed. A new grasping data set is collected and a hierarchical encoder-decoder neural network is also proposed. The experimental results demonstrate the feasibility of the design method.

Original languageEnglish
Title of host publicationProceedings of 2022 Chinese Intelligent Systems Conference - Volume II
EditorsYingmin Jia, Weicun Zhang, Yongling Fu, Shoujun Zhao
PublisherSpringer Science and Business Media Deutschland GmbH
Pages828-838
Number of pages11
ISBN (Print)9789811962257
DOIs
StatePublished - 2022
Event18th Chinese Intelligent Systems Conference, CISC 2022 - Beijing, China
Duration: 15 Oct 202216 Oct 2022

Publication series

NameLecture Notes in Electrical Engineering
Volume951 LNEE
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

Conference18th Chinese Intelligent Systems Conference, CISC 2022
Country/TerritoryChina
CityBeijing
Period15/10/2216/10/22

Keywords

  • Robotic end-effector
  • Tool changer
  • Visual detection

Fingerprint

Dive into the research topics of 'An Automatic Robotic End-Effector System Based on Visual Detection'. Together they form a unique fingerprint.

Cite this