Skip to main navigation Skip to search Skip to main content

Research on robotic arm recognition and grasping based on RGB-D sensor

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

Abstract

As people's demand for service robots continues to grow, how to solve the problem of robot interaction with the physical world, especially solving the problem of robot crawling, has become a hot issue in the world. In this paper, the algorithm of target recognition and 6D pose estimation is studied based on RGB-D sensor Kinect. The target recognition, which The object to be captured is determined in a complex environment, is performed by ORB algorithm and template matching. The point cloud registration is performed by LM-ICP algorithm to calculate the position and attitude of the object relative to the robot. Finally, the feasibility of the capture experiment verification algorithm in the Gazebo physics simulation environment is carried out.

Original languageEnglish
Title of host publicationProceedings of the 2019 2nd International Conference on Service Robotics Technologies, ICSRT 2019
PublisherAssociation for Computing Machinery
Pages7-11
Number of pages5
ISBN (Electronic)9781450362467
DOIs
StatePublished - 22 Mar 2019
Event2nd International Conference on Service Robotics Technologies, ICSRT 2019 - Beijing, China
Duration: 22 Mar 201924 Mar 2019

Publication series

NameACM International Conference Proceeding Series

Conference

Conference2nd International Conference on Service Robotics Technologies, ICSRT 2019
Country/TerritoryChina
CityBeijing
Period22/03/1924/03/19

Keywords

  • Machine vision
  • Pose estimation
  • Service robot
  • Target recognition

Fingerprint

Dive into the research topics of 'Research on robotic arm recognition and grasping based on RGB-D sensor'. Together they form a unique fingerprint.

Cite this