Skip to main navigation Skip to search Skip to main content

Singularity Avoidance Strategies for Target Tracking Visual Servo Systems

  • Harbin Institute of Technology

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

Abstract

A typical vision servo system for motion target tracking consists of a robotic manipulator and a camera mounted at its end. The image acquired by the camera is processed by a vision algorithm to obtain the position of the motion target in 3D space, whereby the servo controller controls the robotic manipulator to track the motion of the target and keep it in the camera's field of view at all times. In this paper, we proposed an evaluation indicator to evaluate such tracking tasks, and proposed an adaptive damped least-square algorithm to avoid singularities during the motion of the robotic arm. An experimental platform consist of ZED binocular camera and UR5 robotic arm is built to conduct experiments on singularity avoidance and target tracking, verifying that the visual servo system with the singularity avoidance algorithm can achieve a good tracking result.

Original languageEnglish
Title of host publicationProceedings of the 40th Chinese Control Conference, CCC 2021
EditorsChen Peng, Jian Sun
PublisherIEEE Computer Society
Pages2855-2859
Number of pages5
ISBN (Electronic)9789881563804
DOIs
StatePublished - 26 Jul 2021
Event40th Chinese Control Conference, CCC 2021 - Shanghai, China
Duration: 26 Jul 202128 Jul 2021

Publication series

NameChinese Control Conference, CCC
Volume2021-July
ISSN (Print)1934-1768
ISSN (Electronic)2161-2927

Conference

Conference40th Chinese Control Conference, CCC 2021
Country/TerritoryChina
CityShanghai
Period26/07/2128/07/21

Fingerprint

Dive into the research topics of 'Singularity Avoidance Strategies for Target Tracking Visual Servo Systems'. Together they form a unique fingerprint.

Cite this