Please use this identifier to cite or link to this item: https://scholarbank.nus.edu.sg/handle/10635/153431
Title: ROBOTICS : CONTOURING CONTROL USING VISION FEEDBACK
Authors: SAY KWEE TECK
Issue Date: 1986
Citation: SAY KWEE TECK (1986). ROBOTICS : CONTOURING CONTROL USING VISION FEEDBACK. ScholarBank@NUS Repository.
Abstract: A system that can guide the robot to follow the contour of a given shape using a camera is described. The system consists of a low cost vidicon camera for image capturing, an IBM PC microcomputer for vision processing and communication and a six degree-of-freedom PUMA 560 robot for contour following. The system developed has been tested on several odd shapes with various curvatures and straight lines combinations. The result shows very good agreement between the actual contour and the robot generated contour. The necessary hardware circuit has been designed to interf3ce the video camera to the microcomputer. The processing of the digital image involves segmentation, contour extraction, contour approximation and contour scaling. Information are send to the PUMA controller by emulating its terminal and keyboard functions. The software is written in compiled BASIC with the essential vision algorithm written in 8088 machine codes to achieve an execution speed which is about I 5-20 seconds for contours of 400-800 pixels (extracted from a 200 by 200 image array). Multiple independent contours can also be processed in a single pass. In addition to a one-to-one contour reproduction, contour enlargement, reduction and rotation is also included. The system can be linked to teach and reproduce the profile on any Point-to-Point robot which has provision for straight line motions and should be useful in many practical applications, for example metal cutting, welding, patterns cutting in woodwork, textile industries, etc.
URI: https://scholarbank.nus.edu.sg/handle/10635/153431
Appears in Collections:Master's Theses (Restricted)

Show full item record
Files in This Item:
File Description SizeFormatAccess SettingsVersion 
b14354585.pdf4.41 MBAdobe PDF

RESTRICTED

NoneLog In

Page view(s)

2
checked on May 12, 2019

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.