DocumentCode :
583520
Title :
Precise welding line detection of a hexahedron based on twisted motion of a scanning LRF
Author :
Lee, Sungmin ; Park, Jaebyung
Author_Institution :
Div. of Electron. Eng., Chonbuk Nat. Univ., Jeonju, South Korea
fYear :
2012
fDate :
17-21 Oct. 2012
Firstpage :
1178
Lastpage :
1180
Abstract :
The precise welding line detection method based on twisted motion of a scanning laser range finder (LRF) is proposed for autonomous robotic welding of a hexahedron into a steel plate. For successful welding, the directions of the welding lines should be obtained precisely. For detecting welding line, more than two points on the welding line should be obtained. Thus, two points on the welding line are obtained based on the twisted motion of the scanning LRF. In this case, the feature point on the welding line is detected by applying the Hough transform into the sensor data of the LRF, taking the intrinsic characteristics of the sensor into consideration. Since the Hough transform is based on the voting mechanism, the sensor noise can be reduced. For verifying the feasibility of the proposed method, the simulation has been carried out with a commercial LRF model, UBG-04LX-F01 of Hokuyo Automatic Co., Ltd.
Keywords :
Hough transforms; edge detection; feature extraction; laser ranging; robotic welding; steel; Hokuyo Automatic Co. Ltd; Hough transform; UBG-04LX-F01; autonomous robotic welding; feature point detection; hexahedron; precise welding line detection method; scanning LRF twisted motion; scanning laser range finder; sensor data; sensor noise reduction; steel plate; voting mechanism; Feature extraction; Image edge detection; Robot sensing systems; Service robots; Transforms; Welding; Automatic Robotic Welding; Scanning Laser Range Finder (LRF); Twisted Motion;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Control, Automation and Systems (ICCAS), 2012 12th International Conference on
Conference_Location :
JeJu Island
Print_ISBN :
978-1-4673-2247-8
Type :
conf
Filename :
6393305
Link To Document :
بازگشت