Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0819104-115332 Statistics This thesis had been viewed 4091 times. Download 1316 times. Author Chung-Jen Hsieh Author's Email Address email@example.com Department Mechanical Engineering Year 2003 Semester 2 Degree Master Type of Document Master's Thesis Language English Page Count 47 Title An Intelligent Control System with Automatic Training
for Improvement of Robot Position Control
Keyword Vision System Robot Position Control Fuzzy Logic Control Artificial Neural Network Artificial Neural Network Fuzzy Logic Control Robot Position Control Vision System Abstract To improve position control of vision robot, an intelligent control system which consists of two ANNs and one FLC is used to eliminate the position error due to the model inaccuracy. One ANN in the feedforward path is used to compensate the major position error and the other ANN in the feedback path is used to correct the minor error. Besides, the FLC is applied to adjust the position error between the target and end-effector. In order to save human effort, the data for training the ANNs is automatically acquired. The experiment results show that the performance of the judging algorithm used in the automatic data acquiring is as good as manual teaching and the control system proposed can be used for peg-in-hole insertion. Advisor Committee Yen-Cheng Lin - advisor
Guan-Chun Luh - co-chair
Yin-Tien Wang - co-chair
Files Date of Defense 2004-07-27 Date of Submission 2004-08-19