Using Reinforcement Learning Tue Visual Servo System Control Gain
碩士 === 國立中正大學 === 電機工程研究所 === 103 === How to set control gain is always an important issue in control system design. The control gain is also important in visual servo system. If control gain is too high, the system will become unstable. In contrast, small control gain results in long converge time....
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/eaf294 |
id |
ndltd-TW-103CCU00442010 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-103CCU004420102019-05-15T21:42:48Z http://ndltd.ncl.edu.tw/handle/eaf294 Using Reinforcement Learning Tue Visual Servo System Control Gain 以增強式學習法改善視覺伺服系統控制增益 Chuang, Yi-Lin 莊易霖 碩士 國立中正大學 電機工程研究所 103 How to set control gain is always an important issue in control system design. The control gain is also important in visual servo system. If control gain is too high, the system will become unstable. In contrast, small control gain results in long converge time. Approaches like adaptive control and cerebellar model articulation controller (CMAC) are proposed for solving this issue. But the adaptive control system is too complex that hard to design, and CMAC needs to be trained over the whole workspace of visual servo system which requires significant computational resources. In this thesis, we propose using Q-learning to tune the control gain of image-based visual servoing system, decrease the time consumption of the robot approaching to desired position. 黃國勝 陳昱仁 2014 學位論文 ; thesis 48 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立中正大學 === 電機工程研究所 === 103 === How to set control gain is always an important issue in control system design. The control gain is also important in visual servo system. If control gain is too high, the system will become unstable. In contrast, small control gain results in long converge time. Approaches like adaptive control and cerebellar model articulation controller (CMAC) are proposed for solving this issue. But the adaptive control system is too complex that hard to design, and CMAC needs to be trained over the whole workspace of visual servo system which requires significant computational resources. In this thesis, we propose using Q-learning to tune the control gain of image-based visual servoing system, decrease the time consumption of the robot approaching to desired position.
|
author2 |
黃國勝 |
author_facet |
黃國勝 Chuang, Yi-Lin 莊易霖 |
author |
Chuang, Yi-Lin 莊易霖 |
spellingShingle |
Chuang, Yi-Lin 莊易霖 Using Reinforcement Learning Tue Visual Servo System Control Gain |
author_sort |
Chuang, Yi-Lin |
title |
Using Reinforcement Learning Tue Visual Servo System Control Gain |
title_short |
Using Reinforcement Learning Tue Visual Servo System Control Gain |
title_full |
Using Reinforcement Learning Tue Visual Servo System Control Gain |
title_fullStr |
Using Reinforcement Learning Tue Visual Servo System Control Gain |
title_full_unstemmed |
Using Reinforcement Learning Tue Visual Servo System Control Gain |
title_sort |
using reinforcement learning tue visual servo system control gain |
publishDate |
2014 |
url |
http://ndltd.ncl.edu.tw/handle/eaf294 |
work_keys_str_mv |
AT chuangyilin usingreinforcementlearningtuevisualservosystemcontrolgain AT zhuāngyìlín usingreinforcementlearningtuevisualservosystemcontrolgain AT chuangyilin yǐzēngqiángshìxuéxífǎgǎishànshìjuécìfúxìtǒngkòngzhìzēngyì AT zhuāngyìlín yǐzēngqiángshìxuéxífǎgǎishànshìjuécìfúxìtǒngkòngzhìzēngyì |
_version_ |
1719119517547757568 |