Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 陳弘哲 | en_US |
dc.contributor.author | Hong-Tze Chen | en_US |
dc.contributor.author | 宋開泰 | en_US |
dc.contributor.author | Kai-Tai Song | en_US |
dc.date.accessioned | 2014-12-12T01:14:21Z | - |
dc.date.available | 2014-12-12T01:14:21Z | - |
dc.date.issued | 2007 | en_US |
dc.identifier.uri | http://140.113.39.130/cdrfb3/record/nctu/#GT009512547 | en_US |
dc.identifier.uri | http://hdl.handle.net/11536/38253 | - |
dc.description.abstract | 本論文主要目的在於設計一移動式機械臂的抓物控制系統,藉由安裝於手臂上之攝影機擷取到的影像資訊,使機器人得以在環境中找尋設定之目標物體,並自主導引移動式機器手臂至適當的抓取位置完成物體之抓取。本文中採用尺度不變性特徵轉換(Scale Invariant Feature Transform,SIFT)來定義目標物體的特徵點,並且藉由比對當前畫面中的特徵點來確認物體是否存在於影像中。本論文發展出一套演算法,提高特徵點比對的準確度,且同時得以計算當前物體與攝影機之間的相對距離。實驗結果顯示,特徵點比對的準確度提升至90%。此外在與控制器的整合設計上,本論文提出虛擬特徵點的概念,可以透過此額外定義之特徵點座標,計算Image Jacobian並達成影像伺服控制,導引一移動式機械臂自主取物。本論文以實驗室之4自由度的移動式機械手臂搭配嵌入式影像平台,驗證所提出方法的可行性。經過實驗驗證,此系統可導引機器人順利拿取所指定的目標物。 | zh_TW |
dc.language.iso | zh_TW | en_US |
dc.subject | 移動式機械臂 | zh_TW |
dc.subject | 物體抓取 | zh_TW |
dc.subject | 影像伺服 | zh_TW |
dc.subject | 影像辨識 | zh_TW |
dc.subject | 尺度不變性特徵轉換 | zh_TW |
dc.subject | Mobile Manipulator | en_US |
dc.subject | Object Grasping | en_US |
dc.subject | Visual Servo | en_US |
dc.subject | Image Recognition | en_US |
dc.subject | Scale Invariant Feature Transform | en_US |
dc.title | 基於影像辨識之移動式機械臂抓物控制設計 | zh_TW |
dc.title | Object Grasping of a Mobile Manipulator Using Image Recognition | en_US |
dc.type | Thesis | en_US |
dc.contributor.department | 電控工程研究所 | zh_TW |
Appears in Collections: | Thesis |
Files in This Item:
If it is a zip file, please download the file and unzip it, then open index.html in a browser to view the full text content.