English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2346842      Online Users : 39
RC Version 4.0 © Powered By DSPACE, MIT. Enhanced by NTU Library IR team.
Scope Adv. Search
LoginUploadHelpAboutAdminister

Please use this identifier to cite or link to this item: http://ntour.ntou.edu.tw:8080/ir/handle/987654321/6353

Title: 整合聲光視覺感測與定位系統之智慧型自走車
Integration of Sonic-Visual Sensing and Localization System for an Intelligent WMR
Authors: Wei-Hsun Wang
王偉勳
Contributors: NTOU:Department of Communications Navigation and Control Engineering
國立臺灣海洋大學:通訊與導航工程系
Keywords: 定位系統;視覺感測;智慧型自走車
localization system;Visual;WMR
Date: 2009
Issue Date: 2011-06-22T08:47:36Z
Abstract: 本篇論文提出以感測資料為基礎,利用模糊系統來模擬人類的推論模式,經由使用者的經驗和感測器的整合,建立一個兼具控制及判斷的方法,不需要非常複雜的數學方程式,就可以設計出一個效果不錯的控制器。本文主要利用室內定位系統來提供自走車的位置以及頭向夾角,結合模糊邏輯建立停車的行為模式與使用超音波及紅外線感測器作為停車安全的考量,再搭配基因演算法所搜尋之參考路徑,達到自走車追跡效能最佳化控制。在停車模式分為:車庫已知、車庫未知及運送病歷之應用。另外亦使用攝影機與影像處理技術來擷取路面特定顏色的線條,並且計算其長度藉以判斷停車格地點,再透過超音波感測器完成路邊停車動作。進行硬體實驗前先經由套裝軟體Matlab模擬影像處理及模糊理論,在WMR實體測試中,使用LabView 8.5來撰寫人機介面。硬體實驗結果顯示,使用室內定位系統,能有效提供車體精確的位置,避免使用WMR編碼值運算所造成的累積誤差,提高停車控制的準確性及成功率;而使用攝影機與超音波感測器辨識停車地點及完成停車動作,亦符合吾人駕車之行為,經由硬體的實現,證明此智慧型控制器的可行性及可靠性。
Abstract This thesis presents a wheeled mobile robot WMR using sensor data in path following and parking control. An intelligent control scheme is proposed, which includes the fuzzy system, genetic algorithm, localization system, and image processing technique. Through system integration, the control system can effectively control the robot without using any complicated mathematical equations. Ultrasonic sensors are used to detect vacancy and examine safety distance during parking process. A CCD camera is utilized to search the location of a parking lot. The localization system provides the position and heading direction of the robot. Fuzzy logic is used to form parking behavior pattern. Reference paths are searched by a genetic algorithm. Difference parking modes are introduced, they are forward garage parking, backward garage parking, multiple forward parking, and parallel parking. At the WMR entity tests, we use the LabView 8.5 to encode the interface between human and machine and utilize a personal computer to compute the expected trajectory. Recursive computations are used in WMR to achieve trajectory tracking control. Experiments show that the proposed control scheme can guide the WMR in different parking modes successfully.
URI: http://ethesys.lib.ntou.edu.tw/cdrfb3/record/#G0M96670038
http://ntour.ntou.edu.tw/ir/handle/987654321/6353
Appears in Collections:

Files in This Item:

There are no files associated with this item.



All items in NTOUR are protected by copyright, with all rights reserved.

 


著作權政策宣告: 本網站之內容為國立臺灣海洋大學所收錄之機構典藏,無償提供學術研究與公眾教育等公益性使用,請合理使用本網站之內容,以尊重著作權人之權益。
網站維護: 海大圖資處 圖書系統組
DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library IR team Copyright ©   - Feedback