English  |  正體中文  |  简体中文  |  Items with full text/Total items : 26988/38789
Visitors : 2349654      Online Users : 31
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/987654321/28353

Title: 智慧型移動式機器人運動控制設計與實現(II)
Intelligent WMR Motion Control Design and It's Hardware Implementation(II)
Authors: 莊季高
Contributors: NTOU:Department of Communications Navigation and Control Engineering
國立臺灣海洋大學:通訊與導航工程學系
Keywords: 輪式移動機器人;智慧型控制;模糊系統;基因演算法;灰色理論;回饋式類神經網路;小腦模型控制器;FPGA
Intelligent Control;Fuzzy System;Genetic Algorithm;Grey Theory;RecurrentNeural Network;CMAC;FPGA
Date: 2008-08
Issue Date: 2011-10-21T02:37:14Z
Publisher: 行政院國家科學委員會
Abstract: 摘要:工研院機械所的調查報告指出,未來市場最被看好的五款機器人分別為Cleaning Robot、Security Robot、Reception Robot、Childcare Robot、Intelligent Wheelchair 等, 均為輪式移動機器人,市場價值於2010 年將達1.8 trillion。為了使移動式機器人成為 服務性智慧機器人合用的載具,以及利用此種機器人進行車輛行駛自動控制的研究, 並使自動導引系統更具強健性,並得以適應於不同的環境,本計畫將針對一實驗用的 小型移動式機器人,Dr Robot X80,先進行追跡控制,再利用人工智慧進行路徑規劃, 最後再利用DSP 及一組多功能的FPGA 晶片組,將控制律的運算及系統週邊的感測 器輸入輸出控制轉換成邏輯電路,以為將來自動駕駛控制器奠定理論及硬體商品化之 基礎。以台灣在IC 電子製造業的優勢,期望將來能設計製作出具有市場競爭力之智 慧型移動式機器人或車輛自動導引控制器。本計畫分三年來完成智慧型移動式機器人 運動控制的理論分析、軟體模擬及硬體實現。目前正執行第一年計畫中,第一年係應 用模糊理論與灰色預測器並結合基因演算法,針對追跡控制設計灰預測模糊控制器, 至今已完成以Type-1 模糊系統設計追跡控制器,現正進行Type-2 模糊系統的控制器 分析;第二年將應用可即時學習的類神經網路與小腦模型控制器並結合不同的演化計 算法則,進行移動式機器人的即時學習及控制;第三年則結合感測元件進行路徑規劃 與避撞控制及硬體控制器的實現。
abstract:According to the ITRI report, the top five demands of robot industry in the future are Cleaning Robot, Security Robot, Reception Robot, Childcare Robot, and Intelligent Wheelchair. They are all Wheeled Mobile Robot (WMR). The market value will be 1.8 trillion in the year 2010. In order to make the WMR a suitable carrier for multiple purpose services, this project will put focus on automatic guidance control. Robust and adaptive control will also be addressed. This project will investigate the control problem using an experimental WMR setup, Dr Robot X80. Trajectory tracking control will be first investigated. Path planning that uses artificial intelligent techniques will then be applied. This research will also integrate different sensors to trajectory tracking, shortest distance search, collision avoidance, and automatic parking control. Finally the control law and I/O interface will be transformed into logic circuits and be implemented on a multiple purpose Field Programmable Gate Array (FPGA) set. The feasibility of the proposed commercialized intelligent automatic control system will be evaluated by the hardware test. This is a three-year project and there are three phases: theory analysis, software simulations, and hardware integration and test. At the first year, this project intends to apply the fuzzy reasoning capability of the fuzzy system and the parameter predicting and searching ability of the grey theory and genetic algorithm to the trajectory tracking control design. Currently, we have finished Type-1 fussy controller design. During the second year, Recurrent Neural Network (RNN) and Cerebellar Model Arithmetic Controller (CMAC) with different evolutionary computations will be utilized to the real-time learning and control. In the third year, different sensors will be integrated in the control scheme. Path planning and collision avoidance control will be performed. Hardware controller will be implemented in a DSP/FPGA module.
URI: http://ntour.ntou.edu.tw/handle/987654321/28353
Appears in Collections:[通訊與導航工程學系] 研究計畫

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