Intelligent WMR Motion Control Design and It's Hardware Implementation(II)

瀏覽統計 Email 通知 RSS Feed

簡歷

基本資料

Project title

Code/計畫編號

NSC97-2221-E019-025

Translated Name/計畫中文名

智慧型移動式機器人運動控制設計與實現(II)

Project Coordinator/計畫主持人

Jih-Gau Juang

Funding Organization/主管機關

National Science and Technology Council

Department/Unit

Department of Communications, Navigation and Control Engineering

Website

https://www.grb.gov.tw/search/planDetail?id=1698963

Year

2008

Start date/計畫起

01-08-2008

Expected Completion/計畫迄

31-07-2009

ResearchField/研究領域

電子電機工程

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. 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。

Keyword(s)

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

DSpace CRIS

Intelligent WMR Motion Control Design and It's Hardware Implementation(II)

基本資料

Description