Application of Hybrid Intelligent System Integration and Control to Twin-Robot Patrol

瀏覽統計 Email 通知 RSS Feed

簡歷

基本資料

Project title

Code/計畫編號

MOST105-2221-E019-001

Translated Name/計畫中文名

混合式智慧型系統整合與控制於雙機器人巡守隊之應用

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=11903276

Year

2016

Start date/計畫起

01-08-2016

Expected Completion/計畫迄

31-07-2017

Bugetid/研究經費

793千元

ResearchField/研究領域

電子電機工程

The basic technologies of Industry 4.0, or the fourth industrial revolution, are: Cyber-Physical Systems, Big Data, Internet of Things and Internet of Services. Some experts predict the Industry 4.0 will become reality in 10 to 20 years. Taiwan’s researchers should put more attention on this subject. In the proposed project, we utilize image process, intelligent systems, GPS, and Wi-Fi communications to service robot applications. The purpose of this project is to design service robots that can take elevator, remote surveillance, and indoor-outdoor patrol. In this project we will continue the development of the previous projects and make the robot be able to perform patrol and surveillance. In addition, this project will develop dual-robot system for working on outdoor patrol. Such that the proposed service robots can replace some of security guard’s works and reduce personnel cost. The project puts focus on integration of color space transformation, pattern recognition, and fuzzy control. Backpropagation through time (BPTT) neural networks, A* algorithm, iterative closest point algorithm (ICP), evolutionary algorithm, and artificial potential field are applied to path planning, tracking and obstacle avoidance control. Laser sensor, camera, and DGPS are integrated to enhance positioning accuracy. Positions of robot and target can be updated in real time. In dual-robot patrols, Wi-Fi is utilized to control center and robots communications. In this study, LabVIEW 2010 is utilized for human-machine interface. The robot is controlled by the calculated angle and distance. This research will develop an adaptive system that can adopt surrounding changes for image recognition, and provide suitable rules for control strategy. Finally, set up easy structure, fast learning and adequate algorithm for hardware realization, which can reduce production cost. This study uses two wheeled mobile robots (WMR) as the carriers and integrates camera, wireless communication module, GPS, and laser range finder to perform 表CM02 共 2 頁第 1 頁 automatic guidance, path tracking, obstacle avoidance, and remote surveillance. Through image processing technique, object can be identified and the distance can be obtained. This information is then used to control robot arm to reach target button or to drive the wheeled robot to follow the object. Fuzzy system is applied to robot motor controller design. Images of surroundings can be transmitted to smartphone and control center via Wi-Fi. The smartphone can monitor robot movement and perform remote surveillance. 工業 4.0(第四次工業革命)之基礎技術包含智慧整合感控系統、大數據、物聯網及網路服務，許多專家相信第四次工業革命會在今後的10 至20 年實現，台灣的相關研究亦應跟上這潮流。本計畫是智慧整合感控系統之應用，結合影像識別、智慧型系統、GPS 及Wi-Fi 無線通訊於服務型機器人之實現，期望設計具備搭乘電梯、遠端監控、室內外巡邏監視等功能的保全機器人。本計畫延續前一計畫之搭乘電梯、傳遞公文、大樓室內巡守功能之服務型機器人，將設計雙機器人巡守隊，從事戶外巡邏、定點檢視、異象回報等工作，以期取代目前保全人員部分的工作，節省人事費的支出。本研究主要目的是整合色彩空間的影像處理、自適應共振理論的圖形識別、倒傳遞時間延續神經網路的路徑追跡、模糊控制系統、A*演算法、Iterative Closest Point 演算法、演化理論及人工勢能場，建立雙機器人巡守隊的路徑規劃及避撞控制。結合雷射感測器及影像感測器，並利用差分GPS 以提高定位精度，即時修正目標物與機器人之間的位置關係，規劃出最佳化的行進路線。另外結合Wi-Fi 執行雙機器人與監控中心的聯繫，並提出結合影像處理之入侵物追蹤法則。硬體實現將使用LabVIEW 2010 做為人機介面，利用影像處理後所得之角度及距離作為輪式機器人路徑追蹤的依據。本研究要尋找具備適應環境變化能力之影像識別及路徑規劃法則，並利用智慧型控制訂定控制策略，以期建立結構簡單、學習快速的適當演算方式，以便在硬體實現時，可使得成本降至最低。本研究將應用2 台輪式人型機器人，結合攝影機、無線通訊模組、雷射感測器、GPS 等，進行自動導航、尋跡、避撞、巡邏及監視。經由攝影機擷取到的環境影像，利用色彩空間轉換，篩選出目標物，再透過影像處理技術與距離演算法，計算機器人與目標物的實際距離，模糊系統將應用在伺服馬達控制與機器人控制器的設計上，以控制機器人追隨目標物或控制機械手臂觸控牆壁上的按鈕及開關。機器人可執行監控動態目標物，影像亦可經由 Wi-Fi 無線傳輸傳送至手機及監控中心，手機可遠端透過監控中心電腦對機器人進行室內外巡邏監視。

Keyword(s)

避障控制
路徑規劃
影像處理
A*演算法
ICP 演算法
演化理論
人工勢能場
差分GPS
自動導航
collision avoidance control
path planning
image process
A* algorithm
ICP algorithm
evolutionary algorithm
artificial repulsive force
DGPS
automatic guidance

DSpace CRIS

Application of Hybrid Intelligent System Integration and Control to Twin-Robot Patrol

基本資料

Description