Research Of Precision Location Technology For Automated Guided Vehicle

Automated Guided Vehicle (AGV) with many significant advantages such as flexibility,intelligence and so on is widely used in automated warehouse, flexible assembly system,logistics system etc. The widespread use of AGV not only reduces labor costs, improvesproduction efficiency, but also ensures the reliability of the material transport.Automated Guided Vehicle integrates several key technologies, such as navigation,vehicle servo drive technology, information acquisition and processing technology and so on.Among these, navigation is one of the key technologies, however, precision locationtechnology is the key to achieve navigation. Currently, visual navigation technology with itsbest flexible in theory become a research hotspot, at the same time visual positioning problembased on artificial landmarks is derived.In combination with the hotspots of the visual positioning problem based on artificiallandmarks, this paper sets QR Code as the artificial landmarks in order to accurately locate forAGV. The main content of this paper includes two parts, as follow:The part of QR Code recognition. This part mainly introduces the principle of QR Coderecognition and its brief description. There is focus on the research about the binarizationmethod of the QR Code image with uneven illumination. And this paper presents acorresponding QR Code image binarization algorithm which can be used to solve the problemof QR Code image with uneven distribution of the light. Experimental results show that theQR code binarization can be done quickly by the improved algorithm with high accuracy andstability, and it also can be implemented in embedded systems.The part of the position estimation for Automated Guided Vehicle. This part mainlyintroduces the basic knowledge of navigation, camera model, overall design and so on. Thispart focuses on QR Code-based AGV positioning algorithm and dead reckoning algorithmbased on odometer, and then combines the two algorithms to achieve precise positioning ofautomatic guided vehicles in the structured indoor environment. Experimental results show that the algorithm is robust and positioning accuracy can meet the demand of practicalapplication basically.