Research On AGV Combined Positioning Technology Based On QR Code Recognition

AGV is a kind of unmanned vehicle which can move independently according to the need by manual or automatic loading and unloading of goods and equipped with automatic guidance equipment.In recent years,with the continuous development of intelligent manufacturing and intelligent logistics,AGV has been applied more and more widely in the field of industrial production and logistics transportation,and has become an indispensable important equipment in manufacturing automation and logistics automation system.In the application research of AGV field,the problem of autonomous positioning has always been a hot issue of research.As the basis of AGV navigation and path planning,positioning is the premise of AGV to complete transportation tasks.At present,GPS positioning,inertial positioning and laser positioning are widely used and mature positioning technologies in the field of AGV.However,these positioning technologies have some limitations in application scenarios,positioning accuracy and cost.In order to solve this problem,this paper refers to the advanced positioning technology at home and abroad,and combines with the development trend of AGV positioning technology nowadays,puts forward an AGV combination positioning scheme based on QR code recognition.The main work is as follows:Firstly,this paper analyses the advantages and disadvantages of the commonly used AGV positioning methods,combines monocular vision positioning and Dead-reckoning,and proposes an AGV integrated positioning scheme based on QR code.Compared with other AGV positioning methods,this scheme has the advantages of low cost and high reliability.On this basis,the hardware of the AGV positioning system is selected,the AGV car for experiment is made.Secondly,the QR code recognition and decoding process in visual positioning is deeply studied.In order to improve the accuracy of QR code recognition in visual positioning scheme,a detailed image preprocessing process is developed in image processing.In the aspect of QR code detection and positioning,the commonly used QR code positioning schemes are analyzed.In view of the shortcomings of these detection schemes,combined with the specific identification of the QR code in the positioning system of this paper,the position detection pattern is detected first,and then the position detection pattern is used.The solution of locating the QR code effectively improves the real-time performance of the QR code detection and positioning;In addition,the relative position relationship between the AGV vehicle and the QR code is established by using the 3d pinhole model of the camera,and the precise positioning of the AGV vehicle based on QR code recognition is realized.In the estimation of the dead-reckoning positioning,the MPU6050 and the photoelectric encoder displacement measurement error are analyzed and corrected.Finally,in order to further improve the fusion positioning accuracy,the extended Kalman filter is used to fuse the visual positioning information with the dead-reckoning positioning information.The test results show that the scheme can meet the expected positioning requirements of the AGV trolley,which lays a good foundation for further research work of the subsequent AGV system.