The Research Of The Vision-Guided AGV System

The logistics system in manufacturing often doing material handling,assembly by means of manual,but with the rising of the labor costs,this approach exposes some problem such as low logistics efficiency,low reliability,and high cost etc.So new development opportunities for AGV technology is coming.But the traditional magnetic-guided AGV can just detect single deviation information,and the control effect is poor.Trackless-guide way is very expensive.Intend to study the problem of automated storage and logistics in manufacturing production line,the technology of vision-guided is introduced in this paper.The main content of this paper is as follows:Firstly,in order to solve the disadvantages of traditional magnetic-guided AGV and trackless-guided AGV.Base on the idea of modularized-design to complete the overall design of vision-guided vehicle(AGV).that include the mechanical structure design,the hardware design of each function modules of AGV and design the software of vehicle control system.Secondly,this paper expounds the AGV guiding principle based on machine vision.Proposal using the lateral deviation e and the direction deviation angle ? as guidance information.In order to realize the extraction of guidance information,this paper does the image processing work based on Visual Studio 2008 integrated development environment configuration with opencv 2.4.4 development package,including image filtering,threshold segmentation,edge detection,ribbon identification and ribbon center line fitting.Thirdly,this paper analyzes trajectory correcting process of differential type vision-guided AGV,and establish the mathematical model of AGV's trajectory correction.According to the results of mathematical model,there is a coupling relationship between the two control variables in the process of rectification,so this paper designs a fuzzy controller to realize the nonlinear control of trajectory correction process.Finally,Set up the experiment platform for vision-guided AGV based on the overall design scheme.And verify the image processing capacity,loading capacity,rectifying deviation capacity,stopping obstacle and positioning accuracy of vision-guided AGV by experiments.