Research on Intelligent Glue-coating Robot Based on Visual Servo

Abstract At present, Glue-coating machines have some shortages, such as unintelligence, complexity of setting glue path for new parts. In this paper, real-time image capture was achieved by using digital camera technology and image processing technology. The captured image is converted into a character vector. Workpiece model is determined through comparing with the standard library and the similarity. The image of workpiece was vectored through frame extracting and fitting. With NC (Numerical Control) code generation technology, the NC code is automatically generated for sprinkler nozzle walking track. By Appling visual servo and embedding the vision system into feedback loop of the robot, the system achieves high-precision robot control. By extracting the glue line curve from image, thinning glue curve by morphological method, and extracting the frame information, the closure and quality of the glue curve can be detected. Results of test show that the effect is satisfactory and the method is effective.