INDUSTRIAL ROBOT GUIDANCE USING COMPUTER VISION. ROBOTIZATION OF A RADIATOR MANUFACTURING PROCESS.

Abstract

In some manufacturing processes, products with different shapes and sizes are manufactured and these products are often presented at the manipulation sites by means of systems that do not control their position or orientation. The automatic manipulation in these processes has traditionally been very intricate and expensive. Nevertheless, the performance of the new sensors, such as computer vision, and their easy integration with robots have make the automation really accessible. In an effort to contribute in the field of guided vision robot to gain higher flexibility and adaptability in industrial robots applications, this paper presents our work towards the automation of a sealing process in a radiator manufacturing line, where many different sizes and models must be processed both simultaneously and in movement. The robot guidance problem is solved using two vision systems that determine accurately the position of the pieces. A fixed vision system acquires a global image of the approaching radiators and computes a first pose estimation. This estimation is used for the robot to approach to the part and a second system mounted on the robot arm, acquires a closer image to determine precisely the position and orientation just before the manipulation is performed. The developed system is working nowadays in an industrial line making it possible to robotize a complex task.