Artificial Vision in Embedded System for Rigid Parts Recognition

摘要

Since the first robot manipulator for industrial applications was installed for General Motors, the planning and execution of its movements has been an important part in the development of robotic systems involving researchers from different specialties. The planning and guidance of the movement in the robots has been increasingly complex due to the wide variety of applications in which they are used, from repetitive tasks in the traditional assembly lines to the assistance in the movements of very precise surgical operations which require real-time movement guidance, this has established an area of research and technological development known as “Robotics hardware and software driving”. The article shows the implementation of the methodology called “Boundary Object Function BOF” [Pe?a 2005], algorithm for recognition and location of rigid forms, in an embedded electronic device of the RaspBerry Pi type 3. In the method used, the electronic system acquires and condition the image, to be converted to a binary image used by the BOF algorithm. Experimental results within a manufacturing cell were performed with the implementation of the method. The result of the integration of recognition algorithms and location of rigid manufacturing parts in embedded electronic systems, shows the possibility of using them in manufacturing applications with processing high speed requirements and concurrent processes, in this way, a robot learns online and identify objects that are familiar to the performed tasks. The technological proposal presented for the invariant recognition of objects based on the BOF algorithm implemented in an electronic embedded system calculates the contour of rigid pieces very quickly.