Screw and wrench orientation estimation using the artificial vision in the NAO humanoid robot

Abstract

Industrial robots are having major involvement in assembly lines, where they are able to identify, classify and even grasp objects and place them in non-default locations; furthermore, assembling pieces autonomously. We describe step by step the image processing to determine the objects orientation located in the field of view of the NAO robot, initial step in posterior developments in task execution using those objects. The processing stages described are: RGB color space segmentation, interest points detection and objects orientation estimation with respect to a reference frame. The results are compared with measures obtained using a commercial image processing software. The absolute error is less than 1.5° in the objects orientation angles, which is considered acceptable due to the size of the processed objects. The introduced methodology is a first step in the execution of assembling tasks or handling of tools by a robotic platform, where the artificial vision has a relevant place in the identification, location and orientation of the objects.