Fig 12 - uploaded by Mario Peña-Cabrera
Content may be subject to copyright.
Source publication
The research presented in this chapter presents an alternative methodology to integrate a robust invariant object recognition capability into industrial robots using image features from the object's contour (boundary object information) and its form (i.e. type of curvature or topographical surface information). Both features can be concatenated in...
Context in source publication
Context 1
... the neural network was trained with the patterns, then the network was tested placing the different pieces at different orientation and location within the work space. The figure 12 shows some examples of the object's contour. The object's were recognised in all cases having only failures between Rounded shaped objects and Square shaped ones. ...
Citations
... The camera system is used to input data to program the robot new trajectories and to correct any misalignment during part welding but also it is being used as an input to the object recognition application. This object recognition is a developed application for 2.5D object recognition, complete details of the algorithm and development is explained further in this issue (Lopez-Juarez, et al., 2009). ...
During welding tasks there are quality specifications to be met. However, there are several factors that affect the process accuracy such as welding part positioning; motion errors in the production line, mechanical errors, backlash, ageing of mechanisms, etc. which are error sources that make robots to operate in uncertain conditions, i.e. unstructured environments. The scope of this work has been focused on the compensation of these errors generated during the welding process and that the robot system needs to compensate automatically. The proposed solution includes the development of the StickWeld V1.0 application which is a windows based solution programmed in Visual C++ that uses a CCD camera, Basler SDK, wireless gamepad and pointing stick as a teaching tools. The system also uses IDL functions so that the manipulator can receive verbal instructions such as motion commands or start/stop the task. The developed user interface contains two main functions. One operation is to follow the contour of irregular or regular metal objects to be welded and the other is to follow and weld random paths on flat surfaces. Simple welding trajectories were tested using the KUKA manipulator as shown in figure 8. Several issues rose from the accomplished welding tasks such as starting point synchronization, best torch angle, setting of the correct parameters (voltage and wire speed). It was detected that the geometric parameters such as width and high of the seam weld were not uniform along the paths, though the trajectory was correctly followed.
Nowadays, and considering flexibility, industrial robots still present some drawback that prevent them to be used in vast fields of the industry. One of their major limitations is related with their perception skills. In this area, and although the many developments verified on 3D object recognition systems in the research sphere, the number of solutions appearing in the industry level has been slow. Hence, this article tries to clarify some of the motives that difficult the technology transference (in what concerns object recognition) between both worlds. At the same time, it will be presented an industrial case scenario (inserted in an European Project) where some of the problems enumerated during the article are present.
