Distributed Architecture for Intelligent Robotic Assembly Part III: Design of the Invariant Object Recognition System

In previous chapter it has been described the overall architecture for multimodal learning in the robotic assembly domain (Lopez-Juarez & Rios Cabrera, 2006). The acquisition of assembly skills by robots is greatly supported by the effective use of contact force sensing and object recognition. In this chapter we will describe the robot’s ability to invariantly recognise assembly parts at different scale, rotation and orientation within the work space. The chapter shows a methodology for on-line recognition and classification of pieces in robotic assembly tasks and its application into an intelligent manufacturing cell. The performance of industrial robots working in unstructured environments can be improved using visual perception and learning techniques. In this sense, the described technique for object recognition is accomplished using an Artificial Neural Network (ANN) architecture which receives a descriptive vector called CFD&POSE as the input. This vector represents an innovative methodology for classification and identification of pieces in robotic tasks, every stage of the methodology is described and the proposed algorithms explained. The vector compresses 3D object data from assembly parts and it is invariant to scale, rotation and orientation, and it also supports a wide range of illumination levels. The approach in combination with the fast learning capability of ART networks indicates the suitability for industrial robot applications as it is demonstrated through experimental results.