Fast Object Recognition for Grasping Tasks using Industrial Robots

Abstract

Working in unstructured assembly robotic environments, i.e. with unknown part location; the robot has to accurately not only to locate the part, but also to recognize it in readiness for grasping. The aim of this research is to develop a fast and robust approach to accomplish this task. We propose an approach to aid the learning of assembly parts on-line. The approach which is based on ANN and a reduced set of recurrent training patterns which speed up the recognition task compared with our previous work is introduced. Experimental learning results using a fast camera are presented. Some simple parts (i.e. circular, squared and radiused square) were used for comparing different connectionist models (Backpropagation, Perceptron and FuzzyARTMAP) and to select the appropriate model. Later during experiments, complex figures were learned using the chosen FuzzyARTMAP algorithm showing a 93.8% overall efficiency and 100% recognition rate. Recognition times were lower than 1 ms, which clearly indicates the suitability of the approach to be implemented in real-world operations.