Fast Object Recognition for Grasping Tasks using Industrial Robots

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.