Machine vision approach for robotic assembly

Abstract

Purpose -Outcome with a novel methodology for online recognition and classification of pieces in robotic assembly tasks and its application into an intelligent manufacturing cell. Design/methodology/approach -The performance of industrial robots working in unstructured environments can be improved using visual perception and learning techniques. The object recognition is accomplished using an artificial neural network (ANN) architecture which receives a descriptive vector called CFD&POSE as the input. Experimental results were done within a manufacturing cell and assembly parts. Findings -Find this vector represents an innovative methodology for classification and identification of pieces in robotic tasks, obtaining fast recognition and pose estimation information in real time. 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.Research limitations/implications -Provides vision guidance in assembly tasks, current work addresses the use of ANN's for assembly and object recognition separately, future work is oriented to use the same neural controller for all different sensorial modes. Practical implications -Intelligent manufacturing cells developed with multimodal sensor capabilities, might use this methodology for future industrial applications including robotics fixtureless assembly. 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. Originality/value -This paper introduces a novel method which uses collections of 2D images to obtain a very fast feature data -"current frame descriptor vector" -of an object by using image projections and canonical forms geometry grouping for invariant object recognition.

On-line knowledge acquisition and enhancement in robotic assembly tasks

“…Then we made a contour analysis of the objects. For each object, the centroid and the BOF are calculated as explained in [9].…”

“…This agent should demonstrate its "intelligence" by using new knowledge, refine and apply it autonomously during skill learning showing the required skill during real world tasks as demonstrated by Lopez-Juarez et al [8]. The research is founded on previous approach by Lopez-Juarez in terms of creating intelligent robotic agents for assembly using force sensing in conjunction with an image processing method called the boundary object function (BOF) to describe invariantly an object using object's features as initially presented by Peña Cabrera et al [9]. Although the work was centred on the PIH operation, the method can easily extend the robot's capability in more complex processes like for instance, the kitting process under high uncertainty.…”

Movement and Color Detection of a Dynamic Object: An application to a Mobile Robot

“…In the acquired image there are many defects and noise, but not all are common and some people have develop a real time systems for inspection, detection and tracking moving objects in production systems such as potato inspection where the potatoes are inspected (size and color) on the fly while passing on a belt conveyor [25]. A machine vision system trained to distinguish between different objects of the same class but with different characteristics uses threshold techniques for image segmentation [26]. A Neural Network and a Vector Description methodology to recognize and calculate POSE of manufacturing objects uses a Color classification method using image processing techniques [27].…”

Network-based Vision Guidance of Robot for Remote Quality Control

“…Even after mathematical modeling, calibration becomes susceptible to slight changes in setup. Consequently, only a few calibration methods have been practical, simple, economical and quick enough for use with industrial robots (Abderrahim & Whittaker, 2000;Hosek & Bleigh, 2002;Meng & Zhuang, 2001;Meng & Zhuang, 2007;Pena-Cabrera et al, 2005;Perks, 2006;Young & Pickin, 2000;Zhang & Goldberg, 2005;Zhang et al, 2006).…”