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.

In this paper, we propose a low-cost contact-free measurement system for both 3-D data acquisition and fast surface parameter registration by digitized points. Despite the fact that during the last decade several approaches for both contact-free measurement techniques aimed at carrying out object surface recognition and 3-D object recognition have been proposed, they often still require complex and expensive equipment. Therefore, alternative low cost solutions are in great demand. Here, two low-cost solutions to the above-mentioned problem are presented. These are two examples of practical applications of the novel passive optical scanning system presented in this paper.

Robot vision systems can differentiate parts by pattern matching irrespective of part orientation and location. Some manufacturers offer 3D guidance systems using robust vision and laser systems so that a 3D programmed point can be repeated even if the part is moved varying its location, rotation and orientation within the working space. Despite these developments, current industrial robots are still unable to recognize objects in a robust manner; that is, to distinguish an object among equally shaped objects taking into account not only the object’s contour but also its form and depth information, which is precisely the major contribution of this research. Our hypothesis establishes that it is possible to integrate a robust invariant object recognition capability into industrial robots by using image features from the object’s contour (boundary object information), its form (i.e., type of curvature or topographical surface information) and depth information (from stereo disparity maps). These features can be concatenated in order to form an invariant vector descriptor which is the input to an artificial neural network (ANN) for learning and recognition purposes. In this paper we present the recognition results under different working conditions using a KUKA KR16 industrial robot, which validated our approach

A common objective in mobile robotics is to find an optimal trajectory to reach a final destination from a starting point location. Obstacles are likely to be encountered in the robot's trajectory that need to be avoided. In this article, a path planning approach for mobile robots that uses the algorithms of potential field in conjunction with Local Minimal Avoidance (LMA) is presented in order to avoid local minima and to achieve an optimal robot's navigation.

The process of recognizing manufacturing parts in real time requires fast, accurate, small, and low-power-consumption sensors. Here, we describe a method to extract descriptors from several objects observed from a wide range of angles in a three-dimensional space. These descriptors define the dataset, which allows for the training and further validation of a convolutional neural network. The classification is implemented in reconfigurable hardware in an embedded system with an RGB sensor and the processing unit. The system achieved an accuracy of 96.67% and a speed $2.25\times$ faster than the results reported for state-of-the-art solutions. Our proposal is 655 times faster than implementation on a PC. The presented embedded system meets the criteria of real-time video processing and it is suitable as an enhancement for the hand of a robotic arm in an intelligent manufacturing cell.