Abstract Purpose – Outcome with a novel methodology for online recognition and classification of pieces in robotic assembly tasks its application into an intelligent manufacturing cell. Design/methodology/approach The performance industrial robots working unstructured environments can be improved using visual perception learning techniques. object is accomplished artificial neural network (ANN) architecture which receives descriptive vector called CFD&POSE as the input. Experimental results...

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 last decade several approaches techniques aimed at carrying out object recognition have been proposed, they often still require complex expensive equipment. Therefore, alternative low cost solutions are in great demand. Here, two to above-mentioned problem presented. These examples of practical...

The Fourth Industrial Revolution, also known as industry 4.0, is changing the way businesses operate and society performs in environments which they are forced to compete. convergence between automation of industrial processes daily tasks with information technologies, allows improving operations, reducing costs, quality life processes. connection domestic devices network makes it possible extract control data real time, technologies like Big Data, artificial intelligence, IoT, Information...

Robot vision systems can differentiate parts by pattern matching irrespective of part orientation and location. Somemanufacturers offer 3D guidance using robust laser so that a programmed point canbe repeated even if the is moved varying its location, rotation within working space. Despitethese developments, current industrial robots are still unable to recognize objects in manner; is, todistinguish an object among equally shaped taking into account not only object’s contour but also formand...

The use of dual arm robots for human like operations such as the peg-in-hole tasks can be facilitated by learning contact states during manipulation. In this paper, we propose a control scheme that includes operations. approach Motoman SDA-20 dual-arm robot equipped with two three-fingered gripper and force/torque sensing capability. A real operation using assembly an automotive starter motor is used case study. Several patterns are generated classified stages assembly. Three categories were...

This paper presents cobots (collaborating robots) and their impact on automation real life. The of using is analyzed from the economic, philosophical, human point view. Current models cobot use are presented illustrated through examples Cobot today what it might look like in future. Finally, believed that could be valuable for developing countries small manufacturing companies.

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

In accordance with the new trends demanded by Industry 4.0, idea of having manufacturing processes using industrial robotic arms capabilities and functionalities to achieve reconfigurable adaptable production, has become a novel research field. A concept have different tools integrated controlled same system arises, this allows implementation hybrid systems for process purposes. last decade, three-axis viable or promising option cover these needs, it shows feasibility achieving applications...

Time-series statistical pattern recognition is of prime importance in statistics, especially quality control techniques for manufacturing processes. A frequent problem this application the complexity when trying to determine behaviour (pattern) from sample data. There have been identified standard patterns which are commonly present using X chart; its detection depends on human judgement supported by norms and graphical criteria. In last few years, it has demonstrated that Artificial Neural...

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 wide range angles three-dimensional space. These define the dataset, which allows for training further validation convolutional neural network. classification is implemented reconfigurable hardware an embedded system with RGB sensor processing unit. achieved accuracy 96.67% speed 2.25×...

The recognition of objects and the proper handling them is a common problem in service robots. This article presents set computational vision algorithms to improve an object detection system using RGBD sensor. Within this algorithm identify plane, second determine position third that performs Principal Components Analysis orientation perform correct manipulation. Several tests are presented validate our approach. group used by robot Justina at upcoming RoboCup 2018 international tournament [1].

The performance of industrial robots working in unstructured environment can be improved using visual perception and learning techniques. In this work, a novel approach that uses 2D data simple image processing techniques is introduced. A unique vector descriptor (CFD&POSE) containing also depth information computed then input to Fuzzy ART MAP architecture for recognition purposes. This compresses 3D object from assembly parts invariant scale, rotation orientation. combination with the fast...

The article presents a method for obtaining the contour of an object in real time from non-binarized images recognition purpose. information is integrated into descriptive vector named BOF used by FuzzyARTMAP Artificial Neural Network (ANN) model to learn and then recognize it later. In this way, possible obtain learning process regarding location parts; communicate robot arm position orientation assembly purposes. Other using binarized images, compared with described paper order implement...

Fast object recognition and classification is highly important when handling operations with robots. This article shows the design implementation of an invariant machine vision system to compute a descriptive vector called Boundary Object Function (BOF) using FuzzyARTMAP (FAM) Neural Network. The integrated in Zybo Z7-20 module that includes reconfigurable FPGA hardware RISC processor. encoding, description prediction carried out rapidly compared processing time devoted video capture at...

Working in unstructured assembly robotic environments, i.e. with unknown part location; the robot has to accurately not only locate part, but also recognize it readiness for grasping. The aim of this research is develop a fast and robust approach accomplish task. We propose an aid learning parts on-line. which based on ANN reduced set recurrent training patterns speed up recognition task compared our previous work introduced. Experimental results using camera are presented. Some simple (i.e....

Since the first robot manipulator for industrial applications was installed General Motors, planning and execution of its movements has been an important part in development robotic systems involving researchers from different specialties. The guidance movement robots increasingly complex due to wide variety which they are used, repetitive tasks traditional assembly lines assistance very precise surgical operations require real-time guidance, this established area research technological...

An Omni directional mobile platform control using the intelligence technique of Fuzzy Logic is showed in article, allows a practical and reliable driving 4 wheels, implemented FPGA allowing to have an independent autonomous single chip system out central computer dependence order be used with different applications like service robots platforms. additional feature performed by Bluetooth communication cellular phone based on smartphone OS Android as handset device. Driving movement for...

The article shows the design and implementation of an artificial vision system capable to obtain in real time position object (working piece or end-effector a robot manipulator) within enclosed environment like manufacturing cell using graphical symbols "wall marks" recognition location. comprises digital camera with pan-tilte movements attached as non-contact sensor get its location; might be working piece, end effector robot-arm any other mobil subject current application. obtains location...

Industrial production systems for smart factories or the so-called Industry 4.0 will demand high interoperability and connectivity between modules, so that modules could be monitored in real-time. Production should make decisions on their own, with no human intervention, they must modular adaptable to changing circumstances customers' requirements. The autonomous operation of imposes asynchronous delays due several reasons. For instance, object recognition time, grasping time welding change...