Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869209
Yoann Solana, Héctor Herrero, A. García, Sergio Martínez Calvo, Urko Esnaola, D. Sallé, Juan Cortés
Nowadays, factories are required to increase production flexibility in order to manufacture small-lot variants, rapidly adapting to customer demands. Furthermore, manufacturing may involve complex manipulation tasks, usually performed by human workers. In such a context, traditional robotic systems are not competitive due to the huge costs of installation, maintenance and adaptation. A new generation of robots, equipped with multiple arms, is appearing as an attractive alternative because of their potential versatility and ability to execute intricate manipulation tasks. To facilitate the integration of these robots in a work-cell and a rapid adaptation to different tasks, easy-to-use programming interfaces and a high degree of autonomy are mandatory. Autonomous task and motion planning are particularly relevant in this context. In this paper, we present our recent progress in this direction. Hardware and software developments are explained in the context of a pilot dual-arm robot station that is being integrated in the production line of a big airplane manufacturer. First experimental results are also presented.
{"title":"A case study of automated dual-arm manipulation in industrial applications","authors":"Yoann Solana, Héctor Herrero, A. García, Sergio Martínez Calvo, Urko Esnaola, D. Sallé, Juan Cortés","doi":"10.1109/ETFA.2019.8869209","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869209","url":null,"abstract":"Nowadays, factories are required to increase production flexibility in order to manufacture small-lot variants, rapidly adapting to customer demands. Furthermore, manufacturing may involve complex manipulation tasks, usually performed by human workers. In such a context, traditional robotic systems are not competitive due to the huge costs of installation, maintenance and adaptation. A new generation of robots, equipped with multiple arms, is appearing as an attractive alternative because of their potential versatility and ability to execute intricate manipulation tasks. To facilitate the integration of these robots in a work-cell and a rapid adaptation to different tasks, easy-to-use programming interfaces and a high degree of autonomy are mandatory. Autonomous task and motion planning are particularly relevant in this context. In this paper, we present our recent progress in this direction. Hardware and software developments are explained in the context of a pilot dual-arm robot station that is being integrated in the production line of a big airplane manufacturer. First experimental results are also presented.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"7 1","pages":"563-570"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73893208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869248
Bedir Halci, V. Gazi, Onur Cihan
In this article we develop an energy based model for the dynamics of a swarm of quadrotors using Lagrangian approach. Both the individual quadrotor dynamics and the interaction dynamics between the agents in the swarm are modeled within the framework. Artificial potential energy and the corresponding potential forces are utilized for modeling the interaction between the quadrotors. Various simulations are performed to illustrate the viability and effectiveness of the developed swarm model. The kinetic and potential energy of the swarm is also illustrated.
{"title":"Modelling and Coordination of a Swarm of Quadrotors Using Lagrange Dynamics and Potential Functions","authors":"Bedir Halci, V. Gazi, Onur Cihan","doi":"10.1109/ETFA.2019.8869248","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869248","url":null,"abstract":"In this article we develop an energy based model for the dynamics of a swarm of quadrotors using Lagrangian approach. Both the individual quadrotor dynamics and the interaction dynamics between the agents in the swarm are modeled within the framework. Artificial potential energy and the corresponding potential forces are utilized for modeling the interaction between the quadrotors. Various simulations are performed to illustrate the viability and effectiveness of the developed swarm model. The kinetic and potential energy of the swarm is also illustrated.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"56 1","pages":"963-970"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73647303","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869303
Udayanto Dwi Atmojo, V. Vyatkin
This paper presents a software design pattern for systems composed from distributed intelligent mechatronic modules which communicate with each other via wireless interface. The design pattern is formed by integrating the reliable communication mechanism called channel, which comes from a system-level programming language SystemJ. The paper demonstrates how the design pattern can be applied in an industrial automation example.
{"title":"A Design Pattern for Systems Composed from Intelligent Mechatronic Modules with Wireless Communication","authors":"Udayanto Dwi Atmojo, V. Vyatkin","doi":"10.1109/ETFA.2019.8869303","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869303","url":null,"abstract":"This paper presents a software design pattern for systems composed from distributed intelligent mechatronic modules which communicate with each other via wireless interface. The design pattern is formed by integrating the reliable communication mechanism called channel, which comes from a system-level programming language SystemJ. The paper demonstrates how the design pattern can be applied in an industrial automation example.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"41-48"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79999623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869359
Julen Balzategui, Luka Eciolaza, N. Arana-Arexolaleiba, Jon Altube, J. Aguerre, Iñaki Legarda-Ereño, A. Apraiz
Quality control of solar cells is a very important part of the production process. A little crack or joint failure can cause bad performance of the cell in the future, partly because the defective areas can be electrically disconnected from the active zones. Nowadays, one of the techniques to carry out this control is electroluminescence (EL), which allows obtaining high-resolution images of the cells where a visual and non-invasive inspection of defects can be done. This inspection is mostly performed by trained human operators. However, as the eyes become tired after a working day and the subjectivity of the operators, the accuracy with which the defect detection is done may be compromised. In order to solve this problem, a method to assist the operator in the inspection of polycrystalline silicon solar cells surface from EL images based on Convolutional Neural Networks is proposed. The method would classify the cells as defective and non-defective, and suggest those cells that are defective for re-inspection. Also, it would propose a segmentation map of the defects in the cell. To compensate for the lack of image samples in the dataset, each cell image is divided into regions by a sliding window. Then, each region is classified as defective or non-defective. And finally, all classifications related to the cell are resembled obtaining a segmented image of defective areas in the cell.
{"title":"Semi-automatic quality inspection of solar cell based on Convolutional Neural Networks","authors":"Julen Balzategui, Luka Eciolaza, N. Arana-Arexolaleiba, Jon Altube, J. Aguerre, Iñaki Legarda-Ereño, A. Apraiz","doi":"10.1109/ETFA.2019.8869359","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869359","url":null,"abstract":"Quality control of solar cells is a very important part of the production process. A little crack or joint failure can cause bad performance of the cell in the future, partly because the defective areas can be electrically disconnected from the active zones. Nowadays, one of the techniques to carry out this control is electroluminescence (EL), which allows obtaining high-resolution images of the cells where a visual and non-invasive inspection of defects can be done. This inspection is mostly performed by trained human operators. However, as the eyes become tired after a working day and the subjectivity of the operators, the accuracy with which the defect detection is done may be compromised. In order to solve this problem, a method to assist the operator in the inspection of polycrystalline silicon solar cells surface from EL images based on Convolutional Neural Networks is proposed. The method would classify the cells as defective and non-defective, and suggest those cells that are defective for re-inspection. Also, it would propose a segmentation map of the defects in the cell. To compensate for the lack of image samples in the dataset, each cell image is divided into regions by a sliding window. Then, each region is classified as defective or non-defective. And finally, all classifications related to the cell are resembled obtaining a segmented image of defective areas in the cell.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"24 1","pages":"529-535"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83289656","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869108
K. Gibert, Conxi Pérez Andreu, Núria Castell
Gender gap in computer science related fields is one of the most critical among all technological areas. This paper describes the methodology used to create gender commissions and providing them of a territorial structure around informatics engineering and artificial intelligence, two close areas where the presence of women is critical both at professional level, as well as training level. Territorial structure provides an additional potential very useful for the impact of the activities of the commission. Here the creation of two gender structures in Catalonia is presented
{"title":"Deployment of territorial structures to reduce gender gap in technology and some real cases in Catalonia","authors":"K. Gibert, Conxi Pérez Andreu, Núria Castell","doi":"10.1109/ETFA.2019.8869108","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869108","url":null,"abstract":"Gender gap in computer science related fields is one of the most critical among all technological areas. This paper describes the methodology used to create gender commissions and providing them of a territorial structure around informatics engineering and artificial intelligence, two close areas where the presence of women is critical both at professional level, as well as training level. Territorial structure provides an additional potential very useful for the impact of the activities of the commission. Here the creation of two gender structures in Catalonia is presented","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"27 1","pages":"1823-1830"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83313157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869451
Eneko Lerma, R. Costa-Castelló, R. Griñó, Carlos Sanchis
This document presents a project to develop freely redistributable materials to conduct educational lab projects with MATLAB, Simulink, Arduino and low-cost plants. This work materials introduce the fundamentals of Control Engineering through exercises and videos. Along with all this, the most important steps and issues appeared in the project are explained, so anyone interested on doing a project can have a starting point instead of starting a project from scratch, which most of times this results hard to implement.
{"title":"Duino-Based Learning (DBL) in Control Engineering Courses","authors":"Eneko Lerma, R. Costa-Castelló, R. Griñó, Carlos Sanchis","doi":"10.1109/ETFA.2019.8869451","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869451","url":null,"abstract":"This document presents a project to develop freely redistributable materials to conduct educational lab projects with MATLAB, Simulink, Arduino and low-cost plants. This work materials introduce the fundamentals of Control Engineering through exercises and videos. Along with all this, the most important steps and issues appeared in the project are explained, so anyone interested on doing a project can have a starting point instead of starting a project from scratch, which most of times this results hard to implement.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"89 1","pages":"798-803"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73553539","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869074
Frederick Prinz, Michael Schoeffler, A. Lechler, A. Verl
Future production systems are expected to support dynamic plug-and-produce scenarios across different component manufacturers. Therefore, the concept of I4.0 components was developed. An I4.0 component describes an asset with an asset administration shell providing a standardized representation of its capabilities. Real-time I4.0 components additionally demand for a deterministic communication with bounded low latency, where the network topology is typically defined by physical links and infrastructure. In order to avoid rewiring and to support dynamic plug-and-produce scenarios with real-time I4.0 components, we present so-called virtual topologies decoupled from the physical network infrastructure. Thereby, we extend the concept of real-time I4.0 components to configure the required behavior and introduce an additional submodel for the administration shell. Moreover, a central SDN controller is enhanced to automatically configure the virtual topologies during runtime. These topologies are based on the new real-time communication technology IEEE 802.1 Time-Sensitive Networking (TSN). Finally, we evaluate the latency of the prototypical implementation within real-time I4.0 components depending on the frame size and network bandwidth.
{"title":"Virtual Network Topologies for Real-time I4.0 Components based on Time-Sensitive Networking","authors":"Frederick Prinz, Michael Schoeffler, A. Lechler, A. Verl","doi":"10.1109/ETFA.2019.8869074","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869074","url":null,"abstract":"Future production systems are expected to support dynamic plug-and-produce scenarios across different component manufacturers. Therefore, the concept of I4.0 components was developed. An I4.0 component describes an asset with an asset administration shell providing a standardized representation of its capabilities. Real-time I4.0 components additionally demand for a deterministic communication with bounded low latency, where the network topology is typically defined by physical links and infrastructure. In order to avoid rewiring and to support dynamic plug-and-produce scenarios with real-time I4.0 components, we present so-called virtual topologies decoupled from the physical network infrastructure. Thereby, we extend the concept of real-time I4.0 components to configure the required behavior and introduce an additional submodel for the administration shell. Moreover, a central SDN controller is enhanced to automatically configure the virtual topologies during runtime. These topologies are based on the new real-time communication technology IEEE 802.1 Time-Sensitive Networking (TSN). Finally, we evaluate the latency of the prototypical implementation within real-time I4.0 components depending on the frame size and network bandwidth.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"10 1","pages":"1388-1391"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90770472","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869024
Bjarne Johansson, B. Leander, Aida Čaušević, A. Papadopoulos, T. Nolte
In process automation installations, the I/O system connect the field devices to the process controller over a fieldbus, a reliable, real-time capable communication link with signal values cyclical being exchanged with a 10–100 millisecond rate. If a deviation from intended behaviour occurs, analyzing the potentially vast data recordings from the field can be a time consuming and cumbersome task for an engineer. For the engineer to be able to get a full understanding of the problem, knowledge of the used I/O configuration is required. In the problem report, the configuration description is sometimes missing. In such cases it is difficult to use the recorded data for analysis of the problem.In this paper we present our ongoing work towards using neural network models as assistance in the interpretation of an industrial fieldbus communication recording. To show the potential of such an approach we present an example using an industrial setup where fieldbus data is collected and classified. In this context we present an evaluation of the suitability of different neural net configurations and sizes for the problem at hand.
{"title":"Classification of PROFINET I/O Configurations utilizing Neural Networks","authors":"Bjarne Johansson, B. Leander, Aida Čaušević, A. Papadopoulos, T. Nolte","doi":"10.1109/ETFA.2019.8869024","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869024","url":null,"abstract":"In process automation installations, the I/O system connect the field devices to the process controller over a fieldbus, a reliable, real-time capable communication link with signal values cyclical being exchanged with a 10–100 millisecond rate. If a deviation from intended behaviour occurs, analyzing the potentially vast data recordings from the field can be a time consuming and cumbersome task for an engineer. For the engineer to be able to get a full understanding of the problem, knowledge of the used I/O configuration is required. In the problem report, the configuration description is sometimes missing. In such cases it is difficult to use the recorded data for analysis of the problem.In this paper we present our ongoing work towards using neural network models as assistance in the interpretation of an industrial fieldbus communication recording. To show the potential of such an approach we present an example using an industrial setup where fieldbus data is collected and classified. In this context we present an evaluation of the suitability of different neural net configurations and sizes for the problem at hand.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"7 1","pages":"1321-1324"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78452908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/etfa.2019.8869277
{"title":"Adaptive and Reconfigurable Cyber-Physical Systems [breaker page]","authors":"","doi":"10.1109/etfa.2019.8869277","DOIUrl":"https://doi.org/10.1109/etfa.2019.8869277","url":null,"abstract":"","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"59 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78821870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8868987
Rafael Herguedas, G. López-Nicolás, Rosario Aragues, C. Sagüés
Autonomous manipulation of deformable objects is a research topic of increasing interest due to the variety of current processes and applications that include this type of tasks. It is a complex problem that involves aspects such as modeling, control, perception, planning, grasping, estimation, etc. A single robot may be unable to perform the manipulation when the deformable object is too big, too heavy or difficult to grasp. Then, using multiple robots working together naturally arises as a solution to perform coordinately the manipulation task. In this paper, we contribute a survey of relevant state-of-the-art approaches concerning manipulation of deformable objects by multiple robots, which includes a specific classification with different criteria and a subsequent analysis of the leading methods, the main challenges and the future research directions.
{"title":"Survey on multi-robot manipulation of deformable objects","authors":"Rafael Herguedas, G. López-Nicolás, Rosario Aragues, C. Sagüés","doi":"10.1109/ETFA.2019.8868987","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8868987","url":null,"abstract":"Autonomous manipulation of deformable objects is a research topic of increasing interest due to the variety of current processes and applications that include this type of tasks. It is a complex problem that involves aspects such as modeling, control, perception, planning, grasping, estimation, etc. A single robot may be unable to perform the manipulation when the deformable object is too big, too heavy or difficult to grasp. Then, using multiple robots working together naturally arises as a solution to perform coordinately the manipulation task. In this paper, we contribute a survey of relevant state-of-the-art approaches concerning manipulation of deformable objects by multiple robots, which includes a specific classification with different criteria and a subsequent analysis of the leading methods, the main challenges and the future research directions.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"49 1","pages":"977-984"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84720602","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：