Pub Date : 2019-09-01DOI: 10.1109/ETFA.2019.8869502
Sabine Wolny, Alexandra Mazak, M. Wimmer
Nowadays, software-as well as hardware systems produce log files that enable a continuous monitoring of the system during its execution. Unfortunately, such text-based log traces are very long and difficult to read, and therefore, reasoning and analyzing runtime behavior is not straightforward. However, dealing with log traces is especially needed in cases, where (i) the execution of the system did not perform as intended, (ii) the process flow is unknown because there are no records, and/or (iii) the design models do not correspond to its real-world counterpart. These facts cause that log data has to be prepared in a more user-friendly way (e.g., in form of graphical representations) and algorithms are needed for automatically monitoring the system’s operation, and for tracking the system components interaction patterns. For this purpose we present an approach for transforming raw sensor data logs to a UML or SysML sequence diagram in order to provide a graphical representation for tracking log traces in a time-ordered manner. Based on this sequence diagram, we automatically identify interaction models in order to analyze the runtime behavior of system components. We implement this approach as prototypical plug-in in the modeling tool Enterprise Architect and evaluate it by an example of a self-driving car.
{"title":"Automatic Reverse Engineering of Interaction Models from System Logs","authors":"Sabine Wolny, Alexandra Mazak, M. Wimmer","doi":"10.1109/ETFA.2019.8869502","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869502","url":null,"abstract":"Nowadays, software-as well as hardware systems produce log files that enable a continuous monitoring of the system during its execution. Unfortunately, such text-based log traces are very long and difficult to read, and therefore, reasoning and analyzing runtime behavior is not straightforward. However, dealing with log traces is especially needed in cases, where (i) the execution of the system did not perform as intended, (ii) the process flow is unknown because there are no records, and/or (iii) the design models do not correspond to its real-world counterpart. These facts cause that log data has to be prepared in a more user-friendly way (e.g., in form of graphical representations) and algorithms are needed for automatically monitoring the system’s operation, and for tracking the system components interaction patterns. For this purpose we present an approach for transforming raw sensor data logs to a UML or SysML sequence diagram in order to provide a graphical representation for tracking log traces in a time-ordered manner. Based on this sequence diagram, we automatically identify interaction models in order to analyze the runtime behavior of system components. We implement this approach as prototypical plug-in in the modeling tool Enterprise Architect and evaluate it by an example of a self-driving car.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"53 1","pages":"57-64"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86695802","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.2019.8869019
Alberto Sabater, L. Montesano, A. C. Murillo
Wearable technologies are enabling plenty of new applications of computer vision, from life logging to health assistance. Many of them are required to recognize the elements of interest in the scene captured by the camera This work studies the problem of object detection and localization on videos captured by this type of camera. Wearable videos are a much more challenging scenario for object detection than standard images or even another type of videos, due to lower quality images (e.g. poor focus) or high clutter and occlusion common in wearable recordings. Existing work typically focuses on detecting the objects of focus or those being manipulated by the user wearing the camera. We perform a more general evaluation of the task of object detection in this type of video, because numerous applications, such as marketing studies, also need detecting objects which are not in focus by the user. This work presents a thorough study of the well known YOLO architecture, that offers an excellent trade-off between accuracy and speed, for the particular case of object detection in wearable video. We focus our study on the public ADL Dataset, but we also use additional public data for complementary evaluations. We run an exhaustive set of experiments with different variations of the original architecture and its training strategy. Our experiments drive to several conclusions about the most promising directions for our goal and point us to further research steps to improve detection in wearable videos.
{"title":"Performance of object recognition in wearable videos","authors":"Alberto Sabater, L. Montesano, A. C. Murillo","doi":"10.1109/ETFA.2019.8869019","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869019","url":null,"abstract":"Wearable technologies are enabling plenty of new applications of computer vision, from life logging to health assistance. Many of them are required to recognize the elements of interest in the scene captured by the camera This work studies the problem of object detection and localization on videos captured by this type of camera. Wearable videos are a much more challenging scenario for object detection than standard images or even another type of videos, due to lower quality images (e.g. poor focus) or high clutter and occlusion common in wearable recordings. Existing work typically focuses on detecting the objects of focus or those being manipulated by the user wearing the camera. We perform a more general evaluation of the task of object detection in this type of video, because numerous applications, such as marketing studies, also need detecting objects which are not in focus by the user. This work presents a thorough study of the well known YOLO architecture, that offers an excellent trade-off between accuracy and speed, for the particular case of object detection in wearable video. We focus our study on the public ADL Dataset, but we also use additional public data for complementary evaluations. We run an exhaustive set of experiments with different variations of the original architecture and its training strategy. Our experiments drive to several conclusions about the most promising directions for our goal and point us to further research steps to improve detection in wearable videos.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"25 1","pages":"1813-1820"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82020861","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.2019.8869341
Takumi Furusaka, N. Kawaguchi, Takao Sato, N. Araki, Y. Konishi
Multi-agent systems (MASs) are used for distributed control purposes and substantial research attention has been directed to these systems because of their practical merits. In MASs, agents’ information is shared through networks. In networked-control systems, the measured data is usually quantized because of sensor performance or specification, and its resolution is inadequate. Furthermore, because of network quality, the measurement interval is often longer than the control interval. Therefore, the present study introduces a design method for a dual-rate quantized control system, in which the measurement interval of agents is an integer multiple of the control interval.
{"title":"A Multi-agent System with Dual-rate Control and a Quantized-value Communication Constraint","authors":"Takumi Furusaka, N. Kawaguchi, Takao Sato, N. Araki, Y. Konishi","doi":"10.1109/ETFA.2019.8869341","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869341","url":null,"abstract":"Multi-agent systems (MASs) are used for distributed control purposes and substantial research attention has been directed to these systems because of their practical merits. In MASs, agents’ information is shared through networks. In networked-control systems, the measured data is usually quantized because of sensor performance or specification, and its resolution is inadequate. Furthermore, because of network quality, the measurement interval is often longer than the control interval. Therefore, the present study introduces a design method for a dual-rate quantized control system, in which the measurement interval of agents is an integer multiple of the control interval.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"5 1","pages":"1473-1476"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85338643","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.2019.8869421
D. Bujosa, Sergi Arguimbau, Patricia Arguimbau, J. Proenza, M. Barranco
Critical Adaptive Distributed Embedded Systems (ADESs) are nowadays the focus of many researchers. ADESs are envisioned to dynamically modify their behavior to support changes of their real-time and dependability requirements at runtime as the conditions of the environment in which they operate vary. To provide ADESs with an adequate communication infrastructure, our research group proposed the Flexible-Time-Triggered Replicated Star (FTTRS). FTTRS provides highly reliable communication services on top of Ethernet, while keeping the adaptivity benefits that the Flexible-Time-Triggered (FTT) communication paradigm offers from a real-time perspective. This paper formally verifies, by means of model checking, the correctness of the mechanisms FTTRS includes to enforce consistent changes of the communication scheduling at runtime.
{"title":"Formal Verification of the FTTRS Mechanisms for the Consistent Update of the Traffic Schedule","authors":"D. Bujosa, Sergi Arguimbau, Patricia Arguimbau, J. Proenza, M. Barranco","doi":"10.1109/ETFA.2019.8869421","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869421","url":null,"abstract":"Critical Adaptive Distributed Embedded Systems (ADESs) are nowadays the focus of many researchers. ADESs are envisioned to dynamically modify their behavior to support changes of their real-time and dependability requirements at runtime as the conditions of the environment in which they operate vary. To provide ADESs with an adequate communication infrastructure, our research group proposed the Flexible-Time-Triggered Replicated Star (FTTRS). FTTRS provides highly reliable communication services on top of Ethernet, while keeping the adaptivity benefits that the Flexible-Time-Triggered (FTT) communication paradigm offers from a real-time perspective. This paper formally verifies, by means of model checking, the correctness of the mechanisms FTTRS includes to enforce consistent changes of the communication scheduling at runtime.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"61 1","pages":"1017-1024"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89652568","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.2019.8869486
D. Stock, Daniel Schel, T. Bauernhansl
Cyber-Physical Production Systems (CPPS) are Cyber-Physical Systems (CPS), which are applied in manufacturing environments to carry out production related tasks, thus turning them into smart manufacturing environments. They are the evolution of combined regular manufacturing equipment, embedded computing devices and distributed computing functionality, which has been sparked by technical advances in information and communication technology (ICT) and progressively networked production. One of the properties of CPS is the ability to be composed of other CPS and the ability to encapsulate so-called self-x capabilities. Their networked nature enables access to large amounts of data, which can be used to extract information and knowledge about machines, processes, and the manufacturing environment. This paper discusses approaches how data access, storage, and information extraction is currently being handled. We propose how these approaches can be extended and how an information-oriented system and infrastructure for CPPS can be constructed to create a Cyber-Physical Data Access Layer which is based on the self-description capability of CPPS components.
{"title":"Cyber-Physical Production System Self-Description-Based Data Access Layer","authors":"D. Stock, Daniel Schel, T. Bauernhansl","doi":"10.1109/ETFA.2019.8869486","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869486","url":null,"abstract":"Cyber-Physical Production Systems (CPPS) are Cyber-Physical Systems (CPS), which are applied in manufacturing environments to carry out production related tasks, thus turning them into smart manufacturing environments. They are the evolution of combined regular manufacturing equipment, embedded computing devices and distributed computing functionality, which has been sparked by technical advances in information and communication technology (ICT) and progressively networked production. One of the properties of CPS is the ability to be composed of other CPS and the ability to encapsulate so-called self-x capabilities. Their networked nature enables access to large amounts of data, which can be used to extract information and knowledge about machines, processes, and the manufacturing environment. This paper discusses approaches how data access, storage, and information extraction is currently being handled. We propose how these approaches can be extended and how an information-oriented system and infrastructure for CPPS can be constructed to create a Cyber-Physical Data Access Layer which is based on the self-description capability of CPPS components.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"168-175"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89672233","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.2019.8869059
F. Patzer, Friedrich Volz, T. Usländer, Immanuel Blöcher, J. Beyerer
One of the essential concepts of the Reference Architecture Model Industrie 4.0 (RAMI4.0) is the uniform modelling of assets by means of a common meta-data model called the Asset Administration Shell (AAS). However, important practical experience with this concept is still missing, as not many use cases for the AAS have yet been implemented. Thus, practical issues within the AAS concept and respective solutions are hard to identify. In this paper, presents our experience with the implementation of an AAS use case. The AAS is used as information source to create an ontology, which is then used for security analysis. The paper discusses the use-case-specific modelling language selection and provides a practical examination of several of our implementations that use OWL and OPC UA together. Furthermore, it provides recommendations for the implementation of Asset Administration Shells for this and similar use cases.
{"title":"The Industrie 4.0 Asset Administration Shell as Information Source for Security Analysis","authors":"F. Patzer, Friedrich Volz, T. Usländer, Immanuel Blöcher, J. Beyerer","doi":"10.1109/ETFA.2019.8869059","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869059","url":null,"abstract":"One of the essential concepts of the Reference Architecture Model Industrie 4.0 (RAMI4.0) is the uniform modelling of assets by means of a common meta-data model called the Asset Administration Shell (AAS). However, important practical experience with this concept is still missing, as not many use cases for the AAS have yet been implemented. Thus, practical issues within the AAS concept and respective solutions are hard to identify. In this paper, presents our experience with the implementation of an AAS use case. The AAS is used as information source to create an ontology, which is then used for security analysis. The paper discusses the use-case-specific modelling language selection and provides a practical examination of several of our implementations that use OWL and OPC UA together. Furthermore, it provides recommendations for the implementation of Asset Administration Shells for this and similar use cases.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"420-427"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90474980","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.2019.8869035
Imanol Mugarza, Juan Carlos Mugarza
Mobile robots, such as Automated Guided Vehicles (AGV), are widely used in automated manufacturing systems for material and goods handling. In this context, it has to be ensured that collisions among mobile robots, other industrial equipment and people are avoided, specially if dealing with human safety. In this paper, a collision-free navigation and traffic control approach, based on coloured Petri nets and the D* Lite searching algorithm is proposed. The algorithm dynamically computes a sequence of safe and optimal movements of the AGVs to reach the desired marking. A validation example is also provided, where the navigation and traffic control of three AGVs in an industrial shop-floor is simulated.
{"title":"Towards Collision-Free Automated Guided Vehicles Navigation and Traffic Control","authors":"Imanol Mugarza, Juan Carlos Mugarza","doi":"10.1109/ETFA.2019.8869035","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869035","url":null,"abstract":"Mobile robots, such as Automated Guided Vehicles (AGV), are widely used in automated manufacturing systems for material and goods handling. In this context, it has to be ensured that collisions among mobile robots, other industrial equipment and people are avoided, specially if dealing with human safety. In this paper, a collision-free navigation and traffic control approach, based on coloured Petri nets and the D* Lite searching algorithm is proposed. The algorithm dynamically computes a sequence of safe and optimal movements of the AGVs to reach the desired marking. A validation example is also provided, where the navigation and traffic control of three AGVs in an industrial shop-floor is simulated.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"51 1","pages":"1599-1602"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78555442","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.2019.8869147
Slim Ben-Amor, L. Cucu-Grosjean, Dorin Maxim
The continuous integration of new functionality increases the complexity of embedded systems, while each functionality might impose precedence constraints between the programs fulfilling it. In addition, the prevalence of several processors may create the illusion of higher computation capacity easing the associated scheduling problem. However, this capacity is not exploitable in critical real time systems because of the increased variability of the execution times due to processor features designed to provide excellent average time behaviour and not necessarily ensuring small worst case bounds. This difficulty is added to the existence of scheduling anomalies when the systems are built on top of several processors. In this paper, we study the feasibility of independent tasks scheduled according to a given preemptive fixed-priority partitioned policy on identical processors. Each task is composed of several dependent subtasks related between them according to a directed acyclic graph (DAG). We provide a worst case response time analysis for DAG tasks when each sub-tasks have an individual priority level. This assumption allows to decrease the number of possible execution scenarios, making our analysis easier and less pessimistic.
{"title":"Worst-case response time analysis for partitioned fixed-priority DAG tasks on identical processors","authors":"Slim Ben-Amor, L. Cucu-Grosjean, Dorin Maxim","doi":"10.1109/ETFA.2019.8869147","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869147","url":null,"abstract":"The continuous integration of new functionality increases the complexity of embedded systems, while each functionality might impose precedence constraints between the programs fulfilling it. In addition, the prevalence of several processors may create the illusion of higher computation capacity easing the associated scheduling problem. However, this capacity is not exploitable in critical real time systems because of the increased variability of the execution times due to processor features designed to provide excellent average time behaviour and not necessarily ensuring small worst case bounds. This difficulty is added to the existence of scheduling anomalies when the systems are built on top of several processors. In this paper, we study the feasibility of independent tasks scheduled according to a given preemptive fixed-priority partitioned policy on identical processors. Each task is composed of several dependent subtasks related between them according to a directed acyclic graph (DAG). We provide a worst case response time analysis for DAG tasks when each sub-tasks have an individual priority level. This assumption allows to decrease the number of possible execution scenarios, making our analysis easier and less pessimistic.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"1 1","pages":"1423-1426"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75010586","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.2019.8868971
G. Bag, Luka Lednicki, K. Landernäs, Niclas Ericsson
New technologies that comes with recent trends like Internet of Things, Cloud and 5G are promoting new platforms and communication solutions. These trends have also started to impact traditional industrial automation systems, since end customers are starting to expect new services, such as, business intelligence and diagnostic information anywhere at any time. Moreover, the cloud providers lease their infrastructure to be used for deployment of applications using virtualization. Therefore, this paper aims at exploring the possibilities of different virtualization platforms offered by various cloud providers and benchmark the technologies with platforms frequently used within industry. The platform performance was evaluated by conducting experiments with an industrial application, focusing on typical industrial aspect such as latency, jitter and availability. In addition to more industrial focused metrics, the findings in comparison with other related experiments indicate that specific application requirements have an effect on performance. Hence, application specific evaluations may be necessary before taking any decision on where an industrial application may be deployed.
{"title":"Experiments on Approaches of Virtualization for Industrial Internet of Things applications","authors":"G. Bag, Luka Lednicki, K. Landernäs, Niclas Ericsson","doi":"10.1109/ETFA.2019.8868971","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8868971","url":null,"abstract":"New technologies that comes with recent trends like Internet of Things, Cloud and 5G are promoting new platforms and communication solutions. These trends have also started to impact traditional industrial automation systems, since end customers are starting to expect new services, such as, business intelligence and diagnostic information anywhere at any time. Moreover, the cloud providers lease their infrastructure to be used for deployment of applications using virtualization. Therefore, this paper aims at exploring the possibilities of different virtualization platforms offered by various cloud providers and benchmark the technologies with platforms frequently used within industry. The platform performance was evaluated by conducting experiments with an industrial application, focusing on typical industrial aspect such as latency, jitter and availability. In addition to more industrial focused metrics, the findings in comparison with other related experiments indicate that specific application requirements have an effect on performance. Hence, application specific evaluations may be necessary before taking any decision on where an industrial application may be deployed.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"42 1","pages":"1226-1229"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75114859","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.2019.8869095
Muhayy Ud Din, M. U. Sarwar, Imran Zahoor, W. Qazi, J. Rosell
Complex manipulation tasks require grasping strategies that simultaneously satisfy the stability and the semantic constraints that have to be satisfied for an action to be feasible, referred as action-oriented semantic grasp strategies. This study develops a framework using machine learning techniques to compute action-oriented semantic grasps. It takes a 3D model of the object and the action to be performed as input and provides a vector of action-oriented semantic grasps. We evaluate the performance of machine learning (particularly classification techniques) to determine which approaches perform better for this problem. Using the best approaches, a multi-model classification technique is developed. The proposed approach is evaluated in simulation to grasp different kitchen objects using a parallel gripper. The results show that multi-model classification approach enhances the prediction accuracy. The implemented system can be used as to automate the data labeling process required for deep learning approaches.
{"title":"Learning Action-oriented Grasping for Manipulation","authors":"Muhayy Ud Din, M. U. Sarwar, Imran Zahoor, W. Qazi, J. Rosell","doi":"10.1109/ETFA.2019.8869095","DOIUrl":"https://doi.org/10.1109/ETFA.2019.8869095","url":null,"abstract":"Complex manipulation tasks require grasping strategies that simultaneously satisfy the stability and the semantic constraints that have to be satisfied for an action to be feasible, referred as action-oriented semantic grasp strategies. This study develops a framework using machine learning techniques to compute action-oriented semantic grasps. It takes a 3D model of the object and the action to be performed as input and provides a vector of action-oriented semantic grasps. We evaluate the performance of machine learning (particularly classification techniques) to determine which approaches perform better for this problem. Using the best approaches, a multi-model classification technique is developed. The proposed approach is evaluated in simulation to grasp different kitchen objects using a parallel gripper. The results show that multi-model classification approach enhances the prediction accuracy. The implemented system can be used as to automate the data labeling process required for deep learning approaches.","PeriodicalId":6682,"journal":{"name":"2019 24th IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"42 1","pages":"1575-1578"},"PeriodicalIF":0.0,"publicationDate":"2019-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75130326","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：