Pub Date : 2017-09-01DOI: 10.1109/ETFA.2017.8247760
Abiud Rojas-de-Silva, R. Suárez
This paper presents a method to compute contact forces for bimanual grasps. The method is based on the optimization of the force distribution of the hands and minimizing the force exerted by each finger, using two different cost functions. Both cost functions and the constrains of the optimization problem are formulated as functions of the joint torques based on the existing relation between the grasping forces, the hand-jacobian matrix and the torque of the joint fingers. Additionally, a bimanual grasp index is presented to measure the force distribution between the hands. The paper includes some application examples of the proposed approach.
{"title":"Contact force computation for bimanual grasps","authors":"Abiud Rojas-de-Silva, R. Suárez","doi":"10.1109/ETFA.2017.8247760","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247760","url":null,"abstract":"This paper presents a method to compute contact forces for bimanual grasps. The method is based on the optimization of the force distribution of the hands and minimizing the force exerted by each finger, using two different cost functions. Both cost functions and the constrains of the optimization problem are formulated as functions of the joint torques based on the existing relation between the grasping forces, the hand-jacobian matrix and the torque of the joint fingers. Additionally, a bimanual grasp index is presented to measure the force distribution between the hands. The paper includes some application examples of the proposed approach.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"20 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90369913","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247583
Constantin Wagner, Julian Grothoff, U. Epple, R. Drath, S. Malakuti, Sten Grüner, M. Hoffmeister, Patrick Zimmermann
Industry 4.0 has come up with an impressive number of additional terms and definitions e.g. Asset Administration Shell or Digital Twin. Those terms stand for Industry 4.0 coreparadigms, but their meaning is not harmonized even among experts. This is a source of misunderstanding and confusion. In this paper, the mentioned terms are discussed along the life cycle of a plant. A plant's life cycle comprises the whole process from its idea to its destruction. During the discussion of the terms not only the concepts, but also the visions of Industry 4.0 are clarified. Goal of this paper is not to define additional terms, but to explain and substantiate existing ones and to solve apparent contradictions. Additional outcome of the discussion are architectural recommendations for an upcoming Industry 4.0 architecture. Moreover, suggestions for device manufacturers, system integrators, plant owners and Industry 4.0 architects are given.
{"title":"The role of the Industry 4.0 asset administration shell and the digital twin during the life cycle of a plant","authors":"Constantin Wagner, Julian Grothoff, U. Epple, R. Drath, S. Malakuti, Sten Grüner, M. Hoffmeister, Patrick Zimmermann","doi":"10.1109/ETFA.2017.8247583","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247583","url":null,"abstract":"Industry 4.0 has come up with an impressive number of additional terms and definitions e.g. Asset Administration Shell or Digital Twin. Those terms stand for Industry 4.0 coreparadigms, but their meaning is not harmonized even among experts. This is a source of misunderstanding and confusion. In this paper, the mentioned terms are discussed along the life cycle of a plant. A plant's life cycle comprises the whole process from its idea to its destruction. During the discussion of the terms not only the concepts, but also the visions of Industry 4.0 are clarified. Goal of this paper is not to define additional terms, but to explain and substantiate existing ones and to solve apparent contradictions. Additional outcome of the discussion are architectural recommendations for an upcoming Industry 4.0 architecture. Moreover, suggestions for device manufacturers, system integrators, plant owners and Industry 4.0 architects are given.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"23 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82136082","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247665
A. Moronis, C. Koulamas, A. Kalogeras
The evaluation of the energy consumption or the energy performance of buildings, from a complex engineering system point of view, is a multi-parametric problem where different static or dynamic methods are being used. Quantitative analysis is usually required, not only in the context of building regulations, but also as an important engineering tool for planning energy efficiency measures or interventions. In this paper a quasi-steady state model for the energy use in buildings is presented, which combines simplicity, minimum requirements for data input and adequate accuracy. This model is based on the methodologies described in the ISO 13790 standard. It combines a basic steady state physical model, where dynamic effects are also taken into account by introducing different correlation factors and reference parameters. It's main advantage over more complex dynamic models requiring detailed data and high expertise, is that it can be used not only from a small number of experts but also from engineers involved in energy management or energy efficiency projects. This model is validated according to the procedures of the EN 15265 standard, in order to investigate the dependence of the results on the different parameters used.
{"title":"Validation of a monthly quasi-steady-state simulation model for the energy use in buildings","authors":"A. Moronis, C. Koulamas, A. Kalogeras","doi":"10.1109/ETFA.2017.8247665","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247665","url":null,"abstract":"The evaluation of the energy consumption or the energy performance of buildings, from a complex engineering system point of view, is a multi-parametric problem where different static or dynamic methods are being used. Quantitative analysis is usually required, not only in the context of building regulations, but also as an important engineering tool for planning energy efficiency measures or interventions. In this paper a quasi-steady state model for the energy use in buildings is presented, which combines simplicity, minimum requirements for data input and adequate accuracy. This model is based on the methodologies described in the ISO 13790 standard. It combines a basic steady state physical model, where dynamic effects are also taken into account by introducing different correlation factors and reference parameters. It's main advantage over more complex dynamic models requiring detailed data and high expertise, is that it can be used not only from a small number of experts but also from engineers involved in energy management or energy efficiency projects. This model is validated according to the procedures of the EN 15265 standard, in order to investigate the dependence of the results on the different parameters used.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"35 1","pages":"1-6"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80657835","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247622
Sarmad Riazi, Oskar Wigström, Kristofer Bengtsson, B. Lennartson
Many people in need of care still live in their homes, requiring the caretakers to travel to them. Assigning the people to caretakers and generating their schedules can be formulated as a mixed integer linear programming problem (MILP) that inherits many features of the well-known vehicle routing problem with time windows (VRPTW). Currently, the most successful exact algorithms for VRPTW are based on branch and price framework, which combine column generation (CG) and branching. While these methods could be successful for Home Healthcare Routing and Scheduling Problem (HHCRSP) as well, fast approximate algorithms are appealing, especially for large problems. We recently employed a heuristic distributed gossip algorithm to solve HHCRSP. The method had the potential to provide approximate solutions for relatively large problem instances, but its effectiveness was limited to the performance of its local MILP solver. In this paper, we integrate the gossip algorithm with a local solver based on CG, which makes it an effective algorithm for larger problem instances. We also provide numerical experiments and complexity evaluations of the improved gossip algorithm (gossip-CG) with the standard gossip (gossip-MILP) and CG, and show that gossip-CG outperforms the pure CG in case of large problems.
{"title":"Decomposition and distributed algorithms for home healthcare routing and scheduling problem","authors":"Sarmad Riazi, Oskar Wigström, Kristofer Bengtsson, B. Lennartson","doi":"10.1109/ETFA.2017.8247622","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247622","url":null,"abstract":"Many people in need of care still live in their homes, requiring the caretakers to travel to them. Assigning the people to caretakers and generating their schedules can be formulated as a mixed integer linear programming problem (MILP) that inherits many features of the well-known vehicle routing problem with time windows (VRPTW). Currently, the most successful exact algorithms for VRPTW are based on branch and price framework, which combine column generation (CG) and branching. While these methods could be successful for Home Healthcare Routing and Scheduling Problem (HHCRSP) as well, fast approximate algorithms are appealing, especially for large problems. We recently employed a heuristic distributed gossip algorithm to solve HHCRSP. The method had the potential to provide approximate solutions for relatively large problem instances, but its effectiveness was limited to the performance of its local MILP solver. In this paper, we integrate the gossip algorithm with a local solver based on CG, which makes it an effective algorithm for larger problem instances. We also provide numerical experiments and complexity evaluations of the improved gossip algorithm (gossip-CG) with the standard gossip (gossip-MILP) and CG, and show that gossip-CG outperforms the pure CG in case of large problems.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"73 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80893631","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247647
N. Druml, Bernhard Rutte-Vas, Sandra Wilfling, C. Consani, M. Baumgart, T. Herndl, G. Holweg
Industrie 4.0, Industrial IoT, and cyber-physical production systems in general introduce high levels of automation. Hence, at shop floor level, for example, the interfaces between human and machines are crucial. If a robot's environment perception is not robust and fail-safe, humans may not be detected properly, which may cause critical consequences. However, given the resource constraints of safety controllers typically used in critical application domains, the implementation of complex computer vision algorithms is often challenging. Here we explore the capabilities the indirect Time-of-Flight environment perception technology provides in order to speed up complex computer vision algorithms. In particular we are investigating the use-case of human detection in the domains of critical and resource-constrained applications, such as factory automation and automotive. We demonstrate that preprocessing based on Time-of-Flight 3D data can reduce computation time of typically used computer vision algorithms, such as Viola-Jones, by up to 50%. Furthermore, we showcase a human detection demonstrator case-study implemented on an AURIX processing system that represents a state-of-the-art safety controller. By exploiting the Time-of-Flight technology's depth and amplitude data in a clever way, safety-critical human detection is enabled on the AURIX platform. Compared to competing environment perception technologies, the outlined solution is hardly achievable with structured light or stereo visioning due to the safety controller's resource constraints.
{"title":"Safety-critical human detection featuring time-of-flight environment perception","authors":"N. Druml, Bernhard Rutte-Vas, Sandra Wilfling, C. Consani, M. Baumgart, T. Herndl, G. Holweg","doi":"10.1109/ETFA.2017.8247647","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247647","url":null,"abstract":"Industrie 4.0, Industrial IoT, and cyber-physical production systems in general introduce high levels of automation. Hence, at shop floor level, for example, the interfaces between human and machines are crucial. If a robot's environment perception is not robust and fail-safe, humans may not be detected properly, which may cause critical consequences. However, given the resource constraints of safety controllers typically used in critical application domains, the implementation of complex computer vision algorithms is often challenging. Here we explore the capabilities the indirect Time-of-Flight environment perception technology provides in order to speed up complex computer vision algorithms. In particular we are investigating the use-case of human detection in the domains of critical and resource-constrained applications, such as factory automation and automotive. We demonstrate that preprocessing based on Time-of-Flight 3D data can reduce computation time of typically used computer vision algorithms, such as Viola-Jones, by up to 50%. Furthermore, we showcase a human detection demonstrator case-study implemented on an AURIX processing system that represents a state-of-the-art safety controller. By exploiting the Time-of-Flight technology's depth and amplitude data in a clever way, safety-critical human detection is enabled on the AURIX platform. Compared to competing environment perception technologies, the outlined solution is hardly achievable with structured light or stereo visioning due to the safety controller's resource constraints.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"93 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82006099","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247576
Julian Rahm, Markus Graube, L. Urbas
During the life cycle of an industrial processing plant, a variety of domain specific data models are generated. All these models will be changed independently by a group of engineers over time. Maintaining the consistency of these models involves a time consuming and costly manual process. Here we introduce an interactive roundtrip engineering system for processing industry environments. The system use a complementary rule-based transformation language to provide generation and synchronisation processes. For this, an interactive concept is presented with a knowledge-based system and user interaction. The goal is to have a consistent digital twin of the plant through the whole life cycle in a highly automated manner. This leads to a traceable transformation process which ensures more parallel design phases and an efficient maintenance or reconstruction of the digital plant twin.
{"title":"A proposal for an interactive roundtrip engineering system","authors":"Julian Rahm, Markus Graube, L. Urbas","doi":"10.1109/ETFA.2017.8247576","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247576","url":null,"abstract":"During the life cycle of an industrial processing plant, a variety of domain specific data models are generated. All these models will be changed independently by a group of engineers over time. Maintaining the consistency of these models involves a time consuming and costly manual process. Here we introduce an interactive roundtrip engineering system for processing industry environments. The system use a complementary rule-based transformation language to provide generation and synchronisation processes. For this, an interactive concept is presented with a knowledge-based system and user interaction. The goal is to have a consistent digital twin of the plant through the whole life cycle in a highly automated manner. This leads to a traceable transformation process which ensures more parallel design phases and an efficient maintenance or reconstruction of the digital plant twin.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"150 1","pages":"1-7"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74494379","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247607
Z. Iqbal, L. Almeida, M. Ashjaei
Ethernet is a promising candidate for networking real-time embedded systems such as automobiles, and it is already used in several embedded scopes, such as airplanes and trains. Moreover, its higher bandwidth enables applications made of dispersed embedded systems that exchange large amounts of data through the so-called Internet-of-Things, such as wide-area video sensing. In this realm, network reservations are an important design element that favor composability in the time domain thereby supporting the design of complex systems. However, reservations may impact negatively on the network bandwidth efficiency due to over-specification, particularly when they are designed to meet worst-case delay constraints. In this work, we use a specific Ethernet protocol that provides real-time reservations, namely FTT-SE, and we assess through extensive simulations the efficiency of a worst-case network delay analysis for sporadic reservations associated to asynchronous messages. Essentially, we compare the analytical worst-case delay with the one observed in the simulations using two data sets comprising up to 20000 and 100000 message sets, respectively, and we change the system configuration, namely properties of the message sets and network and protocol configuration parameters. We find that the analysis is accurate, i.e. matches observations, for a significant percentage of messages in the message sets (up to 60% on average). Conversely, we found that a small percentage of message sets (below 6%) generated rather pessimistic analytic estimates exceeding the observations by 6 times, thus with a negative impact on efficiency. The results we present in the paper, particularly their distributions, inform system designers of how to tune their designs to improve network bandwidth efficiency under strict timing constraints.
{"title":"Analyzing the efficiency of sporadic reservations on ethernet with FTT-SE","authors":"Z. Iqbal, L. Almeida, M. Ashjaei","doi":"10.1109/ETFA.2017.8247607","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247607","url":null,"abstract":"Ethernet is a promising candidate for networking real-time embedded systems such as automobiles, and it is already used in several embedded scopes, such as airplanes and trains. Moreover, its higher bandwidth enables applications made of dispersed embedded systems that exchange large amounts of data through the so-called Internet-of-Things, such as wide-area video sensing. In this realm, network reservations are an important design element that favor composability in the time domain thereby supporting the design of complex systems. However, reservations may impact negatively on the network bandwidth efficiency due to over-specification, particularly when they are designed to meet worst-case delay constraints. In this work, we use a specific Ethernet protocol that provides real-time reservations, namely FTT-SE, and we assess through extensive simulations the efficiency of a worst-case network delay analysis for sporadic reservations associated to asynchronous messages. Essentially, we compare the analytical worst-case delay with the one observed in the simulations using two data sets comprising up to 20000 and 100000 message sets, respectively, and we change the system configuration, namely properties of the message sets and network and protocol configuration parameters. We find that the analysis is accurate, i.e. matches observations, for a significant percentage of messages in the message sets (up to 60% on average). Conversely, we found that a small percentage of message sets (below 6%) generated rather pessimistic analytic estimates exceeding the observations by 6 times, thus with a negative impact on efficiency. The results we present in the paper, particularly their distributions, inform system designers of how to tune their designs to improve network bandwidth efficiency under strict timing constraints.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"53 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78130945","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247650
S. Trapani, M. Indri
A joint research between Politecnico di Torino and COMAU is going on, aimed at defining a task oriented programming approach to allow soft skilled programmers to develop optimized programs for complex robotic cells. Within this paradigm, the user is simply asked to specify the features of the robotic cell and a structured set of tasks defining the required process. The paper is focused on the first step necessary to achieve the overall goal, i.e., the definition of a generic task model. The model is built starting from the analysis of the most important industrial applications, and can include physical and synchronization constraints, as well as various possible requirements and situations relative to the characteristics of the robots in the cell and of the involved work-pieces. A welding process is considered as typical industrial case study, to show how to build the corresponding task model according to the proposed approach.
{"title":"Task modeling for task-oriented robot programming","authors":"S. Trapani, M. Indri","doi":"10.1109/ETFA.2017.8247650","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247650","url":null,"abstract":"A joint research between Politecnico di Torino and COMAU is going on, aimed at defining a task oriented programming approach to allow soft skilled programmers to develop optimized programs for complex robotic cells. Within this paradigm, the user is simply asked to specify the features of the robotic cell and a structured set of tasks defining the required process. The paper is focused on the first step necessary to achieve the overall goal, i.e., the definition of a generic task model. The model is built starting from the analysis of the most important industrial applications, and can include physical and synchronization constraints, as well as various possible requirements and situations relative to the characteristics of the robots in the cell and of the involved work-pieces. A welding process is considered as typical industrial case study, to show how to build the corresponding task model according to the proposed approach.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"40 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74321197","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247759
Vojtěch Vonásek, A. Vick, M. Saska
In the bin picking problem, the task is to automatically unload objects from a container using a robotic manipulator. The task is often approached by organizing the objects into a predictable pattern, e.g., a workpiece carrier, in order to simplify all integral subtasks like object recognition, motion planning and grasping. In such a case, motion planning can even be solved offline as it is ensured that the objects are always at the same positions at known times. However, there is a growing demand for non-structured bin picking, where the objects can be placed randomly in the bins. This arises from recent trends of transforming classical factories into smart production facilities allowing small lot sizes at the efficiency of mass production. The demand for fast and highly flexible handling and manipulation abilities of industrial robots requires to solve all the bin picking methods, including motion planning, online. In this paper, we propose a novel technique for fast sampling-based motion planning of robotic manipulators using motion primitives. Motion primitives are short trajectories that boost search of the configuration space and consequently speed up the planning phase. The proposed work has been verified in a simulation and on a prototype of a bin picking system.
{"title":"Motion planning with motion primitives for industrial bin picking","authors":"Vojtěch Vonásek, A. Vick, M. Saska","doi":"10.1109/ETFA.2017.8247759","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247759","url":null,"abstract":"In the bin picking problem, the task is to automatically unload objects from a container using a robotic manipulator. The task is often approached by organizing the objects into a predictable pattern, e.g., a workpiece carrier, in order to simplify all integral subtasks like object recognition, motion planning and grasping. In such a case, motion planning can even be solved offline as it is ensured that the objects are always at the same positions at known times. However, there is a growing demand for non-structured bin picking, where the objects can be placed randomly in the bins. This arises from recent trends of transforming classical factories into smart production facilities allowing small lot sizes at the efficiency of mass production. The demand for fast and highly flexible handling and manipulation abilities of industrial robots requires to solve all the bin picking methods, including motion planning, online. In this paper, we propose a novel technique for fast sampling-based motion planning of robotic manipulators using motion primitives. Motion primitives are short trajectories that boost search of the configuration space and consequently speed up the planning phase. The proposed work has been verified in a simulation and on a prototype of a bin picking system.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"55 1","pages":"1-4"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90594619","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 : 2017-09-01DOI: 10.1109/ETFA.2017.8247651
Denis Stogl, Daniel Zumkeller, S. E. Navarro, Alexander Heilig, B. Hein
Many manipulation applications in industrial settings using robots depend on reliable detection and grasping capabilities of stationary or moving objects. The latter demand an extended use of intrinsic and extrinsic sensors being in a closed control-loop with a robotic system. In this paper we present an approach for tracking, reconstruction and grasping of unknown objects from a moving conveyor belt using an external depth sensor and an industrial robot. The approach consists of an algorithm for the estimation of the position, velocity and form of an object, an algorithm for estimation of the conveyor's path and an algorithm for calculating an interception trajectory for the robot. The presented scheme is designed for tracking and reconstruction of unknown rotationally symmetrical objects. Nevertheless, the reconstruction algorithm is able to detect asymmetrical parts of an object and recognize if an object is hollow. This is further used for calculation of a feasible grasp. From the reconstruction data a mesh of the object is created. Finally, robots interception and grasping trajectory are calculated on-line for any arbitrary position on the conveyor. The objects are sucessfully grasped from moving conveyor up to the speed of more than 10 [cm/s].
{"title":"Tracking, reconstruction and grasping of unknown rotationally symmetrical objects from a conveyor belt","authors":"Denis Stogl, Daniel Zumkeller, S. E. Navarro, Alexander Heilig, B. Hein","doi":"10.1109/ETFA.2017.8247651","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247651","url":null,"abstract":"Many manipulation applications in industrial settings using robots depend on reliable detection and grasping capabilities of stationary or moving objects. The latter demand an extended use of intrinsic and extrinsic sensors being in a closed control-loop with a robotic system. In this paper we present an approach for tracking, reconstruction and grasping of unknown objects from a moving conveyor belt using an external depth sensor and an industrial robot. The approach consists of an algorithm for the estimation of the position, velocity and form of an object, an algorithm for estimation of the conveyor's path and an algorithm for calculating an interception trajectory for the robot. The presented scheme is designed for tracking and reconstruction of unknown rotationally symmetrical objects. Nevertheless, the reconstruction algorithm is able to detect asymmetrical parts of an object and recognize if an object is hollow. This is further used for calculation of a feasible grasp. From the reconstruction data a mesh of the object is created. Finally, robots interception and grasping trajectory are calculated on-line for any arbitrary position on the conveyor. The objects are sucessfully grasped from moving conveyor up to the speed of more than 10 [cm/s].","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"60 1","pages":"1-8"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87517132","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：