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.2017.8247763
S. Zug, Veit Müller, M. Seidel, Pascal Krenckel
Autonomous grasping operations in dynamical environments are key elements of solutions for Factory-of-the-Future scenarios. The manipulator has to cope with a broad variety of objects with different shapes, materials and uncertain poses but at the same time it should provide reliable grasping and placement operations. Within this context, tactile sensors mounted directly on the grippers are a promising solution for monitoring the grasping process. They operate independently from light or line of sight configurations, thus offer a new object detection modality, besides optical-based systems. We receive an imprint of the grasped object with a spatial resolution according to the sensor pattern. However, in case of grippers with a flexible structure and material, this method generates spurious measurements if the gripper is deformed during a manipulation process. This effect disturbs the evaluation of the gripper's state or object position. In this paper, we develop the specification of a tailored tactile sensor configuration able to handle gripper deformations. Based on the results we present a proof-of-concept implementation.
{"title":"Optimized configuration of a tactile sensor system for flexible grippers","authors":"S. Zug, Veit Müller, M. Seidel, Pascal Krenckel","doi":"10.1109/ETFA.2017.8247763","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247763","url":null,"abstract":"Autonomous grasping operations in dynamical environments are key elements of solutions for Factory-of-the-Future scenarios. The manipulator has to cope with a broad variety of objects with different shapes, materials and uncertain poses but at the same time it should provide reliable grasping and placement operations. Within this context, tactile sensors mounted directly on the grippers are a promising solution for monitoring the grasping process. They operate independently from light or line of sight configurations, thus offer a new object detection modality, besides optical-based systems. We receive an imprint of the grasped object with a spatial resolution according to the sensor pattern. However, in case of grippers with a flexible structure and material, this method generates spurious measurements if the gripper is deformed during a manipulation process. This effect disturbs the evaluation of the gripper's state or object position. In this paper, we develop the specification of a tailored tactile sensor configuration able to handle gripper deformations. Based on the results we present a proof-of-concept implementation.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"26 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":"84299497","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.2017.8247734
Insaf Sassi, Alexia Gouin, J. Thiriet
The integration of the wireless network into the control loop of Networked Control Systems NCSs, given the stochastic behavior of wireless communication, can degrade the system performance i.e, its Quality of Control (QoC). It is necessary to study the implications of the communication constraints because control systems need a perfect communication medium. The performance of wireless network and its Quality of Service (QoS) must thus be analyzed in order to guarantee a good QoC. The present paper proposes an analysis of QoS performance metrics for networked systems (networked robots) using an analytic model based on Markov chain theory. The Markov model describes the IEEE 802.11 Distributed Coordination Function (DCF) for periodic round trip traffic of Wireless Networked Control System (WNCS).
{"title":"Wireless network performance evaluation for networked robots","authors":"Insaf Sassi, Alexia Gouin, J. Thiriet","doi":"10.1109/ETFA.2017.8247734","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247734","url":null,"abstract":"The integration of the wireless network into the control loop of Networked Control Systems NCSs, given the stochastic behavior of wireless communication, can degrade the system performance i.e, its Quality of Control (QoC). It is necessary to study the implications of the communication constraints because control systems need a perfect communication medium. The performance of wireless network and its Quality of Service (QoS) must thus be analyzed in order to guarantee a good QoC. The present paper proposes an analysis of QoS performance metrics for networked systems (networked robots) using an analytic model based on Markov chain theory. The Markov model describes the IEEE 802.11 Distributed Coordination Function (DCF) for periodic round trip traffic of Wireless Networked Control System (WNCS).","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"79 3 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87940601","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.2017.8247639
HyungTae Kim, KyungChan Jin, Jongseok Kim, EungJoo Ha, JinHyeok Lee
Illumination is one of the important factors in machine-vision systems, and optimization of illumination is essential to acquire high-quality images during an inspection process. This paper proposes optimization process of the light color and intensity for inspection of active matrix organic light emitting diode (AMOLED) panels using a random-search method. The raw image acquired by a line scan camera had low luminance uniformity due to the surface condition of the AMOLED. The brightness deviation of the image was corrected to increase uniformity. The image quality after the correction was evaluated using a kind of image index, namely Tenenbaum gradient. The random-search method switched the dimming levels of the color source until a better image index was obtained. The random search was formulated for a multi-dimensional vector to be used in an arbitrary number of color sources. The random value in this study was generated using Gaussian random method, and was terminated when the size of a random vector became sufficiently smaller. The random-search method for automatic light control of AMOLED inspection showed 0.6% difference in the image index between the equal-step search and the proposed method. However the number of iterations in the proposed method was 22 but that of the combinations was 20484.
{"title":"Automatic light control of an arbitrary color source for AMOLED inspection using random-search method","authors":"HyungTae Kim, KyungChan Jin, Jongseok Kim, EungJoo Ha, JinHyeok Lee","doi":"10.1109/ETFA.2017.8247639","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247639","url":null,"abstract":"Illumination is one of the important factors in machine-vision systems, and optimization of illumination is essential to acquire high-quality images during an inspection process. This paper proposes optimization process of the light color and intensity for inspection of active matrix organic light emitting diode (AMOLED) panels using a random-search method. The raw image acquired by a line scan camera had low luminance uniformity due to the surface condition of the AMOLED. The brightness deviation of the image was corrected to increase uniformity. The image quality after the correction was evaluated using a kind of image index, namely Tenenbaum gradient. The random-search method switched the dimming levels of the color source until a better image index was obtained. The random search was formulated for a multi-dimensional vector to be used in an arbitrary number of color sources. The random value in this study was generated using Gaussian random method, and was terminated when the size of a random vector became sufficiently smaller. The random-search method for automatic light control of AMOLED inspection showed 0.6% difference in the image index between the equal-step search and the proposed method. However the number of iterations in the proposed method was 22 but that of the combinations was 20484.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"21 1","pages":"1-5"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89698825","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.2017.8247738
Deepak Pal, J. Vain, S. Srinivasan, S. Ramaswamy
Industry 4.0 aims at highly flexible and digitized model of industrial production that is smarter and more reliable than the current possibilities. This requires vertical integration of different operations in a manufacturing to promote reconfigurable smart factory. This investigation proposes a method to schedule maintenance operations using formal methods considering power balance and production constraints in process industries. First, we provide an optimization model for scheduling maintenance and operation along production schedules. Second, we use timed model checking to schedule maintenance considering various physical and operating constraints. Third, we illustrate the method in a smart aluminium factory. The main contribution of this investigation is the integration of optimization models and formal methods in one framework, which leads to verified production/maintenance schedules and contributes to the objectives of Industry 4.0.
{"title":"Model-based maintenance scheduling in flexible modular automation systems","authors":"Deepak Pal, J. Vain, S. Srinivasan, S. Ramaswamy","doi":"10.1109/ETFA.2017.8247738","DOIUrl":"https://doi.org/10.1109/ETFA.2017.8247738","url":null,"abstract":"Industry 4.0 aims at highly flexible and digitized model of industrial production that is smarter and more reliable than the current possibilities. This requires vertical integration of different operations in a manufacturing to promote reconfigurable smart factory. This investigation proposes a method to schedule maintenance operations using formal methods considering power balance and production constraints in process industries. First, we provide an optimization model for scheduling maintenance and operation along production schedules. Second, we use timed model checking to schedule maintenance considering various physical and operating constraints. Third, we illustrate the method in a smart aluminium factory. The main contribution of this investigation is the integration of optimization models and formal methods in one framework, which leads to verified production/maintenance schedules and contributes to the objectives of Industry 4.0.","PeriodicalId":6522,"journal":{"name":"2017 22nd IEEE International Conference on Emerging Technologies and Factory Automation (ETFA)","volume":"3 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":"82096961","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：