Pub Date : 2010-06-24DOI: 10.1109/RAAD.2010.5524605
M. Awais, D. Henrich
Combining the intelligent and situation dependent decision making capabilities of a human with the accuracy and power of a robot, performance of many tasks can be improved. The human-robot collaboration scenarios are increasing. Human-robot interaction is not only restricted to the humanoid robots interacting with the humans or to the mobile service robots providing different services but also industrial robots opens a wide range of human-robot collaboration set-ups. Intention recognition plays a key role in intuitive human-robot collaboration. In this paper we present a novel approach for recognizing the human intention using weighted probabilistic state machines. We categorize the recognition task into two categories namely explicit and implicit intention communication. We present a general intention recognition approach that can be applied to any human-robot cooperation situation. The algorithm is tested with an industrial robotic arm.
{"title":"Human-robot collaboration by intention recognition using probabilistic state machines","authors":"M. Awais, D. Henrich","doi":"10.1109/RAAD.2010.5524605","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524605","url":null,"abstract":"Combining the intelligent and situation dependent decision making capabilities of a human with the accuracy and power of a robot, performance of many tasks can be improved. The human-robot collaboration scenarios are increasing. Human-robot interaction is not only restricted to the humanoid robots interacting with the humans or to the mobile service robots providing different services but also industrial robots opens a wide range of human-robot collaboration set-ups. Intention recognition plays a key role in intuitive human-robot collaboration. In this paper we present a novel approach for recognizing the human intention using weighted probabilistic state machines. We categorize the recognition task into two categories namely explicit and implicit intention communication. We present a general intention recognition approach that can be applied to any human-robot cooperation situation. The algorithm is tested with an industrial robotic arm.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123427248","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524612
E. Ravina
The paper describes the result of a theoretical and experimental research activity oriented to the design and realization of a low-cost pneumatic unit able to drive bows in relative motion respect to strings in bowed musical instrument. Pneumatic technology reduces costs and the proportional control allows the flexible programming of motion laws. The unit is specifically conceived to support laboratory tests of interest of violin makers and researchers. Results of specific experiments are collected and discussed.
{"title":"Pneumatronic unit for motion of bows","authors":"E. Ravina","doi":"10.1109/RAAD.2010.5524612","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524612","url":null,"abstract":"The paper describes the result of a theoretical and experimental research activity oriented to the design and realization of a low-cost pneumatic unit able to drive bows in relative motion respect to strings in bowed musical instrument. Pneumatic technology reduces costs and the proportional control allows the flexible programming of motion laws. The unit is specifically conceived to support laboratory tests of interest of violin makers and researchers. Results of specific experiments are collected and discussed.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122552078","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524614
T. Borangiu, S. Răileanu, D. Trentesaux, T. Berger
The paper describes a new, open control paradigm for discrete, repetitive shop floor production, designed as a solution for agile manufacturing reengineering through (a) multi-agent robot service reconfiguring and (b) implementing the robot service access model (RSAM) in a distributed, semi-heterarchical production planning, scheduling and execution control architecture. This distributed architecture integrates two layers with generic functionalities: (1) Dynamic reconfiguring of the resource (robot-vision) service access model RSAM through a multi-agent system organization; (2) Holonic manufacturing scheduling (robot allocation), control and tracking based on the PROSA holarchy and the Intelligent Product technology — implemented through intelligent embedded devices (acting as Active Holon Entities) which use OpenEmbedded Linux as real-time operating system. Experimental results are reported from production scenarios tested in the two shop-floor platforms of the Laboratories AIP-PRIMECA (University of Valenciennes) and CIMR (University Politehnica of Bucharest) composed by robot-vision workstations.
{"title":"Open manufacturing control with agile reconfiguring of robot services","authors":"T. Borangiu, S. Răileanu, D. Trentesaux, T. Berger","doi":"10.1109/RAAD.2010.5524614","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524614","url":null,"abstract":"The paper describes a new, open control paradigm for discrete, repetitive shop floor production, designed as a solution for agile manufacturing reengineering through (a) multi-agent robot service reconfiguring and (b) implementing the robot service access model (RSAM) in a distributed, semi-heterarchical production planning, scheduling and execution control architecture. This distributed architecture integrates two layers with generic functionalities: (1) Dynamic reconfiguring of the resource (robot-vision) service access model RSAM through a multi-agent system organization; (2) Holonic manufacturing scheduling (robot allocation), control and tracking based on the PROSA holarchy and the Intelligent Product technology — implemented through intelligent embedded devices (acting as Active Holon Entities) which use OpenEmbedded Linux as real-time operating system. Experimental results are reported from production scenarios tested in the two shop-floor platforms of the Laboratories AIP-PRIMECA (University of Valenciennes) and CIMR (University Politehnica of Bucharest) composed by robot-vision workstations.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121950219","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524599
M. Stoica, G. Calangiu, F. Sisak
Artificial neural networks play an important role in robot programming by demonstration. In this paper we present a method for artificial neural network training. The main idea of this method is to train the artificial neural network with all of the data, before the current training step, and at a certain step the network is already trained a huge number of times. Some features of the quality of neural network trainning, using this method, were presented in [9]. Because the method uses all of the data before the current training step, in this paper, we are concerned about training time and computing time comportment of the neural network. A software application for obtaining training time based on the number of training steps was designed. This software application implements the training method on an unidirectional multi-layer neural network and prints into a graph the training time and computing time. The results obtained using the software application and important conclusions towards the training and computing time comportment are also presented.
{"title":"Measuring the time needed for training a neural network based on the number of training steps","authors":"M. Stoica, G. Calangiu, F. Sisak","doi":"10.1109/RAAD.2010.5524599","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524599","url":null,"abstract":"Artificial neural networks play an important role in robot programming by demonstration. In this paper we present a method for artificial neural network training. The main idea of this method is to train the artificial neural network with all of the data, before the current training step, and at a certain step the network is already trained a huge number of times. Some features of the quality of neural network trainning, using this method, were presented in [9]. Because the method uses all of the data before the current training step, in this paper, we are concerned about training time and computing time comportment of the neural network. A software application for obtaining training time based on the number of training steps was designed. This software application implements the training method on an unidirectional multi-layer neural network and prints into a graph the training time and computing time. The results obtained using the software application and important conclusions towards the training and computing time comportment are also presented.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115870641","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524542
L. Horváth, I. Rudas, K. Jezernik
One of the main recent achievements in engineering is description of complex products and their physical environment in a single object model. This model has capabilities to serve engineering from the first specification of a product to recycling. New research programs were needed in order to establish a new style of engineering where engineers communicate model creation and application procedures. The authors joined to these efforts and developed new modeling methods for the above purpose. In this paper they introduce some of these methods considering needs by the complex and knowledge intensive engineering for robot systems. Paper starts with an outline of application of virtual spaces in robot system modeling. Following this, a content based contextual object definition is explained considering robotic application. Next, application of human control by contextual spaces for adaptive definition of engineering objects and the related control of product definition are shown. Finally, object space for robot system is outlined as application related issue of the proposed modeling.
{"title":"Engineering for industrial robots in content based virtual space","authors":"L. Horváth, I. Rudas, K. Jezernik","doi":"10.1109/RAAD.2010.5524542","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524542","url":null,"abstract":"One of the main recent achievements in engineering is description of complex products and their physical environment in a single object model. This model has capabilities to serve engineering from the first specification of a product to recycling. New research programs were needed in order to establish a new style of engineering where engineers communicate model creation and application procedures. The authors joined to these efforts and developed new modeling methods for the above purpose. In this paper they introduce some of these methods considering needs by the complex and knowledge intensive engineering for robot systems. Paper starts with an outline of application of virtual spaces in robot system modeling. Following this, a content based contextual object definition is explained considering robotic application. Next, application of human control by contextual spaces for adaptive definition of engineering objects and the related control of product definition are shown. Finally, object space for robot system is outlined as application related issue of the proposed modeling.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121714055","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524579
G. Nawratil
In the general case the singularity loci of parallel manipulators of Stewart Gough type is a cubic surface in the space of translations. In [G. Nawratil, Stewart Gough platforms with non-cubic singularity surface, Technical Report No. 204, Geometry Preprint Series, Vienna University of Technology (2010)] all manipulators with a non-cubic singularity surface were characterized. Based on this result we determine the whole set of parallel manipulators of Stewart Gough type possessing a linear singularity surface. These manipulators have the advantage, that their singularity surface can easily be visualized because it is a plane for any orientation of the platform. We also give a geometric interpretation of these manipulators.
一般情况下，Stewart Gough型并联机器人的奇异轨迹是平移空间中的三次曲面。在[G。Nawratil, Stewart Gough平台的非三次奇异面，技术报告第204号，几何预印本系列，维也纳理工大学(2010)]。在此基础上，确定了一类具有线性奇异曲面的Stewart Gough型并联机器人。这些机械手的优点是，它们的奇异面可以很容易地可视化，因为它是平台任何方向的平面。我们也给出了这些机械臂的几何解释。
{"title":"Stewart Gough platforms with linear singularity surface","authors":"G. Nawratil","doi":"10.1109/RAAD.2010.5524579","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524579","url":null,"abstract":"In the general case the singularity loci of parallel manipulators of Stewart Gough type is a cubic surface in the space of translations. In [G. Nawratil, Stewart Gough platforms with non-cubic singularity surface, Technical Report No. 204, Geometry Preprint Series, Vienna University of Technology (2010)] all manipulators with a non-cubic singularity surface were characterized. Based on this result we determine the whole set of parallel manipulators of Stewart Gough type possessing a linear singularity surface. These manipulators have the advantage, that their singularity surface can easily be visualized because it is a plane for any orientation of the platform. We also give a geometric interpretation of these manipulators.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131422838","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524594
X. Zhang, O. Ivlev
Soft robot arms, driven by novel pneumatic actuators with Rotary Elastic Chambers (REC), are well suitable for assistive and service tasks. However, the control of such robots is quite difficult because of high nonlinearities in actuators dynamics in addition to robot arm models. In this paper the recently developed Simulink-based program library “SoftRob” for simulation of the soft robots with REC actuators is described. A new adaptive admittance control scheme for pneumatic soft robots is proposed. The approach imitates the human force control capacity to regulate the contact force by adapting the arm stiffness. The algorithm is assumed to be realized without explicit force measurement, i.e. without the use of expensive external force sensors. The proposed control scheme is tested in simulation on example of a planar 2DOF model.
{"title":"Simulation of interaction tasks for pneumatic soft robots using SimMechanics","authors":"X. Zhang, O. Ivlev","doi":"10.1109/RAAD.2010.5524594","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524594","url":null,"abstract":"Soft robot arms, driven by novel pneumatic actuators with Rotary Elastic Chambers (REC), are well suitable for assistive and service tasks. However, the control of such robots is quite difficult because of high nonlinearities in actuators dynamics in addition to robot arm models. In this paper the recently developed Simulink-based program library “SoftRob” for simulation of the soft robots with REC actuators is described. A new adaptive admittance control scheme for pneumatic soft robots is proposed. The approach imitates the human force control capacity to regulate the contact force by adapting the arm stiffness. The algorithm is assumed to be realized without explicit force measurement, i.e. without the use of expensive external force sensors. The proposed control scheme is tested in simulation on example of a planar 2DOF model.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"448 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134272589","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524600
A. Kos, J. Babič
The goal of our research was to create an application which could be used to program the humanoid robot with tasks needed to play football. The design of our system enables us to program sequential tasks. The tasks are constructed from a programmed logic interface and pre-programmed motions. This system is easy to use and can be adapted to perform different tasks. Because of its characteristics the system was used to demonstrate basic concepts of mobile humanoid robots to students.
{"title":"Programming and control of humanoid robot football playing tasks","authors":"A. Kos, J. Babič","doi":"10.1109/RAAD.2010.5524600","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524600","url":null,"abstract":"The goal of our research was to create an application which could be used to program the humanoid robot with tasks needed to play football. The design of our system enables us to program sequential tasks. The tasks are constructed from a programmed logic interface and pre-programmed motions. This system is easy to use and can be adapted to perform different tasks. Because of its characteristics the system was used to demonstrate basic concepts of mobile humanoid robots to students.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114181809","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524610
A. Itu, I. Starețu
The paper presents an intuitive interface for controlling a three fingered anthropomorphic robotic hand in both virtual and real environments. The study presented in this paper will be focus on developing a multimodal interface that will be used for interacting with the Barrett hand. The main problem in using the WIMP metaphor for interacting with the Barrett hand is the increased number of degrees of freedom which must be manipulated with the mouse and the keyboard. In this case the gripper has three fingers with one degrees of freedom for each finger and another one for spreading two fingers. So the interface must deal with a total number of four degrees of freedom which in certain conditions will need to be manipulated simultaneously. The approach is using a multimodal interface based on voice commands, tele-manipulation and smart mobile devices remote controlling.
{"title":"Multimodal control interface for an anthropomorphic gripper","authors":"A. Itu, I. Starețu","doi":"10.1109/RAAD.2010.5524610","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524610","url":null,"abstract":"The paper presents an intuitive interface for controlling a three fingered anthropomorphic robotic hand in both virtual and real environments. The study presented in this paper will be focus on developing a multimodal interface that will be used for interacting with the Barrett hand. The main problem in using the WIMP metaphor for interacting with the Barrett hand is the increased number of degrees of freedom which must be manipulated with the mouse and the keyboard. In this case the gripper has three fingers with one degrees of freedom for each finger and another one for spreading two fingers. So the interface must deal with a total number of four degrees of freedom which in certain conditions will need to be manipulated simultaneously. The approach is using a multimodal interface based on voice commands, tele-manipulation and smart mobile devices remote controlling.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116961255","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 : 2010-06-24DOI: 10.1109/RAAD.2010.5524576
A. Melnykov, F. Palis, A. Rudskyy, M. Konyev
The paper deals with designing and developing a biped robot for research purposes. Robot's mechanical structure and drives system are described hereunder in details. Moreover the new modified actuator is discussed. An industrial Ethernet-based real-time communication protocol is introduced and the communication ability between the robot-side hardware and PC-side control system is investigated.
{"title":"Biped robot “ROTTO”: Stiff and compliant","authors":"A. Melnykov, F. Palis, A. Rudskyy, M. Konyev","doi":"10.1109/RAAD.2010.5524576","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524576","url":null,"abstract":"The paper deals with designing and developing a biped robot for research purposes. Robot's mechanical structure and drives system are described hereunder in details. Moreover the new modified actuator is discussed. An industrial Ethernet-based real-time communication protocol is introduced and the communication ability between the robot-side hardware and PC-side control system is investigated.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127518856","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：