Pub Date : 2010-06-24DOI: 10.1109/RAAD.2010.5524607
O. Ogorodnikova
The paper discusses the concept of the integrated safety monitoring system for the human-robot interaction domain. These main elements are the advisory, computer aided expert system, the safety mode controller and the human awareness interface. The introduced approach allows to ensure the required level of safety for the collaborative tasks performance in manufacturing setup within or beyond the robotized workcell. The generated protocols of the expert system, safety criteria (danger index) and functional modes are the determining elements of the safety framework. The expert system, which inference engine is built on the fuzzy theory application, provides designer with an explicit workcell ergonomic and human factor analysis, task related hazards and risk category evaluation. Safety mode controller functional algorithm is based on the safety modes monitoring parameters definition and their continuous control. It is represented as a separated unit that monitors interconnected elements in compliance with the safety criteria and predefined transition rules. The proposed human warning system, mounted on the individual wrist and interconnected with the overall safety system, suppose to alert an operator about the system current state by imparting vibrotactile and visual cueing in compliance with predefined rules.
{"title":"Safe and reliable human-robot interaction in manufactory, within and beyond the workcell","authors":"O. Ogorodnikova","doi":"10.1109/RAAD.2010.5524607","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524607","url":null,"abstract":"The paper discusses the concept of the integrated safety monitoring system for the human-robot interaction domain. These main elements are the advisory, computer aided expert system, the safety mode controller and the human awareness interface. The introduced approach allows to ensure the required level of safety for the collaborative tasks performance in manufacturing setup within or beyond the robotized workcell. The generated protocols of the expert system, safety criteria (danger index) and functional modes are the determining elements of the safety framework. The expert system, which inference engine is built on the fuzzy theory application, provides designer with an explicit workcell ergonomic and human factor analysis, task related hazards and risk category evaluation. Safety mode controller functional algorithm is based on the safety modes monitoring parameters definition and their continuous control. It is represented as a separated unit that monitors interconnected elements in compliance with the safety criteria and predefined transition rules. The proposed human warning system, mounted on the individual wrist and interconnected with the overall safety system, suppose to alert an operator about the system current state by imparting vibrotactile and visual cueing in compliance with predefined rules.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"11 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":"130301657","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.2010.5524567
Denis Forte, A. Ude, A. Kos
Intelligent robots cannot be programmed in advance for all possible situations, but they should be able to generalize based on the acquired knowledge. In robot learning based on imitation of human activity we often use statistical methods that generalize observed (learned) movements. The acquired data is used to generate useful robots responses in situations for which the robot has not been specifically instructed how to respond. The paper describes the robot learning with Gaussian process regression that creates the model and estimates the parameters for generalization of the acquired motor knowledge, which is accumulated as a database of example movements. New actions are synthesized by applying Gaussian process regression, where the goal and other characteristics of an action are utilized as queries to create an optimal control policy with respect to the previously acquired knowledge. The paper demonstrates that the proposed methodology can be integrated with an active vision system of a humanoid robot. 3D vision data is used to provide query points for statistical generalization.
{"title":"Robot learning by Gaussian process regression","authors":"Denis Forte, A. Ude, A. Kos","doi":"10.1109/RAAD.2010.5524567","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524567","url":null,"abstract":"Intelligent robots cannot be programmed in advance for all possible situations, but they should be able to generalize based on the acquired knowledge. In robot learning based on imitation of human activity we often use statistical methods that generalize observed (learned) movements. The acquired data is used to generate useful robots responses in situations for which the robot has not been specifically instructed how to respond. The paper describes the robot learning with Gaussian process regression that creates the model and estimates the parameters for generalization of the acquired motor knowledge, which is accumulated as a database of example movements. New actions are synthesized by applying Gaussian process regression, where the goal and other characteristics of an action are utilized as queries to create an optimal control policy with respect to the previously acquired knowledge. The paper demonstrates that the proposed methodology can be integrated with an active vision system of a humanoid robot. 3D vision data is used to provide query points for statistical generalization.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"88 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":"130911288","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.2010.5524591
K. Arrouk, B. Bouzgarrou, G. Gogu
This paper presents a set of techniques, based on a geometrical approach, for workspace determination and analysis. These techniques are applied for design study of a novel modular parallel manipulator, 3-C̲RS, with 6-DOF. The proposed method is implemented in the CATIA CAD environment, which provides powerful tools for graphical programming and geometric feature handling. A new type of workspace representation is introduced allowing a fine simultaneous characterization of the translation and orientation capacities of the mobile platform.
{"title":"CAD based techniques for workspace analysis and representation of the 3C̲RS parallel manipulator","authors":"K. Arrouk, B. Bouzgarrou, G. Gogu","doi":"10.1109/RAAD.2010.5524591","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524591","url":null,"abstract":"This paper presents a set of techniques, based on a geometrical approach, for workspace determination and analysis. These techniques are applied for design study of a novel modular parallel manipulator, 3-C̲RS, with 6-DOF. The proposed method is implemented in the CATIA CAD environment, which provides powerful tools for graphical programming and geometric feature handling. A new type of workspace representation is introduced allowing a fine simultaneous characterization of the translation and orientation capacities of the mobile platform.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"69 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":"116039977","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.2010.5524611
L. Kis, B. Lantos
A miniature quadrotor helicopter is an underactuated nonlinear system. Usually several types of sensors are used to control it. This article focuses on the emergency situation, when only few sensors are available. These sensors are mainly the inertial ones. Certainly, these sensors are not enough for normal maneuvering, but the controlled system should be able for horizontal stabilization and safe landing. Two types of control are presented. The first is a casual LQ state feedback. The disadvantage of this type of control in real environment is shown. The second control algorithm is an H∞ control method. The control design starts from a very simple linear model. The parameter measurement of the linear system is shown. The goal of this article is to handle the uncertainty in the behavior of the real system.
{"title":"Quadrotor control based on partial sensor data","authors":"L. Kis, B. Lantos","doi":"10.1109/RAAD.2010.5524611","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524611","url":null,"abstract":"A miniature quadrotor helicopter is an underactuated nonlinear system. Usually several types of sensors are used to control it. This article focuses on the emergency situation, when only few sensors are available. These sensors are mainly the inertial ones. Certainly, these sensors are not enough for normal maneuvering, but the controlled system should be able for horizontal stabilization and safe landing. Two types of control are presented. The first is a casual LQ state feedback. The disadvantage of this type of control in real environment is shown. The second control algorithm is an H∞ control method. The control design starts from a very simple linear model. The parameter measurement of the linear system is shown. The goal of this article is to handle the uncertainty in the behavior of the real system.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"64 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":"134080761","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.2010.5524552
D. Kusic, J. Cas
This paper describes a position control of 2 degrees of freedom (DOF) XY Piezo Actuator Stage (XY PAS) with Feedforward Neural Network (FNN) and additional Particle Swarm Optimization (PSO) approach, which is used as an improved learning method for optimizing the weights of FNN rather than just the standard technique of back-propagation of errors.
{"title":"A particle swarm and neural network approach for position control of XY Piezo Actuator Stage","authors":"D. Kusic, J. Cas","doi":"10.1109/RAAD.2010.5524552","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524552","url":null,"abstract":"This paper describes a position control of 2 degrees of freedom (DOF) XY Piezo Actuator Stage (XY PAS) with Feedforward Neural Network (FNN) and additional Particle Swarm Optimization (PSO) approach, which is used as an improved learning method for optimizing the weights of FNN rather than just the standard technique of back-propagation of errors.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"37 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":"129257462","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.2010.5524577
A. Dumitrache, T. Borangiu, A. Dogar
This paper proposes a set of techniques for predictive collision avoidance, which ensure robust operation of robot applications. Implementation issues for applying the techniques to state-of-art robots are presented, including integration with manual and automatic operation modes.
{"title":"Collision and proximity avoidance for robust behaviour of real-time robot applications","authors":"A. Dumitrache, T. Borangiu, A. Dogar","doi":"10.1109/RAAD.2010.5524577","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524577","url":null,"abstract":"This paper proposes a set of techniques for predictive collision avoidance, which ensure robust operation of robot applications. Implementation issues for applying the techniques to state-of-art robots are presented, including integration with manual and automatic operation modes.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"49 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":"122725195","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.2010.5524592
A. Gams, T. Petrič, L. Žlajpah, A. Ude
For effective use of learning by imitation with a robot, it is necessary that the robot can adapt to the current state of the external world. This paper describes an optimization approach that enables the generation of a new motion trajectory, which accomplishes the task in a given situation, based on a library of example movements. New movements are generated by applying statistical methods, where the current state of the world is utilized as query into the library. Dynamic movement primitives are employed as the underlying motor representation. The main contribution of this paper is the optimization of dynamic movement primitives with respect to the kernel function positions and over the entire set of demonstrated movements. We applied the algorithm to a robotic throwing task, where the location of the target is determined by a stereo vision system, which can detect infrared markers. The vision system uses two Nintendo WIIMOTEs for cameras.
{"title":"Optimizing parameters of trajectory representation for movement generalization: robotic throwing","authors":"A. Gams, T. Petrič, L. Žlajpah, A. Ude","doi":"10.1109/RAAD.2010.5524592","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524592","url":null,"abstract":"For effective use of learning by imitation with a robot, it is necessary that the robot can adapt to the current state of the external world. This paper describes an optimization approach that enables the generation of a new motion trajectory, which accomplishes the task in a given situation, based on a library of example movements. New movements are generated by applying statistical methods, where the current state of the world is utilized as query into the library. Dynamic movement primitives are employed as the underlying motor representation. The main contribution of this paper is the optimization of dynamic movement primitives with respect to the kernel function positions and over the entire set of demonstrated movements. We applied the algorithm to a robotic throwing task, where the location of the target is determined by a stereo vision system, which can detect infrared markers. The vision system uses two Nintendo WIIMOTEs for cameras.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"1 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":"115230101","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.2010.5524550
György Schuster, R. Lovassy
This paper proposes a new control structure for automatic production lines. To handle the production lines flexibility and to solve the optimal control problem a new methodology is suggested. In our approach the production line workstations are connected sequential, coordinated and controlled with individual (industrial) Personal Computers (PCs) interconnected in grid. These computers are able to supply the whole system control task and to optimize the production. The suggested method advantages and disadvantages are enumerated. Possible control system architecture is presented.
{"title":"A possible control structure for production lines optimization","authors":"György Schuster, R. Lovassy","doi":"10.1109/RAAD.2010.5524550","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524550","url":null,"abstract":"This paper proposes a new control structure for automatic production lines. To handle the production lines flexibility and to solve the optimal control problem a new methodology is suggested. In our approach the production line workstations are connected sequential, coordinated and controlled with individual (industrial) Personal Computers (PCs) interconnected in grid. These computers are able to supply the whole system control task and to optimize the production. The suggested method advantages and disadvantages are enumerated. Possible control system architecture is presented.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"68 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":"115754698","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.2010.5524553
L. Horváth, I. Rudas
Engineering in product definition traditionally concentrates on building structures of parts and assemblies. Other objects such as analysis results, manufacturing methods, and equipment control programs are mapped to part and assembly definitions. This style of engineering has been realized in model and simulation based product development. Product data management systems as extensions to product modeling and simulation systems were forced to apply engineering process definition for organization of group work. Some drawback of the above modeling motivated the authors to define an additional content based extension to current product modeling and simulation for entities of human intent, engineering objectives and decisions. In this paper, the authors analyze characteristics the above process elements and features and define typical engineering processes. Problems with the currently applied product model and an earlier proposed solution by the application of information content based product model extension are introduced. Following this, four typical information content based engineering processes are explained. Finally, robot system is characterized together with its environmental model as a well suitable product for the proposed modeling.
{"title":"Modeling for engineering processes in integrated robot definition","authors":"L. Horváth, I. Rudas","doi":"10.1109/RAAD.2010.5524553","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524553","url":null,"abstract":"Engineering in product definition traditionally concentrates on building structures of parts and assemblies. Other objects such as analysis results, manufacturing methods, and equipment control programs are mapped to part and assembly definitions. This style of engineering has been realized in model and simulation based product development. Product data management systems as extensions to product modeling and simulation systems were forced to apply engineering process definition for organization of group work. Some drawback of the above modeling motivated the authors to define an additional content based extension to current product modeling and simulation for entities of human intent, engineering objectives and decisions. In this paper, the authors analyze characteristics the above process elements and features and define typical engineering processes. Problems with the currently applied product model and an earlier proposed solution by the application of information content based product model extension are introduced. Following this, four typical information content based engineering processes are explained. Finally, robot system is characterized together with its environmental model as a well suitable product for the proposed modeling.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"09 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":"131666283","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.2010.5524570
B. Nemec, Martin Zorko, L. Žlajpah
In the paper we evaluate two learning methods applied to the ball-in-a-cup game. The first approach is based on imitation learning. The captured trajectory was encoded with Dynamic motion primitives (DMP). The DMP approach allows simple adaptation of the demonstrated trajectory to the robot dynamics. In the second approach, we use reinforcement learning, which allows learning without any previous knowledge of the system or the environment. In contrast to the majority of the previous attempts, we used SASRA learning algorithm. Experimental results for both cases were performed on Mitsubishi PA10 robot arm.
{"title":"Learning of a ball-in-a-cup playing robot","authors":"B. Nemec, Martin Zorko, L. Žlajpah","doi":"10.1109/RAAD.2010.5524570","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524570","url":null,"abstract":"In the paper we evaluate two learning methods applied to the ball-in-a-cup game. The first approach is based on imitation learning. The captured trajectory was encoded with Dynamic motion primitives (DMP). The DMP approach allows simple adaptation of the demonstrated trajectory to the robot dynamics. In the second approach, we use reinforcement learning, which allows learning without any previous knowledge of the system or the environment. In contrast to the majority of the previous attempts, we used SASRA learning algorithm. Experimental results for both cases were performed on Mitsubishi PA10 robot arm.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"21 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":"128459931","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：