Pub Date : 2010-06-24DOI: 10.1109/RAAD.2010.5524559
N. Ivanescu, L. Ciupitu
A new method in medicine for detecting and investigating the illness like breast cancer is the Infrared Thermographic Imaging. An infrared thermal camera takes a temperature map of human body. The exact localization of specific areas from 2-dimensions thermal map is difficult and implies an invasive intervention of medicine doctors. In order to automate this process a special scanner for acquire a 4-dimensions map is used and consist of the 3-D scanner and the temperature sensor. In present paper an example of acquisitions the 4-D temperature map in the breast region is presented.
{"title":"Vision system for human body infrared thermography","authors":"N. Ivanescu, L. Ciupitu","doi":"10.1109/RAAD.2010.5524559","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524559","url":null,"abstract":"A new method in medicine for detecting and investigating the illness like breast cancer is the Infrared Thermographic Imaging. An infrared thermal camera takes a temperature map of human body. The exact localization of specific areas from 2-dimensions thermal map is difficult and implies an invasive intervention of medicine doctors. In order to automate this process a special scanner for acquire a 4-dimensions map is used and consist of the 3-D scanner and the temperature sensor. In present paper an example of acquisitions the 4-D temperature map in the breast region is presented.","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":"116935957","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.2010.5524578
W. Wohlkinger, M. Vincze
Building knowledge for robots can be tedious, especially if focused on object class recognition in home environments where hundreds of everyday-objects - some with a huge intra class variability - can be found. Object recognition and especially object class recognition is a key capability in home-robotics. Achieving deployable results from state-of-.the-art algorithms is not yet achievable when the number of classes increases and near real-time is the goal. Hence, we propose to exploit contextual knowledge by using sensor and hardware constraints from the robotics and home domains and show how to use the internet as a source for obtaining the required data for building a fast, vision based object categorization system for robotics. In this paper, we give an overview of the available constraints and advantages of using a robot to set priors for object classification and propose a system which covers automated model acquisition from the web, domain simulation, descriptor generation, 3D data processing from dense stereo and classification for a - not too far - robot scenario in an internet-connected home-environment. In this work we show that this system is capable of being used in home robotics in a fast and robust way for recognition of object classes commonly found in such environments, including but not limited to chairs and mugs. We also discuss challenges and missing pieces in the framework and useful extensions.
{"title":"3D object classification for mobile robots in home-environments using web-data","authors":"W. Wohlkinger, M. Vincze","doi":"10.1109/RAAD.2010.5524578","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524578","url":null,"abstract":"Building knowledge for robots can be tedious, especially if focused on object class recognition in home environments where hundreds of everyday-objects - some with a huge intra class variability - can be found. Object recognition and especially object class recognition is a key capability in home-robotics. Achieving deployable results from state-of-.the-art algorithms is not yet achievable when the number of classes increases and near real-time is the goal. Hence, we propose to exploit contextual knowledge by using sensor and hardware constraints from the robotics and home domains and show how to use the internet as a source for obtaining the required data for building a fast, vision based object categorization system for robotics. In this paper, we give an overview of the available constraints and advantages of using a robot to set priors for object classification and propose a system which covers automated model acquisition from the web, domain simulation, descriptor generation, 3D data processing from dense stereo and classification for a - not too far - robot scenario in an internet-connected home-environment. In this work we show that this system is capable of being used in home robotics in a fast and robust way for recognition of object classes commonly found in such environments, including but not limited to chairs and mugs. We also discuss challenges and missing pieces in the framework and useful extensions.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"10 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":"117349130","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.2010.5524581
N. Belfiore, P. Di Giamberardino, I. Rudas, M. Verotti
The present investigation is dedicated to the study of the static balance at the tip of a planar RR robot. For this case, a configuration can be interpreted, in the static sense, as isotropic when any force applied to the robot wrist yields a small displacement which is theoretically parallel to the applied force (no matter how the force is directed on the plane). This characteristic offers many advantages and is considered as an optimal design goal. Unfortunately, the conditions to achieve such property in RR manipulators are very restrictive, and until now, only one solution is adopted, with a fixed lengths ratio. The present paper reveals how any RR planar robot can achieve isotropy at the tip by using a feedback action at the joints to gain arbitrary elastic coefficients. The new approach of design brings to less restrictive conditions than the previous ones.
{"title":"Isotropy in any RR planar dyad under active joint stiffness regulation","authors":"N. Belfiore, P. Di Giamberardino, I. Rudas, M. Verotti","doi":"10.1109/RAAD.2010.5524581","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524581","url":null,"abstract":"The present investigation is dedicated to the study of the static balance at the tip of a planar RR robot. For this case, a configuration can be interpreted, in the static sense, as isotropic when any force applied to the robot wrist yields a small displacement which is theoretically parallel to the applied force (no matter how the force is directed on the plane). This characteristic offers many advantages and is considered as an optimal design goal. Unfortunately, the conditions to achieve such property in RR manipulators are very restrictive, and until now, only one solution is adopted, with a fixed lengths ratio. The present paper reveals how any RR planar robot can achieve isotropy at the tip by using a feedback action at the joints to gain arbitrary elastic coefficients. The new approach of design brings to less restrictive conditions than the previous ones.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"134 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":"114696390","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.2010.5524615
J. Somló, József Molnár
At the practical application of robots, the part processing time has a key role. The part processing time is an idea borrowed from manufacturing technology. In robotics it mostly means that the robots tool-centre point should go along some given path and the tool orientation in every point should also have the given values. These two requirements have to be satisfied at the same time. In the present paper we propose a method which provides the motion in every point of the path with the possible maximum velocity. In fact, we divide the path to transient and cruising parts and require the maximum velocities only for this second part. The given motion is called “Time-optimal cruising motion”. We demonstrate on an example the simplicity of the approach. Using the parametric method of motion planning, we give the equations for determining time-optimal motions. Not only the translation motions of tool-centre points but, also the orientation motions of tools may be optimally planned. The time-optimal motion planning is also possible for free paths (PTP motions). A general approach for this problem is proposed, too. In the paper, some parts are devoted to the deeper understanding of the optimization problems.
{"title":"Time-optimal motion planning for robots","authors":"J. Somló, József Molnár","doi":"10.1109/RAAD.2010.5524615","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524615","url":null,"abstract":"At the practical application of robots, the part processing time has a key role. The part processing time is an idea borrowed from manufacturing technology. In robotics it mostly means that the robots tool-centre point should go along some given path and the tool orientation in every point should also have the given values. These two requirements have to be satisfied at the same time. In the present paper we propose a method which provides the motion in every point of the path with the possible maximum velocity. In fact, we divide the path to transient and cruising parts and require the maximum velocities only for this second part. The given motion is called “Time-optimal cruising motion”. We demonstrate on an example the simplicity of the approach. Using the parametric method of motion planning, we give the equations for determining time-optimal motions. Not only the translation motions of tool-centre points but, also the orientation motions of tools may be optimally planned. The time-optimal motion planning is also possible for free paths (PTP motions). A general approach for this problem is proposed, too. In the paper, some parts are devoted to the deeper understanding of the optimization problems.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"3 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":"124450432","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.2010.5524582
C. di Castri, A. Messina
This paper introduces two analytical matrix descriptions of the differential eigenvalue problem concerning each admissible posture of a two-link flexible manipulator. In the hypothesis of the Euler-Bernoulli beam theory, analytical natural frequencies and mode shapes are derived through both formulations, which are obtained according to an axial and transverse dynamic characterization of the manipulator links. As is demonstrated by several simulations, such formulations give identical analytical results, though having very different matrix structures. Moreover, additional simulations through a finite element package confirm the analytical predictions of both methods presented herein.
{"title":"Matrix formulations for solving the configuration-dependent eigenvalue problem of a two-link flexible manipulator","authors":"C. di Castri, A. Messina","doi":"10.1109/RAAD.2010.5524582","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524582","url":null,"abstract":"This paper introduces two analytical matrix descriptions of the differential eigenvalue problem concerning each admissible posture of a two-link flexible manipulator. In the hypothesis of the Euler-Bernoulli beam theory, analytical natural frequencies and mode shapes are derived through both formulations, which are obtained according to an axial and transverse dynamic characterization of the manipulator links. As is demonstrated by several simulations, such formulations give identical analytical results, though having very different matrix structures. Moreover, additional simulations through a finite element package confirm the analytical predictions of both methods presented herein.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"13 5-6","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2010-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132757840","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.2010.5524546
C. Dragos, S. Preitl, R. Precup, D. Pirlea, C.-S. Nes, E. Petriu, C. Pozna
The paper presents aspects concerning the modeling and driving scenarios of a class of vehicular power train systems. The modeling includes an analysis of the system components which include the spark-ignition internal combustion engine, the torque converter, the metal V-belt type continuously variable transmission and the wheels. Four driving scenarios are illustrated by digital simulation results: acceleration, overtaking maneuver, ramp encounter and engine brake.
{"title":"Modeling of a vehicle with continuously variable transmission","authors":"C. Dragos, S. Preitl, R. Precup, D. Pirlea, C.-S. Nes, E. Petriu, C. Pozna","doi":"10.1109/RAAD.2010.5524546","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524546","url":null,"abstract":"The paper presents aspects concerning the modeling and driving scenarios of a class of vehicular power train systems. The modeling includes an analysis of the system components which include the spark-ignition internal combustion engine, the torque converter, the metal V-belt type continuously variable transmission and the wheels. Four driving scenarios are illustrated by digital simulation results: acceleration, overtaking maneuver, ramp encounter and engine brake.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"30 6 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":"133114486","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.2010.5524584
K. Jezernik, A. Hace
The hybrid systems contain two distinct types of components, subsystem with continuous dynamics and subsystem with discrete dynamics that interact with each other. Such hybrid systems arise in varied contexts in manufacturing, communication networks, auto-pilot design, and traffic control and in robotics and mechatronics, among others. Hybrid systems have a central role in embedded control systems that interact with the physical world. They also arise from the hierarchical organization of complex systems and from the interaction of discrete planning algorithms and continuous control algorithms in autonomous, intelligent systems. The experimental results demonstrate the efficiency of the hybrid approach for the bilateral control of a 1-DOF master-slave teleoperation.
{"title":"Hybrid system for event-based planning and control of robot operation","authors":"K. Jezernik, A. Hace","doi":"10.1109/RAAD.2010.5524584","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524584","url":null,"abstract":"The hybrid systems contain two distinct types of components, subsystem with continuous dynamics and subsystem with discrete dynamics that interact with each other. Such hybrid systems arise in varied contexts in manufacturing, communication networks, auto-pilot design, and traffic control and in robotics and mechatronics, among others. Hybrid systems have a central role in embedded control systems that interact with the physical world. They also arise from the hierarchical organization of complex systems and from the interaction of discrete planning algorithms and continuous control algorithms in autonomous, intelligent systems. The experimental results demonstrate the efficiency of the hybrid approach for the bilateral control of a 1-DOF master-slave teleoperation.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"42 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":"116287611","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.2010.5524544
W. Kowalczyk, K. Kozlowski, J. Tar
In the paper trajectory tracking algorithm including collision avoidance behaviour is presented. Dynamic properties of the robots are taken into account. Obstacles are assumed to be convex. Artificial potential functions (APF) are used to avoid collisions between robots and with static obstacles in the environment. Stability proof for the presented algorithm is shown and simulation results are presented to illustrate effectiveness of the algorithm.
{"title":"Trajectory tracking for multiple unicycles in the environment with obstacles","authors":"W. Kowalczyk, K. Kozlowski, J. Tar","doi":"10.1109/RAAD.2010.5524544","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524544","url":null,"abstract":"In the paper trajectory tracking algorithm including collision avoidance behaviour is presented. Dynamic properties of the robots are taken into account. Obstacles are assumed to be convex. Artificial potential functions (APF) are used to avoid collisions between robots and with static obstacles in the environment. Stability proof for the presented algorithm is shown and simulation results are presented to illustrate effectiveness of the algorithm.","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":"128916247","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.2010.5524589
A. Popa, M. Popa, M. Marcu
The mobile robots have received considerable attention in the scientific literature. One of the fundamental problems in mobile robotics is motion planning. Motion planning has several constraints, such as: knowledge of the scene, the existence of obstacles, their dimensions, the types of obstacles (static or dynamic), and the metric under consideration. Many existent solutions are based on cell decomposition of the scene. The cells are either free either occupied with an obstacle. The solutions are obtained based on graphs or exploration matrices. This paper presents an application for planning the motion of a wheeled robot in a delimited space. The robot has also the role to acquire information from the scene and send them to the user. The plane of the scene is specified by the user in a file with a certain format and the robot motion is represented in real-time.
{"title":"Motion planning for a mobile robot","authors":"A. Popa, M. Popa, M. Marcu","doi":"10.1109/RAAD.2010.5524589","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524589","url":null,"abstract":"The mobile robots have received considerable attention in the scientific literature. One of the fundamental problems in mobile robotics is motion planning. Motion planning has several constraints, such as: knowledge of the scene, the existence of obstacles, their dimensions, the types of obstacles (static or dynamic), and the metric under consideration. Many existent solutions are based on cell decomposition of the scene. The cells are either free either occupied with an obstacle. The solutions are obtained based on graphs or exploration matrices. This paper presents an application for planning the motion of a wheeled robot in a delimited space. The robot has also the role to acquire information from the scene and send them to the user. The plane of the scene is specified by the user in a file with a certain format and the robot motion is represented in real-time.","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":"130505670","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.2010.5524569
C. Pozna, R. Precup, N. Minculete, C. Antonya, C. Dragos
The paper formulates properties derived from the definitions of classes, subclasses and objects which represent the core of an abstraction model. The abstraction model is characterized by knowledge energy, Shannon entropy and knowledge temperature. The application of the theoretical results is illustrated by a case study.
{"title":"Properties of classes, subclasses and objects in an abstraction model","authors":"C. Pozna, R. Precup, N. Minculete, C. Antonya, C. Dragos","doi":"10.1109/RAAD.2010.5524569","DOIUrl":"https://doi.org/10.1109/RAAD.2010.5524569","url":null,"abstract":"The paper formulates properties derived from the definitions of classes, subclasses and objects which represent the core of an abstraction model. The abstraction model is characterized by knowledge energy, Shannon entropy and knowledge temperature. The application of the theoretical results is illustrated by a case study.","PeriodicalId":104308,"journal":{"name":"19th International Workshop on Robotics in Alpe-Adria-Danube Region (RAAD 2010)","volume":"2 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":"123864526","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：