Pub Date : 1996-10-09DOI: 10.1109/EURBOT.1996.551880
G. Lindstedt
This paper describes the use of arbitrarily chosen transmission signals (e.g. frequency sweeps) in a pulse-echo sonar system. An experimental platform has been built where software generated signals can be loaded into a transmission unit and echoes can be sampled and analyzed by the software. The current experiments utilizes electrostatic transducer elements. The multi-frequency measurement methods in sonar systems gives a much larger statistical material than those using a single frequency. Standing wave phenomena that may result in a zero amplitude at a certain frequency and distance do not deteriorate the measurement since the frequency is varied. Multi-frequency methods can be applied to pure distance measurements as well as to more complicated tasks. An experiment where the system is used for recognition is described.
{"title":"Recognition using frequency sweep sonar","authors":"G. Lindstedt","doi":"10.1109/EURBOT.1996.551880","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551880","url":null,"abstract":"This paper describes the use of arbitrarily chosen transmission signals (e.g. frequency sweeps) in a pulse-echo sonar system. An experimental platform has been built where software generated signals can be loaded into a transmission unit and echoes can be sampled and analyzed by the software. The current experiments utilizes electrostatic transducer elements. The multi-frequency measurement methods in sonar systems gives a much larger statistical material than those using a single frequency. Standing wave phenomena that may result in a zero amplitude at a certain frequency and distance do not deteriorate the measurement since the frequency is varied. Multi-frequency methods can be applied to pure distance measurements as well as to more complicated tasks. An experiment where the system is used for recognition is described.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"127 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130446122","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551890
F. Marchese
Cellular automata model is a powerful instrument used in many applications. In this paper we present an algorithm based on cellular automata for the path planning of a simple rigid body in a planar workspace with obstacles well known a priori. The environment model is realized with a regular decomposition in cells of predefined regular shape. The object has an orientation and has the limitation of moving forward on a smoothed trajectory without stopping and turning in place and with a minimum radius of curvature. We have implemented different versions of the algorithm, showing different properties of the model. The method is illustrated on examples with different characteristics to demonstrate the possibility of use on a real robot in a real environment.
{"title":"Cellular automata in robot path planning","authors":"F. Marchese","doi":"10.1109/EURBOT.1996.551890","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551890","url":null,"abstract":"Cellular automata model is a powerful instrument used in many applications. In this paper we present an algorithm based on cellular automata for the path planning of a simple rigid body in a planar workspace with obstacles well known a priori. The environment model is realized with a regular decomposition in cells of predefined regular shape. The object has an orientation and has the limitation of moving forward on a smoothed trajectory without stopping and turning in place and with a minimum radius of curvature. We have implemented different versions of the algorithm, showing different properties of the model. The method is illustrated on examples with different characteristics to demonstrate the possibility of use on a real robot in a real environment.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123171212","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551894
S. J. Vestli, N. Tschichold-Gurman
This paper describes the new mobile post system (MOPS) developed at the Institute of Robotics, Swiss Federal Institute of Technology. This mobile service robot operates in a building containing several research institutes and various other institutions. The MOPS has the task of distributing the incoming mail (letters and small parcels collected in boxes) from a central post station to the various institutes and to collect the outgoing mail from the said institutes on its return journey back to the central post station. In this paper we describe the task in detail as well as our solutions to such diverse problems as: collision free and robust navigation, position update, position control, communication with building infrastructure, range sensing and mobile manipulation. The MOPS is currently undergoing extensive field testing.
{"title":"MOPS, a system for mail distribution in office type buildings","authors":"S. J. Vestli, N. Tschichold-Gurman","doi":"10.1109/EURBOT.1996.551894","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551894","url":null,"abstract":"This paper describes the new mobile post system (MOPS) developed at the Institute of Robotics, Swiss Federal Institute of Technology. This mobile service robot operates in a building containing several research institutes and various other institutions. The MOPS has the task of distributing the incoming mail (letters and small parcels collected in boxes) from a central post station to the various institutes and to collect the outgoing mail from the said institutes on its return journey back to the central post station. In this paper we describe the task in detail as well as our solutions to such diverse problems as: collision free and robust navigation, position update, position control, communication with building infrastructure, range sensing and mobile manipulation. The MOPS is currently undergoing extensive field testing.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131291308","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551893
D.C. van Oosten, L.F.J. Nijenhuis, A. Bakkers, W. Vervoort
This paper describes a part of the development of an adaptive autonomous machine that is able to move in an unknown world extract knowledge out of the perceived data, has the possibility to reason, and finally has the capability to exchange experiences and knowledge with other agents. The agent is not pre-programmed by its designer but was given simple rules of life, i.e. what is good and what is bad. By evaluating its sensor inputs these rules of life were transformed into a rule based reactive system. Simulations of the system showed that the agent is able to learn by its own experience. By representing the learned knowledge in an appropriate way, the acquired knowledge could be judged on its effectiveness and also this knowledge could be shared with other, less experienced agents.
{"title":"ADAM: adaptive autonomous machine","authors":"D.C. van Oosten, L.F.J. Nijenhuis, A. Bakkers, W. Vervoort","doi":"10.1109/EURBOT.1996.551893","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551893","url":null,"abstract":"This paper describes a part of the development of an adaptive autonomous machine that is able to move in an unknown world extract knowledge out of the perceived data, has the possibility to reason, and finally has the capability to exchange experiences and knowledge with other agents. The agent is not pre-programmed by its designer but was given simple rules of life, i.e. what is good and what is bad. By evaluating its sensor inputs these rules of life were transformed into a rule based reactive system. Simulations of the system showed that the agent is able to learn by its own experience. By representing the learned knowledge in an appropriate way, the acquired knowledge could be judged on its effectiveness and also this knowledge could be shared with other, less experienced agents.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"15 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132264213","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551877
G. Tascini, P. Zingaretti, G. Conte, S. Zanoli
The application described here concerns the detection and the real-time tracking of submarine pipelines from a sequence of underwater images acquired from TV-cameras mounted on a remote operated vehicle (ROV). The problem involves both perception and robotics, in that sensory-motion data are to be acquired and dynamically used for subsequent actions by the system. The basic processing concerns the extraction of the pipe contours which are returned as two straight lines. Motion effects on acquired images have been reduced using a Kalman filter for integrating multiple measurements over time. The filter, positioned at the output of the image processing system improves the precision in the computation of the straight line equations with a little overload. This work is originated from the interest of Snamprogetti in enhancing the level of automation in submarine pipeline inspection.
{"title":"Perception of an underwater structure for inspection and guidance purpose","authors":"G. Tascini, P. Zingaretti, G. Conte, S. Zanoli","doi":"10.1109/EURBOT.1996.551877","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551877","url":null,"abstract":"The application described here concerns the detection and the real-time tracking of submarine pipelines from a sequence of underwater images acquired from TV-cameras mounted on a remote operated vehicle (ROV). The problem involves both perception and robotics, in that sensory-motion data are to be acquired and dynamically used for subsequent actions by the system. The basic processing concerns the extraction of the pipe contours which are returned as two straight lines. Motion effects on acquired images have been reduced using a Kalman filter for integrating multiple measurements over time. The filter, positioned at the output of the image processing system improves the precision in the computation of the straight line equations with a little overload. This work is originated from the interest of Snamprogetti in enhancing the level of automation in submarine pipeline inspection.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"45 10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114303574","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551875
M. Piaggio, A. Sgorbissa, Gianni Vercelli, R. Zaccaria
The task of moving a robot in a complex and totally or partially unknown environment involves the construction of a suitable representation of the robot's surroundings. This paper proposes an analogical statistical representation of the world the robot moves in. Its construction, updating and usage is described, focusing on the techniques used for the integration of sensor data and on their fusion with a priori information about the environment. An additional mechanism that allows the map to be efficiently transmitted to a remote workstation, connected using a radio link, has also been envisaged. Thus the computational load of map related processes can be distributed, taking advantage of the remote station's computational power. The experimental setup and some results obtained are also illustrated.
{"title":"Fusion of sensor data in a dynamic representation","authors":"M. Piaggio, A. Sgorbissa, Gianni Vercelli, R. Zaccaria","doi":"10.1109/EURBOT.1996.551875","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551875","url":null,"abstract":"The task of moving a robot in a complex and totally or partially unknown environment involves the construction of a suitable representation of the robot's surroundings. This paper proposes an analogical statistical representation of the world the robot moves in. Its construction, updating and usage is described, focusing on the techniques used for the integration of sensor data and on their fusion with a priori information about the environment. An additional mechanism that allows the map to be efficiently transmitted to a remote workstation, connected using a radio link, has also been envisaged. Thus the computational load of map related processes can be distributed, taking advantage of the remote station's computational power. The experimental setup and some results obtained are also illustrated.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131702782","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551889
G. Bianco, R. Cassinis
The paper presents a proposal for an autonomous robot path planning system that uses several strategies to reach a target also in an a-priori unknown environment. The proposed method has learning capabilities that allow the robot to take advantage of previous experience, thus improving its performance during successive traveling in the same environment. The proposed multistrategic approach has been tested both on a software simulator and on a real robot.
{"title":"Multi-strategic approach for robot path planning","authors":"G. Bianco, R. Cassinis","doi":"10.1109/EURBOT.1996.551889","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551889","url":null,"abstract":"The paper presents a proposal for an autonomous robot path planning system that uses several strategies to reach a target also in an a-priori unknown environment. The proposed method has learning capabilities that allow the robot to take advantage of previous experience, thus improving its performance during successive traveling in the same environment. The proposed multistrategic approach has been tested both on a software simulator and on a real robot.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"58 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114940139","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.552018
T. Frohlinghaus, J. Buhmann
The performance of a mobile robot crucially depends on the accuracy, duration and reliability of its sensor interpretation. A major source of information are CCD-cameras which provide a detailed view of the robot's environment. This paper presents a real-time stereo algorithm implemented on the mobile robot RHINO of the University of Bonn. The algorithm exploit the phases of wavelet-filtered image pairs to localize edges and to estimate their disparities with subpixel accuracy. The disparities are computed by an initial search for corresponding points within a given interval and a subsequent measurement of phase-differences. The real-time constraints of autonomous object detection and navigation are fulfilled by partially implementing the stereo algorithm on a pipeline computer Datacube. Experimental results on real world scenes under real world conditions demonstrate the stereo algorithm's robustness and suitability for autonomous robot applications.
{"title":"Real-time phase-based stereo for a mobile robot","authors":"T. Frohlinghaus, J. Buhmann","doi":"10.1109/EURBOT.1996.552018","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.552018","url":null,"abstract":"The performance of a mobile robot crucially depends on the accuracy, duration and reliability of its sensor interpretation. A major source of information are CCD-cameras which provide a detailed view of the robot's environment. This paper presents a real-time stereo algorithm implemented on the mobile robot RHINO of the University of Bonn. The algorithm exploit the phases of wavelet-filtered image pairs to localize edges and to estimate their disparities with subpixel accuracy. The disparities are computed by an initial search for corresponding points within a given interval and a subsequent measurement of phase-differences. The real-time constraints of autonomous object detection and navigation are fulfilled by partially implementing the stereo algorithm on a pipeline computer Datacube. Experimental results on real world scenes under real world conditions demonstrate the stereo algorithm's robustness and suitability for autonomous robot applications.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116298293","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551882
Jens-Steffen Gutmann, Christian Schlegel
This paper describes results from evaluating different self-localization approaches in indoor environments for mobile robots. The algorithms examined are based on 2D laser scans and an odometry position estimate and do not need any modifications in the environment. An important requirement for the self-localization is the ability to cope with office-like environments as well as with environments without orthogonal and rectilinear walls. Furthermore, the approaches have to be robust enough to cope with slight modifications in the daily environment and should be fast enough to be used online on board of the robot system. To fulfil these requirements we made some extensions to the existing approaches and combined them in a suitable manner. Real world experiments with our robot within the everyday environment of our institute show that the position error can be kept small enough to perform navigation tasks.
{"title":"AMOS: comparison of scan matching approaches for self-localization in indoor environments","authors":"Jens-Steffen Gutmann, Christian Schlegel","doi":"10.1109/EURBOT.1996.551882","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551882","url":null,"abstract":"This paper describes results from evaluating different self-localization approaches in indoor environments for mobile robots. The algorithms examined are based on 2D laser scans and an odometry position estimate and do not need any modifications in the environment. An important requirement for the self-localization is the ability to cope with office-like environments as well as with environments without orthogonal and rectilinear walls. Furthermore, the approaches have to be robust enough to cope with slight modifications in the daily environment and should be fast enough to be used online on board of the robot system. To fulfil these requirements we made some extensions to the existing approaches and combined them in a suitable manner. Real world experiments with our robot within the everyday environment of our institute show that the position error can be kept small enough to perform navigation tasks.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128221835","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 : 1996-10-09DOI: 10.1109/EURBOT.1996.551886
R. M. Rylatt, C. Czarnecki, T. Routen
The relatively new idea of decomposing the intelligent agent problem into behaviours rather than cognitive functions has had early success but doubts have arisen concerning the validity of its basic building blocks. It may still be worth retaining the idea that intelligent behaviour can be achieved through the accretion of modules each having a tight loop between perception and action but modules based on neural networks may have more potential. One approach that has been demonstrated is to train each module to achieve ifs individual competence. But although explicit teaching may play a part, a more interesting approach is to allow the agent to learn behaviours by interacting directly with the task environment. This paper presents a modular neural net architecture CRILL for the autonomous control of a mobile agent using a form of reinforcement learning. An experiment is described in which CRILL navigates through a simulated environment by seeking a series of light sources. The potential of the CRILL approach is assessed as a way of decomposing a complex goal and simplifying the construction of individual neural nets.
{"title":"Learning behaviours in a modular neural net architecture for a mobile autonomous agent","authors":"R. M. Rylatt, C. Czarnecki, T. Routen","doi":"10.1109/EURBOT.1996.551886","DOIUrl":"https://doi.org/10.1109/EURBOT.1996.551886","url":null,"abstract":"The relatively new idea of decomposing the intelligent agent problem into behaviours rather than cognitive functions has had early success but doubts have arisen concerning the validity of its basic building blocks. It may still be worth retaining the idea that intelligent behaviour can be achieved through the accretion of modules each having a tight loop between perception and action but modules based on neural networks may have more potential. One approach that has been demonstrated is to train each module to achieve ifs individual competence. But although explicit teaching may play a part, a more interesting approach is to allow the agent to learn behaviours by interacting directly with the task environment. This paper presents a modular neural net architecture CRILL for the autonomous control of a mobile agent using a form of reinforcement learning. An experiment is described in which CRILL navigates through a simulated environment by seeking a series of light sources. The potential of the CRILL approach is assessed as a way of decomposing a complex goal and simplifying the construction of individual neural nets.","PeriodicalId":136786,"journal":{"name":"Proceedings of the First Euromicro Workshop on Advanced Mobile Robots (EUROBOT '96)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1996-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127560920","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：