Pub Date : 1994-09-12DOI: 10.1109/IROS.1994.407647
S. Dubowsky, W. Durfee, Thomas Corrigan, Andrew Kuklinski, U. Müller
The dynamic interaction between a space robotic manipulator and its base in micro-gravity can make it difficult to control and lead to system performance degradation. Control and planning algorithms proposed in the past to compensate for this dynamic interaction have lacked sufficient experimental evaluation. A laboratory test bed is described which was developed and built to emulate the dynamic behavior of space robotic systems and investigate proposed planning and control algorithms. Two methods for removing the effects of gravity in the laboratory are presented. Experimental results demonstrate the effectiveness of this test bed in studying the dynamic coupling between a space manipulator and its spacecraft.<>
{"title":"A laboratory test bed for space robotics: the VES II","authors":"S. Dubowsky, W. Durfee, Thomas Corrigan, Andrew Kuklinski, U. Müller","doi":"10.1109/IROS.1994.407647","DOIUrl":"https://doi.org/10.1109/IROS.1994.407647","url":null,"abstract":"The dynamic interaction between a space robotic manipulator and its base in micro-gravity can make it difficult to control and lead to system performance degradation. Control and planning algorithms proposed in the past to compensate for this dynamic interaction have lacked sufficient experimental evaluation. A laboratory test bed is described which was developed and built to emulate the dynamic behavior of space robotic systems and investigate proposed planning and control algorithms. Two methods for removing the effects of gravity in the laboratory are presented. Experimental results demonstrate the effectiveness of this test bed in studying the dynamic coupling between a space manipulator and its spacecraft.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568606","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 : 1994-09-12DOI: 10.1109/IROS.1994.407572
Jörg-Michael Hasemann
New concepts for robot control architectures are presented. Special emphasis is put on planning and monitoring for task level control tasks. New features introduced are behaviour switching, complete monitoring of plan execution and plan validity and rigorous explicit representation of activities and mutual dependencies within plans. The key techniques used to model decision making and plan modification are fuzzy logic and graph grammars. Fuzzy logic is used to guide planning and graph grammars provide the framework for expanding plan components. Moreover, a behaviour switching mechanism is proposed, which allows critical behaviours to interrupt or abandon a current less critical behaviour.<>
{"title":"A robot control architecture based on graph grammars and fuzzy logic","authors":"Jörg-Michael Hasemann","doi":"10.1109/IROS.1994.407572","DOIUrl":"https://doi.org/10.1109/IROS.1994.407572","url":null,"abstract":"New concepts for robot control architectures are presented. Special emphasis is put on planning and monitoring for task level control tasks. New features introduced are behaviour switching, complete monitoring of plan execution and plan validity and rigorous explicit representation of activities and mutual dependencies within plans. The key techniques used to model decision making and plan modification are fuzzy logic and graph grammars. Fuzzy logic is used to guide planning and graph grammars provide the framework for expanding plan components. Moreover, a behaviour switching mechanism is proposed, which allows critical behaviours to interrupt or abandon a current less critical behaviour.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116021220","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 : 1994-09-12DOI: 10.1109/IROS.1994.407378
D. Gachet, M. Salichs, L. Moreno, J. Pimentel
We present an implementation of a reinforcement learning algorithm through the use of a special neural network topology, the AHC (adaptive heuristic critic). The AHC is used as a fusion supervisor of primitive behaviors in order to execute more complex robot behaviors, for example go to goal, surveillance or follow a path. The fusion supervisor is part of an architecture for the execution of mobile robot tasks which are composed of several primitive behaviors which act in a simultaneous or concurrent fashion. The architecture allows for learning to take place at the execution level, it incorporates the experience gained in executing primitive behaviors as well as the overall task. The implementation of this autonomous learning approach has been tested within OPMOR, a simulation environment for mobile robots and with our mobile platform, the UPM Robuter. Both, simulated and actual results are presented. The performance of the AHC neural network is adequate. Portions of this work has been implemented within the EEC ESPRIT 2483 PANORAMA Project.<>
{"title":"Learning emergent tasks for an autonomous mobile robot","authors":"D. Gachet, M. Salichs, L. Moreno, J. Pimentel","doi":"10.1109/IROS.1994.407378","DOIUrl":"https://doi.org/10.1109/IROS.1994.407378","url":null,"abstract":"We present an implementation of a reinforcement learning algorithm through the use of a special neural network topology, the AHC (adaptive heuristic critic). The AHC is used as a fusion supervisor of primitive behaviors in order to execute more complex robot behaviors, for example go to goal, surveillance or follow a path. The fusion supervisor is part of an architecture for the execution of mobile robot tasks which are composed of several primitive behaviors which act in a simultaneous or concurrent fashion. The architecture allows for learning to take place at the execution level, it incorporates the experience gained in executing primitive behaviors as well as the overall task. The implementation of this autonomous learning approach has been tested within OPMOR, a simulation environment for mobile robots and with our mobile platform, the UPM Robuter. Both, simulated and actual results are presented. The performance of the AHC neural network is adequate. Portions of this work has been implemented within the EEC ESPRIT 2483 PANORAMA Project.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116347463","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 : 1994-09-12DOI: 10.1109/IROS.1994.407440
W. Rencken
A mobile robot operating autonomously in unknown, unstructured environments has to be able to map its environment while at the same time determining its own position accurately within this environment. This paper presents an approach where the bootstrapping problem of concurrent localisation and map building is solved by estimating the respective errors introduced by each of the processes and correcting them accordingly. The success of this approach also hinges on the ability to determine which measurement originates from which feature. A heuristic multiple hypothesis data association framework is developed to deal with this problem. The problems encountered with the implementation of the algorithms on the mobile robot ROAMER are discussed. Real experiments in typical office environments have shown that the robot is able to navigate autonomously in such indoor environments.<>
{"title":"Autonomous sonar navigation in indoor, unknown and unstructured environments","authors":"W. Rencken","doi":"10.1109/IROS.1994.407440","DOIUrl":"https://doi.org/10.1109/IROS.1994.407440","url":null,"abstract":"A mobile robot operating autonomously in unknown, unstructured environments has to be able to map its environment while at the same time determining its own position accurately within this environment. This paper presents an approach where the bootstrapping problem of concurrent localisation and map building is solved by estimating the respective errors introduced by each of the processes and correcting them accordingly. The success of this approach also hinges on the ability to determine which measurement originates from which feature. A heuristic multiple hypothesis data association framework is developed to deal with this problem. The problems encountered with the implementation of the algorithms on the mobile robot ROAMER are discussed. Real experiments in typical office environments have shown that the robot is able to navigate autonomously in such indoor environments.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114139827","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 : 1994-09-12DOI: 10.1109/IROS.1994.407400
J. Borenstein
This paper presents an innovative method for accurate mobile robot dead-reckoning, called internal position error correction (IPEC). In previous work, the IPEC method was successfully implemented on a specially designed mobile robot with two differential drive axles, called the multi-degree-of-freedom (MDOF) mobile robot. Experimental results with the MDOF robot showed consistently one to two orders of magnitude better dead-reckoning accuracy than systems based on conventional dead-reckoning. Yet, the IPEC system requires neither external references (such as navigation beacons, artificial landmarks, known floorplans, or satellite signals), nor inertial navigation aids (such as accelerometers or gyros). This paper focuses on our current efforts to implement the IPEC method on a device that can be added to any existing mobile robot. This device, called the "Smart Encoder Trailer" (SET), is a small, single-axle trailer with an incremental encoder on each of its two wheels. Although the SET is not functional yet, simulation results combined with experimental results from the (similarly configured) MDOF vehicle strongly suggest the feasibility of the SET implementation.<>
{"title":"Internal correction of dead-reckoning errors with the smart encoder trailer","authors":"J. Borenstein","doi":"10.1109/IROS.1994.407400","DOIUrl":"https://doi.org/10.1109/IROS.1994.407400","url":null,"abstract":"This paper presents an innovative method for accurate mobile robot dead-reckoning, called internal position error correction (IPEC). In previous work, the IPEC method was successfully implemented on a specially designed mobile robot with two differential drive axles, called the multi-degree-of-freedom (MDOF) mobile robot. Experimental results with the MDOF robot showed consistently one to two orders of magnitude better dead-reckoning accuracy than systems based on conventional dead-reckoning. Yet, the IPEC system requires neither external references (such as navigation beacons, artificial landmarks, known floorplans, or satellite signals), nor inertial navigation aids (such as accelerometers or gyros). This paper focuses on our current efforts to implement the IPEC method on a device that can be added to any existing mobile robot. This device, called the \"Smart Encoder Trailer\" (SET), is a small, single-axle trailer with an incremental encoder on each of its two wheels. Although the SET is not functional yet, simulation results combined with experimental results from the (similarly configured) MDOF vehicle strongly suggest the feasibility of the SET implementation.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114163382","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 : 1994-09-12DOI: 10.1109/IROS.1994.407617
A. J. Hendriks, D. Lyons
A robot system operating in an environment in which there is uncertainty and change needs to combine the ability to react with the ability to plan ahead. In a previous paper we proposed a solution to the problems of integrating planning and reaction: cast planning as adaptation of a reactive system. The planner, asynchronously tuning the reactor, decides on the appropriate parts of the reactor to be modified based on perceptions: information gathered in the reactor for the express purpose to inform the planner. In this paper, we show the benefits of using perception to adapt the reactor where it needs to be updated most and present our first experimental results from the planner-reactor architecture.<>
{"title":"Using perception to plan incremental adaptations","authors":"A. J. Hendriks, D. Lyons","doi":"10.1109/IROS.1994.407617","DOIUrl":"https://doi.org/10.1109/IROS.1994.407617","url":null,"abstract":"A robot system operating in an environment in which there is uncertainty and change needs to combine the ability to react with the ability to plan ahead. In a previous paper we proposed a solution to the problems of integrating planning and reaction: cast planning as adaptation of a reactive system. The planner, asynchronously tuning the reactor, decides on the appropriate parts of the reactor to be modified based on perceptions: information gathered in the reactor for the express purpose to inform the planner. In this paper, we show the benefits of using perception to adapt the reactor where it needs to be updated most and present our first experimental results from the planner-reactor architecture.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114186310","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 : 1994-09-12DOI: 10.1109/IROS.1994.407627
Uwe Wienkop, G. Lawitzky, W. Feiten
Autonomous low-cost mobility of robots has been a challenging problem for quite a long time. In this paper the typical problems of sonar based autonomous navigation and the authors' solutions to overcome them are discussed. The authors have created, robust modules for sonar data fusion and safe steering which significantly improve known methods. There are furthermore robot control behaviors which offer specific competence to solve high-level tasks. These behaviors build a hierarchical architecture but have the ability to assess their respective task and autonomously suggest a different, more competent behavior to continue. Thus, the behaviors work together as distributed competencies. The concept described here is being evaluated in a system on the authors' experimental robot ROAMER. The available modules already operate robustly in cluttered office environments.<>
{"title":"Intelligent low-cost mobility","authors":"Uwe Wienkop, G. Lawitzky, W. Feiten","doi":"10.1109/IROS.1994.407627","DOIUrl":"https://doi.org/10.1109/IROS.1994.407627","url":null,"abstract":"Autonomous low-cost mobility of robots has been a challenging problem for quite a long time. In this paper the typical problems of sonar based autonomous navigation and the authors' solutions to overcome them are discussed. The authors have created, robust modules for sonar data fusion and safe steering which significantly improve known methods. There are furthermore robot control behaviors which offer specific competence to solve high-level tasks. These behaviors build a hierarchical architecture but have the ability to assess their respective task and autonomously suggest a different, more competent behavior to continue. Thus, the behaviors work together as distributed competencies. The concept described here is being evaluated in a system on the authors' experimental robot ROAMER. The available modules already operate robustly in cluttered office environments.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114280513","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 : 1994-09-12DOI: 10.1109/IROS.1994.407409
E. Freund, H. Buxbaum
Industrial robots are increasing being applied in production situations of small quantity or single run units. These applications are characterized by a large product variety hence production flexibility is one of the most important requirements for new robot applications. In these applications, the robot must be seen as a single component of a flexible automation system, the robot-based flexible manufacturing work cell. Due to the numerous possible configurations in factories it is necessary to develop application specific modular manufacturing work cells by the usage of different components. Nevertheless it is the goal to standardize the work cell internal information structure, which permits the utilization of standardized control structures. The control components must be adaptable to different work cell configurations. In this paper the universal controller system LUCAS for robot-based flexible manufacturing work cells is described. For verification of the underlying control concepts some example applications in flexible assembly and flexible machining are shown. In addition, prospects for further developments are presented.<>
{"title":"Universal work cell controller-application experiences in flexible manufacturing","authors":"E. Freund, H. Buxbaum","doi":"10.1109/IROS.1994.407409","DOIUrl":"https://doi.org/10.1109/IROS.1994.407409","url":null,"abstract":"Industrial robots are increasing being applied in production situations of small quantity or single run units. These applications are characterized by a large product variety hence production flexibility is one of the most important requirements for new robot applications. In these applications, the robot must be seen as a single component of a flexible automation system, the robot-based flexible manufacturing work cell. Due to the numerous possible configurations in factories it is necessary to develop application specific modular manufacturing work cells by the usage of different components. Nevertheless it is the goal to standardize the work cell internal information structure, which permits the utilization of standardized control structures. The control components must be adaptable to different work cell configurations. In this paper the universal controller system LUCAS for robot-based flexible manufacturing work cells is described. For verification of the underlying control concepts some example applications in flexible assembly and flexible machining are shown. In addition, prospects for further developments are presented.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128942315","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 : 1994-09-12DOI: 10.1109/IROS.1994.407412
C. Woenckhaus, Doris Kugelmann, G. Reinhart, J. Milberg
The planning of complex production plants makes considerable demands on the planning engineer, who usually has to pursue a wide variety of often conflicting sub-objectives simultaneously. The planner confronted with this task is hampered by a lack of suitable planning tools. 3D simulation can support the design of a three-dimensional manufacturing cell. However, even with 3D simulation, the search for an optimum solution remains relatively complex, because of the large number of interactive planning procedures involved. USIS (Universal Simulation System), a graphic robot simulation package, uses largely automated procedures to support the design engineer at all important stages of planning. This contribution presents some of these procedures.<>
{"title":"USIS-an integrated 3D-tool for planning production cells","authors":"C. Woenckhaus, Doris Kugelmann, G. Reinhart, J. Milberg","doi":"10.1109/IROS.1994.407412","DOIUrl":"https://doi.org/10.1109/IROS.1994.407412","url":null,"abstract":"The planning of complex production plants makes considerable demands on the planning engineer, who usually has to pursue a wide variety of often conflicting sub-objectives simultaneously. The planner confronted with this task is hampered by a lack of suitable planning tools. 3D simulation can support the design of a three-dimensional manufacturing cell. However, even with 3D simulation, the search for an optimum solution remains relatively complex, because of the large number of interactive planning procedures involved. USIS (Universal Simulation System), a graphic robot simulation package, uses largely automated procedures to support the design engineer at all important stages of planning. This contribution presents some of these procedures.<<ETX>>","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130272697","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 : 1994-09-12DOI: 10.1109/IROS.1994.407461
M. Hassoun, C. Laugier
{"title":"An architecture for planning and control the motion of a car-like robot","authors":"M. Hassoun, C. Laugier","doi":"10.1109/IROS.1994.407461","DOIUrl":"https://doi.org/10.1109/IROS.1994.407461","url":null,"abstract":"","PeriodicalId":437805,"journal":{"name":"Proceedings of IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS'94)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1994-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124190598","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：