Pub Date : 1900-01-01DOI: 10.1109/ISIC.1999.796689
M.L. Hadjili, V. Wertz
Predictive control was first developed to control linear time invariant plants described by ARIMAX models. The extension of this control strategy to the case when the behavior of the plant is nonlinear and modeled by a Takagi-Sugeno fuzzy model is considered. This kind of nonlinear model is locally linear and the GPC technique can be extended as a parallel distributed controller.
{"title":"Generalized predictive control using Takagi-Sugeno fuzzy models","authors":"M.L. Hadjili, V. Wertz","doi":"10.1109/ISIC.1999.796689","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796689","url":null,"abstract":"Predictive control was first developed to control linear time invariant plants described by ARIMAX models. The extension of this control strategy to the case when the behavior of the plant is nonlinear and modeled by a Takagi-Sugeno fuzzy model is considered. This kind of nonlinear model is locally linear and the GPC technique can be extended as a parallel distributed controller.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121800410","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796668
S. Aknine
Meta-programming a multi-agent system is a complex task due to the fact that as the agents build their strategies the environment changes. We propose a method and a language for multi-agent meta-programming based on explanation based learning and we unify these ideas under a formal framework. As an example, we report our experience of use of our meta-programming method on the example of predators for meta-programming multi-agent systems.
{"title":"Reasoning structures for multi-agent meta-programming","authors":"S. Aknine","doi":"10.1109/ISIC.1999.796668","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796668","url":null,"abstract":"Meta-programming a multi-agent system is a complex task due to the fact that as the agents build their strategies the environment changes. We propose a method and a language for multi-agent meta-programming based on explanation based learning and we unify these ideas under a formal framework. As an example, we report our experience of use of our meta-programming method on the example of predators for meta-programming multi-agent systems.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122431253","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796661
N. Rakoto-Ravalontsalama
A methodology for modeling and simulating a continuous process is presented. This is done by using a knowledge based approach. This approach is not only based on production rules but include also the mathematical model of the process. The results are compared to those from some classical continuous system simulators. The advantage of the use of the knowledge based system is that a reasoning level is available for the intelligent control task.
{"title":"Knowledge based process control","authors":"N. Rakoto-Ravalontsalama","doi":"10.1109/ISIC.1999.796661","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796661","url":null,"abstract":"A methodology for modeling and simulating a continuous process is presented. This is done by using a knowledge based approach. This approach is not only based on production rules but include also the mathematical model of the process. The results are compared to those from some classical continuous system simulators. The advantage of the use of the knowledge based system is that a reasoning level is available for the intelligent control task.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133624887","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796633
A. Zhdanov, A.N. Yinokurov
We offer a standpoint that emotions are a necessary mechanism for autonomous control systems. By an autonomous controlled object we understand an object, that is controlled by a control system which is its on-board subsystem. The control system performs learning and control in one process. We develop a methodology of autonomous adaptive control (AAC), that allows us to construct a control system for a given controlled object. As the control goals we take the controlled object survival and the knowledge accumulation. As a whole these goals bring maximization of the controlled object lifetime. We suggest an emotions modeling mechanism (EM). We give the description of its functions and their implementation in AAC methodology. These functions are: (1) a compulsion of the control system for activity; (2) an appreciation of the CO current state at its quality; (3) an appreciation of the formed patterns and their usefulness for control goals; (4) an influence on tempo and depth of reasoning of decision making in current state; (5) providing the decision making subsystem with emotional appraisals of the recognized patterns; (6) providing transfer of information on patterns of emotional appraisals simultaneously with information on the patterns while the organism interacts with another organism.
{"title":"Emotions simulation in methodology of autonomous adaptive control","authors":"A. Zhdanov, A.N. Yinokurov","doi":"10.1109/ISIC.1999.796633","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796633","url":null,"abstract":"We offer a standpoint that emotions are a necessary mechanism for autonomous control systems. By an autonomous controlled object we understand an object, that is controlled by a control system which is its on-board subsystem. The control system performs learning and control in one process. We develop a methodology of autonomous adaptive control (AAC), that allows us to construct a control system for a given controlled object. As the control goals we take the controlled object survival and the knowledge accumulation. As a whole these goals bring maximization of the controlled object lifetime. We suggest an emotions modeling mechanism (EM). We give the description of its functions and their implementation in AAC methodology. These functions are: (1) a compulsion of the control system for activity; (2) an appreciation of the CO current state at its quality; (3) an appreciation of the formed patterns and their usefulness for control goals; (4) an influence on tempo and depth of reasoning of decision making in current state; (5) providing the decision making subsystem with emotional appraisals of the recognized patterns; (6) providing transfer of information on patterns of emotional appraisals simultaneously with information on the patterns while the organism interacts with another organism.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"418 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134272575","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796664
T. Fischer, D. Rapela, H. Woern
In the field of research and development of grippers in object-handling applications, many research results in improving grippers performances have been achieved, and many kinds of multifinger grippers have been developed. By using multifinger grippers, it is possible to grasp different objects of different shapes without changing grippers; and most importantly, it can manipulate the grasped object in the hand, under the condition that the object is controlled in real-time. Therefore, an object-pose controller with feedback from an object-pose sensor is presented in this paper.
{"title":"Sensor-based controlling of the objects pose for multifinger grippers","authors":"T. Fischer, D. Rapela, H. Woern","doi":"10.1109/ISIC.1999.796664","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796664","url":null,"abstract":"In the field of research and development of grippers in object-handling applications, many research results in improving grippers performances have been achieved, and many kinds of multifinger grippers have been developed. By using multifinger grippers, it is possible to grasp different objects of different shapes without changing grippers; and most importantly, it can manipulate the grasped object in the hand, under the condition that the object is controlled in real-time. Therefore, an object-pose controller with feedback from an object-pose sensor is presented in this paper.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"194 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131614141","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796697
A. Meystel
The discussion of intelligent system usually starts with issues of defining intelligence as a set of skills, but always ends with specifying the mechanisms of learning. It is important to address the issue of differences and similarities between the techniques of computational/control learning processes (very similar to the processes of semiosis) and biological learning including evolution of species where the resemblance with semiosis is less obvious. We would like to attract attention to the theory of multilevel processes of evolution which are interpreted in this paper as multiresolutional processes of evolution. Novel explanations are preposed for numerous paradoxes known in the area of computational and biological learning including evolution of species. The direct linkage is demonstrated of learning processes and the development of decision-making mechanisms for single and multiple agents.
{"title":"Evolution, emergence, semiosis: components of the model for intelligent system","authors":"A. Meystel","doi":"10.1109/ISIC.1999.796697","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796697","url":null,"abstract":"The discussion of intelligent system usually starts with issues of defining intelligence as a set of skills, but always ends with specifying the mechanisms of learning. It is important to address the issue of differences and similarities between the techniques of computational/control learning processes (very similar to the processes of semiosis) and biological learning including evolution of species where the resemblance with semiosis is less obvious. We would like to attract attention to the theory of multilevel processes of evolution which are interpreted in this paper as multiresolutional processes of evolution. Novel explanations are preposed for numerous paradoxes known in the area of computational and biological learning including evolution of species. The direct linkage is demonstrated of learning processes and the development of decision-making mechanisms for single and multiple agents.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129329082","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796640
J. Choi, J. Farrell
This paper presents an adaptive observer using neural networks for a class of nonlinear systems. The adaptive observer follows the nonlinear model estimation method for automated fault diagnosis. The contributions of this article include: modification of the estimation model as appropriate for certain nonlinear control applications; modification of the stability proofs; investigation of the observer performance through an illustrative simulation.
{"title":"Adaptive observer for a class of nonlinear systems using neural networks","authors":"J. Choi, J. Farrell","doi":"10.1109/ISIC.1999.796640","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796640","url":null,"abstract":"This paper presents an adaptive observer using neural networks for a class of nonlinear systems. The adaptive observer follows the nonlinear model estimation method for automated fault diagnosis. The contributions of this article include: modification of the estimation model as appropriate for certain nonlinear control applications; modification of the stability proofs; investigation of the observer performance through an illustrative simulation.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123080342","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796674
R. Kumar, J. Stover
This paper describes the formal background and suggests some enhancements for the fuzzy classifier, developed by Stover et al. (1996), called the continuous inferencing network (CINET), as part of the perceptor module of the prototype intelligent controller (PIC). These enhancements include, providing a mathematical foundation to the CINET fuzzy classifier seen as the cascade of a fuzzifier and a fuzzy-aggregator, extending the functionality of both the fuzzifier and the fuzzy-aggregator by incorporating a measure for randomness (called the ambiguity degree) besides a measure for vagueness (called the membership degree), and formalizing as well as simplifying the connectives used for fuzzy-aggregation.
{"title":"The CINET fuzzy classifier: formal background and enhancements","authors":"R. Kumar, J. Stover","doi":"10.1109/ISIC.1999.796674","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796674","url":null,"abstract":"This paper describes the formal background and suggests some enhancements for the fuzzy classifier, developed by Stover et al. (1996), called the continuous inferencing network (CINET), as part of the perceptor module of the prototype intelligent controller (PIC). These enhancements include, providing a mathematical foundation to the CINET fuzzy classifier seen as the cascade of a fuzzifier and a fuzzy-aggregator, extending the functionality of both the fuzzifier and the fuzzy-aggregator by incorporating a measure for randomness (called the ambiguity degree) besides a measure for vagueness (called the membership degree), and formalizing as well as simplifying the connectives used for fuzzy-aggregation.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123202835","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796631
R. Ventura, C. Pinto-Ferreira
The relevance of the model presented to the control and the supervision of systems lies in the fact that, in this context, it is very important to respond quickly and efficiently to unexpected situations, by learning associations between current situations and control strategies. The inputs and the state variables of a system can be considered as stimuli to feed a double processing system. The cognitive image can be considered as the set of values collected in a time frame. On the other hand, the perceptual image can result from the determination of certain characteristics such as overshoot, rate of variation of state variables, and so on. The next step is to establish a basic set of associations in order to allow the system to respond to urgent situations (solely based on the perceptual image). As the supervisor starts marking cognitive images with perceptual ones (a basic mechanism of learning), it becomes able to anticipate those situations (this is what humans apparently do when using the somatic marker). On the other hand, the matching of a certain configuration with one previously stored in memory can be assessed in terms of the positiveness or negativeness of the present situation by consulting the cognitive/perceptual mark. The control and supervision of large scale, non-linear, and non time-invariant systems ought to incorporate planning and decision making mechanisms together with low-level controllers, integrated in such a way that performance (both in terms of learning, quality of response, and efficiency) is ensured.
{"title":"Emotion-based control systems","authors":"R. Ventura, C. Pinto-Ferreira","doi":"10.1109/ISIC.1999.796631","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796631","url":null,"abstract":"The relevance of the model presented to the control and the supervision of systems lies in the fact that, in this context, it is very important to respond quickly and efficiently to unexpected situations, by learning associations between current situations and control strategies. The inputs and the state variables of a system can be considered as stimuli to feed a double processing system. The cognitive image can be considered as the set of values collected in a time frame. On the other hand, the perceptual image can result from the determination of certain characteristics such as overshoot, rate of variation of state variables, and so on. The next step is to establish a basic set of associations in order to allow the system to respond to urgent situations (solely based on the perceptual image). As the supervisor starts marking cognitive images with perceptual ones (a basic mechanism of learning), it becomes able to anticipate those situations (this is what humans apparently do when using the somatic marker). On the other hand, the matching of a certain configuration with one previously stored in memory can be assessed in terms of the positiveness or negativeness of the present situation by consulting the cognitive/perceptual mark. The control and supervision of large scale, non-linear, and non time-invariant systems ought to incorporate planning and decision making mechanisms together with low-level controllers, integrated in such a way that performance (both in terms of learning, quality of response, and efficiency) is ensured.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"115 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114559516","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 : 1900-01-01DOI: 10.1109/ISIC.1999.796669
Henry Voos
The control of complex dynamic systems is one of the major tasks of modern control theory. The high dimensionality of complex systems often requires decentralized control concepts. In computer science, multiagent systems are proposed for use in distributed intelligent applications. To solve the common task, the single agents have to communicate and to interact in a suitable way. In the case of a resource allocation problem, so called market-based control algorithms can be used. Such algorithms imitate the behavior of human economies. Since most research in market-based control is done in the field of communication and computer networks, this work examines the application for the control of complex dynamic systems.
{"title":"Market-based control of complex dynamic systems","authors":"Henry Voos","doi":"10.1109/ISIC.1999.796669","DOIUrl":"https://doi.org/10.1109/ISIC.1999.796669","url":null,"abstract":"The control of complex dynamic systems is one of the major tasks of modern control theory. The high dimensionality of complex systems often requires decentralized control concepts. In computer science, multiagent systems are proposed for use in distributed intelligent applications. To solve the common task, the single agents have to communicate and to interact in a suitable way. In the case of a resource allocation problem, so called market-based control algorithms can be used. Such algorithms imitate the behavior of human economies. Since most research in market-based control is done in the field of communication and computer networks, this work examines the application for the control of complex dynamic systems.","PeriodicalId":300130,"journal":{"name":"Proceedings of the 1999 IEEE International Symposium on Intelligent Control Intelligent Systems and Semiotics (Cat. No.99CH37014)","volume":"136 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1900-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134318106","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：