Pub Date : 1995-08-27DOI: 10.1109/ISIC.1995.525067
Xiaobo Shi, Fei-Yue Wang, P. Lever
This paper presents a formulation of excavation tasks and behaviors using finite state machines (FSM). A robotic excavation goal is achieved through several excavation tasks, while a task is completed through sequences of excavation behaviors, which are carries out by an ordered application of primitive, machine executable excavation actions. Both tasks and behaviors are specified by finite state machines that define all feasible sequences of behaviors or actions. The behavior selection for state transitions in a task FSM is achieved through situation assessment and behavior arbitration. For a behavior FSM, a method of terminating a behavior execution based on the activation levels of its actions is proposed. Since it is almost impossible to infer the exact status of bucket/environment interaction from force/torque data, excavation actions are specified using fuzzy logic rules acquired from human experience and heuristics. Experimental results have indicated that the proposed formulation has lead to a more efficient execution of excavation tasks than the authors' previous formulation.
{"title":"Task and behavior formulations for robotic rock excavation","authors":"Xiaobo Shi, Fei-Yue Wang, P. Lever","doi":"10.1109/ISIC.1995.525067","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525067","url":null,"abstract":"This paper presents a formulation of excavation tasks and behaviors using finite state machines (FSM). A robotic excavation goal is achieved through several excavation tasks, while a task is completed through sequences of excavation behaviors, which are carries out by an ordered application of primitive, machine executable excavation actions. Both tasks and behaviors are specified by finite state machines that define all feasible sequences of behaviors or actions. The behavior selection for state transitions in a task FSM is achieved through situation assessment and behavior arbitration. For a behavior FSM, a method of terminating a behavior execution based on the activation levels of its actions is proposed. Since it is almost impossible to infer the exact status of bucket/environment interaction from force/torque data, excavation actions are specified using fuzzy logic rules acquired from human experience and heuristics. Experimental results have indicated that the proposed formulation has lead to a more efficient execution of excavation tasks than the authors' previous formulation.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114931193","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525071
R. Colbaugh, K. Glass
This paper presents a new trajectory tracking control scheme for uncertain rigid-link electrically-driven manipulators. The proposed controller is an adaptive strategy which is computationally efficient, requires virtually no information concerning either the manipulator or actuator models, and is very general and readily implementable. It is shown that the controller ensures semiglobal uniform boundedness of all signals in the presence of bounded disturbances, and that the ultimate size of the tracking errors can be made arbitrarily small.
{"title":"Adaptive tracking control of rigid-link electrically-driven manipulators","authors":"R. Colbaugh, K. Glass","doi":"10.1109/ISIC.1995.525071","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525071","url":null,"abstract":"This paper presents a new trajectory tracking control scheme for uncertain rigid-link electrically-driven manipulators. The proposed controller is an adaptive strategy which is computationally efficient, requires virtually no information concerning either the manipulator or actuator models, and is very general and readily implementable. It is shown that the controller ensures semiglobal uniform boundedness of all signals in the presence of bounded disturbances, and that the ultimate size of the tracking errors can be made arbitrarily small.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116562973","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525091
R. Ortega
Makes three remarks concerning adaptive implementations of neural networks and fuzzy systems. First, the author brings to the readers attention the fact that the potential power of these systems as function approximators is lost when, as done in recently published work, the adjustable parameters are only the linear combination weights of the basis functions. Second, the author shows that the stability analysis in those papers uses properties particular to neural nets or fuzzy systems, and follows immediately from well established results in adaptive systems theory. The second fact is well known to people familiar with adaptive systems theory, but not necessarily so to the neuro-fuzzy community. On the other hand, the opposite seems to be the case for the first remark. Finally, the author presents a simple version of a result on adaptive stabilization of nonlinearly parametrized nonlinear systems which might be useful for the stability analysis of adaptive neuro-fuzzy systems. This result, though well known in the Russian literature for a long time, has apparently been overlooked in "western" publications.
{"title":"Some remarks on adaptive neuro-fuzzy systems","authors":"R. Ortega","doi":"10.1109/ISIC.1995.525091","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525091","url":null,"abstract":"Makes three remarks concerning adaptive implementations of neural networks and fuzzy systems. First, the author brings to the readers attention the fact that the potential power of these systems as function approximators is lost when, as done in recently published work, the adjustable parameters are only the linear combination weights of the basis functions. Second, the author shows that the stability analysis in those papers uses properties particular to neural nets or fuzzy systems, and follows immediately from well established results in adaptive systems theory. The second fact is well known to people familiar with adaptive systems theory, but not necessarily so to the neuro-fuzzy community. On the other hand, the opposite seems to be the case for the first remark. Finally, the author presents a simple version of a result on adaptive stabilization of nonlinearly parametrized nonlinear systems which might be useful for the stability analysis of adaptive neuro-fuzzy systems. This result, though well known in the Russian literature for a long time, has apparently been overlooked in \"western\" publications.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134484743","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525035
S. Jagannathan, Frank L. Lewis
An implicit self tuning regulator (STR) is presented, based on Lyapunov analysis for the control of a class of multi-input and multi-output (MIMO) dynamical system. Linearity in the parameters is assumed to hold, but the estimation error is considered to be non zero; this allows control of a larger class of systems and also has the effect of producing a robust controller. Moreover, certainty equivalence is not used in the design overcoming a major problem in adaptive control. It is indicated that gradient-based parameter tuning of the STR, when employed for closed-loop control, can yield unbounded parameter estimates if: (1) linearity in the unknown parameters does not exactly hold, or (2) there are unknown disturbances acting on the system. Finally, this paper provides a comprehensive theory in the development of identification, prediction, and adaptive control schemes for discrete-time systems.
{"title":"Robust implicit self tuning regulator/MRAC convergence and stability","authors":"S. Jagannathan, Frank L. Lewis","doi":"10.1109/ISIC.1995.525035","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525035","url":null,"abstract":"An implicit self tuning regulator (STR) is presented, based on Lyapunov analysis for the control of a class of multi-input and multi-output (MIMO) dynamical system. Linearity in the parameters is assumed to hold, but the estimation error is considered to be non zero; this allows control of a larger class of systems and also has the effect of producing a robust controller. Moreover, certainty equivalence is not used in the design overcoming a major problem in adaptive control. It is indicated that gradient-based parameter tuning of the STR, when employed for closed-loop control, can yield unbounded parameter estimates if: (1) linearity in the unknown parameters does not exactly hold, or (2) there are unknown disturbances acting on the system. Finally, this paper provides a comprehensive theory in the development of identification, prediction, and adaptive control schemes for discrete-time systems.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133851432","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525074
Y. Narahari, N. Hemachandra
Performance evaluation studies in manufacturing systems have traditionally considered models in which the arrival process and service process are time independent. Real-world manufacturing systems however, are subjected to highly complex and usually time-dependent input workloads. This motivates the study of performance models of manufacturing systems under nonstationary conditions. In this paper, we present several situations in manufacturing systems where nonstationary models are relevant. For studying such models, transient analysis is more appropriate than steady-state analysis. We explore various techniques for analyzing such models, including numerical and simulation techniques, and present two illustrative examples.
{"title":"Non-stationary models of manufacturing systems: relevance and analysis","authors":"Y. Narahari, N. Hemachandra","doi":"10.1109/ISIC.1995.525074","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525074","url":null,"abstract":"Performance evaluation studies in manufacturing systems have traditionally considered models in which the arrival process and service process are time independent. Real-world manufacturing systems however, are subjected to highly complex and usually time-dependent input workloads. This motivates the study of performance models of manufacturing systems under nonstationary conditions. In this paper, we present several situations in manufacturing systems where nonstationary models are relevant. For studying such models, transient analysis is more appropriate than steady-state analysis. We explore various techniques for analyzing such models, including numerical and simulation techniques, and present two illustrative examples.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129374298","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525124
S. Prabhu, D. Garg
Compliance inherently involves modification of the robot trajectory based on the contact forces occurring during the motion and enables the robot to perform a variety of manipulation tasks which require fine motion skills. Learning of active compliance behavior can endow a robot with some form of autonomous intelligence which can be very useful for the control of manipulators working in a partially known environment and for manufacturing automation. This paper reports on the acquisition of robot fine motion skills by means of learning a compliance control strategy using fuzzy reinforcement learning. The fuzzy reinforcement compliance controller is applied to a typical robotic assembly task and its performance is compared with other learning controllers.
{"title":"Fuzzy reinforcement compliance control for robotic assembly","authors":"S. Prabhu, D. Garg","doi":"10.1109/ISIC.1995.525124","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525124","url":null,"abstract":"Compliance inherently involves modification of the robot trajectory based on the contact forces occurring during the motion and enables the robot to perform a variety of manipulation tasks which require fine motion skills. Learning of active compliance behavior can endow a robot with some form of autonomous intelligence which can be very useful for the control of manipulators working in a partially known environment and for manufacturing automation. This paper reports on the acquisition of robot fine motion skills by means of learning a compliance control strategy using fuzzy reinforcement learning. The fuzzy reinforcement compliance controller is applied to a typical robotic assembly task and its performance is compared with other learning controllers.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121763829","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525052
S. Kawaji, K. Ogasawara
We propose a new search method of genetic algorithm (GA), which reduces the difficulties of the design of the fitness function. In the method, the control objective is divided into some intermediate control objectives according to the control strategy. The search process progresses with the fitness function corresponding to the intermediate control objective, and the process is controlled by switching the fitness function based on the average fitness value of the current candidate solutions so that the optimum solution with desired quality may be found. Thus, the search space is structured repeatedly during the search process by switching the fitness function based on the quality of the current candidate solutions. In order to confirm the availability of the proposed method, the swing-up control of the cart-pendulum system is used as an example, and some simulation results are given.
{"title":"Solving the nonlinear dynamic control problems by GA with structurizing the search space","authors":"S. Kawaji, K. Ogasawara","doi":"10.1109/ISIC.1995.525052","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525052","url":null,"abstract":"We propose a new search method of genetic algorithm (GA), which reduces the difficulties of the design of the fitness function. In the method, the control objective is divided into some intermediate control objectives according to the control strategy. The search process progresses with the fitness function corresponding to the intermediate control objective, and the process is controlled by switching the fitness function based on the average fitness value of the current candidate solutions so that the optimum solution with desired quality may be found. Thus, the search space is structured repeatedly during the search process by switching the fitness function based on the quality of the current candidate solutions. In order to confirm the availability of the proposed method, the swing-up control of the cart-pendulum system is used as an example, and some simulation results are given.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126194405","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525034
Z. Manna, H. B. Sipma
This paper proposes a deductive approach towards controller synthesis. The system to be controlled and the environment are modeled as phase transition systems and the specification of the entire system is expressed by a hybrid temporal logic formula. Verification rules are used to determine whether the system in conjunction with a control strategy meets the specification. The control strategy is refined until it meets the given specification.
{"title":"A deductive approach towards controller synthesis","authors":"Z. Manna, H. B. Sipma","doi":"10.1109/ISIC.1995.525034","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525034","url":null,"abstract":"This paper proposes a deductive approach towards controller synthesis. The system to be controlled and the environment are modeled as phase transition systems and the specification of the entire system is expressed by a hybrid temporal logic formula. Verification rules are used to determine whether the system in conjunction with a control strategy meets the specification. The control strategy is refined until it meets the given specification.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124409284","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525037
C. Bett, M. Lemmon
Hybrid control systems (HCS) arise when the plant, a continuous state system (CSS), is controlled by a discrete event system (DES) controller. It is assumed that there exists a specification on the plant's desired symbolic behaviour which describes how various operational modes of the controlled plant should fit together. One design problem involves determining an HCS that "realizes" the specified behaviour in a "stable" manner. The solution of this problem involves finding a sequence of subgoals and controllers achieving the specified behaviour in a "logically" stable manner. This paper shows how such a "stable" extension can be constructed using multiple H/sup /spl infin// control systems exhibiting robust stability.
{"title":"Stable H/sup /spl infin// extensions of hybrid control systems","authors":"C. Bett, M. Lemmon","doi":"10.1109/ISIC.1995.525037","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525037","url":null,"abstract":"Hybrid control systems (HCS) arise when the plant, a continuous state system (CSS), is controlled by a discrete event system (DES) controller. It is assumed that there exists a specification on the plant's desired symbolic behaviour which describes how various operational modes of the controlled plant should fit together. One design problem involves determining an HCS that \"realizes\" the specified behaviour in a \"stable\" manner. The solution of this problem involves finding a sequence of subgoals and controllers achieving the specified behaviour in a \"logically\" stable manner. This paper shows how such a \"stable\" extension can be constructed using multiple H/sup /spl infin// control systems exhibiting robust stability.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117111876","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 : 1995-08-27DOI: 10.1109/ISIC.1995.525031
C. Lin
An integrated intelligent control approach is proposed for the design of high performance control systems based on advanced sensor processing, and neural fuzzy control integration. Our approach features the following innovations: 1) the complexity and uncertainty issues are addressed via the distributed parallel processing, learning, and online reoptimization properties of neural networks; 2) the nonlinear dynamics and the severe coupling can be naturally incorporated into the design framework; and 3) the knowledge base and decision making logic furnished by fuzzy systems leads to a human intelligence enhanced control scheme. In addition, fault tolerance, health monitoring and reconfigurable control strategies can be accommodated by this approach to ensure stability graceful degradation and reoptimization in the case of failures, malfunctions and damage.
{"title":"Integrated modular neural intelligent control systems","authors":"C. Lin","doi":"10.1109/ISIC.1995.525031","DOIUrl":"https://doi.org/10.1109/ISIC.1995.525031","url":null,"abstract":"An integrated intelligent control approach is proposed for the design of high performance control systems based on advanced sensor processing, and neural fuzzy control integration. Our approach features the following innovations: 1) the complexity and uncertainty issues are addressed via the distributed parallel processing, learning, and online reoptimization properties of neural networks; 2) the nonlinear dynamics and the severe coupling can be naturally incorporated into the design framework; and 3) the knowledge base and decision making logic furnished by fuzzy systems leads to a human intelligence enhanced control scheme. In addition, fault tolerance, health monitoring and reconfigurable control strategies can be accommodated by this approach to ensure stability graceful degradation and reoptimization in the case of failures, malfunctions and damage.","PeriodicalId":219623,"journal":{"name":"Proceedings of Tenth International Symposium on Intelligent Control","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"1995-08-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115462742","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：