Pub Date : 2001-09-05DOI: 10.1109/ISIC.2001.971478
V. Gazi, K. Passino
In this article we consider a discrete time one-dimensional asynchronous swarm. First, we describe the mathematical model for motions of the swarm members. Then, we analyze the stability properties of that model. The stability concept that we consider, which matches exactly with stability of equilibria in control theory, characterizes stability of a particular position (relative arrangement) of the swarm members, that we call the comfortable position (with comfortable intermember distance). Our stability analysis employs some results on contractive mappings from the parallel and distributed computation literature.
{"title":"Stability of a one-dimensional discrete-time asynchronous swarm","authors":"V. Gazi, K. Passino","doi":"10.1109/ISIC.2001.971478","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971478","url":null,"abstract":"In this article we consider a discrete time one-dimensional asynchronous swarm. First, we describe the mathematical model for motions of the swarm members. Then, we analyze the stability properties of that model. The stability concept that we consider, which matches exactly with stability of equilibria in control theory, characterizes stability of a particular position (relative arrangement) of the swarm members, that we call the comfortable position (with comfortable intermember distance). Our stability analysis employs some results on contractive mappings from the parallel and distributed computation literature.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134485317","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971492
Jagannathan, Annie Levesque, Yesh Singh
MARS greenhouse needs mobile robots with on-board arms, that are capable of navigating autonomously in the greenhouse, performing tasks such as carrying plant trays, farming, harvesting, plucking fruits and vegetables and so on. An adaptive neural net (NN) is used for coordinated motion control of base and arm using Lyapunov's approach. A one-layer NN based controller is designed to estimate the unknown dynamics of the system after the incorporation of nonholonomic constraints. This approach provides an inner loop that accounts for possible motion of the arm, with changing loads, while the base is carrying out a task. The case of maintaining a desired course and speed or tracking a desired Cartesian trajectory as the arm moves to its desired orientation with a load is considered. Outer loops are designed not only to avoid both stationary and moving obstacles but also to navigate the mobile base with the onboard arm along the path. The net result is a base plus arm motion controller that is capable of achieving a coordinated motion of the base plus arm in the presence of uncertain dynamics, load and the environment.
{"title":"Approximation-based control and avoidance of a mobile base with an onboard arm for MARS greenhouse operation","authors":"Jagannathan, Annie Levesque, Yesh Singh","doi":"10.1109/ISIC.2001.971492","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971492","url":null,"abstract":"MARS greenhouse needs mobile robots with on-board arms, that are capable of navigating autonomously in the greenhouse, performing tasks such as carrying plant trays, farming, harvesting, plucking fruits and vegetables and so on. An adaptive neural net (NN) is used for coordinated motion control of base and arm using Lyapunov's approach. A one-layer NN based controller is designed to estimate the unknown dynamics of the system after the incorporation of nonholonomic constraints. This approach provides an inner loop that accounts for possible motion of the arm, with changing loads, while the base is carrying out a task. The case of maintaining a desired course and speed or tracking a desired Cartesian trajectory as the arm moves to its desired orientation with a load is considered. Outer loops are designed not only to avoid both stationary and moving obstacles but also to navigate the mobile base with the onboard arm along the path. The net result is a base plus arm motion controller that is capable of achieving a coordinated motion of the base plus arm in the presence of uncertain dynamics, load and the environment.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130835486","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971509
S. Caramihai, I. Dumitrache
Presents a hybrid agent based architecture for the control of flexible manufacturing systems The main goal of the architecture is to solve a class of problems raised by agent based control systems: the non-optimality of the control policy, especially from the time point of view. A supervisory level is designed for this purpose, having as its main task to evaluate different possible control policies and to advise agents in choosing the optimal one. The modeling support used for this purpose is T-temporal Petri nets.
{"title":"Hybrid agent based control architecture supported by T-temporal Petri nets","authors":"S. Caramihai, I. Dumitrache","doi":"10.1109/ISIC.2001.971509","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971509","url":null,"abstract":"Presents a hybrid agent based architecture for the control of flexible manufacturing systems The main goal of the architecture is to solve a class of problems raised by agent based control systems: the non-optimality of the control policy, especially from the time point of view. A supervisory level is designed for this purpose, having as its main task to evaluate different possible control policies and to advise agents in choosing the optimal one. The modeling support used for this purpose is T-temporal Petri nets.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122193751","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971502
C. Martin, R. Martin
The cotton aphid is an important pest affecting the profitability of cotton production. We study the problem of the optimal timing of pesticide application to control the aphid. The problem is complicated by the presence of a significant predator insect. The predator serves as a natural control of the aphid and is adversely affected by application of pesticide. Observation of the system is costly. We determine optimal state dependent rules for application of pesticide. We show that the first application of pesticide is a switching time between two dynamic systems.
{"title":"A control theoretic analysis of the cotton aphid: an economics approach","authors":"C. Martin, R. Martin","doi":"10.1109/ISIC.2001.971502","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971502","url":null,"abstract":"The cotton aphid is an important pest affecting the profitability of cotton production. We study the problem of the optimal timing of pesticide application to control the aphid. The problem is complicated by the presence of a significant predator insect. The predator serves as a natural control of the aphid and is adversely affected by application of pesticide. Observation of the system is costly. We determine optimal state dependent rules for application of pesticide. We show that the first application of pesticide is a switching time between two dynamic systems.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123171737","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971521
A. Doncescu, J. Waisman, G. Roux, G. Richard, B. Dahhou
This paper presents a methodology to design a discrete-event system (DES) for the online supervision of a biotechnological process. The DES is synthesised applying wavelet transform and inductive logic programming on the measured signals constrained to the biotechnologist expert validation.
{"title":"Intelligent analyzing system based on inductive logic programming","authors":"A. Doncescu, J. Waisman, G. Roux, G. Richard, B. Dahhou","doi":"10.1109/ISIC.2001.971521","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971521","url":null,"abstract":"This paper presents a methodology to design a discrete-event system (DES) for the online supervision of a biotechnological process. The DES is synthesised applying wavelet transform and inductive logic programming on the measured signals constrained to the biotechnologist expert validation.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116958870","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971540
Y. Kobayashi, E. Aiyoshi
When a nuclear power reactor is shut down between successive operation cycles, refueling or reloading is needed. Developing a good refueling or reloading pattern is called "loading pattern optimization". It is a large, combinatorial optimization problem with a nonlinear objective function and nonlinear constraints. An algorithm based on the genetic algorithm was developed to generate optimized boiling water reactor (BWR) reloading patterns. The proposed algorithms are demonstrated in an actual BWR plant. In test calculations, candidates that shuffled fresh and burned fuel assemblies within a reasonable computation time were obtained.
{"title":"Optimization of boiling water reactor loading pattern using an improved genetic algorithm","authors":"Y. Kobayashi, E. Aiyoshi","doi":"10.1109/ISIC.2001.971540","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971540","url":null,"abstract":"When a nuclear power reactor is shut down between successive operation cycles, refueling or reloading is needed. Developing a good refueling or reloading pattern is called \"loading pattern optimization\". It is a large, combinatorial optimization problem with a nonlinear objective function and nonlinear constraints. An algorithm based on the genetic algorithm was developed to generate optimized boiling water reactor (BWR) reloading patterns. The proposed algorithms are demonstrated in an actual BWR plant. In test calculations, candidates that shuffled fresh and burned fuel assemblies within a reasonable computation time were obtained.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"1108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116057748","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971507
Li Shi, Chenfeng Jiang, Ye Zhen, S. Zeng-qi
RoboCup is a worldwide popular research domain. Because of the complexity of the systems, how to describe cooperation and competition between agents is a great challenge in the RoboCup Simulation Game. On one hand, the rich experience of a human soccer player is of great service to the robot players. On the other hand, the difference between the simulation game and the real game make it a must to fit the transcendental knowledge into the new environment. Commonly used reinforcement learning is weak in utilizing transcendental knowledge, thus is limited in complex multi-agent system learning problems. The paper puts forward a supervised learning method on the basis of the adapted neuro-fuzzy inference system (ANFIS) for mapping the competition among the robots. This method can build an ANFIS according to experts' knowledge, and with data obtained in the simulation environment. It can establish a correct map to describe the competition among the robots. We use this method to describe the antagonization between the shooter and goalie, and have successfully applied it in the RoboCup Simulation Game to build the champion team in RoboCup 2000 of China.
{"title":"Learning competition in robot soccer game based on an adapted neuro-fuzzy inference system","authors":"Li Shi, Chenfeng Jiang, Ye Zhen, S. Zeng-qi","doi":"10.1109/ISIC.2001.971507","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971507","url":null,"abstract":"RoboCup is a worldwide popular research domain. Because of the complexity of the systems, how to describe cooperation and competition between agents is a great challenge in the RoboCup Simulation Game. On one hand, the rich experience of a human soccer player is of great service to the robot players. On the other hand, the difference between the simulation game and the real game make it a must to fit the transcendental knowledge into the new environment. Commonly used reinforcement learning is weak in utilizing transcendental knowledge, thus is limited in complex multi-agent system learning problems. The paper puts forward a supervised learning method on the basis of the adapted neuro-fuzzy inference system (ANFIS) for mapping the competition among the robots. This method can build an ANFIS according to experts' knowledge, and with data obtained in the simulation environment. It can establish a correct map to describe the competition among the robots. We use this method to describe the antagonization between the shooter and goalie, and have successfully applied it in the RoboCup Simulation Game to build the champion team in RoboCup 2000 of China.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130858885","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971485
J. Stecha, Z. Vlcek
Monte Carlo approach is used in this paper to solve predictive control problem of an uncertain system. Monte Carlo approach uses samples of unknown variables. This approach enables to solve the minimization problem and the mean value computation of the chosen criterion. For nonlinear uncertain systems there is no general analytical method how to solve the optimal control problem and our approach gives solution with prescribed accuracy.
{"title":"Robust predictive control by statistical learning theory","authors":"J. Stecha, Z. Vlcek","doi":"10.1109/ISIC.2001.971485","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971485","url":null,"abstract":"Monte Carlo approach is used in this paper to solve predictive control problem of an uncertain system. Monte Carlo approach uses samples of unknown variables. This approach enables to solve the minimization problem and the mean value computation of the chosen criterion. For nonlinear uncertain systems there is no general analytical method how to solve the optimal control problem and our approach gives solution with prescribed accuracy.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134394400","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971481
Derong Liu, T. Chang, Yi Zhang
We develop in the present paper a constructive learning algorithm for feedforward neural networks. We employ an incremental training procedure where training patterns are learned one by one. Our algorithm starts with a single training pattern and a single hidden layer neuron. During the course of neural network training, when the algorithm gets stuck in a local minimum, we will attempt to escape from the local minimum by using the weight scaling technique. It is only after several consecutive failed attempts in escaping from a local minimum, we will allow the network to grow by adding a hidden layer neuron. At this stage, we employ an optimization procedure based on quadratic/linear programming to select initial weights for the newly added neuron. Our optimization procedure tends to make the network reach the error tolerance with no or little training after adding a hidden layer neuron Our simulation results indicate that the present constructive algorithm can obtain neural networks very close to minimal structures and that convergence (to a solution) in neural network training can be guaranteed. We tested our algorithm extensively using the parity problem.
{"title":"A new learning algorithm for feedforward neural networks","authors":"Derong Liu, T. Chang, Yi Zhang","doi":"10.1109/ISIC.2001.971481","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971481","url":null,"abstract":"We develop in the present paper a constructive learning algorithm for feedforward neural networks. We employ an incremental training procedure where training patterns are learned one by one. Our algorithm starts with a single training pattern and a single hidden layer neuron. During the course of neural network training, when the algorithm gets stuck in a local minimum, we will attempt to escape from the local minimum by using the weight scaling technique. It is only after several consecutive failed attempts in escaping from a local minimum, we will allow the network to grow by adding a hidden layer neuron. At this stage, we employ an optimization procedure based on quadratic/linear programming to select initial weights for the newly added neuron. Our optimization procedure tends to make the network reach the error tolerance with no or little training after adding a hidden layer neuron Our simulation results indicate that the present constructive algorithm can obtain neural networks very close to minimal structures and that convergence (to a solution) in neural network training can be guaranteed. We tested our algorithm extensively using the parity problem.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"78 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128239305","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 : 2001-09-05DOI: 10.1109/ISIC.2001.971477
T. Samad, D. Gorinevsky, F. Stoffelen
We describe an approach for dynamic route optimization for autonomous high-performance aircraft. A multiresolution representation scheme is presented that uses B-spline basis functions of different support and at different locations along the trajectory, parametrized by a dimensionless parameter. A multirate receding horizon problem is formulated as an example of online multiresolution optimization under feedback. The underlying optimization problem is solved with an anytime evolutionary computing algorithm. By selecting particular basis function coefficients as the optimization variables, computing resources can flexibly be devoted to those regions of the trajectory requiring most attention. A simulation scenario is presented.
{"title":"Dynamic multiresolution route optimization for autonomous aircraft","authors":"T. Samad, D. Gorinevsky, F. Stoffelen","doi":"10.1109/ISIC.2001.971477","DOIUrl":"https://doi.org/10.1109/ISIC.2001.971477","url":null,"abstract":"We describe an approach for dynamic route optimization for autonomous high-performance aircraft. A multiresolution representation scheme is presented that uses B-spline basis functions of different support and at different locations along the trajectory, parametrized by a dimensionless parameter. A multirate receding horizon problem is formulated as an example of online multiresolution optimization under feedback. The underlying optimization problem is solved with an anytime evolutionary computing algorithm. By selecting particular basis function coefficients as the optimization variables, computing resources can flexibly be devoted to those regions of the trajectory requiring most attention. A simulation scenario is presented.","PeriodicalId":367430,"journal":{"name":"Proceeding of the 2001 IEEE International Symposium on Intelligent Control (ISIC '01) (Cat. No.01CH37206)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2001-09-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128463334","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：