Pub Date : 2009-05-27DOI: 10.1109/CICA.2009.4982792
Yushing Cheung, J. Chung, N. Coleman
The primary objective of this paper is to develop an adaptive formation control method for a team of mobile robotic agents, which implements formation control, obstacle avoidance, and operator induced error compensation for unconstrained motions. In this approach, a leader robot is selected and teleoperated by an operator and the follower robots are autonomously coordinated to make a formation to perform a variety of tasks such as searching and/or pursuing targets, reconnaissance, etc. The formation can be reconfigured to avoid collisions with stationary obstacles and among the member robots. The performance of the developed method was investigated through haptic simulations and experiments. In the simulation study, a haptic device was used as the master robot, and three virtual nonholonomic mobile platforms were employed. The developed method was implemented on two differentially driven Pioneer-AT platforms. Both studies demonstrated consistent performance of the semi-autonomous formation control method in the presence of time-varying communication delays, erroneous operator commands, and stationary obstacles.
{"title":"Semi-autonomous formation control of a single-master multi-slave teleoperation system","authors":"Yushing Cheung, J. Chung, N. Coleman","doi":"10.1109/CICA.2009.4982792","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982792","url":null,"abstract":"The primary objective of this paper is to develop an adaptive formation control method for a team of mobile robotic agents, which implements formation control, obstacle avoidance, and operator induced error compensation for unconstrained motions. In this approach, a leader robot is selected and teleoperated by an operator and the follower robots are autonomously coordinated to make a formation to perform a variety of tasks such as searching and/or pursuing targets, reconnaissance, etc. The formation can be reconfigured to avoid collisions with stationary obstacles and among the member robots. The performance of the developed method was investigated through haptic simulations and experiments. In the simulation study, a haptic device was used as the master robot, and three virtual nonholonomic mobile platforms were employed. The developed method was implemented on two differentially driven Pioneer-AT platforms. Both studies demonstrated consistent performance of the semi-autonomous formation control method in the presence of time-varying communication delays, erroneous operator commands, and stationary obstacles.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"97 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128870454","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982774
G. Venayagamoorthy
System characterization and identification are fundamental problems in systems theory and play a major role in the design of controllers. System identification and nonlinear control has been proposed and implemented using intelligent systems such as neural networks, fuzzy logic, reinforcement learning, artificial immune system and many others using inverse models, direct/indirect adaptive, or cloning a linear controller. Adaptive Critic Designs (ACDs) are neural networks capable of optimization over time under conditions of noise and uncertainty. The ACD technique develops optimal control laws using two networks - critic and action. There are merits for each approach adopted will be presented. The primary aim of this tutorial is to provide control and system engineers/researchers from industry/academia, new to the field of computational intelligence with the fundamentals required to benefit from and contribute to the rapidly growing field of computational intelligence and its real world applications, including identification and control of power and energy systems, unmanned vehicle navigation, signal and image processing, and evolvable and adaptive hardware systems.
{"title":"Tutorial CICA-T Computing with intelligence for identification and control of nonlinear systems","authors":"G. Venayagamoorthy","doi":"10.1109/CICA.2009.4982774","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982774","url":null,"abstract":"System characterization and identification are fundamental problems in systems theory and play a major role in the design of controllers. System identification and nonlinear control has been proposed and implemented using intelligent systems such as neural networks, fuzzy logic, reinforcement learning, artificial immune system and many others using inverse models, direct/indirect adaptive, or cloning a linear controller. Adaptive Critic Designs (ACDs) are neural networks capable of optimization over time under conditions of noise and uncertainty. The ACD technique develops optimal control laws using two networks - critic and action. There are merits for each approach adopted will be presented. The primary aim of this tutorial is to provide control and system engineers/researchers from industry/academia, new to the field of computational intelligence with the fundamentals required to benefit from and contribute to the rapidly growing field of computational intelligence and its real world applications, including identification and control of power and energy systems, unmanned vehicle navigation, signal and image processing, and evolvable and adaptive hardware systems.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125060492","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982788
K. Salahshoor, Mojtaba Kordestani, M. S. Khoshro
An accurate on-line measurement of important quality variables is essential for successful monitoring and controlling of chemical processes. However, these variables are usually difficult to measure on-line due to the practical limitations such as the time-delay, high cost and reliability considerations. To overcome this problem, two online soft sensors are proposed based upon a combined adaptive principal component analysis (PCA) and a radial basis functions (RBF) artificial neural network. For this purpose, a recursive PCA and a PCA based on a sliding window scheme are presented to adaptively extract the inherent features inside the measurements with high dimensions. The extracted low-dimension features are then used recursively as the main inputs to the RBF neural network. The developed online soft sensors are finally tested on a highly nonlinear distillation column benchmark problem to illustrate their effective performances. The simulation results demonstrate the superiority of the proposed soft sensor based on the combined recursive PCA and the RBF neural network.
{"title":"Design of online soft sensors based on combined adaptive PCA and RBF neural networks","authors":"K. Salahshoor, Mojtaba Kordestani, M. S. Khoshro","doi":"10.1109/CICA.2009.4982788","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982788","url":null,"abstract":"An accurate on-line measurement of important quality variables is essential for successful monitoring and controlling of chemical processes. However, these variables are usually difficult to measure on-line due to the practical limitations such as the time-delay, high cost and reliability considerations. To overcome this problem, two online soft sensors are proposed based upon a combined adaptive principal component analysis (PCA) and a radial basis functions (RBF) artificial neural network. For this purpose, a recursive PCA and a PCA based on a sliding window scheme are presented to adaptively extract the inherent features inside the measurements with high dimensions. The extracted low-dimension features are then used recursively as the main inputs to the RBF neural network. The developed online soft sensors are finally tested on a highly nonlinear distillation column benchmark problem to illustrate their effective performances. The simulation results demonstrate the superiority of the proposed soft sensor based on the combined recursive PCA and the RBF neural network.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116536803","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982777
N. Nahapetian, M. Jahed-Motlagh, M. Analoui
This paper addresses an application that involves the adaptive control of robot manipulator joint. It tries to explore the potential of using soft computing methodologies in control of plant (robot manipulator) with unknown internal behavior and environmental changes.
{"title":"Adaptive robot manipulator control based on plant-controller model reference using soft computing and performance index analyzer","authors":"N. Nahapetian, M. Jahed-Motlagh, M. Analoui","doi":"10.1109/CICA.2009.4982777","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982777","url":null,"abstract":"This paper addresses an application that involves the adaptive control of robot manipulator joint. It tries to explore the potential of using soft computing methodologies in control of plant (robot manipulator) with unknown internal behavior and environmental changes.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129473797","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982780
D. Jabri, K. Guelton, N. Manamanni, M. Abdelkrim
This paper deals with decentralized stabilization of nonlinear systems composed of interconnected Takagi-Sugeno fuzzy descriptors. To ensure the stability of the overall closed-loop system, a set of decentralized Parallel Distributed Compensations (PDC) controllers is employed. The stability conditions are then derived into Linear Matrix Inequalities (LMI) using a fuzzy Lyapunov function for less conservatism. Nevertheless, it contains decision parameters that are not available in practice. So the LMIs are casted into relaxed quadratic conditions using simple assumptions. Finally, a numerical example is proposed to illustrate the effectiveness of the suggested decentralized approach.
{"title":"Fuzzy Lyapunov decentralized control of Takagi-Sugeno interconnected descriptors","authors":"D. Jabri, K. Guelton, N. Manamanni, M. Abdelkrim","doi":"10.1109/CICA.2009.4982780","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982780","url":null,"abstract":"This paper deals with decentralized stabilization of nonlinear systems composed of interconnected Takagi-Sugeno fuzzy descriptors. To ensure the stability of the overall closed-loop system, a set of decentralized Parallel Distributed Compensations (PDC) controllers is employed. The stability conditions are then derived into Linear Matrix Inequalities (LMI) using a fuzzy Lyapunov function for less conservatism. Nevertheless, it contains decision parameters that are not available in practice. So the LMIs are casted into relaxed quadratic conditions using simple assumptions. Finally, a numerical example is proposed to illustrate the effectiveness of the suggested decentralized approach.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123536159","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982785
S. Tafazoli, M. Menhaj
Dynamical systems theory has helped brain scientists to cope better with brain complexity. In this paper, we proposed a novel approach to include uncertainty in dynamical system describing brain function such as one neuron or coupled neurons. Fuzzy dynamical systems represented by a set of fuzzy differential inclusions (FDI) are very convenient tools for modeling and simulation of various uncertain systems. We used fuzzy differential inclusion in modeling neural responses in several types of neurons. We showed that our results are very similar to real experimental data showing variability in neural responses. Further, we have shown that FDI has advantage in comparison with modeling uncertainty in neural systems with Stochastic Differential Equations (SDEs).
{"title":"Fuzzy differential inclusion in neural modeling","authors":"S. Tafazoli, M. Menhaj","doi":"10.1109/CICA.2009.4982785","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982785","url":null,"abstract":"Dynamical systems theory has helped brain scientists to cope better with brain complexity. In this paper, we proposed a novel approach to include uncertainty in dynamical system describing brain function such as one neuron or coupled neurons. Fuzzy dynamical systems represented by a set of fuzzy differential inclusions (FDI) are very convenient tools for modeling and simulation of various uncertain systems. We used fuzzy differential inclusion in modeling neural responses in several types of neurons. We showed that our results are very similar to real experimental data showing variability in neural responses. Further, we have shown that FDI has advantage in comparison with modeling uncertainty in neural systems with Stochastic Differential Equations (SDEs).","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129424764","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982790
B. Klöpper, Christoph Sondermann-Wölke, C. Romaus, Henner Vöcking
Self-optimizing mechatronic systems are a new class of technical systems. On the one hand, new challenges regarding dependability arise from their additional complexity and adaptivity. On the other hand, their abilities enable new concepts and methods to improve the dependability of mechatronic systems. This paper introduces a multi-level dependability concept for self-optimizing mechatronic systems and shows how planning can be used to improve the availability and reliability of systems in the operating stages.
{"title":"Probabilistic planning integrated in a multi-level dependability concept for mechatronic systems","authors":"B. Klöpper, Christoph Sondermann-Wölke, C. Romaus, Henner Vöcking","doi":"10.1109/CICA.2009.4982790","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982790","url":null,"abstract":"Self-optimizing mechatronic systems are a new class of technical systems. On the one hand, new challenges regarding dependability arise from their additional complexity and adaptivity. On the other hand, their abilities enable new concepts and methods to improve the dependability of mechatronic systems. This paper introduces a multi-level dependability concept for self-optimizing mechatronic systems and shows how planning can be used to improve the availability and reliability of systems in the operating stages.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117086911","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 : 2009-05-27DOI: 10.1109/CICA.2009.4982786
S. Tafazoli, K. Salahshoor, M. Menhaj
Neural system that controls movement and posture is a highly nonlinear complex system. Its adaptability and easy accommodation to changes in environment and task specifications make it an ideal system. In this paper, the muscle control system from spinal cord to muscle displacement has been studied. At first, a detailed nonlinear model is simulated in Simulink based on an already developed work. Then, three system identification techniques are examined to estimate the behavior of this complex system. The first one is based on popular linear ARX model. Then, the system is modeled by NARX neural network (Nonlinear Autoregressive Network with Exogenous Inputs) which has a powerful structural network in modeling dynamical systems. Finally, a new method of modeling using combined NARX and ARX structure is proposed in which ARX gets the linear part of the system and the NARX picks up the nonlinearities. The simulation results demonstrate the superiority of the latter method with respect to other examined approaches.
{"title":"Use of combined ARX - NARX model in identification of neuromuscular system","authors":"S. Tafazoli, K. Salahshoor, M. Menhaj","doi":"10.1109/CICA.2009.4982786","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982786","url":null,"abstract":"Neural system that controls movement and posture is a highly nonlinear complex system. Its adaptability and easy accommodation to changes in environment and task specifications make it an ideal system. In this paper, the muscle control system from spinal cord to muscle displacement has been studied. At first, a detailed nonlinear model is simulated in Simulink based on an already developed work. Then, three system identification techniques are examined to estimate the behavior of this complex system. The first one is based on popular linear ARX model. Then, the system is modeled by NARX neural network (Nonlinear Autoregressive Network with Exogenous Inputs) which has a powerful structural network in modeling dynamical systems. Finally, a new method of modeling using combined NARX and ARX structure is proposed in which ARX gets the linear part of the system and the NARX picks up the nonlinearities. The simulation results demonstrate the superiority of the latter method with respect to other examined approaches.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124566274","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 : 2009-05-08DOI: 10.1109/CICA.2009.4982778
Zeeshan-ul-hassan Usmani, A. Tariq
This work proposes a supermarket optimization simulation model called Swarm-Moves is based on self organized complex system studies to identify parameters and their values that can influence customers to buy more on impulse in a given period of time. In the proposed model, customers are assumed to have trolleys equipped with technology like RFID that can aid the passing of products' information directly from the store to them in real-time and vice-versa. Therefore, they can get the information about other customers purchase patterns and constantly informing the store of their own shopping behavior. This can be easily achieved because the trolleys “know” what products they contain at any point. The Swarm-Moves simulation is the virtual supermarket providing the visual display to run and test the proposed model. The simulation is also flexible to incorporate any given model of customers' behavior tailored to particular supermarket, settings, events or promotions. The results, although preliminary, are promising to use RFID technology for marketing products in supermarkets and provide several dimensions to look for influencing customers via feedback, real-time marketing, target advertisement and on-demand promotions.
{"title":"Influencing customers through customers - Simulation of herd behavior in supermarkets","authors":"Zeeshan-ul-hassan Usmani, A. Tariq","doi":"10.1109/CICA.2009.4982778","DOIUrl":"https://doi.org/10.1109/CICA.2009.4982778","url":null,"abstract":"This work proposes a supermarket optimization simulation model called Swarm-Moves is based on self organized complex system studies to identify parameters and their values that can influence customers to buy more on impulse in a given period of time. In the proposed model, customers are assumed to have trolleys equipped with technology like RFID that can aid the passing of products' information directly from the store to them in real-time and vice-versa. Therefore, they can get the information about other customers purchase patterns and constantly informing the store of their own shopping behavior. This can be easily achieved because the trolleys “know” what products they contain at any point. The Swarm-Moves simulation is the virtual supermarket providing the visual display to run and test the proposed model. The simulation is also flexible to incorporate any given model of customers' behavior tailored to particular supermarket, settings, events or promotions. The results, although preliminary, are promising to use RFID technology for marketing products in supermarkets and provide several dimensions to look for influencing customers via feedback, real-time marketing, target advertisement and on-demand promotions.","PeriodicalId":383751,"journal":{"name":"2009 IEEE Symposium on Computational Intelligence in Control and Automation","volume":"265 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2009-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127545169","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：