检索结果-内蒙古大学图书馆

IEEE International Workshop on Intelligent Robots and Systems (IROS)

作者： W. Abd-Almageed C.E. Smith Department of Electrical and Computer Engineering Robotics Artificial Intelligence and Vision Laboratory University of New Mexico Albuquerque NM USA

A fundamental problem in computer vision is the issue of shape ambiguity. Simply stated, a silhouette cannot uniquely identify an object or an object's classification since many unique objects can present identical occluding contours. This problem has no solution in the general case for a monocular vision system. This paper presents a method for disambiguating objects during silhouette matching using a visual servoing system. This method identifies the camera motion(s) that gives disambiguating views of the objects. These motions are identified through a new technique called contour migration. The occluding contour's shape is used to identify objects or object classes that are potential matches for that shape. A contour migration is then determined that disambiguates the possible matches by purposive viewpoint adjustment. The technique is demonstrated using an example set of objects.

关键词： Shape Cameras computer vision Object recognition Machine vision Databases Intelligent robots Robot vision systems Artificial intelligence Laboratories

来源：评论

学校读者我要写书评

暂无评论

Mixture models for dynamic statistical pressure snakes

Mixture models for dynamic statistical pressure snakes

引用

International Conference on Pattern Recognition

作者： W. Abd-Almageed C.E. Smith Robotics Artificial Intelligence and Vision Laboratory Electrical and Computer Engineering Department University of New Mexico Albuquerque NM USA

This paper introduces a new approach to statistical pressure snakes. It uses statistical modeling for both object and background to obtain a more robust pressure model. The Expectation Maximization (EM) algorithm is used to model the data into a Mixture of Gaussians (MoG). Bayesian theory is then employed as a decision making mechanism. Experimental results using the traditional pressure model and the new mixture pressure model demonstrate the effectiveness of the new models.

关键词： Image edge detection computer vision Equations Robot vision systems Robustness Bayesian methods Active contours Gaussian distribution Intelligent robots Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Adaptive non model-based piezoelectric control of flexible beams with translational base

Adaptive non model-based piezoelectric control of flexible b...

引用

American Control Conference (ACC)

作者： N. Jalili M. Dadfarnia F. Hong S.S. Ge Robotics and Mechatronics Laboratory Department of Mechanical Engineering Clemson University Clemson SC USA Department of Electrical and Computer Engineering National University of Singapore Singapore

An adaptive, nonmodel-based controller is proposed for the tracking control of a flexible cantilever beam with a translational base support. A piezoelectric (PZT) patch actuator is bonded on the top surface of the beam to apply a controlled moment for vibration suppression requirement. By selecting a Lyapunov function candidate based on a very simple energy relationship, an adaptive nonlinear feedback gain for the PZT input voltage and a simple PD controller for the moving base input force are designed to make the closed-loop system energy dissipative and hence stable. Due to the non model-based nature of the controller, some favorable features appear such as elimination of control spillovers, suppression of residual oscillations of the beam and simplicity of the control implementation. The feasibility of the controller is demonstrated using numerical simulations. Although the controller derivation is based on the original distributed partial differential model, a two-node finite element model is used for the numerical solution of the coupled PDE of the system.

关键词： Programmable control Adaptive control Force feedback Structural beams Piezoelectric actuators Bonding Vibration control Lyapunov method PD control Force control

来源：评论

学校读者我要写书评

暂无评论

Generalized adaptive output-feedback form with unknown parameters multiplying high output relative-degree states

Generalized adaptive output-feedback form with unknown param...

引用

IEEE Conference on Decision and Control

作者： P. Krishnamurthy F. Khorrami Control/Robotics Research Laboratory Department of Electrical and Computer Engineering Six Metrotech Center Polytechnic University Brooklyn NY USA

We propose a global high-gain scaling based observer/controller for systems in the uncertain generalized output-feedback canonical form. Time-varying nonlinear parametric uncertainty is allowed to occur coupled with unmeasured states in the system dynamics. This represents a significant generalization from existing results which allow unknown parameters only in output-dependent terms. This restriction in previous results is mainly owing to the fact that no general solution is known for systems involving bilinear terms in unmeasured states. The design utilizes the dual architecture of a high-gain observer and controller with the underlying state scaling being dynamically output-dependent. The proposed observer/controller structure provides a globally asymptotically stabilizing output-feedback solution for the benchmark open problem proposed in our earlier work with the provision that a magnitude bound on the unknown parameter be given.

关键词： Riccati equations Control systems Linear matrix inequalities Differential equations Robot control Laboratories Ear Uncertainty Lyapunov method Linear systems

来源：评论

学校读者我要写书评

暂无评论

FUZZY COGNITIVE MAPS MODEL FOR LARGE SCALE COMPLEX SYSTEMS

引用

IFAC Proceedings Volumes 2002年第1期35卷 277-282页

作者： C.D. Stylios Peter P. Groumpos Laboratory for Automation and Robotics Department of Electrical and Computer Engineering University of Patras Rion 26500 GREECE Tel. +30 61 997293 Fax. +30 61 997309

Most of the technological systems are characterized by complexity, coupled relationships with feedback and a demanding procedure to develop their models. This paper presents the Soft Computing technique of Fuzzy Cognitive Maps that are knowledge-based methodologies suitable to describe and model complex systems and handle with available information from an abstract point of view. Fuzzy cognitive Maps develop behavioral model of the system exploiting the experience and knowledge of experts. Fuzzy Cognitive Maps applicability in modeling complex systems is presented and a general hierarchical structure is proposed to model any complex system. Within the hierarchical structure, Fuzzy Cognitive Map models the coordinator of the system and develops an abstract conceptual model of the complex system.

关键词： Complex Systems Fuzzy Cognitive Map Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

ACTIVATION HEBBIAN LEARNING RULE FOR FUZZY COGNITIVE MAPS

引用

IFAC Proceedings Volumes 2002年第1期35卷 319-324页

作者： Elpiniki Papageorgiou Chrysostomos D. Stylios Peter P. Groumpos Laboratory for Automation and Robotics Department of Electrical and Computer Engineering University of Patras Rion 26500 GREECE Tel. +30 61 997293 Fax. +30 61 997309

Fuzzy Cognitive Maps (FCM) is a soft computing, modeling methodology for complex systems, which is originated from the combination of fuzzy logic and neural networks. Many different learning algorithms have been suggested for the training of neural networks. Only some initial thoughts on learning rules have described for FCMs. A learning law is a mathematical algorithm, which can train the FCM by selecting the appropriate weights and it is very important for a system to have learning and adaptive capabilities. In this paper a new learning algorithm, the Activation Hebbian Learning (AHL) has been proposed for FCMs. The learning rule for a FCM is a procedure where FCM weight matrix is modified in order the FCM to model the behavior of a system. Simulation results proving the strength of the learning rule are provided.

关键词： Hebbian learning Fuzzy Cognitive Maps Modeling Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

ON–LINE IMPROVEMENT FOR THE DECENTRALIZED PREDICTIVE CONTROL OF THE HEAT DYNAMICS OF A GREENHOUSE

引用

IFAC Proceedings Volumes 2002年第1期35卷 37-42页

作者： E.J. Kyriannakis K.G. Arvanitis N. Sigrimis National Technical University of Athens Dept. of Electrical and Computer Engineering Intelligent Robotics and Automation Laboratory Zographou 15773 Athens GREECE Agricultural University of Athens Department of Agricultural Engineering Athens 11855 GREECE

A decentralized model-based predictive controller is used for the design of discrete-time control systems aiming at regulating the air temperature and heat supply in greenhouses. Moreover, alternative techniques are proposed for the approximation of the decentralized part of the control and the on-line improvement of the overall control problem. A state space model is used to predict the corresponding local indoor temperature over a long-range time-period and approximate models are used to predict the interactions among the subsystems. The sun radiation and outdoor temperature are treated as external disturbances that affect the overall system dynamics. A series of energy fluxes consist the heating system and the predictive controllers have proved to be powerful in controlling the supply temperature.

关键词： Decentralized control predictive control greenhouse heat dynamics

来源：评论

学校读者我要写书评

暂无评论

Entire region filling in indoor environments using neural networks

Entire region filling in indoor environments using neural ne...

引用

World Congress on Intelligent Control and Automation (WCICA)

作者： Chaomin Luo S.X. Yang M. Meng Advanced Robotics and Intelligent Systems (ARIS) Laboratory School of Engineering University of Guelph Guelph Canada Department of Electrical and Computer Engineering University of Alberta Edmonton Canada

Entire region filling is a special type of robot path planning strategy that requires the mobile robot to cover every part of the whole workspace, which has many applications such as cleaning robots, vacuum cleaners, painter robots, land mine detectors, lawn mowers, and window cleaners. In this paper, a novel biologically inspired neural network approach is proposed for entire region filling with obstacle avoidance of a mobile cleaning robot in a nonstationary environment. The dynamics of each neuron in the topologically organized neural network is characterized by a shunting equation or an additive equation derived from Hodgkin and Huxley's (1952) membrane equation. There are only local lateral connections among neurons. Thus the computational complexity linearly depends on the neural network size. The robot path is autonomously generated from the dynamic activity landscape of the neural network and the previous robot location. The proposed model algorithm is computationally efficient. It can deal with an unstructured environment with irregular obstacles. The effectiveness of the proposed model is demonstrated by simulation results.

关键词： Filling Indoor environments Neural networks Mobile robots Equations Cleaning Landmine detection Neurons Computational modeling Path planning

来源：评论

学校读者我要写书评

暂无评论

A new approach to credit assignment in a team of cooperative Q-learning agents

A new approach to credit assignment in a team of cooperative...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： A. Harati M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Q-learning is widely used in many multi agent systems. In most cases, a separate critic is considered for qualifying each individual agent behavior or it is assumed that the critic is completely aware of effects of all agents' actions on the team qualification. But, in many cases, the role of each team member in the group performance is not known. In order to distribute a common credit among the agents, a suitable criterion must be provided to estimate the role of each agent in the team performance and to judge if an agent has done a wrong action. In this paper two such criteria, named certainty and expertness, for a team of agents with parallel tasks are introduced. In addition, two methods for reinforcing the agents based on the proposed measures are provided. Some simulation results are also reported to show the effectiveness of the proposed measures and methods.

关键词： Intelligent agent Learning systems Multiagent systems Intelligent sensors Artificial intelligence Laboratories Intelligent systems Intelligent robots Physics Mathematics

来源：评论

学校读者我要写书评

暂无评论

Cooperative Q-learning with heterogeneity in actions

Cooperative Q-learning with heterogeneity in actions

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： S.M. Reza MirFattah M.N. Ahmadabadi Institute for Studies on Theoretical Physics and Mathematics School of Intelligent Systems Tehran Iran Robotics and AI Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

Cooperation in learning improves the speed of convergence and the quality of learning. Special care is needed when heterogeneous agents cooperate in learning. It is discussed that, cooperation in learning may cause the learning process to diverge if heterogeneity is not handled properly. In this paper, it is assumed that two heterogeneous Q-learning agents cooperate to learn. The heterogeneity is assumed in their action order (and not in their action set). A Q-learning-based method is introduced for the agents to learn the mapping among their actions. It is shown that, the agents are able to learn this mapping while cooperating in learning. Some simulation results are reported to show the effectiveness of the proposed method.

关键词： Intelligent agent Intelligent robots Humans Telecommunication control Artificial intelligence Laboratories Intelligent systems Physics Mathematics Convergence

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：