检索结果-内蒙古大学图书馆

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

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

Certainty and expertness-based credit assignment for cooperative Q-Learning agents with an AND-type task

Certainty and expertness-based credit assignment for coopera...

引用

International Conference on Neural Information Processing

作者： A. Harati M.N. Ahmadabadi School of Intelligent Systems Institute of Studies in Theoretical Physics and Mathematics Tehran Iran Control and Intelligent Processing Center of Excellence & AI and Robotics Laboratory Department of Electrical and Computer Engineering University of Tehran Tehran Iran

In multiagent reinforcement learning, inter-agent credit assignment is a fundamental problem, since a single scalar reinforcement signal is the only reliable feedback that teams of learning agents receive. This problem is more critical in groups of independent learners with a joint task. In this research, it is assumed that a critic agent receives the environment feedback and assigns a proper credit to each agent using some measures. Three of such measures for a team of cooperative agents with a parallel and AND-type task are introduced. These measures somehow compare the agents' knowledge. One of these criteria, called normal expertness, is a non-relative measure while two other ones (certainty and relative normal expertness) are relative measure. It is experimentally shown that relative measures work better as they contain more information for the critic agent.

关键词： Feedback intelligent agent intelligent robots Process control Control systems intelligent control Artificial intelligence Robot kinematics Physics computing Reliability engineering

来源：评论

学校读者我要写书评

暂无评论

A new model of the visual feedback coordinate transformation in humans based on disturbance noise and feedback error that accounts for time delays

A new model of the visual feedback coordinate transformation...

引用

IEEE International Workshop on intelligent Robots and systems (IROS)

作者： E. Oyama K.F. MacDorman T. Maeda S. Tachi A. Agah Science and Technology (AIST) National Institute for Advanced Industrial Science and Technology Tsukuba Ibaraki Japan Intelligent Robotics Laboratory Graduate School of Systems Engineering Wakayama University Wakayama Japan School of Engineering University of Tokyo Bunkyo Tokyo Japan Department of Electrical Engineering and Computer Science University of Kansas Lawrence KS USA

An essential factor in understanding the motor learning capability of humans, is the coordinate transformation learning of the visual feedback controller. Although a number of learning models for the visual feedback controller have been proposed, none has been able to establish a definitive approach. In our previous work, we have suggested a learning model that uses disturbance noise and the feedback error signal to learn the human visual feedback controller's coordinate transformation. However, the model does not fully consider the time delay in the visual feedback control loop. This paper presents a modified learning model taking into account the time delay and the convergence properties of the model. Numerical simulations are presented to illustrate the effectiveness of the proposed approach.

关键词： Humans Delay effects Adaptive control Error correction Biological system modeling Feedback control Convergence Kinematics intelligent robots Velocity control

来源：评论

学校读者我要写书评

暂无评论

Recognizing hand posture by vision: applications in humanoid personal robotics

Recognizing hand posture by vision: applications in humanoid...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： C. Laschi M. Gonzalo-Tasis J.F. Codes P. Dario Arts Lab (Advanced Robotics Technology and Systems Laboratory) Scuola Superiore Sant'' Anna Pisa Italy Humanoid Robotics Institute Waseda University Tokyo Japan Eca-Simm Group Department of Computer Science University of Valladolid Spain Department of Algebra Geometry and Topology University of Valladolid Spain

In the development of humanoid personal robots, accompanying the life of humans in their everyday activities, vision is no doubt an extremely important sensory capability to provide the robots with. We propose the application of robot vision to the identification of hand posture, as a first step in gesture detection, for two main classes of reasons: 1) the recognition of human hand posture can help human-robot interaction, especially in relation to 'teaching by demonstration'; 2) the recognition of the robot hand can allow visual servoing, especially helpful in environments and tasks with a high level of uncertainty. The paper presents the development of a vision system for hand posture recognition, by describing the basic algorithmic implementation, based on symbolic representations, and reporting the experimental results obtained in the recognition of a three-fingered robotic hand.

关键词： Humanoid robots Robot vision systems Robot kinematics Robot sensing systems Human robot interaction Visual servoing Education robotics and automation Grasping Subspace constraints

来源：评论

学校读者我要写书评

暂无评论

3D simultaneous localisation and map-building using active vision for a robot moving on undulating terrain

3D simultaneous localisation and map-building using active v...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： A.J. Davison N. Kita Robotics Research Group Department of Engineering Science University of Oxford UK Intelligent Systems Institute AIST Tsukuba Ibaraki Japan

ISBN: (纸本)0769512720

Work in simultaneous localisation and map-building ("SLAM") for mobile robots has focused on the simplified case in which a robot is considered to move in two dimensions on a ground plane. While this is often a good approximation, a large number of real-world applications require robots to move around terrain which has significant slopes and undulations, and it is desirable that these robots too should be able to estimate their locations by building maps of natural features. We describe a real-time EKF-based-SLAM system permitting unconstrained 3D localisation, and in particular develop models for the motion of a wheeled robot in the presence of unknown slope variations. In a fully automatic implementation, our robot observes visual point features using fixating stereo vision and builds a sparse map on-the-fly. Combining this visual measurement with information from odometry and a roll/pitch accelerometer sensor, the robot performs accurate, repeatable localisation while traversing an undulating course.

关键词： Robot vision systems Mobile robots Robot sensing systems robotics and automation Simultaneous localization and mapping Accelerometers computer vision Real time systems Stereo vision intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Learning relational rule from examples that are neither positive nor negative

引用

systems and computers in Japan 2001年第14期32卷 34-40页

作者： Ichise, Ryutaro Numao, Masayuki Knowledge Systems Research Intelligent Systems Research Division National Institute of Informatics Tokyo 101-8430 Japan Department of Computer Science Graduate School of Information Science and Engineering Tokyo Institute of Technology Tokyo 152-8552 Japan

Over the past decade, several inductive logic programming (ILP) systems have been developed. However, the normal ILP system does not have enough power to induce logic programs in some domains. Therefore, various new ILP systems, such as nonmonotonic ILP, that apply new learning tasks, have been proposed. In the present paper, a new learning task, called relational learning from nondichotomizable examples, is proposed for relational domains. The scheme of this task is similar to that of normal ILP, with the exception of the training examples. Normally, conventional ILP uses positive and negative examples in the training process. However, the examples of the proposed learning task are not strictly positive or negative: the training examples have a continuous scale. This new learning task is defined and a new method for learning this task is proposed. A new ILP system, SYNGIP (for SYNthesized system using Genetic programming and Inductive logic Programming), is developed based on this method and the performance of SYNGIP is compared experimentally to that of the conventional ILP method for the task of human feeling acquisition. © 2001 Scripta Technica, Syst. Comp. Jpn.

关键词： Logic programming

来源：评论

学校读者我要写书评

暂无评论

Fault detection using RBFN- and AR-based general parameter methods

Fault detection using RBFN- and AR-based general parameter m...

引用

IEEE International Conference on systems, Man and Cybernetics

作者： Y. Dote S.J. Ovaska Xiao-Zhi Gao Department of Computer Science and Systems Engineering Muroran Institute of Technology Muroran Japan Institute of Intelligent Power Electronics Helsinki University of Technology Espoo Finland

This paper compares the performance of nonlinear radial basis function network-based (RBFN) and linear autoregressive (AR) model-based general parameter (GP) methods in a fault detection application. We use the efficient GP approach for initializing the weights of the RBFN model in the beginning of the off-line system identification phase, as well as for fine-tuning the modeling accuracy of RBFN and AR models online. Our fault detection scheme is based on monitoring the expectation value of the scalar general parameter. This provides improved robustness and detection sensitivity over such methods where the online prediction error is used directly in the decision-making process. In order to illustrate the performance of the efficient nonlinear and linear schemes, they are applied to fault detection of automobile transmission gears. As the acoustic sound level time-series, providing the necessary basis information for fault detection, is slightly nonlinear, the GP-RBFN outperformed the linear methods: the GP-AR method and conventional AR inverse filtering. Both of the GP-based methods provide competitive alternatives for real-world fault detection and diagnosis.

关键词： Fault detection System identification Condition monitoring Robustness Acoustic signal detection Decision making Automobiles Gears Nonlinear acoustics Information filtering

来源：评论

学校读者我要写书评

暂无评论

DFSLIF: dynamical fuzzy system with linguistic information feedback

DFSLIF: dynamical fuzzy system with linguistic information f...

引用

IEEE Workshop on Soft Computing in Industrial Applications (SMCia)

作者： X.Z. Gao S.J. Ovaska Y. Dote Institute of Intelligent Power Electronics Helsinki University of Technology Espoo Finland Department of Computer Science and Systems Engineering Muroran Institute of Technology Muroran Japan

ISBN: (纸本)0780371542

We propose a new dynamical fuzzy system with linguistic information feedback (DFSLIF). Instead of crisp system output, the delayed conclusion fuzzy membership function in the consequence part is fed back locally with adjustable scaling and shifting in order to overcome the static mapping drawback of conventional fuzzy systems. We give a detailed description of the corresponding structure and algorithm. Our novel scheme has the advantage of inherent dynamics, and is therefore well suited for handling temporal problems like dynamical system identification, control, and filtering. Simulation experiments have been carried out to demonstrate its effectiveness.

关键词： Fuzzy systems Feedback Fuzzy logic Fuzzy sets Filtering Modeling Nonlinear dynamical systems Engines Power electronics computer science

来源：评论

学校读者我要写书评

暂无评论

Machining feature-based comparisons of mechanical parts

Machining feature-based comparisons of mechanical parts

引用

International Conference on Shape Modeling and Applications

作者： V. Cicirello W.C. Regli The Robotics Institute Carnegie Mellon University Pittsburgh PA USA Geometric and Intelligent Computing Laboratory Department of Mathematics and Computer Science Drexel University Philadelphia PA USA

ISBN: (纸本)0769508537

Solid models are the critical data elements in modern computer-aided design (CAD) environments, describing the shape and form of manufactured artifacts. Their growing ubiquity has created new problems in how to effectively manage the many models that are now stored in the digital libraries of large design and manufacturing enterprises. Existing techniques from the engineering literature and from industrial practice, such as group technology, rely on human-supervised encoding and classification, while techniques from the multimedia database and computer graphics/vision communities often ignore the manufacturing attributes most significant in the classification of models. This paper presents our approach to the manufacturing similarly assessment of solid models of mechanical parts based on machining features. Our technical approach is three-fold: (1) perform machining feature extraction to map the solid model to a set of STEP AP 224 machining features; (2) construct a model dependency graph from the set of machining features; and (3) find the nearest neighbors to the query graph using an iterative improvement search across a database of other models. We also present empirical experiments to validate our approach using our testbed, the National Design Repository ( ). The contribution of this research is the first fully automated technique for machining feature-based comparisons of mechanical artifacts. We believe that this work can lead to radical changes in the way in which design data is managed in modern engineering enterprises.

关键词： Machining Solid modeling Virtual manufacturing Design automation computer aided manufacturing Data engineering Shape Software libraries computer industry Manufacturing industries

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：