检索结果-内蒙古大学图书馆

2011 IEEE/RSJ International Conference on intelligent Robots and Systems

作者： David Folio Christian Dahmen Tim Wortmann M. Arif Zeeshan Kaiyu Shou Salvador Pané Bradley J. Nelson Antoine Ferreira Sergej Fatikow Laboratoire PRISME ENSI de Bourges Bourges France Division Microrobotics and Control Engineering University of Oldenburg Oldenburg Germany Multi-Scale Robotics Laboratory Institute of Robotics and Intelligent Systems ETH Zurich Zurich Switzerland

The propulsion of nano-ferromagnetic objects by means of MRI gradients is a promising approach to enable new forms of therapy. In this work, necessary techniques are presented to make this approach work. This includes path planning algorithms working on MRI data, ferromagnetic artifact imaging and a tracking algorithm which delivers position feedback for the microdevice and a propulsion sequence to enable interleaved magnetic propulsion and imaging. Using a dedicated software environment integrating path-planning methods and real-time tracking, a clinical MRI system is adapted to provide this new functionality for potential controlled interventional targeted therapeutic applications. Through MRI-based sensing analysis, this paper aims to propose a framework to plan a robust pathway to enhance the navigation ability to reach deep locations in human body. The proposed approaches are validated with different experiments.

关键词： Magnetic resonance imaging Navigation Target tracking Uncertainty Planning Sensors

来源：评论

学校读者我要写书评

暂无评论

Modified Banker's algorithm for scheduling in multi-AGV systems

Modified Banker's algorithm for scheduling in multi-AGV syst...

引用

IEEE International Conference on Automation Science and Engineering (CASE)

作者： Luka Kalinovcic Tamara Petrovic Stjepan Bogdan Vedran Bobanac Laboratory for Robotics and Intelligent Control Systems Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia Laboratory for Renewable Energy Sources Department of Control and Computer Engineering Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

In today's highly complex multi-AGV systems key research objective is finding a scheduling and routing policy that avoids deadlock while assuring that vehicle utilization is as high as possible. It is well known that finding such an optimal policy is a NP-hard task in general case. Therefore, big part of the research is oriented towards finding various suboptimal policies that can be applied to real world plants. In this paper we propose modified Banker's algorithm for scheduling in multi-AGV systems. A predetermined mission's path is executed in a way that some non-safe states are allowed in order to achieve better utilization of vehicles. A graph-based method of polynomial complexity for verification of these states is given. Algorithm is tested on a layout of a real plant for packing and warehousing palettes. Results shown at the end of the paper demonstrate advantages of the proposed method compared with other methods based on Banker's algorithm.

关键词： Vehicles System recovery Layout Resource management Job shop scheduling Workstations

来源：评论

学校读者我要写书评

暂无评论

New simplified model for an under-actuated quadruped robot in bounding motion

New simplified model for an under-actuated quadruped robot i...

引用

International Conference on control, Instrumentation, and Automation

作者： Hamed Kazemi Vahid Johari Majd Majid M. Moghaddam Intelligent Control Systems Laboratory School of Electrical and Computer Engineering Tarbiat Moalem University Tehran Iran Intelligent Control Systems Laboratory Tarbiat Modares University Tehran Iran Robotics and Mechatronics Laboratory Mechanical Engineering Department Tarbiat Moalem University Tehran Iran Mechanical Engineering Department Tarbiat Modares University Tehran Iran

In this paper, a quadruped robot is studied in bounding motion. A new simplified model of quadruped robot in bounding motion with four actuated and two unactuated joints is developed. The kinetic and potential energies of the under-actuated mechanical model of the quadruped robot are obtained and the dynamics of the robot model is derived using the Lagrangian method. It is shown that the dynamical equation of the proposed simplified model belongs to a class of second-order nonholonomic mechanical systems. The main motivation of this paper is to obtain quadruped model in bounding motion such that one can apply different control methods directly or after transformation in the obtained dynamic equations. Utilizing MATLAB, dynamics of the planar model has been simulated in backward and forward states. Physical parameters of the Little-Dog robot as an instance of the quadruped robot are considered in simulation The simulation is without control and therefore is unstable but it illustrates robot's manner in bounding motion before instability.

关键词： Mathematical model Legged locomotion Dynamics Equations Joints Robot kinematics

来源：评论

学校读者我要写书评

暂无评论

Real-time co-operative decision making & control systems

Real-time co-operative decision making & control systems

引用

XXII International Symposium on Information, Communication and Automation Technologies, ICAT

作者： Ljubo B. Vlacic Daniel I. Thomas Joshué Pérez Intelligent Control Systems Laboratory (ICSL) Griffith University Brisbane Australia Technology One Limited Brisbane Australia Centre of Automation and Robotics University Polytechnic of Madrid Madrid Spain

Learning and adaptability (and thus the ability of being co-operative) are important features of decision & control systems. This paper investigates decision making and control concepts that enable human beings and artificial beings to interact and co-operate in real time in a dynamic and reliable way. It examines the aspects of being co-operative and substitutable in the context of: (i) co-operative driving by driverless vehicles; and (ii) computer game play scenarios for collaborative and social interactions.

关键词： Humans Games Decision making Collaboration Computers control systems Robots

来源：评论

学校读者我要写书评

暂无评论

Agent self-assessment: Determining policy quality without execution

Agent self-assessment: Determining policy quality without ex...

引用

IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning, (ADPRL)

作者： Alexander Hans Siegmund Duell Steffen Udluft Neuroinformatics and Cognitive Robotics Laboratory Ilmenau University of Technology Ilmenau Germany Machine Learning Group Berlin Institute of Technology Berlin Germany Intelligent Systems and Control Siemens AG Munich Germany

With the development of data-efficient reinforcement learning (RL) methods, a promising data-driven solution for optimal control of complex technical systems has become available. For the application of RL to a technical system, it is usually required to evaluate a policy before actually applying it to ensure it operates the system safely and within required performance bounds. In benchmark applications one can use the system dynamics directly to measure the policy quality. In real applications, however, this might be too expensive or even impossible. Being unable to evaluate the policy without using the actual system hinders the application of RL to autonomous controllers. As a first step toward agent self-assessment, we deal with discrete MDPs in this paper. We propose to use the value function along with its uncertainty to assess a policy's quality and show that, when dealing with an MDP estimated from observations, the value function itself can be misleading. We address this problem by determining the value function's uncertainty through uncertainty propagation and evaluate the approach using a number of benchmark applications.

关键词： Uncertainty Equations Markov processes Benchmark testing Approximation algorithms Machine learning Histograms

来源：评论

学校读者我要写书评

暂无评论

Extracting salient lines by Visual Attention for omnidirectional image classification

Extracting salient lines by Visual Attention for omnidirecti...

引用

IEEE Symposium on Computational Intelligence for Multimedia, Signal and Vision Processing (CIMSIVP)

作者： AmirHossein Habibian Majid Nili-Ahmadabadi Babak Nadjar Araabi Robotics and AI Laboratory Control and Intelligent Processing Center of Excellence School of Electrical and Computer Engineering Faculty of Engineering University of Tehran Tehran Iran School of Cognitive Sciences Institute for Research in Fundamental Sciences Tehran Iran

Representing an image as a set of its key and interesting lines facilitates the image understanding and classification. In this paper, we propose a method to extract the significant and interesting lines of the scene, which probably are useful in image classification. The proposed method is inspired from the Visual Attention, which is a perceptual mechanism in human and other primates that direct their perceptions to the limited regions of the scene. The attended regions are usually valuable in performing the task. Since the approach of using the lines to classify the images is particularly useful for omnidirectional images, we specialize our method to deal with these kinds of images. In the experiments, we demonstrate how our proposed methods improve the image classification performance with processing only small parts of the input images.

关键词： Feature extraction Visualization Image classification Gabor filters Image edge detection Histograms Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Adaptive and Repetitive controller for Robotic Manipulators with Slowly Updating Scheme Using B-Spline Shape Function

Adaptive and Repetitive Controller for Robotic Manipulators ...

引用

IEEE International Conference on robotics and Biomimetics

作者： Pannatee Rakprayoon Peerayot Sanposh Nattapon Chayopitak Intelligent Mechatronics Automation Robotics and Control Laboratory Department of Electrical Engineering Kasetsart University Industrial Control and Automation Laboratory National Electronics and Computer Technology Center

ISBN: (纸本)9781457721366

This paper studies the real-time adaptive and repetitive control problem using the Desired Compensation Learning Law (DCLL) that has the advantage of robustness under the presence of unknown parameters with low memory requirement. The control structure of DCLL consists of a feedforward compensator that is designed by a linear combination of shape functions that is adaptable to parameter variations;hence the selection of appropriate shape functions plays an important role in the adaptive ability and accuracy of DCLL. In this study, the B-spline shape function is proposed to be used under the slowly updating scheme and the obtained results show that the robustness and accuracy of the tracking can be greatly improved even under payload variation and torque limits.

关键词： shape functions Repetitive controllers Self tuning splines (mathematics) Scheme Robot Manipulator adaptive capacity memory requirements control Architecture Manipulators Unknown parameter Linear Combination

来源：评论

学校读者我要写书评

暂无评论

Enhancing student learning: On-line interactive laboratory for modelling of real world control system applications

引用

IFAC Proceedings Volumes 2011年第1期44卷 7268-7273页

作者： Joshué Pérez Sebastián Dormido Ljubo Vlacic Centre of Automation and Robotics (CAR) University Polytechnic of Madrid (UPM) – Spanish National Research Council (CSIC) Madrid Spain Dep. Informática y Automática Escuela Técnica Superior de Ingeniería Informática Universidad Nacional de Educación a Distancia Madrid Spain Intelligent Control Systems Laboratory Griffith University Brisbane Australia

Abstract Teaching an introductory course on control systems to undergraduate students often seeks elaborations on real engineering world control system applications to assist students in grasping theoretical concepts. In this paper, the newly developed animated and interactive control systems tutorials are presented. The paper shows that this teaching approach helps students in bridging the gap between the classical control techniques and the real world applications. The course evaluations undertaken since the time of the inclusion of the animated tutorials into the teaching process clearly show the learning improvement gained, reflected in increased average scores, and reduced course fail grade.

关键词： Interactive control system tutorials Interactive teaching tools Animation Distance Education

来源：评论

学校读者我要写书评

暂无评论

An inverted pendulum model based humanoid gait generation using convex optimization

引用

Journal of Information and Computational Science 2010年第12期7卷 2529-2538页

作者： Xiong, Rong Sun, Yichao Chu, Jian Zhou, Changjiu State Key Laboratory of Industrial Control Technology Zhejiang University Hangzhou 310000 China Centre for Advance Robotics and Intelligent Control Singapore Polytechnic Singapore Singapore

Convex optimization has the advantages on solving the problems with hundreds of variables and thousands of constraints. However, traditional multi-body model based zero moment point (ZMP) formulation makes it impossible to introduce the convex optimization into humanoid gait generation because the constraint can not be transferred into convex. This paper derives a new ZMP formulation by combining the linear inverted pendulum model and the multi-body model in the representation of Lie group. With this new ZMP formulation, an instance of walking gait generation by using convex optimization is given. The experimental results show that the number of iterations involved in solving the problem is less than 10, which ensures the effectiveness and efficiency of using convex optimization to generate humanoid gait online. © 2010 Binary Information Press.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

Ensembles of Neural Networks for Robust Reinforcement Learning

Ensembles of Neural Networks for Robust Reinforcement Learni...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Alexander Hans Steffen Udluft Neuroinformatics and Cognitive Robotics Laboratory Ilmenau University of Technology Ilmenau Germany Intelligent Systems and Control Corporate Technology Siemens AG Germany

Reinforcement learning algorithms that employ neural networks as function approximators have proven to be powerful tools for solving optimal control problems. However, their training and the validation of final policies can be cumbersome as neural networks can suffer from problems like local minima or over fitting. When using iterative methods, such as neural fitted Q-iteration, the problem becomes even more pronounced since the network has to be trained multiple times and the training process in one iteration builds on the network trained in the previous iteration. Therefore errors can accumulate. In this paper we propose to use ensembles of networks to make the learning process more robust and produce near-optimal policies more reliably. We name various ways of combining single networks to an ensemble that results in a final ensemble policy and show the potential of the approach using a benchmark application. Our experiments indicate that majority voting is superior to Q-averaging and using heterogeneous ensembles (different network topologies) is advisable.

关键词： Training Function approximation Artificial neural networks Network topology Approximation algorithms Neurons

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：