检索结果-内蒙古大学图书馆

2011 3rd International Asia Conference on Informatics in Control, Automation and Robotics(CAR 2011)

作者： Liangbing Feng Masanao Obayashi Takashi Kuremoto Kunikazu Kobayashi Division of Computer Science & Design Engineering Yamaguchi University

The optimization and verification for a robot control system have been studied *** this paper,we propose a robot control model which combines optimization and verification based on Learning Petri Net(LPN).In our former work,learning Petri net model has been constructed based on high-level time Petri net and Reinforcement Learning(RL).The reinforcement learning is applied to optimize the parameters of Petri *** parameters adjusting may make the properties of learning Petri net *** this paper,the verification algorithms for learning Petri net are *** this model,a robot control system with optimization and verification capability is ***,for the purpose of certification of the effectiveness of our proposed methods,this robot control system is used to control a robot system–E-puck as an *** result of the experiment shows the methods are correct and effective.

关键词： Petri net,reinforcement learning,robot control system,e-puck

来源：评论

学校读者我要写书评

暂无评论

A Neuro-fuzzy Network with Reinforcement Learning Algorithms for Swarm Learning

A Neuro-fuzzy Network with Reinforcement Learning Algorithms...

引用

2011 International Conference on Future Wireless Networks and Information Systems (ICFWI 2011)

作者： Takashi Kuremoto Yuki Yamano Liang-Bing Feng Kunikazu Kobayashi Masanao Obayashi Division of Computer Science & Design Engineering Graduate School of Science and EngineeringYamaguchi University

An internal model of autonomous mobile robots(agent) is proposed in this paper. A TSK-type fuzzy net is used as a classifier of environment information, i.e., the state of an agent, and reinforcement learning methods such as Q-learning, sarsa-learning are used to make multiple agents acquire adaptive behaviors. Goal navigated exploration problem was simulated to confirm the effectiveness of the proposed methods, and the results showed that the new learning methods are more efficient than actor-critic method which was proposed by our previous work.

关键词： multi-agent system,reinforcement learning,swarm learning,neurofuzzy network

来源：评论

学校读者我要写书评

暂无评论

Intelligent tracking control method of a target by group of agents with nonlinear dynamics

Intelligent tracking control method of a target by group of ...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Masanao Obayashi Yuuki Yokoji Shogo Uchiyama Liangbing Feng Takashi Kuremoto Kunikazu Kobayashi Division of Computer Science & Design Engineering Yamaguchi University Ube Japan

This paper proposes the intelligent tracking control of the target by group of agents with nonlinear dynamics. In the proposed method, agents can exchange only information of positions and the group of agents track the target based on only its position, taking a predefined formation. In the real world, the method that agents do not require a lot of information is useful for the case of existing communication delay of information and weak communication. In addition, each agent shall have the nonlinear dynamics and external disturbance. Therefore an auto- structuring fuzzy neural control system (ASFNCS) is introduced to provide appropriate control inputs while coping well with disturbance and nonlinear dynamics. Thus, while maintaining adequate control performance, the method can reduce the computational load. In the simulation, it is verified that the proposed method is useful in the point of target tracking performance through distributed agent cooperation behaviors.

关键词： Target tracking Fuzzy neural networks Fuzzy control Control systems Orbits Nonlinear dynamical systems Robustness

来源：评论

学校读者我要写书评

暂无评论

Robust Reinforcement Learning Control System with H∞ tracking performance compensator

Robust Reinforcement Learning Control System with H∞ tracki...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： Shogo Uchiyama Masanao Obayashi Takashi Kuremoto Kunikazu Kobayashi Division of Computer Science & Design Engineering Yamaguchi University Ube Japan

Robust control theory generally guarantees robustness and stability of the closed-loop system, however it requires mathematical model of the system to design the control system. Therefore, it can't often deal with nonlinear systems because of difficulty of modeling of the system. Other, reinforcement learning method can deal with the nonlinear system without mathematical model, however, it usually doesn't guarantee the stability of control. In this paper, we propose a “Robust Reinforcement Learning Control System (RRLCS)” through combining reinforcement learning to treat unknown nonlinear systems and using robust control theory to guarantee the robustness and stability of the system. As a robust control method, we adopt H ∞ control which is robust to modelling error and disturbance. On the other hand, as a reinforcement learning method, we adopt an Actor-Critic method with minimal amount of computation for the continuous action and state space. Moreover, we analyze the stability of the proposed system using H ∞ tracking performance and Lyapunov function. Finally, through the computer simulation for controlling the inverted pendulum system, we show the effectiveness of the proposed method comparing with an Adaptive Fuzzy Control method with H ∞ tracking performance compensator (AFC) and an Auto-Structuring Fuzzy Neural Control System method (ASFNCS).

关键词： Learning Control systems Stability analysis Robustness Robust control Nonlinear systems Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Multiple Cooperative Bilateral Teleoperation with Time-Varying Delay

引用

SICE Journal of Control, Measurement, and System Integration 2011年第2期4卷 89-96页

作者： Nam Duc Do Yusuke Yamashina Toru Namerikawa Division of Electrical Engineering and Computer Science Graduate School of Natural Science and Technology Kanazawa University Department of System Design Engineering Keio University

This paper deals with a passive-decomposition based control of bilateral teleoperation between a single master robot and multiple cooperative slave robots with time varying delay. First, we decompose the dynamics of multiple slave robots into two decoupled dynamics by using the passive-decomposition: the shape-system describing dynamics of the cooperative works and the locked-system representing the overall behavior of the multiple slave robots. Second, we propose a PD control method for bilateral teleoperation to guarantee asymptotic stability of the system with time varying delay. Finally, experimental results show the effectiveness of the proposed teleoperation.

关键词： bilateral teleoperation SMMS time-varying delay Lyapunov stability

来源：评论

学校读者我要写书评

暂无评论

An Approach to SysML and Simulink Based Motion Controller design for Inverted Pendulum Robots

An Approach to SysML and Simulink Based Motion Controller De...

引用

SICE Annual Conference

作者： Danai Phaoharuhansa Akira Shimada Division of Electronical Engineering and Computer Science Shibaura Institute of Technology Department of Engineering and Design Shibaura Institute of Technology

ISBN: (纸本)9781457707148

Nowadays, a lot of inverted pendulum robots have been developed. The complexity of the dynamical control systems is increased and they are advanced toward autonomous inverted pendulum robots. When the controllers are designed, the software MATLAB/Simulink is often used. It is well known that it is a very useful tool to design and analyze motion control systems. However, it is not always useful to express huge or multifunctional systems. At that time, System Modeling language (SysML) is known as a useful tool for that system design. Then it seems the usage of the both tools are useful. In order to develop the inverted pendulum robots in practice, we need multi-stand points for the real time systems. We have to study the both of them and investigate how to fill the gap. This paper introduces our requirement, overview of inverted pendulum robot system, hardware configurations, and map the balancing control using observer based control from Simulink model to SysML models. Furthermore, SysML is a guideline to define the interconnection between functions and combine them together.

关键词： SysML Simulink Inverted pendulum Robot

来源：评论

学校读者我要写书评

暂无评论

Cross-cultural study on feasible sound levels of possible warning sounds for quiet vehicles

Cross-cultural study on feasible sound levels of possible wa...

引用

40th International Congress and Exposition on Noise Control engineering 2011, INTER-NOISE 2011

作者： Yamauchi, Katsuya Menzel, Daniel Fastl, Hugo Takada, Masayuki Nagahata, Koji Iwamiya, Shin-Ichiro Division of Electrical Engineering and Computer Science Faculty of Engineering Nagasaki University Bunkyo-machi 1-14 Nagasaki 852-8521 Japan AG Technische Akustik MMK TU München Archisstrasse 21 München 80333 Germany Communication Design Science Faculty of Design Kyushu University Shiobaru 4-9-1 Minami-ku Fukuoka 815-8540 Japan Department of Human Support System Faculty of Symbiotic Systems Science Fukushima University 1 Kanayagawa Fukushima 960-1296 Japan

ISBN: (纸本)9781618392800

Electric and hybrid electric vehicles (EV/HEV) have the advantage of being more environmentally friendly and quieter than internal combustion engine vehicles. However, reduced noise can also lead to potentially dangerous situations for pedestrians when an oncoming vehicle is inaudible due to background noise (e.g. Kerber and Fastl, internoise 2007). The installation of devices that produce warning sounds in vehicles to alert pedestrians is being considered in various countries. Because this is a global topic, it is of vital interest to determine whether there exist cross-cultural differences. Pilot studies on this topic were performed in Japan (Yamauchi et al., internoise 2010) and, with improved input devices and test procedure, in Germany (Menzel et al., DAGA 2011). The level of three possible warning sounds (engine noise, car horn, and band-pass noise) were adjusted in presence of four different urban background sounds (busy street, residential area, heavy traffic, and shopping area) in laboratory environments. In the first part of the experiments, subjects were asked to adjust the level of the warning sounds so that they were clearly audible and could be reliably detected in the background noise. In the second part the goal was to adjust the level so that the warning sounds were just audible. The results of the adjustments showed no significant difference between the two subjects groups. The results were discussed in view of inter-individual and intraindividual differences. Moreover, the results were compared to current recommendations for sound levels of warning sounds in quiet vehicles.

关键词： Acoustic noise

来源：评论

学校读者我要写书评

暂无评论

Ant-inspired search techniques for solving the zero-one knapsack problem with multiple constraints

引用

International Journal of Advancements in Computing Technology 2011年第4期3卷 242-255页

作者： Chiang, Chuan-Wen Huang, Yu-Qing Lu, Guo-Qin Lin, Shou-Sheu Department of Computer and Communication Engineering National Kaohsiung First University of Science and Technology Taiwan Institute of Engineering Science and Technology National Kaohsiung First University of Science and Technology Taiwan Planning and Design Division Southern District Branch Chunghwa Telecommunication Taiwan

In this paper, we consider the multidimensional zero-one knapsack problem (0-1 MKP). The objective of the problem is to find a subset of objects that yields maximum profit without violating knapsack constraints. The 0-1 MKP is known to be NP-hard. Due to the intractability of the problem, numerous research efforts have focused on various approximation algorithms to acquire satisfactory suboptimal solutions within a reasonable amount of computation cost. However, most realistic approaches for solving the 0-1 MKP still remain to be improved. On the basis of ant colony optimization, we therefore propose a novel constructive algorithm. The proposed algorithm, namely AST-MKP, adopts a new type of constructive graph for leading artificial ants in making decisions to select effective solution components. Moreover, we also devise a local search scheme to advance the quality of solutions obtained. The performance of the AST-MKP algorithm is demonstrated by comparing it against other existing algorithms in terms of overall profit for a set of problem instances obtained form the OR-Library. Experimental results indicate that the algorithm proposed here performs significantly better than the competitive approaches.

关键词： Ant colony optimization

来源：评论

学校读者我要写书评

暂无评论

Work in progress — Developing an individualized life-long learning plan for junior electrical and computer engineering majors

Work in progress — Developing an individualized life-long l...

引用

Frontiers in Education (FIE) Conference

作者： Michael Elmore James Constable Engineering Design Division Thomas J. Watson School of Engineering and Applied Science Binghamton University State University of New York Binghamton NY USA Electrical and Computer Engineering Department Thomas J. Watson School of Engineering and Applied Science Binghamton University State University of New York Binghamton NY USA

The Accreditation Board for engineering and Technology (ABET), now ABET Inc., adopted engineering Criteria 2000 (EC2000) in 1997. At the time this was considered a revolutionary approach to accreditation criteria, because of its focus on what is learned in the classroom rather than what is taught. In the spring of 2003 the faculty of the Electrical engineering and computer engineering department at Binghamton University approved a new course - EECE 382 - Electrical and computer engineering Seminar II. The intent was to consolidate topics that were being taught across several courses within one focused seminar to better ensure that Criteria 3 of General Criteria for Basic Level Programs - Program Outcomes and Objectives - was consistently addressed. EECE 382 was to provide an overview of the professional aspects of the fields of Electrical engineering and computer engineering. This paper reports on how one of the objectives of Criteria 3: `a recognition of the need for and an ability to engage in life-long learning' is addressed in EECE 382.

关键词： engineering profession Educational institutions Seminars computers Accreditation engineering education Conference proceedings

来源：评论

学校读者我要写书评

暂无评论

Materials design Workbench: An open-access database for materials and molecular design

Materials Design Workbench: An open-access database for mate...

引用

Computational Molecular science and engineering Forum - Core Programming Topic at the 2011 AIChE Annual Meeting

作者： Ferguson, Glen Allen Greeley, Jeff Zapol, Peter Curtiss, Larry A. Nestorov, Svetlozar Evtimov Foster, Ian T. Landis, David Hummelshj, Jens Strabo Jacobsen, Karsten W. Bligaard, Thomas Nrskov, Jens Material Science Department Argonne National Laboratory ArgonneIL United States Center for Nanoscale Materials ArgonneIL United States Materials Science Division Argonne National Laboratory ArgonneIL United States Computer Science University of Chicago ChicagoIL United States Mathematics and Computer Science Department of Computer Science Argonne National Laboratory University of Chicago ArgonneIL United States Department of Physics CAMD Technical University of Denmark Kongens Lyngby Denmark SLAC National Accelerator Laboratory SUNCAT Menlo ParkCA United States Center for Atomic-scale Materials Physics Dept. of Physics Technical University of Denmark Lyngby Denmark Center for Atomic-scale Materials Design Technical University of Denmark Kgs. Lyngby Denmark Chemical Engineering Stanford University and SUNCAT StanfordCA United States

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：