检索结果-内蒙古大学图书馆

distributed autonomous Control system of the Smart Grid Based on the Turing Pattern Model

IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING 2013年第6期8卷 649-651页

作者： Ishida, Takeshi Natl Fisheries Univ Shimonoseki Yamaguchi 7596595 Japan

Renewable energy resources, which are generally unstable, affect the performance of electricity grids when they are fully connected. A distributed energy supply network system is expected to compensate for the anticipated performance problems. We have constructed a distributed autonomous system that controls batteries installed in each house. In this system, even if central control does not exist, electrical charging and discharging of the batteries are carried out for self-organization. As a result, the grid stability is maintained in the local urban district. Our system is based on the Turing pattern model. (c) 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

关键词： smart grid photovoltaic cell secondary battery distributed autonomous system Turing pattern model

来源：评论

学校读者我要写书评

暂无评论

A distributed autonomous Approach to Developing a Disaster Evacuation Assist system

引用

JOURNAL OF DISASTER RESEARCH 2015年第6期10卷 1081-1090页

作者： Iizuka, Yasuki Kinoshita, Katsuya Iizuka, Kayo Tokai Univ Dept Math Sci 4-1-1 Kitakaname Hiratsuka Kanagawa 2591292 Japan Syst Res Co LTD Nakamura Ku Nagoya Aichi 4530861 Japan Senshu Univ Sch Network & Informat Tama Ku Kawasaki Kanagawa 2148580 Japan

In times of disaster, or other emergency situations, it is essential for people to be evacuated in a smooth manner. Evacuation must be performed promptly and safely. It is necessary to avoid generating a secondary disaster at the time of evacuation. However, this is not easy to realize, because people often tend to panic when faced with disaster, crowding the evacuation passageways of buildings. On the other hand, people do not attempt to evacuate themselves from danger when the normalcy bias has occurred. Therefore, evacuation guidance is very important. However, it is impossible to guide all evacuees through authorities such as disaster countermeasure offices. To deal with this issue, the authors propose a system that provides optimal evacuation guidance autonomously without central server. The system works on the mobile devices of evacuees, performs distributed calculations using the framework of the distributed constraint optimization problem on ad-hoc communication, and does not need a central server. In the experiment using multi-agent simulation, for the case where the evacuees can receive evacuation guidance from this system, the evacuation completion time decreased. This paper presents an overview and the evaluation results of the prototype of the disaster evacuation assistance system.

关键词： disaster evacuation distributed autonomous system DCOP multi-agent simulation

来源：评论

学校读者我要写书评

暂无评论

distributed self-reconfiguration of M-TRAN III modular robotic system

引用

INTERNATIONAL JOURNAL OF ROBOTICS RESEARCH 2008年第3-4期27卷 373-386页

作者： Kurokawa, Haruhisa Tomita, Kohji Kamimura, Akiya Kokaji, Shigeru Hasuo, Takashi Murata, Satoshi Natl Inst Adv Ind Sci & Technol Intelligent Syst Res Inst Tsukuba Ibaraki 3058564 Japan Univ Tsukuba Grad Sch Syst & Informat Engn Tsukuba Ibaraki 3058573 Japan Tokyo Inst Technol Interdisciplinary Grad Sch Sci & Engn Yokohama Kanagawa 2268502 Japan

A new prototype of a self-reconfigurable modular robot, M-TRAN III, has been developed, with an improved fast and rigid connection mechanism. Using a distributed controller, various control modes are possible: single-master, globally synchronous control or parallel asynchronous control. Self-reconfiguration experiments using up to 24 modules were undertaken by centralized or decentralized control. Experiments using decentralized control examined a modular structure moved in a given direction as a flow produced by local self-reconfigurations. In all experiments, system homogeneity and scalability were maintained: modules used identical software except for their ID numbers. Identical self-reconfiguration was realized when different modules were used in initial configurations.

关键词： distributed autonomous system decentralized control controller area network

来源：评论

学校读者我要写书评

暂无评论

Bottom-up multi-agent reinforcement learning by reward shaping for cooperative-competitive tasks

引用

APPLIED INTELLIGENCE 2021年第7期51卷 4434-4452页

作者： Aotani, Takumi Kobayashi, Taisuke Sugimoto, Kenji Nara Inst Sci & Technol Div Informat Sci 8916-5 Takayama Cho Nara Japan

A multi-agent system (MAS) is expected to be applied to various real-world problems where a single agent cannot accomplish given tasks. Due to the inherent complexity in the real-world MAS, however, manual design of group behaviors of agents is intractable. Multi-agent reinforcement learning (MARL), which is a framework for multiple agents in the same environment to learn their policies adaptively by using reinforcement learning, would be a promising methodology for such complexity in the MAS. To acquire the group behaviors by MARL, all the agents are required to understand how to achieve the respective tasks cooperatively. So far, we have proposed "bottom-up MARL", which is a decentralized system to manage real and large-scale MARL, with a reward shaping algorithm to represent the group behaviors. The reward shaping algorithm, however, assumes that all the agents are in cooperative relationships to some extent. In this paper, therefore, we extend this algorithm to allow the agents not to know the interests between them. The interests are regarded as correlation coefficients derived from the agents' rewards, which are numerically estimated in an online manner. Actually, in both simulations and real experiments without knowledge of the interests between the agents, they correctly estimated their interests, thereby allowing them to derive their new rewards to represent the feasible group behaviors in the decentralized manner. As a result, our extended algorithm succeeded in acquiring the group behaviors from cooperative tasks to competitive tasks.

关键词： distributed autonomous system Reinforcement learning Reward shaping Interests between agents

来源：评论

学校读者我要写书评

暂无评论

Self-repairing mechanical systems

引用

autonomous ROBOTS 2001年第1期10卷 7-21页

作者： Murata, S Yoshida, E Kurokawa, H Tomita, K Kokaji, S Minist Int Trade & Ind Agcy Ind Sci & Technol Mech Engn Lab Syst Sci Div Tokyo Japan Minist Int Trade & Ind Agcy Ind Sci & Technol Mech Engn Lab Sound & Vibrat Div Tokyo Japan Minist Int Trade & Ind Agcy Ind Sci & Technol Mech Engn Lab Machine Intelligence Div Tokyo Japan Minist Int Trade & Ind Agcy Ind Sci & Technol Mech Engn Lab Dept Adv Machinery Tokyo Japan

This paper reviews several types of self-repairing systems developed in the Mechanical Engineering Laboratory. We have developed a modular system capable of "self-assembly" and "self-repair." The former means a set of units can form a given shape of the system without outside help;the latter means the system restores the original shape if an arbitrary part of the system is cut off. We show both two-dimensional and three-dimensional unit designs, and distributed algorithms for the units.

关键词： self-repairing system self-reconfiguration distributed autonomous system fault tolerance fractum

来源：评论

学校读者我要写书评

暂无评论

Holonic assembly system with plug and produce

引用

COMPUTERS IN INDUSTRY 2001年第3期46卷 289-299页

作者： Arai, T Aiyama, Y Sugi, M Ota, J Univ Tsukuba Inst Engn Mech & Syst Tsukuba Ibaraki 3058573 Japan Univ Tokyo Grad Sch Engn Dept Precis Machinery Engn Tokyo 1138556 Japan Univ Tsukuba Inst Engn Mech & Syst Tsukuba Ibaraki 3058573 Japan

An assembly system based on holonic concept has been newly installed. The system consists of three manipulators, one belt-conveyor and two warehouses. The system assembles several parts into a product. Its sequences are planned by negotiation among the assembly devices by means of contract net protocol. Thus, even though the parts are supplied at different warehouses, the system can generate a sequence of transportation automatically. Utilizing the characteristics of distributed autonomous systems, a new concept Plug and Produce is proposed. A device can be installed easily and then immediately start to work. This system has high robustness against the reconfiguration and sudden changes of products. Experiments were made for two kinds of assembly tasks and verified the efficiency of the system. (C) 2001 Elsevier Science B.V. All rights reserved.

关键词： holonic system distributed autonomous system plug and produce

来源：评论

学校读者我要写书评

暂无评论

A three-dimensional self-reconfigurable system

引用

ADVANCED ROBOTICS 2000年第6期13卷 591-602页

作者： Kurokawa, H Murata, S Yoshida, E Tomita, K Kokaji, S AIST Agcy Ind Sci & Technol Mech Engn Lab Tsukuba Ibaraki 3058564 Japan

A three-dimensional (3D) self-reconfigurable system made of identical units is proposed. Each unit has six arms on the surface of its base cube which can connect to neighboring units mechanically. By the connection, a cubic-lattice structure is formed. A unit can carry its neighbor unit from one node of the lattice to another by rotating its arm by 90 degrees. Repeating this movement, the structure can reconfigure itself to realize various 3D structures. The general process of reconfiguration was proposed for this system. A prototype system including six units was made and basic motions of self-reconfiguration were verified.

关键词： distributed autonomous system modular structure modular robot

来源：评论

学校读者我要写书评

暂无评论

MAT-DQN: Toward Interpretable Multi-agent Deep Reinforcement Learning for Coordinated Activities 30th

MAT-DQN: Toward Interpretable Multi-agent Deep Reinforcement...

引用

30th International Conference on Artificial Neural Networks (ICANN)

作者： Motokawa, Yoshinari Sugawara, Toshiharu Waseda Univ Dept Comp Sci & Engn Tokyo Japan

ISBN: (纸本)9783030863807;9783030863791

We propose an interpretable neural network architecture for multi-agent deep reinforcement learning to understand the rationale for learned cooperative behavior of the agents. Although the deep learning technology has contributed significantly to multi-agent systems to build coordination among agents, it is still unclear what information the agents depend on to behave cooperatively. Removing this ambiguity may further improve the efficiency and productivity of multi-agent systems. The main idea of our proposal is to adopt the transformer to deep Q-network for addressing the above-mentioned issue. By extracting multi-head attention weights from the transformer encoder, we propose a multi-agent transformer deep Q-network (MAT-DQN) and show that agents using attention mechanisms possess better coordination capability with other agents despite being trained individually for a cooperative patrolling task problem;thus, they can exhibit better performance results compared with the agents with vanilla DQN (which is a baseline method). Furthermore, we indicate that it is possible to visualize heatmaps of attentions, which indicate the influential input-information in agents' decision-making process for their cooperative behaviors.

关键词： distributed autonomous system Multi-agent deep reinforcement learning Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Self-repairing mechanical system

Self-repairing mechanical system

引用

Sensor Fusion and Decentralized Control in Robotic systems II Conference

作者： Murata, S Yoshida, E Kurokawa, H Tomita, K Kokaji, S Mechanical Engineering Lab Japan

ISBN: (纸本)0819434329

A concept of a self-repairable mechanical system which is composed of homogeneous mechanical units is described. We have developed a modular system capable of "self-assembly" and self-repair. The former means a set of units can form a given shape of the system without outside help, and the latter means the system restores the original shape if an arbitrary part of the system cut off. We show both of two-dimensional and three-dimensional unit design, and distributed algorithms for the units.

关键词： self-repairing system self-reconfiguration distributed autonomous system fault tolerant

来源：评论

学校读者我要写书评

暂无评论

Disaster Information Collecting/Providing Service for Local Residents

Disaster Information Collecting/Providing Service for Local ...

引用

Symposium on Human Interface/14th International Conference on Human-Computer Interaction (HCI)

作者： Takahashi, Yuichi Kobayashi, Daiji Yamamoto, Sakae Tokyo Univ Sci Dept Management Sci 1-3 Kagurazaka Shinjuku Tokyo 162 Japan Chitose Inst Sci & Technol Fac Photon Sci Dept Dept Global Syst Design Chitose Hokkaido Japan

ISBN: (纸本)9783642216688;9783642216695

It has been pointed out that when people lack the information needed in the event of a disaster, such as a disastrous earthquake, this could lead to social chaos, including unwanted rumors and outrages, or could disrupt rescue and relief activities(1, 2). In Japan, by law in principle, self-help or mutual assistance is required immediately after a disaster, and local residents are required to make judgments for action on their own. Although disaster information systems are gradually being organized at the municipal level, actual emergency evacuation areas and essential information for local citizens are still not sufficiently ready for provision at this stage.(3) In this study, we established and evaluated a service infrastructure with an autonomous wireless network, aiming at providing services to collect and deliver disaster information, which will be required by local residents.

关键词： earthquake disaster victims distributed autonomous system wireless network

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：