According to the characteristics of distributed industrial control process, we analyzed the feasibility and necessity that multi-agent technology was applied to industrial complicated control process. A multi-agent sy...
详细信息
According to the characteristics of distributed industrial control process, we analyzed the feasibility and necessity that multi-agent technology was applied to industrial complicated control process. A multi-agent system architecture on the basis of industrial process and cooperation control of the system were described as well. Strip hot rolling process is a typical distributed control problem we met in metallurgy. We proposed a multi-agent structure of hot rolling process from the view of synthesized control. The composition and relationship of every function module was described in detail. The cooperation control process of the main device was described in detail. The cooperation control process of flatness and gauge was analyzed in the article.
As a popular research topic in the area of distributed artificial intelligence, the multi-robot pursuit problem is widely used as a testbed for evaluating coordinated and cooperative strategies in multi-robot systems....
详细信息
As a popular research topic in the area of distributed artificial intelligence, the multi-robot pursuit problem is widely used as a testbed for evaluating coordinated and cooperative strategies in multi-robot systems. This study the problem of multi-robot pursuit game using reinforcement learning (RL) techniques is studied. Unlike most existing studies that apply fully centralised deep RL methods based on the centralised-learning and decentralised-execution scheme, the authors propose a fully decentralised multi-agent deep RL approach by modelling each agent as an individual deep RL agent that has its own individual learning system (i.e. individual action-value function, individual leaning update process, and individual action output). To realise coordination among agents, the limited information of other environmental agents is used as input of the learning process. Experimental results show that both distributed and centralised approaches can ultimately solve the pursuit-evasion problem in different dimensions, but the learning efficiency and coordination performance of the proposed distributed approach are much better than the traditional centralised approach.
There is a revolution in decision technology in the form of intelligent agent systems. Very soon, tools in the shape of distributed artificial intelligence will be available and be particularly applicable to the compl...
详细信息
There is a revolution in decision technology in the form of intelligent agent systems. Very soon, tools in the shape of distributed artificial intelligence will be available and be particularly applicable to the complexities of decision-making in the typical global enterprise. A number of issues will arise in the next few years as intelligent agents become the mainstream enablers of ‘real-time’ enterprise process, such as the need to ensure continuity in the transition phase by careful integration of intelligent agent systems into a firm's legacy systems. The authors discuss such issues and conclude with a look at the paradigm shift in enterprise philosophy made possible by a human–machine partnership.
作者:
Jean Pierre BriffautPatrick LallementINT
9 rue Charles Fourier 91011 Evry Cedex France UTT
12 rue Marie Curie 10010 Troyes Cedex France Charles Delaunay Institute FRE CNRS 2848
The key features of collaborative information systems for e-enabled supply chain are described in terms of collaborative control parameters, data processing and architecture. Collaborative control parameters refer to ...
详细信息
The key features of collaborative information systems for e-enabled supply chain are described in terms of collaborative control parameters, data processing and architecture. Collaborative control parameters refer to indicators based on the aggregated capacities and capabilities of resources available to the supply chain stakeholders. These stakeholders can be viewed as a Multi-Agent System (MAS) with a central coordinating agent. This central agent is modelled as a BDI agent whose architecture and running best mimic human reasoning.
作者:
Vladimír MaříkGerstner Laboratory
Czech Technical University Prague Czech Republic & Rockwell Automation Research Center Prague Czech Republic
The paper is aimed at summarizing the current state-of-the-art in development of the agent-based solutions in three areas connected with industrial production, namely in holonic control, production management and virt...
详细信息
The paper is aimed at summarizing the current state-of-the-art in development of the agent-based solutions in three areas connected with industrial production, namely in holonic control, production management and virtual enterprises. It is shown how the results in these three sub-areas converge and that the agent-oriented technology could provide a good background for developing a unifying approach. Two industrial applications of agent-based systems are described in more details. Both the positive and negative aspects of applying the agent-based solutions in industry are discussed.
The paper describes an experimental multi-agent system developed for and aimed at a computer-supported project-oriented production planning. The system is based on a heterogeneous hierarchy of agents of three types th...
详细信息
The paper describes an experimental multi-agent system developed for and aimed at a computer-supported project-oriented production planning. The system is based on a heterogeneous hierarchy of agents of three types that reflect the managerial structure of the manufacturing enterprise. To improve the system's efficiency, a new formalism - called tri-base model - of the multi-agent internal communication/negotiation mechanism has been introduced. The tri-base model, that has been tested in an industrial environment, is treated in far detail in the paper.
The capabilities of a automated theorem prover's interface are essential for the effective use of (interactive) proof systems. LΩUI is the multi-modal interface that combines several features: a graphical display...
详细信息
The capabilities of a automated theorem prover's interface are essential for the effective use of (interactive) proof systems. LΩUI is the multi-modal interface that combines several features: a graphical display of information in a proof graph, a selective term browser with hypertext facilities, proof and proof plan presentation in natural language, and an editor for adding and maintaining the knowledge base. LΩUI is realized in an agent-based client-server architecture and implemented in the concurrent constraint programming language Oz.
Enterprises unite and become so-called vitual enterprises (VE) in order to benefit from market potentials which they could never reach on their own. The operation of VEs, however, is not supported by existing producti...
详细信息
Enterprises unite and become so-called vitual enterprises (VE) in order to benefit from market potentials which they could never reach on their own. The operation of VEs, however, is not supported by existing production planning and control (PPC) systems. These systems allow neither communication with systems of other enterprises, nor the synchronization of master production schedules in a VE. This paper proposes an order management system based on automatic negotiations. This system allows the inclusion and scheduling of orders in real time within virtual enterprises in the semiconductor industry and, at the same time, coordinates the individual master production schedules (MPS) with one another.
This paper discusses about the formulation of the collaborative designing work by multiple heterogeneous agents. We introduce negotiated search algorithm that gets conflict resolution and mutual agreement by sharing l...
详细信息
This paper discusses about the formulation of the collaborative designing work by multiple heterogeneous agents. We introduce negotiated search algorithm that gets conflict resolution and mutual agreement by sharing local information among agents adaptively and relaxing local constraints gradually. Then, we formulate organizational learning for individual agents to get aware of their divergent roles being sensitive to contextual knowledge in collaborative work process using a credit assignment learning. This system is applied to a simple mechanical design problem and the simulated results are shown.
In this paper, cooperative problem-solving in distributedartificial Intelligent System is analyzed. A formal model for Multi-Node Cooperative Processing is proposed. Programming for multi—intelligent—node cooperati...
详细信息
In this paper, cooperative problem-solving in distributedartificial Intelligent System is analyzed. A formal model for Multi-Node Cooperative Processing is proposed. Programming for multi—intelligent—node cooperative solving of well-structured problem is studied. An hierarchical programming approach of multi—intelligent—node cooperative solving is put forward. A processing model is built up. And finally, cooperative solving process and steps are given.
暂无评论