Browsing by Subject "agent communication"
Now showing 1 - 4 of 4
Results Per Page
Sort Options
Item Agent Communication Languages and Agent Coordination(Springer, 2000-07-01) Cost, R. Scott; Labrou, Yannis K.; Finin, TimItem An Agent System for Application Initialization in an Integrated Manufacturing Environment(1999-08-04) Peng, Yun; Finin, Tim; Chen, Harry; Wang, Ling; Labrou, Yannis; Cost, R. Scott; Chu, Bill; Cross, Valerie; Russell, Mike; Tolone, Bill; Boughannam, Akram; McCobb, JerryA great deal of research and development effort has been undertaken in recent years to integrate otherwise disconnected manufacturing production and planning (P/E) application software systems so that the enterprises can react quickly and accurately to the ever changing market dynamics. In such an integrated P/E environment it is, at times, necessary to bring in a new application in order to replace an outmoded one or to provide functionality that is not available in the existing environment. The process of introducing a new application, Application Initialization, is very complicated and can be extremely costly in terms of time and resources. In this paper we propose a multi-agent system (MAS) to assist with the application initialization process. A collection of eight agents with specialized expertise is assembled to carry out the operational steps of the initialization process. These agents interact with each other, with other applications in the environment, and with the human specialist in the process. All agents speak KQML language, supported by Jackal, a JAVA based, light-weighted and flexible agent communication infrastructure we have developed. The MAS is tested with an integrated environment involving real P/E applications. The success of the experiment demonstrates that MAS is a technically viable approach for providing flexible and inexpensive solutions to difficult tasks (application initialization and others) in the integration of manufacturing planning and execution.Item KQML as an agent communication language(ACM, 1994-10-29) Finin, Tim; Fritzson, Richard; McKay, Don; McEntire, RobinThis paper describes the design of and experimentation with the Knowledge Query and Manipulation Language (KQML), a new language and protocol for exchanging information and knowledge. This work is part of a larger effort, the ARPA Knowledge Sharing Effort which is aimed at developing techniques and methodology for building large-scale knowledge bases which are sharable and reusable. KQML is both a message format and a message-handling protocol to support run-time knowledge sharing among agents. KQML focuses on an extensible set of performatives, which defines the permissible “speech acts” agents may use and comprise a substrate on which to develop higher-level models of interagent interaction such as contract nets and negotiation. In addition, KQML provides a basic architecture for knowledge sharing through a special class of agent called communication facilitors which coordinate the interactions of other agents. The ideas which underlie the evolving design of KQML are currently being explored through experimental prototype systems which are being used to support several testbeds in such areas as concurrent engineering, intelligent design and intelligent planning and scheduling.Item Modeling agent conversations with colored petri nets(1999-05-01) Cost, R. Scott; Chen, Ye; Finin, Tim; Labrou, Yannis K.; Peng, YunConversations are a useful means of structuring communica- tive interactions among agents. The value of a conversation- based approach is largely determined by the conversational model it uses. Finite State Machines, used heavily to date for this purpose, are not sufficient for complex agent inter- actions requiring a notion of concurrency. We propose the use of Colored Petri Nets as a model underlying a language for conversation speci cation. This carries the relative sim- plicity and graphical representation of the former approach, along with greater expressive power and support for con- currency. The construction of such a language, Protolin- gua, is currently being investigated within the framework of the Jackal agent development environment. In this paper, we explore the use of Colored Petri Nets in modeling agent communicative interaction.