The research program was initiated under the international Intelligent Manufacturing Systems research program as part of the test case GNOSIS, and involves collaboration with other research groups world-wide. A number of papers and technical reports are now available on various aspects of the Mediator research.
Mediator: Information and Knowledge Management for the Virtual Factory
Brian R Gaines and Douglas H Norrie (SIGMAN AAAI-94 Workshop: Reasoning about the Shop Floor. Menlo Park, California, AAAI, 1994, 30-39)Mediator is an open architecture information and knowledge management system designed to provide a flexible technology to support the management of complex manufacturing activities throughout the product life cycle. A heterogeneous environment is assumed in which the sub-systems are geographically dispersed and involve different application packages, not necessarily designed to work together, multiple platforms, protocols and forms of user interface. The function of Mediator is to provide a knowledge support system for all those involved in the manufacturing process from requirements through design, engineering, production, to maintenance and recycling. It is designed to facilitate communication, compliance with constraints including physical restrictions and legal obligations, and to generally represent knowledge about any activity or sub-system relevant to the manufacturing process.
The Mediator architecture is a distributed client, distributed server design, in which multiple users can collaborate synchronously or asynchronously through processes running anywhere on the network. Much of the user interaction is based on an open architecture visual language tool for representing conceptual schema in a way that is comprehensible to users, and can be easily tailored to different application domains. Mediator supports semantic networks that can be used to represent rules, procedures and constraints with formal, operational semantics such that an inference system can be used to give advice and check for constraint violations.
The representation is domain independent and the system can reason with legal constraints and corporate procedures as well as with design constraints. Less formal concept maps are also supported where the role of the system is primarily information retrieval rather than reasoning, and the formal and informal systems can be combined. Procedures can be triggered through the user interface to the visual language, and the procedures can include other applications or a general-purpose `agent' system that supports active integration between applications and between sites. Data translation and knowledge interchange are supported through such agents.
A Generic Mediator for Multi-Agent Coordination in a Distributed Manufacturing System
Francisco P. Maturana and Douglas H. Norrie A generic agent Mediator has been developed to coordinate heterogeneous intelligent agents in a distributed manufacturing system. Coordination takes place both between dynamically created virtual clusters of agents and within these so-called coordination clusters. Task plans are decomposed successively into subtasks which are allocated down through the agent clusters and coordinated through these. The agent Mediator is composed of three coordinating agent levels, which are named as follows: the Template Mediator, the Data Agent Manager, and the Active Mediator. Each virtual cluster involves a Data Agent Manager and those Active Mediators and Resource agents that are appropriate to the current subtask activities. The Template Mediator is the top-level agent that operates as a global coordinator. It uses a cloning mechanism to create the successive coordinating agent levels.The Mediator's structure and activities are illustrated through application to an intelligent manufacturing scheduling problem. The system components, including all machines and parts, are implemented as intelligent agents. This approach is being further developed to manage a concurrent engineering environment in an intelligent manufacturing system.
A Multi-Agent Coordination Architecture for Distributed Organizational Systems
Francisco P. Maturana and Douglas H. Norrie A generic architecture has been developed for distributed task decomposition in multi-agent systems and the coordination of the agent task activities through dynamically created coordination clusters involving coordination agents and resources. This agent Mediator architecture is composed of three coordination agent levels, which are named as: the Template Mediator, the Data-agent Manager, and the Active Mediator. The Template Mediator is the top-level agent that operates as a global coordinator. This agent contains both the templates and cloning mechanism that allow it to create the successive agent levels. The coordination structure dynamically organizes the system components into collaborative groups to develop partial solutions that integrate into the global solution. These partial solutions are localized at different levels of data abstraction that Mediator uses during the problem solving processes. The Mediator structure and mechanisms are illustrated through an intelligent manufacturing scheduling problem. Both the machines and the parts involved in the production system are implemented as intelligent agents. This approach can also be used for other distributed organizational environments.A Multi-Agent Intelligent Design System Integrating Manufacturing And Shop-Floor Control
Sivaram Balasubramanian and Douglas H. Norrie A multi-agent architecture has been developed for the integration of design, manufacturing, and shop floor control activities. This is based on cooperating intelligent entities in the sub-domains which make decisions through negotiation, using domain-specific knowledge both distributed among the entities and accessible to them. Using this architectural framework, an Agent Based Concurrent Design Environment system has been developed for feature-based design, manufacturability evaluation, and dynamic process planning. This is a multi-agent prototype system involving the following types of agent: design agent; geometric interface agent; feature agent; part agent; machine agent; tool agent; environment manager; and shop floor manager. A new technique for evaluating manufacturability is introduced, based on interacting intelligent features of the part being designed. This proof-of-concept system was developed for three-dimensional prismatic parts, with twenty-five different feature types, but can be extended to other geometries. The system has been completed and tested, and is being integrated into a larger multi-agent environment incorporating routing, scheduling, and overall production control.