One reason why Distributed AI (DAI) technology has been deployed in relatively few real-size applications is that it lacks a clear and implementable model of cooperative problem solving which specifies how agents should operate and interact in complex, dynamic and unpredictable environments. As a consequence of the experience gained whilst building a number of DAI systems for industrial applications, a new principled model of cooperation has been developed. This model, called Joint Responsibility, has the notion of joint intentions at its core. It specifies pre-conditions which must be attained before collaboration can commence and prescribes how individuals should behave both when joint activity is progressing satisfactorily and also when it runs into difficulty. The theoretical model has been used to guide the implementation of a general-purpose cooperation framework and the qualitative and quantitative benefits of this implementation have been assessed through a series of comparativ...

ARCHON ^TM (ARchitecture for Cooperative Heterogeneous ON-line systems) was Europe's largest ever project in the area of Distributed Artificial Intelligence (DAI). It devised a general-purpose architecture, software framework, and methodology which has been used to support the development of DAI systems in a number of real world industrial domains. Two of these applications, electricity transportation management and particle accelerator control, have been run successfully on-line in the organisation for which they were developed (respectively, Iberdrola an electricity utility in the north of Spain and CERN the European Centre for high energy physics research near Geneva). This paper recounts the problems, insights and experiences gained whilst deploying ARCHON technology in these real-world industrial applications. Firstly, it gives the rationale for a DAI approach to industrial applications and highlights the key design forces which shape work in this important domain. Secondly, the...

ARCHON^TM (ARchitecture for Cooperative Heterogeneous ON-line systems) is Europe's largest project in the area of Distributed Artificial Intelligence (DAI). It has devised a general-purpose architecture, software framework and methodology which has been used to support the development of DAI systems in a number of industrial domains. Some examples of the applications to which it has been successfully applied include: electricity distribution and supply, electricity transmission and distribution, control of a cement kiln complex, control of a particle accelerator, and control of a robotics application. The type of cooperating community that it supports has a decentralised control regime and individual problem solving agents which are large grain, loosely coupled, and semi-autonomous. This paper tackles a broad range of issues related to the application of ARCHON technology to industrial applications. Firstly, it gives the rationale for a DAI approach to industrial applications and highl...

: Systems in which semi-autonomous problem solving agents communicate and cooperate with one another represent an exciting vision of future computing environments. However, if this vision is ever going to result in commercially viable systems then consideration must be given to the large software base which exists within many organisations. Success requires the ability to incorporate pre-existing systems alongside purpose built agents in a cooperating community. This requirement is vital because the former represent a substantial resource investment which companies cannot afford to consign to the scrap heap. This paper reports on our experiences of constructing cooperating communities which contain elements which were pre-existing and some which were developed specifically for incorporation into an integrated environment. The general purpose framework of ARCHON (ARchitecture for Cooperative Heterogeneous ON-line systems) provides the underlying technology which facilitates cooperative ...

ARCHON ^TM (ARchitecture for Cooperative Heterogeneous ON-line systems) was Europe's largest project in the area of Distributed Artificial Intelligence (DAI). It devised a general-purpose architecture, software framework, and methodology which has been used to support the development of DAI systems in a number of real world industrial domains. Some examples of the applications to which it has been successfully applied include: electricity distribution and supply, electricity transmission and distribution, control of a cement kiln complex, control of a particle accelerator, and control of a robotics application. The type of cooperating community that it supports has a decentralised control regime and individual problem solving agents which are large grain, loosely coupled, and semi-autonomous. This paper will tackle a broad range of issues related to the application of ARCHON technology to industrial applications. Firstly, it gives the rationale for a DAI approach to industrial applic...

The ARCHON Layer concepts described in this paper have been devised and implemented by

As knowledge-based techniques are introduced in supervision and control applications, the need for a structured, methodological approach in the development of these systems increases. Current knowledge-based systems development methodologies are founded on individualistic models of expertise, and cannot face the challenge of interacting with humans or other systems in dynamic application environments. This article introduces a development method that combines models of expertise with interaction-based distributed artificial intelligence. The applica- bility of the method is demonstrated on an example of supervision of a power transmission network. The analysis of the proposed system is based on the KADS methodology. The design phase is structured in a series of steps: first, the domain description is used to select a model of distributed problem solving. Then, problem constraints and a set of design rules guide the mapping of the analysis' entities to a design solution. Design decisions are justified at every step. Alternative design proposals are experimentally compared with the aid of a multi-agent platform and a simulator. The experimental results indicate possible design refinements. Finally, the generality of the approach is discussed and future research directions are indicated.