Affiliations: School of Electrical and Information Engineering,
Knowledge Based Intelligent Engineering Systems Centre, University of South
Australia, Mawson Lakes, SA 5095, Australia
Abstract: Heuristic computing has consolidated into two streams of research
(personification software and smart products) [1]. Cognitive
Science is one of these fields and is attracting research effort based on
Multi-Agent System (MAS). This research requires the formation of a voluntarily
trust relationship in order for collaboration to occur, otherwise the imposed
goal(s) may be aborted or fail completely [2,3]. An
Agent Transportation Layer Adaption System (ATLAS) communications framework has
been constructed to pass messages between separate agent systems. Discussion
about confined frameworks have recently been extended to enable individual
students associated with our Knowledge-Based and Intellingent Information and
Engineering Systems (KES) Centre to fast track the development of their
research concepts. A Plug 'n' Play concept based on a multi-agent
blackboard architecture forms the basis of this research. This paper highlights
the core architecture, we believe is required for Multi-Agent System (MAS)
developers to achieve such flexibility. Agent teams can provide the ability to
adapt and dynamically organize. The model described, concentrates on the
blackboard design constructs to represents all functional blocks required to
automate the processes required to complete any decomposed goals. Discussion in
this paper is limited to the formative work within the foundation layers of
that framework.
