Toward an architecture for adaptive, rational, mobile agents (abstract)

Abstract

It is becoming widely accepted that neither purely reactive nor purely deliberative control techniques are capable of producing the range of behaviours required of intelligent agents in dynamic, unpredictable, multiagent worlds. We present a new architecture for controlling autonomous, mobile agents - building on previous work addressing reactive and deliberative control methods. The proposed multi-layered control architecture allows a resource-bounded, goal-directed agent to react promptly to unexpected changes in its environment; at the same time it enables the agent to reason predictively about potential conflicts by constructing and projecting theories which hypothesies other agents' intentions.The line of research adopted is very much a pragmatic one. A single, common architecture has been implemented which, being heavily parameterised, allows an experimenter to study functionally- and behaviourally-diverse agent configurations. A principal aim of this research is to understand the role different functional capabilities play in constraining an agent's behaviour under varying environmental conditions. To this end, an experimental testbed comprising a simulated multi-agent world has also been constructed. Some preliminary experience with the new control architecture is described.