Behavior Control of Multiple Agents Based on Locality of Binary Relations

Abstract

In this paper, we propose a variable neighborhood model for reflex agent control, which enables reflex agents to make planning for attaining their goal. The model consists of three layers: (1) topological space (2) agent space and (3) linear temporal logic. In order to make reflex agents which have an ability of goal-attaining superficially, we focus on local properties of the binary relation between agents. As a result such a sequence of low-level behaviors, that is, keeping or abandoning of local properties of binary relations, generates higher level actions as if they could attain a goal with such actions. By simulation, such low-level behaviors are shown to generate attaining some goal like target chasing and cooperation.