Role Assignment, Non-communicative Multi-agent Coordination in Dynamic Environments Based on the Situation Calculus

Abstract

Coordination in multi-robot systems is a very active research field in artificial intelligence and robotics, since through coordination one can achieve a more effective execution of the robotspsila tasks. We achieve collaboration between agents through introducing roles into the situation calculus. Homogeneous agents can flexibly switch roles according to pre-defined triggers to be evaluated at run-time. A role in our framework defines the set of actions and the policy of an agent. Moreover, we demonstrate that, with common knowledge assumptions, an agent can predict the actions of the other agents, rendering communication unnecessary. Experimental results showing the effectiveness of our approach, the method has been successfully implemented in the domain of simulated robotic soccer based on the situation calculus.