Research on Decentralized Communication Decision in the Multi-Agent Robotic System

In order to reduce communication amount in the coordination of multi-agent robotic system,this paper presents a novel approach to make communication decisions in a decentralized fashion.The possible joint beliefs of the team are represented based on a directed acyclic graph,and communication is chosen only when an agent’s local observations indicate that the shared information will lead to an increase in expected reward.The centralized single-agent policies are applied to decentralized multi-agent POMDPs by maintaining and reasoning over the possible joint beliefs of the team.Experiment and a detailed example show that the presented approach can reduce communication amount and improve the distributed execution performance.