Hierarchical prediction model for intelligent communication in multiple robotic systems

This paper describes a predictive decision making strategy for the multiple robotic systems. Although communication plays an important role in the robot system, it tends to be regarded as merely information exchanges by data transmission. However, it is one of the vital intelligent activities in the multiple robot systems. In this paper, we propose a framework of “intelligent communication” which treats communication as an essential part of decision making considering interaction with the other agents. It includes knowledge abstraction from discrete events, intention reasoning and prediction, etc. This paper focuses on the intention reasoning with prediction, and proposes the concept of hierarchical prediction model for its realization. We discuss the advantage of prediction and its difficulty for application to the robot through the simulation results