A Game Theory Model for Multi Robot Cooperation in Industry 4.0 Scenarios

Abstract

Multiple autonomous robots are expected to interact in Industry 4.0 scenarios, which makes it key to identify distributed techniques for their control and coordination. Game theory has a strong potential to be an excellent representation methodology for the establishment of cooperation among distributed robotic agents. In this paper, we consider a model of two industrial robots within a production line and we show how to describe their interaction, with their different objectives and control being kept into account. We also formalize a Bayesian game that takes into account imperfections in the system, such as the possibility that the robots make a wrong evaluation on a specific item in production. For both the standard static game and its Bayesian version, we compute the Nash equilibrium and we argue how it ultimately represents a point of convergence of the distributed control of the robots.