Game Theory as a Unifying Structure for a Variety of Robot Tasks 0 Steven M

In this paper we propose the use of game theory as a general formalism for representing, comparing, and providing insight into solutions to a wide class of robotics problems. Particularly, we show how game theory can be applied to problems of multiple robot coordination, high-level strategy planning, information gathering through manipulation and/or sensor planning, and pursuit-evasion scenarios. Although some concepts from game theory have been considered in previous robotics contexts, we consider a very general game structure, which consequently has much broader application. We present some preliminary experiments on a two-robot corridor navigation problem in which the robots have independent tasks, and the equilibria in a dynamic game with a rolling time horizon are used for coordination.