Potential Game-Based Non-Myopic Sensor Network Planning for Multi-Target Tracking

Abstract

This paper presents a potential game-based method for non-myopic planning of mobile sensor networks in the context of target tracking. The planning objective is to select the sequence of sensing points over more than one future time steps to maximize information about the target states. This multi-step lookahead scheme is studied to overcome getting trapped at local information maximum when there are gaps in sensing coverage due to constraints on the sensor platform mobility or limitations in sensing capabilities. However, the long-term planning becomes computationally intractable as the length of planing horizon increases. This work develops a gametheoretic approach to address the computational challenges. The main contributions of this paper are twofold: (a) to formulate a non-myopic planning problem for tracking multiple targets into a potential game, the size of which linearly increases as the number of planning steps (b) to design a learning algorithm exploiting the joint strategy fictitious play and dynamic programming, which overcomes the gaps in sensing coverage. Numerical examples of multi-target tracking demonstrate that the proposed method gives better estimation performance than myopic planning and is computationally tractable.