A POMDP approach to cooperative localization in sparse environments

In this paper we discuss how communication can be used advantageously for cooperative navigation in sparse environments. Specifically, we analyze the tradeoff between the cost of communication cost and the efficient completion of the navigation task. We make use of a partially observable Markov decision process (POMDP) to model the navigation task, since this model allows to explicitly consider the tradeoff between information-gathering actions and actions that move the robot towards the goal. By explicitly including communication in the POMDP model as an information-gathering action with an associated cost, we are able to optimally settle this tradeoff between the gain in information arising from the use of communication and the corresponding cost. We illustrate our results in a small test application.