In this paper we develop an intermittent communication framework for mobile robot networks. Intermittent communication provides significantly more flexibility to the robots to accomplish their tasks compared to approaches that enforce communication constraints for all time. We consider robots that move along the edges of a mobility graph and communicate only when they meet at the nodes of that graph giving rise to a dynamic communication network. Assuming that the mobility graph is connected, we design distributed controllers for the robots that determine meeting times at the vertices of the mobility graph so that connectivity of the communication network is ensured over time, infinitely often. We show that this requirement can be captured by a global Linear Temporal Logic (LTL) formula that forces robots to meet infinitely often at the rendezvous points. To generate discrete high-level motion plans for all robots that satisfy the LTL expression, we propose a novel technique that performs an approximate decomposition of the global LTL expression into local LTL expressions and assigns them to the robots. Since the approximate decomposition of the global LTL formula can result in conflicting robot behaviors, we develop a distributed conflict resolution scheme that generates discrete motion plans for every robot, based on the assigned local LTL expressions, whose composition satisfies the global LTL formula. Computer simulations are provided that verify the efficacy of the proposed distributed control scheme.