Deep Q-Learning to Preserve Connectivity in Multi-robot Systems

Abstract

Multi-robot systems are widely applied in various areas. The connectivity within robots plays an important role in many cooperative tasks. In this paper, we propose a deep Q-network based learning approach for connectivity preservation problem. We adopt a fully connected neural network with nonlinearities as the Q-function in the deep Q-network based framework. Further, we design and implement a simulation environment for connectivity preservation, which provides states and reward feedbacks to deep Q-network. We demonstrate the learning framework and the simulation environment by a series of simulation experiments. The experimental results show that our learning framework can successfully address the connectivity preservation problem.