Establishing and maintaining wireless communication coverage among multiple mobile robots using artificial neural network

This paper introduces a distributed motion control scheme, using an artificial neural network, to adapt to the fluctuating wireless communication conditions in realistic environments and establish and maintain desired wireless communication connections for multi-robot systems. A neural network controller is designed for each robot, trained with sample data, and applied to multi-robot deployment for communication coverage. In this paper, the received signal strength indicator (RSSI) is used as the measure of the wireless link quality, and the signal propagation condition among mobile robots is modeled using the probabilistic log-distance path loss model. The simulation results show that the proposed scheme can establish and maintain effective communication coverage under different path loss exponents and uncertainties, and the average RSSI converges to the desired range.