Model-based learning of underwater acoustic communication performance for marine robots

Abstract

Accurate prediction of acoustic communication performance is an important capability for marine robots. In this paper, we propose a model-based learning methodology for the prediction of underwater acoustic communication performance. The learning algorithm consists of two steps: (i) estimation of the covariance matrix by evaluating candidate functions with estimated parameters using detrended measurements;and (ii) prediction of communication performance. Covariance estimation is addressed with a multi-stage iterative training method that produces unbiased and robust results with nested models. The efficiency of the framework is validated with simulations and experimental data from field trials. The field trials involved a manned surface vehicle and an autonomous underwater vehicle.