Comparison of Three Data-Driven Identification Methods and Experimental Testing on a YunZhou Unmanned Surface Vehicle

Unmanned Surface Vehicle (USV) plays an important role in lots of areas such as military, hydrological survey, salvage, rescue and exploration. Being different from large-scale vessels, USV has the advantages of small volume, light weight, fast speed and easy control, and thus its modeling and parameter identification is particularly important. In this paper, we first establish the model for USV, and then identify the parameters of the model by employing least square method, recursive least square method and particle swarm optimization (PSO) algorithm, respectively. Comparisons are also made between these three methods.