Dynamic ‘Standing Orders’ for Autonomous Navigation System by means of Machine Learning

Abstract

Globalisation and new environmental legislations lead to a rising need for new technological developments for the shipping industry, espacially creating smart ports and smart waterways. Thus, Maritime Autonomus Surface Ships (MASS) are on the horizon. In order to be able to operate safely in the presence of other vessels, a module that dynamically determines action ranges for avoidance manoeuvres based on machine learning algorithms will be developed. Using historical AIS data, which provide ship’s dynamic as well as static and voyage related data, ship trajectories and thus historical encounter situations of ships are extracted. Using k-means clustering, navigational behaviour of the vessels during an encounter situation can be examined and predicted for future encounter situations.