Search

The emergence of autonomous ship technology holds the promise of enhanced collision avoidance mechanisms and a substantial reduction in human error. However, autonomous ship technology is heavily reliant on sensors and complex algorithms, necessitating a comprehensive understanding of complex situations, such as ship encounter scenarios. In this paper, we introduce a novel method for extracting knowledge from pairwise ship encounters using Automatic Identification System (AIS) data. First, a pairwise ship encounter detection approach is developed, with ships existing in multi-ship encounter scenarios being excluded. Then, a ship encounter type classification method based on cluster technologies is proposed. This includes a data grouping strategy and a data point selection method, aimed at enhancing classification performance while also helping the interpretability of the classified results. Subsequently, ship encounter analysis for knowledge extraction, accompanied by statistical analysis with visualization, is conducted according to the different encounter types. This can not only identify the influencing parameters for decision-making but also get knowledge of different ship encounter situations to get insight into how to make decisions in different encountering situations. A real case study, using AIS data from the commercial autonomous ferry transition in the Oslofjord in Norway, is conducted. Experiments on both labeled and unlabeled data demonstrate the effectiveness of the proposed method. • A comprehensive understanding of ship encounter situations can enhance maritime situational awareness for decision-making. • To gain deeper insights into ship encounter situations, we propose a novel method for extracting knowledge from pairwise ship encounters using Automatic Identification System (AIS) data. • To facilitate knowledge extraction, we propose a pairwise ship encounter detection method and an effective encounter classification method based on clustering techniques, followed by ship encounter analysis to extract knowledge. • A case study is conducted using data from the first commercial autonomous ferry transition in the world, located in the Oslofjord in Norway. [ABSTRACT FROM AUTHOR]