Search

Maritime navigation in multi-ship encounters presents challenges due to dynamic perturbations and complexity, which lead to elevated safety concerns. Conventional path-planning methods exhibit several issues. This paper addresses these issues by proposing a prediction-enabled path-planning method for multi-ship encounters in the Horten and Moss area within Oslofjord, Norway, the first industrial testbed for autonomous ferries nationwide. The method leverages action classification and trajectory projection techniques to enhance path planning with a more informed decision-making process. A convolution neural network is employed for the binary classification of the own ship's action classes, and a dynamic time-warping approach is applied to predict the future positions of the target ships based on trajectory similarity. Experiments utilizing Automatic Identification System data from 2013 to 2019 demonstrated the method's effectiveness. Classification results show a satisfactory F1 score, and comparative evaluations with the classic A* method showcase superior performance. Real-case tests affirm the method's ability to provide a trackable path while ensuring a safe distance between the own ship and target ships. • This study utilizes the expertise of the experienced captains and operators to extract the multi-ship encounters using the AIS data collected from 2013–2019 in the Oslofjord explicitly. • A novel prediction-enabled path planning method is proposed for multi-ship encounter situations. • The uncertainty associated with making evasive manoeuvres is mitigated through the implementation of an action classification technique. • The effectiveness of the proposed method is validated through comparison with other classic path planning methods and case studies in the Oslofjord. [ABSTRACT FROM AUTHOR]

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]