The advancement of smart shipping and autonomous navigation relies on Automatic Identification System (AIS) data, which provides essential ship trajectory information. However, raw AIS data lacks semantic context, making behavior annotation crucial for understanding navigation tasks and processes. Existing research faces two challenges: (1) a lack of clarity on which semantics should be abstracted for effective behavior annotation, and (2) insufficient consideration of spatial interactions between ship maneuvering and the navigational environment, particularly topological interactions. These issues complicate data extraction and hinder machine learning-based applications such as explainable trajectory prediction. This paper proposes a comprehensive framework for semantic annotation and indexing of ship behavior. The framework deconstructs ship behavior into a unified data structure using a relational database, where three types of behavior semantics are defined, including atomic, topological, and traffic behavior. Atomic behaviors (e.g., move and stop) are extracted to annotate raw trajectories, while topological behaviors, describing interactions between trajectories and the environment, are modelled using an improved Dimensionally Extended 9-Intersection Model (DE-9IM). The combination of these semantics enables the annotation of higher-level traffic behavior. The model is further evaluated via behavior annotation statistics, demonstrating its effectiveness in annotation and indexing high-level ship behavior.

Aiming at the cognition problem of systematic ship behavior in harbor, a behavior recognition model based on semantic reasoning based on discrete event system modeling theory was proposed. Firstly, the hierarchical modeling of the behavior of ships in port waters is divided into data layer, event layer, activity layer and process layer. Based on a certain theoretical understanding of ship behavior on different time scales and space scales, build a ship behavior cognitive model; Secondly, in the data layer, the trajectory key point detection and segmentation extraction of the motion trajectory of port ship AIS data are performed by integrating port navigation rules to realize the labeling of ship trajectories. Finally, based on the labeling results of the data layer, the ontology is used to make inferences to discover the implicit ship behavior, and realize the trajectory of the ship from the data layer to the semantic layer. Experiments were performed using Xiamen Port data. The experimental results show that the behavioral cognitive ontology based on discrete system modeling can realize the cognitive and semantic reasoning of ship behavior at different time and space scales.

This paper investigates the motion-planning problem for an unmanned surface vehicle (USV), in which the goal is to find the shortest search time, the shortest path in navigational waters, all subject to collision avoidance and USV dynamics constraints. A new motion-planning method is proposed, based on topological position relationships (TPR), to achieve this solution. Firstly, the TPR of the obstacles and the USV are constructed, based on the spatial distribution of the obstacles. This gives an overall topological navigation map, which is different from the usual grid-based map. Secondly, a numerical model of unit decomposition is built to constrain the dynamics of the USV, so that the motion of the USV better fits the exact situation. Motion planning in this study is achieved by combining the topological navigation map and a numerical model of the USV. Finally, Numerical simulations and field tests verify the effectiveness of our formulated model and proposed algorithm.