Rapid acquisition of an efficient and accurate system dynamics model is crucial for trajectory tracking control of unmanned surface vehicles (USVs) to meet diverse maritime mission requirements. To this end, this paper proposes a nonparametric modeling approach based on physics-informed neural networks (PINNs), where physical constraints derived from the physics model are incorporated into the training loss function to enhance physical consistency and generalization. An adaptive unscented Kalman filter (AUKF) is first employed to identify unknown parameters in the mathematical model of the USV for building the physics model through parameter identification, which are then used to guide the construction of the PINN model. Building on this, a novel integration framework of the nonparametric model with nonlinear model predictive control (NMPC) is developed to achieve accurate trajectory tracking control, without the need for the nominal model. The feasibility of the PINN-NMPC control method in this framework is validated by two simulation scenarios, including one with the measurement disturbances and another for the trajectory tracking task. The experimental results demonstrate that the proposed PINN-NMPC method has higher tracking accuracy and robustness compared with other integration approaches.

Remote Control Maritime Autonomous Surface Ships (RC-MASS) have become promising in the near future, while the delivery of the perception data from the ship to the shore suffers from communication issues, such as packet delay, reordering, and loss. In order to improve the accuracy of RC-MASS state estimation in complex communication environments and ensure the performance of control, two effective real-time state estimation methods are proposed. First, a comprehensive model is established by integrating the state of acceleration into the traditional ship motion model; Secondly, a simplified augment CKF (A-CKF) framework is proposed, in which the system state is augment by the previous states; Third, the State Estimation Algorithm with Last Data (SEA-LD) and the SEA with Retrodicted States (SEA-RS) are proposed, which are built upon the A-CKF framework and incorporate a novel state update strategy to accurately estimate the ship’s true state and reduce the impact of accumulated state errors caused by packet delay, reordering, and loss. To validate the proposed method, real-ship and simulation experiments under different communication conditions are introduced. The results indicate that the proposed method has significant improvements in state estimation performance and control performance of RC-MASS under complex communication scenarios. Under a normal delay distribution with means of 200ms, 500ms, and 1000ms, a variance of 10% of the mean, and a packet loss rate of 0.1%, both the SEA-RS and SEA-LD algorithms achieve errors below 0.047 m/s in velocity and 1.25m in position. In terms of control performance, the proposed methods can maintain stable control under severe delay conditions of 2500ms.

The intelligent shipping of inland waterway ships involves a large amount of information exchange among ship-side, shore-side, traffic cloud center, and other traffic nodes. The massive data exchange imposes high requirements on system data processing and network transmission latency. By constructing the inland intelligent navigation system as a multi-layer collaborative information network involving ships, shores, and clouds, efficient interaction among the multiple information network is achieved. Therefore, this paper proposes a method for building a multi-layer collaborative network based on the composite properties of network nodes, realizing the construction of a complex network for inland vessel intelligent navigation involving ships, shores, and clouds. Compared to traditional random geometric methods, the proposed collaborative network construction method, which combines three characteristic parameters of node clustering coefficient, betweenness centrality, and closeness centrality, can more comprehensively describe the characteristics of network nodes, reflect node importance, and address the issue of incomplete node information description in existing multi-layer complex network models. Finally, typical complex network models and independent data set were utilized to validate the proposed method in this study, and practical network deployments were employed to test the feasibility and superiority of the proposed approach, it is demonstrated that the method of generating collaborative networks can significantly reduce the shortest path values between nodes in the network, decrease transmission time, enhance transmission efficiency, and effectively strengthen the information exchange capability of the system.

The Internet of Ships (IoS), by integrating advanced technologies, such as the Internet of Things, cloud computing, and artificial intelligence, aims to interconnect and communicate various physical devices related to maritime transportation, including ships, ports, traffic infrastructure, and warehouses. This integration is designed to optimize transportation decision making, reduce costs, enhance efficiency, improve safety, and promote environmental sustainability. Traditional IoS adopts a cloud computing-based data processing and service model, which, due to its centralized and remotely deployed nature, often places computing nodes far from the data collection and service demand points. This setup struggles to meet the high real-time and low-latency requirements of intelligent ships, traffic organization, remote control, and other applications. Edge computing, by decentralizing computing, storage, and network resources to the edge of the IoS, enables more responsive handling of device requests. It addresses critical requirements, such as intelligent access, real-time communication, and privacy protection in the IoS environment, facilitating intelligent, green communication, efficient data processing, and timely service responses. In this article, the current state of IoS and the relevant concepts of edge computing are introduced. The edge computing enabling IoS (EC-IoS) architecture and the core technologies driving EC-IoS development are systematically discussed. Emerging applications and the case studies of EC-IoS, including intelligent ships at different autonomy levels, intelligent transportation, smart ports, and warehouses, are summarized. Finally, challenges and future opportunities in open computing environments, maritime data management, system security, and resource management are outlined, providing a reference for optimizing maritime management and autonomous navigation.

Intelligent navigation of inland vessels involves the collaboration of multiple traffic participants, including the vessels themselves, shore-based infrastructure, communication networks, and traffic clouds. The foundation of safe, stable, and efficient vessel operations lies in the construction of a unified information organization and computational architecture that logically integrates these elements. This paper addresses the collaborative computing advantages of intelligent navigation for inland vessels by proposing a cloud-shore-ship collaborative computing architecture. The architecture is examined in detail from various perspectives, including its logical structure, collaborative computing process, and functional implementation. Furthermore, the theoretical operational process of the cloud-shore-ship collaborative computing architecture is modeled based on stackelberg game, and mathematical expressions for the cloud computing mode, ship-shore collaborative computing mode, and cloud-shore-ship collaborative computing mode are presented. The proposed architecture is then validated and analyzed through examples of multi-task computing and collaborative perception. Simulation results indicate that the cloud-shore-ship collaborative computing framework can effectively reduce the processing delay and cost associated with intelligent navigation tasks. At the same time, it can increase the sensing range of the target by 28% and increase the sensing accuracy by 52% in the collaborative perception scenario. Finally, the cloud-shore-ship collaborative computing architecture is applied to the operational process of the Three Gorges lock, with analysis showing that the proposed framework enhances the efficiency of lock operations and reduces the waiting time for vessels. The proposed architecture highlights the importance of cloud-shore-vessel collaboration and clarifies the process of collaborative operation, which can effectively improve the level of navigation services compared with the traditional single information service approach. Thus, it provides a valuable reference scheme for the efficient service response of intelligent navigation tasks.

The development of advanced ship positioning and intelligent sensing technologies has transformed navigation at sea, moving beyond reliance on captains’ experience and standard routes. The trajectories traversed by ships at sea contain valuable data that can be mined to map maritime transportation networks and inform intelligent navigation systems. Ship trajectory data at scale enables discovery of the underlying network of maritime routes, providing key insights for applications like intelligent navigation, abnormal behavior detection, trajectory prediction, and maritime traffic pattern analysis. This study reviews the development of research on maritime route networks (MRNs) derived from ship trajectory data. It summarizes the technical process to construct a MRN, contrasting approaches for identifying waypoints, extracting routes, and representing the overall maritime traffic network structure. Finally, this study explores potential applications of MRNs and anticipates promising future research directions in this domain.

Abstract Understanding human mobility in urban areas is important for transportation, from planning to operations and online control. This paper proposes the concept of user-station attention, which describes the user’s (or user group’s) interest in or dependency on specific stations. The concept contributes to a better understanding of human mobility (e.g., travel purposes) and facilitates downstream applications, such as individual mobility prediction and location recommendation. However, intrinsic unsupervised learning characteristics and untrustworthy observation data make it challenging to estimate the real user-station attention. We introduce the user-station attention inference problem using station visit counts data in public transport and develop a matrix decomposition method capturing simultaneously user similarity and station-station relationships using knowledge graphs. Specifically, it captures the user similarity information from the user-station visit counts matrix. It extracts the stations’ latent representation and hidden relations (activities) between stations to construct the mobility knowledge graph (MKG) from smart card data. We develop a neural network (NN)-based nonlinear decomposition approach to extract the MKG relations capturing the latent spatiotemporal travel dependencies. The case study uses both synthetic and real-world data to validate the proposed approach by comparing it with benchmark models. The results illustrate the significant value of the knowledge graph in contributing to the user-station attention inference. The model with MKG improves the estimation accuracy by 35% in MAE and 16% in RMSE. Also, the model is not sensitive to sparse data provided only positive observations are used.

Vessels sailing in a single platoon could reduce resistance from the perspective of the whole platoon and the individual vessel, and contribute to improving energy benefits. Moreover, transportation energy costs and traffic efficiency are essential indicators for measuring waterborne transportation systems. We attempt to minimize transportation energy costs by coordinating platoon formation using a distributed framework of controllers. A large-scale coordinated vessel platooning program is proposed to minimize transportation energy costs and optimize traffic efficiency while guaranteeing safety. The control framework covers routing, energy consumption-dependent cooperative platooning decision and speed optimization based on graph search algorithm, cluster analysis, optimal control approach and model predictive control. Firstly, a local scheduling strategy combined with the leader vessel selection algorithm is adopted. Furthermore, we used cluster analysis to create a series of mergeable vessel platooning sets. Then, we used the mathematical planning method and a two-step hybrid optimal control approach to calculate the improvement and optimization of each vessel platoon’s path and speed. Finally, the scalability of the scheduling strategy is elucidated. In a simulation of large scale inland waterborne network, savings surpassed 3.5% when six hundreds vessels participated in the system. These simulation results reveal that the scheduling strategy coordinating vessels into vessel platooning, which improves transportation efficiency as well as descends cost, comparing to a fixed origin route in the waterway network.

Temporal traffic prediction is critical for ITS yet remains challenging in handling complex spatio-temporal dynamics of traffic systems. The continuous traffic data (e.g., traffic flow, and speed) from various channels and nodes in a traffic network are coupled with each other over the time points of each channel, spatially between traffic nodes, and jointly in both spatial and temporal dimensions. Such multi-aspect traffic data couplings reflect the conditions of a real-life traffic system and evolve over traffic movement and network dynamics. The recent studies formulate traffic prediction by high-profile graph neural networks. However, they mainly focus on hidden relations captured by neural graph mechanisms while overlooking or simplifying the above multi-aspect traffic data couplings. By modeling a traffic system as a coupled traffic network, we learn the multi-aspect traffic data couplings by a Multi-relational Synchronous Graph Attention Network (MS-GAT). Specifically, MS-GAT learns three embeddings to respectively but synchronously represent the traffic data-based channel, temporal, and spatial relations between nodes by specific graph attention designs. The embeddings are further adaptively coupled according to their respective importance to prediction. Tested on five real-world datasets, MS-GAT outperforms six SOTA graph networks-based traffic predictors. MS-GAT captures not only spatial and temporal couplings but also traffic data-based channel interactions over traffic evolution.

This paper describes the framework of a numerical model coupling system based on distributed computing environment by using mobile agents. The multi-layered system provides a flexible shared workspace for the cooperation of multidisciplinary researchers in geophysical modeling and makes it is possible for the researchers to implement the numerical model coupling by plug in or plug out the models. The system takes meso-scale atmospheric model, regional oceanic model and wave model as the researching prototype. The numerical experiment demonstrates the performance of the distributed coupled modeling system.