As the development of emerging technologies is applied in the maritime industry and nautical operations, an interdisciplinary supervision approach is expected to be designed in this subject to enable students the ability to handle the issues brought by the fusion of industrial conventions and technological evolutions. This paper provides the profile of the participants and the subject in which the co-supervision is to be engaged. We investigate how interdisciplinary supervision and co-supervision can be implemented in the nautical science undergraduate program. The resources of both undergraduate education and maritime-related research at the Department of Ocean Operations and Civil Engineering at NTNU are taken as the principal for the fundamental subject. As expected, not only do the undergraduates are benefitted from the co-supervision, the researchers taking co-supervision responsibilities also pro-mote their insights by absorbing the human-dominant expertise knowledge generated by the students. Through the paper, we propose a route map to explore the mechanism of co-supervision in this subject and the expected outcomes.

The visual attention of navigators is imperative to understand the logic of navigation as well as the surveillance of navigators' status and operation. Current studies are implemented with the help of wearable eye-tracker glasses; yet, the high expenditure demanded by such equipment and service and its limitations on usability have impeded related research from further development. In this letter, the authors propose a framework, which is the first attempt in the maritime domain, to provide a camera-based deep-learning (CaBDeeL) visual attention recognition solution that outperforms the intrusive eye tracker regarding its shortcomings. A wide-angle camera is configured in front of the navigator in the advanced ship-bridge simulator in a way that visual attention reflected by their facial and head movements is captured in the front view. A pair of eye-tracker glasses is used to classify the captured visual attention images, which then form the primary database. During the process of classifying camera-captured images, a convolutional neural network (CNN) is built as an automatic classifier. The CNN is applied to two scenarios, and it shows an overall 95 % accuracy.

The development of maritime autonomous surface ships (MASS) has triggered interest from both academia and industry in recent years. Nevertheless, human operators will continue to perform dominant roles onboard for the next decades. There are several critical phases where human operators are in the navigation loop (MASS-I, II, and III) before full ship autonomy (MASS-IV) is achieved. The authors conceive a cyber-physical human framework for the experiment design and implementation in the maritime domain: based on multiple experimental platforms with data exchange ports, apply monitoring on and learning from navigators’ behaviors, and adapt the ship-bridge system to provide decision support in terms of guidance, navigation, and control. The platforms include a compact simulator from Kongsberg®and an immersive simulator for preliminary research design, a group of standard maritime training simulators, and a research vessel. These platforms are utilized for data collection, scenario design, testbeds to demonstrate and verify new techniques and algorithms, etc. The authors illustrate how the framework aids the MASS research and benefits the development process.

Situation awareness is of great importance for autonomous ships. One key aspect is to estimate the sea state in a real-time manner. Considering the ship as a large wave buoy, the sea state can be estimated from motion responses without extra sensors installed. However, it is difficult to associate waves with ship motion through an explicit model since the hydrodynamic effect is hard to model. In this paper, a data-driven model is developed to estimate the sea state based on ship motion data. The ship motion response is analyzed through statistical, temporal, spectral, and wavelet analysis. Features from multi-domain are constructed and an ensemble machine learning model is established. Real-world data is collected from a research vessel operating on the west coast of Norway. Through the validation with the real-world data, the model shows promising performance in terms of significant wave height and peak period.