As the technology of the maritime autonomous surface ship (MASS) systems has geared toward autonomy, the importance of human operations in the shore control center (SCC) has gained in significance. Accordingly, the effects of the training method, including the traditional and new remote operator training methods have to be investigated in terms of MASS navigation safety. Therefore, this study conducted a comparative analysis to prove the effect of onboard training. The findings include the execution of a simulated navigation experiment, the extraction of rudder steering-related features, selection of significant features, and comparative analysis with network graph visualization. The separate results obtained from the “untrained” group and “trained” group were exhibited as the purpose of research for the effect of onboard training on navigation skills. Then, the authors interpreted the difference in each group allusively in accordance with features considering actual navigation and compared groups using descriptive statistics. Consequently, this study emphasized the importance of proving the effect of training before the new training technologies are used to train MASS remote operators in the future.
The development of autonomous ships has begun. Artificial intelligence (AI) is expected to be partially responsible for navigation; nevertheless, the importance of human intervention is higher than ever. Human intervention in the control of an autonomous ship via the remote operator requires navigation proficiency. The education method for the remote operators that is presently considered is simulation training. However, the simulation training does not take long enough time for enabling trainees to develop their navigation proficiency equivalent to that of conventional ships navigators. In addition, the simulation training should contain various navigation scenarios to train the trainee properly. Therefore, this paper suggests the methods to generate the massive and practical navigation scenarios by extracting navigation elements’ distribution from actual ship trajectory data and applying them to the permutation of navigation elements. The results demonstrated the advantages of the proposed methods by comparing the sample navigation scenario and an example of an impractical navigation scenario. In conclusion, it is expected that the massive generation of practical navigation scenarios using the proposed permutation model will positively affect the simulation training of the maritime autonomous surface ship remote operators.
Maritime collision accidents occur frequently and result in huge damages. Complex collision accidents are especially associated with worse damages. Complex maritime collision accidents involve other types of accidents barring the main accident, such as fire, explosions, capsizes, sinking, and even casualties. When a maritime accident occurs, the maritime accident verdict covers the surveyed facts from the origin of the accident to the consequences. The survey usually reveals the primary cause of the accident; however, complex causes may remain latent. Therefore, this research aims to apply text analytics to maritime verdicts of collision accident cases to identify the latent causes in complex collision accidents. The proposed methods separated the collected corpus into the training dataset and the test dataset. The word propensity database was extracted from the training dataset and applied to sample verdicts of complex maritime collision accidents in the test dataset. The expected results of this research were words that appeared in only complex maritime accidents with a high propensity for additional categories and the relevant context that explains the latent causes that underlie the complexity of the maritime accident. The conclusion suggested that the latent causes derived should be provided to ships to help prevent future complex collision accidents.
The enhancement of navigators’ ability has been promoted by on-scene training; however, considering the safety and repeatability, simulation training (ST) is recommended. Notably, the training of maritime autonomous surface ship (MASS) remote operators has to be performed in a systemic simulated environment. In various fields, ST has differentiated levels of training scenarios considering the proper training effect and evaluation. Although the accuracy and implementation of a realistic situation have received the most attention in simulated navigation, the objective criteria of difficulty are to be established for systemic training. For this purpose, this study aims to propose difficulty criteria in navigation generation scenarios for the development of training simulator MASS remote operators. Proposed methods generated navigation scenarios with differentiated difficulties, simulated navigation experiments were performed, and the results were analyzed as a validation of the differentiated difficulties. Our findings include the difficulty differentiation method, navigation scenario samples, and simulated navigation experimental results.
2 October 2022 in Journal of International Maritime Safety, Environmental Affairs, and Shipping