The increasing complexity of maritime traffic necessitates advanced collision avoidance systems for autonomous navigation. Traditional path planning algorithms often struggle with dynamic obstacle prediction and adherence to navigational regulations. To address these challenges, this study introduces a collision avoidance framework that integrates the Obstacle Zone by Target (OZT) method with an improved A-star algorithm. This paper proposes a combination of the OZT method and an improved A-star algorithm, which incorporates a decision-making module and segmented path planning to generate COLREGs-compliant avoidance routes, optimizing route safety and smoothness. The effectiveness of this system was verified through simulations, and the results demonstrate the system’s ability to generate collision-free paths in multi-ship scenarios while considering and complying with COLREGs. Compared to the traditional A-star algorithm, the proposed approach reduced path length by an average of 5.92% and decreased turning points by 79.44% in give-way situations, significantly improving navigation efficiency and path smoothness.

With the widespread availability of automatic identification system (AIS) data, they have been applied in various maritime research. Due to technical issues and environmental interference, AIS data can have missing data points or irregularly reported intervals, which can cause unreliability in research activities and inaccurate trajectory visualization. In this study, AIS data quality issues and the importance of marine traffic in congested areas are addressed first. In this study, the Yangon River and approaches is selected as the area of study due to its significance in the country’s maritime trade. In this study, the reference trajectory reconstruction is done in two steps. The first step is using Hierarchical Density-Based Spatial Clustering of Applications with Noise (HDBSCAN) to cluster AIS data and identify the locations of major vessel traffic activity and extract their dynamic features. The second step is using interpolation methods to reconstruct the reference trajectory from the detected clusters. The reconstructed trajectory is validated against the surveyed benchmark routes for position and their dynamic AIS features by numerical methods. The evaluation result shows that the trajectory reconstructed in this way has a high similarity to the benchmark routes. We hope that our study would provide more future research opportunities for marine traffic in the Yangon Port.

Global maritime traffic is increasing, and the development of Maritime Autonomous Surface Ships (MASS) is progressing. Demonstrations have been carried out, and the first fully autonomous voyage under human supervision was completed in Norway in 2023. The International Maritime Organization (IMO) is developing regulations for the introduction of MASS and aims to issue a mandatory MASS Code in 2032. Research is being conducted on the actual management of engine plants and maintenance methods for the realization of MASS, but research on how to safely operate and manage ships is still lacking. The aim of this paper is to capture an overview of the changes in ship management with the advent of MASS by means of a questionnaire survey of seafarers in ocean shipping companies. Cooperation was obtained from 100 captains and deck officers to clarify this objective. Regarding the items studied, an analysis is made of the expected changes in ship management and how they are expected to change in the future.

Marine navigation officers perform lookouts, which include visual observation and the use of radar to keep track of the surrounding conditions. Early detection of other ships and obstacles is crucial for ensuring safe navigation, particularly in congested areas. In previous studies, remote maneuvering was achieved using the same communication and steering as ordinary maneuvering. However, when performing a maneuver to avoid another ship, it is necessary to share information with other ships remotely. Therefore, the purpose of this study was to obtain information on other ships of all sizes, by analyzing radar images. Artificial intelligence (AI) was used to predict and enhance radar echoes for small vessels. The tracking performance was compared between normal and AI-processed images using actual radar images obtained in Tokyo Bay. The results showed that the tracking performance of the AI system was better than that of the normal radar images. In addition, the AI-processed images could capture and track a small vessel at an early stage, before the navigation officer detected it.

The International Maritime Organization (IMO) began developing a regulatory framework for MASS in 2018. In the case of a manned MASS, it is assumed that the ship’s maneuvering authority is suddenly transferred from the automated system to the officer on board. Unfortunately, owing to this autonomous system, newer seafarers skills and experience may be relatively lower than traditional seafarers. Numerous emergency scenarios require rapid decision-making. Thus, elucidating experience-based attributes of response time is essential for expressing the competencies required for future MASS officers. In this study, assuming the realization of autonomous navigation at Degree 1 or Degree 2, this study aims to clarify the features of the time taken by ship operators to respond to an emergency, including the first actions taken as an emergency response.

The experiment was conducted with three groups: students, officers, and captains. In this experiment, a sudden transfer of the right to maneuver was simulated. Therefore, a whiteboard was used to keep the display out of sight until the beginning of the scenario. he participants maneuvered the ship to respond to an emergency by avoiding collisions with another vessel. The features of each group’s emergency response were analyzed based on the presence or absence of a collision in the scenario, the time required to respond to the emergency, and the type of initial response. According to the results, the response time of the Student and Officer groups in the non-collision team was relatively short because they judged that the time available to recognize the situation was insufficient and tried to make more time and distance. Furthermore, the response time of the Captain group was relatively long because they responded to the situation after gathering sufficient situational awareness.

Globally, advancements toward the development of autonomous ships are accelerating. However, there has been inadequate focus on the fallback measures—specifically, how to safely revert control to human operators when the system fails to respond adequately. It is essential to specify the skills that marine officers on future autonomous ships will need, such as making rapid collision avoidance decisions. Prior research shown that indicating differences in preparatory actions based on experience even in standard navigation. It is plausible that similar variances of pre-evasion actions exist in emergencies, and understanding these could be pivotal in determining the skills required for seafarers on future autonomous ships. Therefore, this study aims to clarify the characteristics of actions taken by navigators before initiating emergency evasion maneuvers.

This study highlights distinct differences in the ability to gather and utilize information based on the level of experience among navigators. Despite their diligent efforts to thoroughly observe their surroundings, inexperienced students were unable to gather sufficient information to avoid collisions. In contrast, among officers with some experience, those in the non-collision group spent relatively more time per instance observing the radar and were considered successful in acquiring the necessary data through radar observation. Captains had the highest proportion of radar observation behavior among all groups. This suggests that captains may demonstrated proficiency in employing appropriate information-gathering methods that are customized to the demands of the situation.

The Kanmon Passage poses navigational challenges for ships because of its severe conditions, such as long and bending channels, narrow channel widths, and strong currents. Despite the implementation of various measures, ship collisions continue to occur in these waters. To understand the current traffic conditions, this study investigated ship collision accidents and estimated the number of ship encounters, E_n, for three types of encounters, head-on, overtaking, and crossing encounters, in each segment of the passage divided into small areas. The results indicate that a high percentage of overtaking collisions occur in the Hayatomo Seto Fairway of the Kanmon Passage and that overtaking encounters are particularly frequent around the fairway. Based on these results, this study further analyzed ship congestion in the Hayatomo Seto Fairway to confirm the mechanisms underlying collisions and encounters. The traffic speed index (TSI) was employed to analyze the degree of ship congestion. In addition, correlations between the indices were calculated to examine each relationship. The results demonstrate that each index has distinct characteristics and can be used to assess potential collision risk and congestion situations.