The effect of wind disturbance is one of the major factors that complicate heading control in ship control at low speeds. Approach maneuvering while decreasing speed and approaching the pier requires a control adopted to changing maneuverability and wind conditions. In this study, a control scheme using a deep neural network (DNN) was developed to output command values corresponding to wind conditions by training the DNN on maneuvering patterns of approach maneuvering under various wind conditions. The developed control scheme was validated through experiments using an actual ship.

To maintain ship navigation safety, the navigator must understand and predict the movements of other ships. Radar images include both ship (target) and non-ship images (noise), such as sea clutter. To understand the movements of other ships, navigators must detect ship images from radar images manually. To maintain the optimum situation awareness of navigators while reducing the workload, a function that can automatically detect and track ship images, including small ships, is desired on the radar. Therefore, a system to predict ship movements using machine learning and radar images is proposed in this study. The proposed prediction system is based on a learning model developed using a denoising convolutional autoencoder. The learning and validation data are radar images processed via image processing in advance. The prediction accuracy of ship movements in this study is 90.97%, and the loss is 0.0396.

Capacity limitation and communication delay in satellite communication are issues in the development of remote ship control system. This study proposes a system that receives ship’s motion data instead of images from a ship and reproduces the situation at sea in virtual reality. The results of experiments with an actual ship shows that it is possible to reproduce seamless images under small capacity and delay of communication and maneuver a ship in virtual reality.

Dynamic positioning systems (DPSs), which maintain ships at a specific point, have been widely used in marine development; however, ships without DPSs are also required to remain at a specific position, such as during lifesaving situations. However, it is difficult to maneuver a ship to a specific point without using a maneuvering support system such as a DPS. This paper proposes a maneuvering support system that recommends the control inputs of each actuator to deck officers when they maneuver dynamic positioning manually. The support system predicts the motion of the ship and calculates the control inputs required to maintain the ship at a specific position. Subsequently, the recommended control input of each actuator is provided as a value that can be operated by deck officers. The results of the maneuvering experiment indicate that the developed system may reduce the position error in dynamic positioning.

The berthing maneuver requires high maneuvering techniques because the navigators have to stop the ship at a specified point with decreased maneuverability in restricted water area. Therefore, the automation of berthing maneuver has been gaining increased attention from the marine transportation industry. To construct a reliable automatic berthing system, it is desirable to apply a flexible method in regards to changing the ship's maneuverability, similar to the human's manual berthing maneuvering procedure. In this study, an automatic berthing maneuvering method was developed that does not require gain adjustments based on the experience of specialists or model tests, and is flexible for maneuverability changes of the ship as in manual berthing maneuvering procedure. This was accomplished by introducing an optimal control with variable gain based on the statistical model for maneuvering the ship, which was identified in real-time using actual navigation data. From the results of the experiment, it was confirmed that the method developed in this study was effective.

In recent times, several marine accidents have occurred because of human errors. Mental workload is considered as one of the causes of human errors. The physiological index such as heart rate, nasal temperature, brain wave and saliva are commonly used to measure mental workload. Among these, we focus on nasal temperature as it can measure mental workload without contacting subjects. However, measuring nasal temperature is time-consuming because of the manual detection of the nasal position in infrared (IR) images. This study proposes an automatic method for the measurement of nasal temperature based on the combination of motion-sensing devices and an IR camera. Based on experiments conducted using simulators, the automatic measurement of nasal temperature using both motion-sensing devices and an IR camera has been demonstrated. It is necessary to adjust the coordinate system of the motion-sensing devices and IR camera to accurately measure nasal temperature.

Numerous ship collisions occur due to navigator errors such as improper lookout in a navigational watch, which is considered an error in the situation awareness (SA) of a navigator. Moreover, mental workload is considered one of the causes of human error, and navigators are often under a high mental workload onboard, experiencing fatigue and stress. The aim of this study was to confirm that the coefficient of variation of R-R interval (CVRR) and the adaptive weighted workload (AWWL) of the National Aeronautics and Space Administration Task Load Index (NASA-TLX) are effective indexes to measure navigator fatigue. Another aim was to show the effect of fatigue on navigator SA in lookout. Thus, subjective and objective mental workload of navigators caused by fatigue was measured in bridge simulator experiments. Navigator SA was measured by using a Situation Awareness Global Assessment Technique (SAGAT). The results of the experiments were shown that CVRR was confirmed as an effective objective index for measuring navigator fatigue. Further, navigator SA errors are likely to increase under fatigue conditions.

More than 70% of ship collisions are caused when the navigator cannot correctly recognize other ships’ movement. An effective navigation support system is required to decrease the number of collisions. A system showing the position in which a ship is at risk of colliding with another ship was proposed; however, there was a problem with its user interface and it was difficult for the navigator to realize the collision risk position displayed on the system on the surface of sea. This study proposes a navigation support system using augmented reality to grasp the position of collision risk on the actual sea area. To test the effectiveness of the developed system, a simulator experiment was executed.

This paper proposes a new method to support the evading navigation of a ship within a bay-area by indicating the collision probability sea area to each ship through a web system. This study focused on collision at the exit of a sea route. Then, the ship's new course at the exit point was predicted by the support vector machine, which studied marine traffic data. The collision probability sea area at the exit position was calculated for each ship by considering the obstacle zone through the proposed approach, and the data of the predicted ship's new course. The effectiveness of the proposed approach was demonstrated by the simulation results.

This study proposed a route tracking system for an autonomous solar-powered surface vehicle which supported the operation of autonomous underwater vehicles. The route tracking system was designed with consideration of influence of the wave and the current in the ocean. Effectiveness of developed system was carried out with simulation result.

A ship maneuvering simulator is elïective training tool for navigation officers. An instructor of simulator training executes the evaluation based on the check list. The trainee is told the evaluation at the de-briefing, and obtains the chance to improve his maneuvering skill. On the other hand, some objective evaluation methods for the simulator training were proposed, and also a method for estimating trainees' mental workload from their physiological index during the training was proposed. If these assessment data can be shown at the debriefing, effectiveness of ship maneuvering simulator training can be improved. Therefore, this study tried to examine relation between these evaluation methods and proposed usage of these methods.

A navigator draws a route on a chart to navigate a ship from an origin port to a destination port. Then, the navigator sails the ship based on the route. In other word, the navigator misidentifies the route there is a possibility of running aground. In order to prevent navigator's misidentifies, this study proposed a sea route display system which displays the sea route on the surface of the sea by using augmented reality so that navigator may grasp the ship's position from the sea route easily. Effectiveness of the developed system was carried out with actual ship experiment.

The needs to develop an automatic pier docking system has arisen due to a shortage of seafarers. An automatic pier docking system was proposed in a previous study; however, the system was highly limited in its applicability. In order to develop a practical system, applicable to a wide range of conditions and environments, it was necessary to evaluate the mental workload of captains while using this new system. This study proposed a system that could be safely used to test an automatic pier docking system using a real ship. With the proposed system, an experiment involving the automatic pier docking system was safely executed and the captain's mental workload was effectively measured.

These days, reduction of the young crew, aging, reduce labor costs, and overwork of crew have become serious problems. To solve the problem, navigation supporting system was developed for one person bridge operation. However, technological improvement was more necessary and human error still remained in the system. Thus, with a concept of telexistence, a system for supporting navigation officer was proposed by remote control of a telexistence robot from shore side. The telexistence system was communicated between the telexistence robot on a ship and an experienced mariner from shore by satellite communication. However, for achieving the telexistence system, delay time must be measured because the delay time might cause a marine accident. In this study, the round trip delay time of satellite communication was verified, and the result indicated that the telexistence system worked enough on a ship.

If Tsunami (tidal wave) alert is issued, ships in a port should leave the port immediately. In order to leave the pier, a marine pilot handles the ship with tugboat aid. However, it is difficult to use the tugboat and the pilot in the case of emergency. Therefore, the ship's captain should handle the ship for leaving the pier without tugboat. It is difficult to handle the ship for leaving the pier without tugboat in the case of under strong wind disturbance. For the captains, this study proposed maneuvering support system which indicated maneuvering method for emergency leaving pier. The maneuvering method for leaving the pier without tugboat was derived from a lot of simulation results which operated by pilots. Using the system, simulation result of emergency leaving the pier was displayed on mobile PC. And simulation parameters such as own ship's condition and wind condition were easily changed by user. Then, the captain could understand exact maneuvering method for leaving the pier even if there was wind disturbance. The effectiveness of the solution of developed system was indicated with the simulation results which obtained from full mission type ship handling simulator operated by well experienced pilot.

This paper proposed a ship handling simulator using actual training ship for third grade pilot trainees. The ship handling simulator was achieved by developing the control system which reproduced a large vessel's maneuverability on the actual training ship. Moreover, visual system that gave scenery from large vessel's bridge for trainees by using Augmented Reality was developed. In order to evaluate the influence of the developed system on trainees, trainee's mental workload when the system was used was measured at the actual ship experiment. The experimental result showed that developed system derives trainee's high motivation for maneuvering training.

Availability of a ship propulsion system under aging effects is estimated using GO-FLOW. GO-FLOW is an effective software tool for the availability analysis of complex systems. Aging effects are incorporated into GO-FLOW using a time-dependent technique and assuming a linear aging model. The results show that the aging effects can potentially increase the frequency of accidents due to a malfunction of the propulsion system by a factor of 10 over a period of 20 years, if maintenance is conducted annually at dock only.

This study aimed to improve a ship simulator training for third grade pilot trainees, a method for evaluating the trainees' navigation skill was proposed. To evaluate the trainee's navigation skill, two methods were developed in this study. First method was for measuring which ship the trainee was recognizing in the simulation. Second method was for defining the ship that pilot should recognize in the simulation. The effectiveness of proposed method was showed with the simulator experimental results.

In this study, berthing simulator training data were analyzed then a method of quantitatively evaluating the training result was proposed. Effectiveness of the proposed evaluation method was described with the training results of some experiments.

A navigator efforts to guide a ship for safe and efficient navigation, and s/he gets a navigational information through five senses. Visual information is most important because it is said to occupy more than eighty percents to whole information. We are researching on relationship between a visual image of seascape and a physiological/ a body response using ship bridge simulator, which is used to train and educate ship handling and how to handle a navigational instrument. The simulator training is popular worldwide. The purpose of this paper is to find characteristics of body response to artificial ship movement by vision and motion platform. The result shows characteristics of body response to artificial rolling and pitching by vision and motion platform differ.

In this study, problems of understanding ship's maneuverability for the third grade pilot trainees were analyzed from their training data of berthing the ship using ship handling simulator. To improve their knowledge of ship's maneuverability, training tool that simulate the berthing the ship with a mobile computer was developed.

In this study, training data of berth maneuvering using ship handling simulator was analyzed from the viewpoint of the minimum time berth maneuvering problem. The safety margin of the minimum time berthing problem was derived from the minimum value and the maximum value of the simulator training data of the first class pilot trainee.

We use a simulator for research of human factor in ship handling; however, in case of arriving port, it is not enough for a visual image around own ship. The ship handling simulator does not have the visual image (screen) around own ship. We tried to build up the ship handling simulator that has visual system around own ship for arriving port. In this paper, details of the visual image system of the ship handling simulator and results of some experiment performed for effectiveness of this visual system is shown.

Mental workload is useful to evaluate performance of a ship's bridge teammate: a captain, a duty officer and a helmsman, sometimes adding a pilot. The heart rate variability and the nasal temperature predict well based on pre-experiments; however, we have not evaluated them at the same time yet. In this paper, we evaluate simultaneously heart rate variability and nasal temperature of a subject as he guides a ship into port. The experiment is carried out using a ship handling simulator, not a real ship. We show they are good indices for efficient navigation skills.

In ship's berthing at a harbor, ship operator is required to derive the maximum maneuverability from the ship. The minimum time berthing method is one of the rational and effective maneuvering methods for such tedious problems. In this paper, development of automatic minimum time berthing control system is described. And, effectiveness of the system is examined by actual sea test.

A human skill is evaluated by a professional who has lots of experience and good sense. Quantitative evaluation comes from a performance and a questionnaire. Mental workload shows internal conditions and it is important for us to evaluate human skills, especially, intellectual performance. The physiological indices used to evaluate mental workload (decision-making effort). The heart rate variability (R-R interval) and the nasal temperature, are hopeful indices for the navigator based on our research. This paper proposes that the nasal temperature is an effective index to evaluate the mental workload of a navigator. The nasal temperature responds when the navigator makes a decision regarding ship-handling and collision avoidance, and shows well the whole trend of his decision-making.

Usage of a ship handling simulator extend to many topics such as crew trains, evaluation of nautical instrument and research of human factor etc. In any case, it is necessary to observe operator's behavior at bridge work. The procedures of performed operator's task could be recorded by a monitoring video camera. However, it is difficult to estimate operator's mental workload at each performance from the monitoring video. In this paper, practical technique is introduced for presuming navigator's mental workload in ship handling simulator by using data of navigator's nasal temperature which is measured by thermal image video camera. And effectiveness of this technique is examined by some practical simulations.

In recent years, serious problems have arisen in coastal shipping along in Japan, because lack of expert sailors and the successors have gone on the increase year by year. Since such state of harbor operations has required immediately improving the technology of operation, authors proposed a solution to contribute to the development of the coastal shipping and the decrease of marine casualties. Taking variation of harbor circumstances into consideration, authors proposed a minimum time harbor operation system for coastal vessels in this paper. This system must make them possible of time shortening of harbor operation, load reduction for sailors and fuel consumption of vessels as well. A minimum time maneuvering method was obtained by mathematical optimal solutions with SCGRA method. The effectiveness of this new operation system was confirmed through some actual ship experiments of steering by the captains.

Ship-ship collisions have the potential to cause catastrophic marine accidents with human and economic losses as well as environmental pollution. Safe navigation is a major operative task for the officer(s) on the watch (OOW) as the ultimate responsibility for safe navigation resides with the human navigator. Though the universal use of automatic radar plotting aid (ARPA) system on board ships has greatly reduced the maritime collision risks, it brings the OOW great burden for collision risk assessment and in the planning of suitable evasive actions in complex situations (e.g., many targets approaching own ship simultaneously). This paper concerns the development of a direct perception interface that displays collision danger lines (CDL) and collision danger sectors (CDS) to acquired targets for the OOW to enable a quick collision risk assessment and plan evasive maneuvers well in advance of a developing situation. A preliminary experimental study of this display has been conducted. The results showed that CDS display had the potential to improve navigators' performance compared with ARPA display. Further study is required to investigate the merits and demerits of this display.

Development of navigation support system was important for the safety navigation. However, it was also important to evaluate the influence of a new navigation support system on mariners for the safe maneuvering. In this research, ship maneuvering simulation experiment was executed to examine the impact of a new navigation support system and subject's response and performance in the experiment were measured and analyzed. As a result, the effectiveness of new navigation system for mariners was shown in this report.