Avoidance maneuvering support program, avoidance maneuvering support method, and avoidance maneuvering support device

Abstract

To reduce an amount of calculations for risk assessment regarding routes of collision avoidance maneuvers at the time of detection of a range of possible collision.SOLUTION: A collision avoidance maneuvering support program causes a computer to execute processing of: detecting a range of possible collision between an own vessel and another vessel; setting a passing point where the own vessel passes between a position of the own vessel at the time of detection and a destination of the own vessel when the range of possible collision with the other vessel is detected; determining whether or not the range of possible collision with the other vessel is detected in the route passing through the position of the own vessel, the passing point, and the destination; and outputting a route in which no range of possible collision is detected.SELECTED DRAWING: Figure 8

Description

Technical Field

[0001] The present invention relates to an evasive maneuver support program and the like.

Background Art

[0002] As technologies for evaluating risks such as collision risks in ships, a route generation device, a navigation support method, etc. have been proposed. For example, the route generation device generates a route on which a ship can safely navigate in consideration of the potential for the predicted risk by combining the potential method with OZT. Also, in the navigation support method, a collision risk value of the planned route is obtained based on the navigation status of other ships throughout the entire planned route and the meteorological and oceanographic prediction information on the planned route, and the collision risk value is output as risk information.

Prior Art Documents

Patent Documents

[0003]

Patent Document 1

Patent Document 2

Summary of the Invention

Problems to be Solved by the Invention

[0004] However, conventional technologies, such as the aforementioned route generation devices and navigation support methods, only generate routes that are less likely to cause OZT (Optical Zero Toll) at the planning stage before the ship departs. Therefore, when OZT occurs during operation, how to achieve collision avoidance is left to the personnel on site. Thus, the above conventional technologies do not have a way to generate collision avoidance routes when OZT occurs during operation, making it difficult to support collision avoidance. Furthermore, even if the above conventional technologies are used when OZT occurs, they all evaluate the risk for each divided section of the sea area in which the ship is navigating and generate routes with low risk, which increases the computational load related to collision risk evaluation.

[0005] While OZT was used as an example of a risk assessment algorithm here, similar challenges may arise when other risk assessment algorithms detect areas with potential collisions.

[0006] In one aspect, the present invention aims to provide a collision avoidance support program, a collision avoidance support method, and a collision avoidance support device that can reduce the computational cost of risk assessment regarding the path of collision avoidance maneuver when detecting a collision-prone area. [Means for solving the problem]

[0007] A collision avoidance maneuvering support program according to one embodiment involves the following processes: detecting a range in which a collision between one's own vessel and another vessel is possible; when a collision range with another vessel is detected, setting waypoints for the own vessel to pass through between the position of the own vessel at the time of detection and the destination of the own vessel; determining whether a collision range with another vessel is detected along the route passing through the position of the own vessel, the waypoints, and the destination; and outputting a route in which no collision range is detected. [Effects of the Invention]

[0008] This reduces the computational complexity of risk assessments regarding avoidance maneuvers when detecting areas where collisions are possible. [Brief explanation of the drawing]

[0009] [Figure 1] Figure 1 shows an example of the configuration of a collision avoidance maneuvering support system. [Figure 2] Figure 2 shows an example of the relationship between ship type and type of location information. [Figure 3] Figure 3 shows an example of OZT. [Figure 4] Figure 4 shows an example of a machine learning model used in AI for predicting course. [Figure 5] Figure 5 shows an example of the OZT display. [Figure 6] Figure 6 shows an example of the OZT display. [Figure 7] Figure 7 shows an example of risk assessment based on AI-based course prediction. [Figure 8] Figure 8 shows an example of assistance in collision avoidance maneuvering. [Figure 9] Figure 9 is a block diagram showing an example of the functional configuration of a server device. [Figure 10] Figure 10 is a flowchart showing the procedure for assisting collision avoidance maneuvers. [Figure 11] Figure 11 shows an example of a hardware configuration. [Modes for carrying out the invention]

[0010] The following describes embodiments of the collision avoidance support program, collision avoidance support method, and collision avoidance support device according to the present invention, with reference to the attached drawings. Each embodiment is merely an example or aspect, and such examples do not limit the range of values, functions, or usage scenarios. Furthermore, each embodiment can be appropriately combined as long as the processing content is not contradictory. [Examples]

[0011] <System Configuration> FIG. 1 is a diagram showing a configuration example of an avoidance maneuver support system. The avoidance maneuver support system 1 shown in FIG. 1 provides an avoidance maneuver support function for supporting an avoidance maneuver when detecting an OZT (Obstacle Zone by Target) at the operation site. Hereinafter, as an example of an algorithm for performing risk assessment, OZT is taken as an example, but it may be assumed that a range where a collision is possible is detected by other risk assessment algorithms.

[0012] As shown in FIG. 1, the avoidance maneuver support system 1 may include a server device 10 and client terminals 30A to 30N. Hereinafter, the client terminals 30A to 30N may be referred to as "client terminal 30" in some cases.

[0013] Communication between the server device 10 and the client terminal 30 can be realized via a network NW such as the Internet or a LAN (Local Area Network). As an example only, the client terminal 30 connects to the network NW via a base station in a coastal area where radio waves of a mobile network base station can reach, while connecting to the network NW via an artificial satellite included in a satellite communication network in an open sea area where radio waves of the base station cannot reach.

[0014] The server device 10 is an example of a computer that provides the above-described avoidance maneuver support function. For example, the server device 10 can be realized as a server that provides the above-described avoidance maneuver support function on-premises. In addition, the server device 10 can provide the above-described avoidance maneuver support function as a cloud service by being realized as a PaaS (Platform as a Service)-type or SaaS (Software as a Service)-type application.

[0015] The client terminal 30 is an example of a computer that receives the provision of the above-described avoidance maneuver support function. For example, the client terminal 30 may be realized by a portable terminal device such as a personal computer, a smartphone, a tablet terminal, or a wearable terminal.

[0016] Note that, in FIG. 1, an example of a usage scenario of the server device 10 as a service for providing the above-mentioned evasive steering support function to the client terminal 30 is given, but this is merely an example. For example, by causing an application operating on the client terminal 30 to execute processing corresponding to the above-mentioned evasive steering support function on the client terminal 30, the above-mentioned evasive steering support function may be provided stand-alone. As merely an example, since satellite communication during open sea navigation has an increased time lag and cost compared to carrier communication, the client terminal 30 may operate stand-alone.

[0017] <An example of an AIS-equipped ship> As merely an example, the client terminal 30 may be mounted on a ship. The "ship" mentioned here is not limited to a specific ship type or a specific loading capacity, and all ship types and loading capacities are within the scope.

[0018] For example, in the example shown in FIG. 1, the client terminal 30A is mounted on the tanker 3A. The client terminal 30B is mounted on the tugboat 3B. The client terminal 30N is mounted on the pleasure boat 3N. Hereinafter, when referring to ships in general such as the tanker 3A, the tugboat 3B, and the pleasure boat 3N, it may be described as "ship 3".

[0019] The client terminal 30 can upload the position information of the ship 3 to the server device 10. For example, in the case of a ship 3 equipped with an AIS (Automatic Identification System) 50, the AIS data transmitted by the AIS 50 can be uploaded. Also, in the case of a ship 3 not equipped with an AIS 50, the position information measured by the GPS (Global Positioning System) receiver of the client terminal 30 can be uploaded.

[0020] Figure 2 shows an example of the relationship between ship type and type of position information. In Figure 2, tanker 3A is shown as an example of a vessel with a gross tonnage of 500 tons or more. Vessels with a gross tonnage of 500 tons or more are required to be equipped with AIS50 due to legal requirements such as international treaties. In addition, there are also vessels with a gross tonnage of less than 500 tons that are equipped with AIS50, such as tugboat 3B.

[0021] In the case of a vessel equipped with AIS50, the client terminal 30 can upload the AIS data transmitted by AIS50. For example, the AIS data transmitted by AIS50 may include "ship-related information" and "dynamic information." Of these, "ship-related information" may include destination, estimated time of arrival, and voyage plan. "Dynamic information" may include position information, course, speed, and bearing.

[0022] On the other hand, AIS50 may not be installed on vessels with a gross tonnage of less than 500 tons. For example, fishing boats and pleasure boats 3N are not always equipped with AIS50. In the case of vessels that are not equipped with AIS50, the client terminal 30 can upload location information measured by the GPS receiver that the client terminal 30 has.

[0023] In this way, location information is uploaded from the client terminal 30 to the server device 10, including not only vessels equipped with AIS50 but also vessels not equipped with AIS50. This expands the range of vessels supported by the above-mentioned collision avoidance assistance function to include vessels with a gross tonnage of less than 500 tons, such as small vessels like fishing boats and pleasure boats.

[0024] This expansion of support has technical significance for the following reasons: Since the majority of ship collisions, for example 80%, involve collisions between large vessels that are required to navigate in designated shipping lanes and smaller vessels that are not subject to such obligations, the technical significance of being able to support avoidance maneuvers for smaller vessels, including fishing boats and pleasure boats, is considerable.

[0025] Note that Figure 2 uses whether or not the gross tonnage is 500 tons or more as an example of a vessel that is required to be equipped with AIS50, but this is only one example. For example, there may be vessels that are required to be equipped with AIS50 even if their gross tonnage is not 500 tons or more, such as vessels engaged in international voyages or passenger ships engaged in international voyages.

[0026] <An example of risk assessment> In ship risk assessment, the Navigation Zone (OZT), or OZT, is used. For example, the OZT is determined by the speed of the other ship. O and direction φ O This is detected based on the ship's speed V and course angle φ. The ship speed V of the other ship O and direction φ O This information can be obtained from AIS data transmitted by the AIS50 installed on the other vessel. On the other hand, the ship's speed V is assumed to remain constant, while the course angle φ is assumed to be changeable. Although OZT is given as an example of the algorithm used for risk assessment, other risk assessment algorithms are similar. Furthermore, below, an example of one's own vessel may be referred to as "one's own vessel." In addition, below, an example of another vessel may be referred to as "another vessel" or "the other vessel."

[0027] Figure 3 shows an example of an OZT (Oxygen-Zero-Teleportation). In Figure 3, tanker 3A is shown as an example of the own vessel, and tugboat 3B is shown as an example of another vessel. As shown in Figure 3, the orientation of the other vessel 3B is φ O The course along the straight line is, ship speed V OA risk determination circle (t) for movement is set. Among such a set of risk determination circles (t), a subset of the risk determination circles that includes the predicted position (t, φ) of the own ship 3A sailing at a constant speed V and a course angle φ is detected as OZT. For example, in the example shown in FIG. 3, when the direction φ of the own ship 3A is changed within a specific angle range, for example, within a range of 10° to the left and right, a set of hatched risk determination circles where the course of the own ship 3A intersects is detected as OZT. By taking an avoidance maneuver with a course φ that does not enter such OZT, a collision between the own ship 3A and the other ship 3B can be avoided.

[0028] In addition to the above OZT, an automatic collision prevention assistance device that calculates the closest distance between the own ship and the other ship, the time required to reach the closest distance, etc. based on radar supplementary information, etc., so-called ARPA (Automatic Radar Plotting Aids), etc. are also known.

[0029] <One aspect of the problems of OZT and ARPA> In these OZT and ARPA, since the risk is evaluated under the condition that the course of the other ship is straight without changing the ship speed and direction of the other ship obtained at the time of acquisition by AIS50 or radar, the inaccuracy of the course of the other ship is one of the reasons for the decrease in the accuracy of risk evaluation.

[0030] Furthermore, there have been attempts to infer future tracks from the tracks of a plurality of AIS data acquired in the past. However, since the course of the other ship can change depending on the ship type and the shape of the port facilities, there is a current situation where the course of the other ship cannot be accurately predicted.

[0031] In addition, according to ARPA, when fiber reinforced plastics, so-called FRP (Fiber Reinforced Plastics), are used for the hull, there is an aspect that the other ship cannot be detected by radar in the first place.

[0032] <Course prediction AI> Therefore, the above-mentioned collision avoidance maneuvering support function uses course prediction AI (Artificial Intelligence) that accurately predicts the course of the other vessel. Such course prediction AI may be implemented using a machine learning model, such as the LSTM (Long Short Term Memory) model, which is a type of recurrent neural network.

[0033] As just one example, a machine learning model is built for each type of ship in the course prediction AI. Figure 4 shows an example of a machine learning model used in the course prediction AI. Figure 4 illustrates a machine learning model m that predicts the course of a ship of a certain type. As shown in Figure 4, the machine learning model m takes time-series data of location information obtained as historical data as input and outputs time-series data of future predicted positions. As just one example, the machine learning model m can take time-series data of location information from the most recent location information backward to the past 20 points as input. In response to such input, the machine learning model m can output time-series data of predicted positions from the present time to a specific time later, for example, 10 minutes later. Hereafter, the time-series data of the location information of ship 3 may be referred to as "track data".

[0034] The training data TR used to train such a machine learning model m can be generated from flight path data from the past few months. For example, in the example shown in Figure 4, the flight path data from the past few months is alternately divided into segments corresponding to the input size of the machine learning model m and segments containing the correct labels that follow those segments. This type of segmentation yields a dataset containing the training data TR and its correct labels from the flight path data from the past few months.

[0035] For example, in the learning phase, the training data can be used as explanatory variables for the machine learning model m, the labels as the target variable for the machine learning model m, and the machine learning model m can be trained according to any machine learning algorithm, such as deep learning. This results in a trained machine learning model M.

[0036] In the inference phase, time-series data of location information obtained from a predetermined number of past AIS or GPS data points, working backward from the latest AIS or GPS data, is input to the machine learning model M as track data 40. The machine learning model M, having received the track data 40 in this way, outputs time-series data of predicted locations from the present time when the latest AIS or GPS data was acquired to a specific time later, for example, 10 minutes later, as track data 60.

[0037] Thus, the machine learning model M is generated based on a large amount of actual track data. Therefore, the machine learning model M can predict the course of the vessel 3, taking into account factors such as the route it will take and the shape of port facilities. Furthermore, the machine learning model M is generated for each type of vessel. Therefore, it is possible to predict the course corresponding to the characteristics of each vessel type.

[0038] Figures 5 and 6 show examples of OZT (Oxygen-Zero) display. Figure 5 shows an example of the OZT display for pleasure boat 3N based on conventional course prediction, while Figure 6 shows an example of the OZT display for pleasure boat 3N based on course prediction by course prediction AI. In addition, in Figures 5 and 6, the track of pleasure boat 3N is shown as a thick solid line for comparison with the OZT.

[0039] For example, as shown in Figure 5, according to conventional course prediction, when the position, speed, and orientation of the pleasure boat 3N are obtained from the AIS 50 of the pleasure boat 3N, the OZT is detected on the straight line of the orientation of the pleasure boat 3N.

[0040] Thus, according to conventional course predictions, the OZT of pleasure boat 3N is set to a course toward the open ocean, while the actual course of pleasure boat 3N is not toward the open ocean, but rather a course that follows the shape of the harbor.

[0041] On the one hand, as shown in FIG. 6, according to the course prediction AI, time-series data of the position information of the pleasure boat 3N obtained from the AIS data at time point A and traced back through the past 20 points of AIS data is input into a machine learning model corresponding to the ship type "pleasure boat". Thereby, the machine learning model outputs time-series data of predicted positions from time point A to a specific time later, for example, 10 minutes later, as track data.

[0042] When OZT is detected according to such track data, the change in the course from time point A to time point B can be predicted. Therefore, similar to the actual course of the pleasure boat 3N, the OZT of the pleasure boat 3N can be set to a course along the shape of the harbor.

[0043] As described above, according to the course prediction AI, when the ship type is a pleasure boat, the track of the pleasure boat shows that the probability of coastal navigation is higher than that of ocean navigation. Further, according to the course prediction AI, when coastal navigation is performed, the track of the pleasure boat shows that the probability of navigating along the shape of the harbor is also high. These facts can be reflected in course prediction.

[0044] FIG. 7 is a diagram showing an example of risk assessment based on the course prediction AI. In FIG. 7, the tanker 3A is shown as an example of the own ship, and the tugboat 3B is shown as an example of the other ship. Further, in FIG. 7, the actual tracks of the own ship 3A and the other ship 3B are shown by thick solid lines, while the track of the other ship 3B predicted by the course prediction AI is shown by a dotted line. Further, in FIG. 7, when the current time is 13:00, the relative positions of the own ship 3A and the other ship 3B after t1, t2, and t3 are plotted. Further, in FIG. 7, the OZT is shown by a hatched danger determination circle. In FIG. 7, an example where the relationship of t1, t2, and t3 is "t1 = 10 minutes < t2 = 20 minutes < t3 = 30 minutes" is shown.

[0045] As shown by the dashed arrow in FIG. 7, according to the conventional course prediction, a risk assessment (misjudgment) is made that both the own ship 3A and the other ship 3B will go straight and collide while maintaining their current directions.

[0046] On the other hand, the course prediction AI can predict the course and relative distance of "2.5km" at 13:10 after t1, "1.8km" at 13:20 after t2, and "1.0km" at 13:30 after t3. Therefore, as shown by the dotted and thick solid lines in Figure 7, the OZT can be detected based on the actual courses of the own vessel 3A and the other vessel 3B. Consequently, the course prediction AI can improve the accuracy of collision risk assessment.

[0047] <Application to assisting collision avoidance maneuvers> As explained in the background technology section above, technologies such as route generation devices and navigation support methods have been proposed to evaluate risks such as collision hazards in ships. For example, a route generation device combines the potential method with OZT to generate a route that allows ships to navigate safely, taking into account the potential for expected risks. In addition, a navigation support method calculates the collision risk value of a planned route based on the traffic conditions of other ships along the entire planned route and weather and oceanographic forecast information along the planned route, and outputs the collision risk value as risk information.

[0048] <One aspect of the problem> However, conventional technologies, such as the aforementioned route generation devices and navigation support methods, only generate routes that are less likely to cause OZT (Optical Zero Threshold) at the planning stage before the ship departs. Therefore, when OZT occurs during operation, it is left to the personnel on site to implement collision avoidance maneuvers. Thus, the conventional technologies described above do not have a way to generate collision avoidance routes when OZT occurs during operation, making it difficult to support collision avoidance maneuvers.

[0049] Furthermore, even if the above-mentioned conventional technologies are used when an OZT occurs, these technologies all evaluate the risk for each divided section of the sea area in which the ship is navigating and generate a low-risk route, which increases the computational load related to collision risk assessment. For example, in the example shown in Figure 7, it is clear that the computational load will increase if the risk is evaluated for each divided section of the sea area shown in Figure 7. Moreover, if the sections are defined more finely to improve the accuracy of the risk assessment, the computational load will increase even further.

[0050] <One aspect of a problem-solving approach> Therefore, the collision avoidance maneuvering support function according to this embodiment sets the current position of the vessel and waypoints to pass through the destination when an OZT is detected, determines whether or not an OZT is detected for each route passing through the current position, waypoints, and destination, and outputs a route in which no OZT is detected.

[0051] Figure 8 shows an example of collision avoidance maneuvering support. Similar to Figure 7, Figure 8 shows tanker 3A as an example of the own vessel, and tugboat 3B as an example of another vessel. Furthermore, in Figure 8, the actual tracks of the own vessel 3A and the other vessel 3B are shown as thick solid lines, while the track of the other vessel 3B predicted by the course prediction AI is shown as a dotted line. In addition, Figure 8 shows the OZT (Obstruction Zone) using a hatched danger judgment circle.

[0052] In the example shown in Figure 8, the above-mentioned collision avoidance support function, when detecting the OZT of the other vessel 3B, sets the six points indicated by the X marks as waypoints, as an example. For each collision avoidance route that passes through these six waypoints, the above-mentioned collision avoidance support function determines whether or not an OZT is detected. The above-mentioned collision avoidance support function then outputs the collision avoidance route in which no OZT is detected, i.e., the route shown by the dashed line in Figure 7, to the client terminal 30. In this way, the above-mentioned collision avoidance support function can narrow down the calculations related to the assessment of collision risk to the six routes with six waypoints set.

[0053] Therefore, the above-mentioned collision avoidance maneuvering support function can reduce the computational complexity of risk assessment regarding the collision avoidance maneuvering route when detecting a potential collision area.

[0054] <Configuration of Server Device 10> Figure 9 is a block diagram illustrating an example of the functional configuration of the server device 10. Figure 9 schematically shows the blocks related to the collision avoidance support function of the server device 10. As shown in Figure 9, the server device 10 has a communication control unit 11, a storage unit 13, and a control unit 15. Note that Figure 9 only shows a selection of the functional units related to the collision avoidance support function, and the server device 10 may also be equipped with functional units other than those shown.

[0055] The communication control unit 11 is a functional unit that controls communication with other devices such as the client terminal 30. As just one example, the communication control unit 11 can be implemented using a network interface card such as a LAN card. In one aspect, the communication control unit 11 receives location information of the vessel 3 from the client terminal 30, or outputs a route for avoiding collisions to the client terminal 30.

[0056] The storage unit 13 is a functional unit that stores various types of data. As an example, the storage unit 13 can be implemented using internal, external, or auxiliary storage within the server device 10. For example, the storage unit 13 stores map data 13A and model data 13M. The map data 13A and model data 13M will be explained in conjunction with the descriptions of their reference, generation, or registration.

[0057] The control unit 15 is a functional unit that performs overall control of the server device 10. For example, the control unit 15 can be implemented by a hardware processor. Alternatively, the control unit 15 may be implemented by hardwired logic. As shown in Figure 9, the control unit 15 includes an acquisition unit 15A, a detection unit 15B, a setting unit 15C, a determination unit 15D, a calculation unit 15E, and an output control unit 15F.

[0058] The processes corresponding to the acquisition unit 15A, detection unit 15B, setting unit 15C, determination unit 15D, calculation unit 15E, and output control unit 15F may be executed in parallel for each client terminal 30, i.e., each ship 3.

[0059] The acquisition unit 15A is a processing unit that acquires the position information of the own ship and other ships. As an example, the acquisition unit 15A can operate at a sampling period of, for example, every second, to acquire the position information of the own ship from the client terminal 30. For example, the acquisition unit 15A can acquire the position information of the own ship from the client terminal 30 and also acquire AIS data that the AIS 50 of the own ship, which is connected to the client terminal 30, receives from the AIS 50 of other ships. Such AIS data may include not only the position information of other ships but also the type of ship of the other ships. Here, we have given an example in which the own ship is equipped with an AIS 50, but it is also possible to acquire the position information of other ships by extracting the position information of other ships that are located within a predetermined range from the position information of the own ship from the position information of other ships acquired from other client terminals 30.

[0060] The detection unit 15B is a processing unit that detects the OZT of other ships. As an example, the detection unit 15B predicts the course of other ships using a course prediction AI. When such a course prediction AI is executed, the model data 13M stored in the memory unit 13 is referenced. For example, the model data 13M includes machine learning models corresponding to each ship type, such as hyperparameters related to the layer structure of neurons and synapses in the input layer, hidden layer, and output layer that form an LSTM, and parameters related to the objective function such as weights and biases of each layer.

[0061] More specifically, the detection unit 15B selects a machine learning model corresponding to the ship type of the other ship acquired by the acquisition unit 15A from among the machine learning models corresponding to each ship type. The detection unit 15B then inputs a predetermined number of time-series data of past location information into the machine learning model M, working backward from the location information of the other ship acquired by the acquisition unit 15A. As a result, the machine learning model outputs time-series data of predicted positions from the present time when the location information of the other ship was acquired by the acquisition unit 15A up to a specific time later as predicted track data. Then, the detection unit 15B calculates the OZT of the other ship based on the planned track data corresponding to the automatically navigated route set for the own ship and the predicted track data of the other ship predicted by the course prediction AI. Any algorithm may be applied to calculate the OZT.

[0062] The setting unit 15C is a processing unit for setting waypoints. As an example, when the detection unit 15B detects an OZT from another vessel, the setting unit 15C sets one or more waypoints, i.e., one or more waypoints. Such waypoint settings may be implemented by system settings or by user settings. For example, if the route the vessel is navigating is a regular route, the system administrator can define waypoints for each spot in the coastal area where OZT is likely to occur. In addition, by sending a notification to the client terminal 30 prompting the setting of waypoints when an OZT occurs, the system can also accept the specification of waypoints from users receiving the above-mentioned avoidance maneuvering support function via the client terminal 30.

[0063] The determination unit 15D is a processing unit that determines whether or not OZT is detected for each avoidance maneuver route that passes through the current position, waypoints, and destination. As an example, the determination unit 15D interpolates the current position of the vessel acquired by the acquisition unit 15A and the interval of the waypoint set by the setting unit 15C, and sets a spline curve that interpolates the interval between the waypoint and the destination set for the vessel. This allows the avoidance maneuver route that passes through the current position, waypoints, and destination to be set. Then, the determination unit 15D determines whether or not the OZT of the other vessel is detected based on the avoidance maneuver route of the vessel and the predicted track data of the other vessel. Here as well, any algorithm may be applied to detect OZT.

[0064] The calculation unit 15E is a processing unit that calculates an evaluation value for each avoidance maneuver route. As an example, the calculation unit 15E extracts avoidance maneuver routes in which no OZT is detected. Then, for each avoidance maneuver route in which no OZT is detected, the calculation unit 15E calculates an evaluation value, such as cost, based on at least one of the ship dynamic characteristics of the route, such as curvature and total operating distance.

[0065] Here, as an example of an evaluation value, we will consider the case where cost is used. For example, the calculation unit 15E can calculate the cost of each route based on a cost function that includes the ship's dynamic characteristics and total operating distance as explanatory variables. As an example, as the curvature of the route increases, the inertia of the ship during maneuvering increases, so braking due to sudden braking or sudden steering also increases, and the ship's hull becomes more unstable. For this reason, the above cost function can be set to calculate a higher cost as the curvature of the route increases, and a penalty term that calculates a lower cost as the curvature of the route decreases. Also, as the total operating distance of the route increases, fuel consumption increases, so costs and environmental burden increase. For this reason, the above cost function can be set to calculate a higher cost as the total operating distance of the route increases, and a penalty term that calculates a lower cost as the total operating distance of the route decreases. Here, cost was used as an example of an evaluation value, but it is also possible to calculate a score where the score increases as the evaluation improves.

[0066] The output control unit 15F is a processing unit that performs various output controls. As an example, the output control unit 15F controls the display on the display unit (not shown) of the client terminal 30. Here, display output is given as an example of an output controlled by the output control unit 15F, but naturally, other outputs such as print output and audio output may also be controlled.

[0067] More specifically, the output control unit 15F outputs a collision avoidance maneuver route based on the evaluation value calculated for each route by the calculation unit 15E. For example, the output control unit 15F extracts the route with the best evaluation value from among the evaluation values ​​calculated for each route by the calculation unit 15E. Then, the output control unit 15F extracts a map of a sea area within a predetermined range from the map data 13A stored in the storage unit 13 based on the ship's position information, and transmits display data with the collision avoidance maneuver route plotted on the map of that sea area to the client terminal 30. At this time, the map of the sea area where the ship is located can also include displays of the current positions of the ship and other ships, predicted track data of other ships predicted by the course prediction AI, and planned track data corresponding to the automatically navigated route set for the ship.

[0068] Subsequently, if the output control unit 15F receives an approval operation for a collision avoidance maneuver route from the client terminal 30, it changes the route set by automatic navigation to a collision avoidance maneuver route. Note that, although this example shows the route being changed to a collision avoidance maneuver route only after receiving an approval operation, the route set by automatic navigation may be automatically changed to a collision avoidance maneuver route without requiring an approval operation.

[0069] <Processing flow> Figure 10 is a flowchart showing the procedure for collision avoidance maneuvering support processing. This process is merely an example and can be executed repeatedly at a sampling period, for example, every second, when acquiring the ship's position information from the client terminal 30.

[0070] As shown in Figure 10, the acquisition unit 15A acquires the ship's position information from the client terminal 30, and also acquires AIS data received by the ship's AIS 50 connected to the client terminal 30 from the AIS 50 of other ships (step S101).

[0071] Next, the detection unit 15B uses a course prediction AI to predict the course of the other vessel (step S102). Then, the detection unit 15B calculates the OZT of the other vessel based on the planned track data corresponding to the automatically navigated route set for its own vessel and the predicted track data of the other vessel predicted by the course prediction AI in step S102 (step S103).

[0072] If another ship's OZT is detected at this time (step S104 Yes), the setting unit 15C sets K (natural number) waypoints (step S105).

[0073] Subsequently, the determination unit 15D executes loop processing 1, which repeats the process of step S106 below a number of times corresponding to the K waypoints. Note that the process of step S106 does not necessarily have to be executed repeatedly and can be executed in parallel.

[0074] In other words, the determination unit 15D determines whether or not the OZT of the other vessel is detected based on the current position, the waypoint k and the route of the avoidance maneuver that passes through the destination, and the predicted track data of the other vessel (step S106).

[0075] As this loop process 1 is repeated, it is determined whether or not the OZT of other ships is detected for each avoidance maneuver route corresponding to the K waypoints.

[0076] Subsequently, the calculation unit 15E extracts the avoidance maneuver routes from among the K avoidance maneuvers for which the OZT of other vessels was not detected in step S106 (step S107).

[0077] The calculation unit 15E then executes a loop process 2 that repeats the process in step S108 below a number of times corresponding to the number M of avoidance maneuvers where the OZT of other vessels was not detected. Note that the process in step S108 does not necessarily have to be executed repeatedly and can be executed in parallel.

[0078] In other words, the calculation unit 15E calculates an evaluation value C based on at least one of the ship's dynamic characteristics of the route m, such as curvature and total sailing distance (step S108).

[0079] As this loop process 2 is repeated, an evaluation value C is calculated for each of the M avoidance maneuvers.

[0080] Subsequently, the output control unit 15F selects the best evaluation value C from among the evaluation values ​​C calculated for each of the M avoidance maneuver paths. max The path R is extracted (step S109). Then, the output control unit 15F sends display data to the client terminal 30 in which the path R of the avoidance maneuver extracted in step S109 is plotted on a map of the sea area within a predetermined range from the ship's position information (step S110), and the process ends.

[0081] <One aspect of the effect> As described above, the server device 10 according to this embodiment sets the current position of the vessel and waypoints to pass through the destination when OZT is detected, and determines whether or not OZT is detected for each route passing through the current position, waypoints, and destination, and outputs the route for which no OZT is detected.Therefore, the server device 10 according to this embodiment can reduce the amount of computation required for risk assessment regarding the route for avoidance maneuvering when detecting a collision-prone area. [Examples]

[0082] Now, while embodiments of the disclosed apparatus have been described, the present invention may be implemented in various other forms besides those described above. Therefore, other embodiments included in the present invention will be described below.

[0083] <Multiple OZT detections> In the above Example 1, we showed an example where one OZT of another vessel was detected. However, if multiple OZTs are detected, multiple waypoints can be set for a single avoidance maneuver route. In this case, as an example, the number of waypoints can be set to be less than or equal to the number of detected OZTs of other vessels for a single route. Then, for each route passing through multiple waypoints, it can be determined whether or not a collision area with another vessel is detected. Furthermore, when calculating the evaluation value of the avoidance maneuver route, a better evaluation can be calculated as the number of turns, such as the number of inflection points, decreases, and a worse evaluation can be calculated as the number of turns, such as the number of inflection points, increases.

[0084] <Distributed and Integrated> Furthermore, the components of each illustrated device do not necessarily have to be physically configured as shown. In other words, the specific forms of distribution and integration of each device are not limited to those shown, and all or part of them can be functionally or physically distributed and integrated in any unit according to various loads and usage conditions. For example, the acquisition unit 15A, detection unit 15B, setting unit 15C, determination unit 15D, calculation unit 15E, or output control unit 15F may be connected to the server device 10 as an external device via a network. Alternatively, the acquisition unit 15A, detection unit 15B, setting unit 15C, determination unit 15D, calculation unit 15E, or output control unit 15F may each be possessed by other devices, which may be connected via a network and cooperate to realize the functions of the server device 10.

[0085] <Hardware Configuration> Furthermore, the various processes described in the above embodiments can be realized by executing a pre-prepared program on a computer such as a personal computer or workstation. Therefore, below, using Figure 11, an example of a computer that executes a collision avoidance support program having the same functions as in Embodiments 1 and 2 will be described.

[0086] Figure 11 shows an example of a hardware configuration. As shown in Figure 11, the computer 100 has an operating unit 110a, a speaker 110b, a camera 110c, a display 120, and a communication unit 130. Furthermore, the computer 100 has a CPU 150, a ROM 160, an HDD 170, and RAM 180. These parts 110 to 180 are connected via a bus 140.

[0087] As shown in Figure 11, HDD170 stores a collision avoidance support program 170a that performs the same functions as the acquisition unit 15A, detection unit 15B, setting unit 15C, determination unit 15D, calculation unit 15E, and output control unit 15F shown in Embodiment 1 above. This collision avoidance support program 170a may be integrated or separated, similar to the components of the acquisition unit 15A, detection unit 15B, setting unit 15C, determination unit 15D, calculation unit 15E, and output control unit 15F shown in Figure 9. In other words, HDD170 does not necessarily have to store all the data shown in Embodiment 1 above; it is sufficient that the data used for processing is stored in HDD170.

[0088] Under these conditions, the CPU 150 reads the collision avoidance support program 170a from the HDD 170 and then loads it into the RAM 180. As a result, the collision avoidance support program 170a functions as a collision avoidance support process 180a, as shown in Figure 11. This collision avoidance support process 180a loads various data read from the HDD 170 into the memory area of ​​the RAM 180 allocated to the collision avoidance support process 180a, and then executes various processes using the loaded data. For example, one example of a process executed by the collision avoidance support process 180a may include the process shown in Figure 10. Note that the CPU 150 does not necessarily need to operate all of the processing units shown in the above embodiment 1; it is sufficient if the processing units corresponding to the processes to be executed are virtually implemented.

[0089] Furthermore, the collision avoidance support program 170a described above does not necessarily have to be stored in the HDD 170 or ROM 160 from the beginning. For example, the collision avoidance support program 170a could be stored on a "portable physical medium" such as a flexible disk, floppy disk, CD-ROM, DVD disk, magneto-optical disk, or IC card inserted into the computer 100. The computer 100 could then retrieve and execute the collision avoidance support program 170a from these portable physical media. Alternatively, the collision avoidance support program 170a could be stored on another computer or server device connected to the computer 100 via a public network, the internet, LAN, WAN, etc. The collision avoidance support program 170a stored in this way could then be downloaded to the computer 100 and executed.

[0090] With regard to embodiments including the above examples, the following additional information is disclosed.

[0091] (Note 1) Detect the area where a collision between your vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. A collision avoidance maneuvering support program that uses a computer to perform the necessary actions.

[0092] (Note 2) Multiple waypoints may be set, The process for making the determination includes a process for determining whether or not a range where collision with other vessels is possible is detected for each of the multiple waypoints along the route. The collision avoidance maneuvering support program described in Appendix 1, characterized by the above.

[0093] (Note 3) For each route in which no collision-prone area is detected, the computer is further instructed to perform a process to calculate an evaluation value based on the ship dynamic characteristics along that route. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support program described in Appendix 1, characterized by the above.

[0094] (Note 4) The calculation process includes a process that calculates a good evaluation value as the curvature of the path decreases and a bad evaluation value as the curvature of the path increases. The collision avoidance maneuvering support program described in Appendix 3, characterized by the above.

[0095] (Note 5) The computer is further instructed to perform a process to calculate an evaluation value based on the total distance traveled along each route in which no collision-prone area is detected. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support program described in Appendix 1, characterized by the above.

[0096] (Note 6) The calculation process described above includes a process that calculates a better evaluation value as the total operating distance of the route decreases, and a worse evaluation value as the total operating distance of the route increases. The collision avoidance maneuvering support program described in Appendix 5, characterized by the above.

[0097] (Note 7) The detection process includes a process to detect the area where a collision is possible based on time-series data of the predicted position of the other vessel output by the machine learning model, which is obtained by inputting time-series data of the position information of the other vessel into the machine learning model, and time-series data of the position information corresponding to the automatically operated route set for the own vessel. The collision avoidance maneuvering support program described in Appendix 1, characterized by the above.

[0098] (Note 8) The detection process includes inputting time-series data of the location information of the other vessel into the machine learning model corresponding to the type of the other vessel, among the multiple machine learning models corresponding to multiple ship types. The collision avoidance maneuvering support program described in Appendix 7, characterized by the above.

[0099] (Note 9) Detect the area where a collision between your vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. A method of assisting ship maneuvers by having a computer perform the necessary processing.

[0100] (Note 10) Multiple waypoints may be set, The process for making the determination includes a process for determining whether or not a range where collision with other vessels is possible is detected for each of the multiple waypoints passing through each route. The collision avoidance maneuvering support method according to Appendix 9, characterized by the features described herein.

[0101] (Note 11) For each route in which no collision-prone area is detected, the computer further performs a process to calculate an evaluation value based on the ship dynamic characteristics along the route. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support method according to Appendix 9, characterized by the features described herein.

[0102] (Note 12) The calculation process includes a process that calculates a good evaluation value as the curvature of the path decreases and a bad evaluation value as the curvature of the path increases. The collision avoidance maneuvering support method described in Appendix 11, characterized by the features described herein.

[0103] (Note 13) The computer further performs a process to calculate an evaluation value based on the total distance traveled along each route in which no collision-prone area is detected. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support method according to Appendix 9, characterized by the features described herein.

[0104] (Note 14) The calculation process described above includes a process that calculates a better evaluation value as the total operating distance of the route decreases, and a worse evaluation value as the total operating distance of the route increases. The collision avoidance maneuvering support method described in Appendix 13, characterized by the features described herein.

[0105] (Note 15) The detection process includes a process to detect the area where a collision is possible based on time-series data of the predicted position of the other vessel output by the machine learning model, which is obtained by inputting time-series data of the position information of the other vessel into the machine learning model, and time-series data of the position information corresponding to the automatically operated route set for the own vessel. The collision avoidance maneuvering support method according to Appendix 9, characterized by the features described herein.

[0106] (Note 16) The detection process includes inputting time-series data of the location information of the other vessel into the machine learning model corresponding to the vessel type of the other vessel, among the multiple machine learning models corresponding to multiple vessel types. The collision avoidance maneuvering support method described in Appendix 15, characterized by the features described herein.

[0107] (Note 17) Detect the area where a collision between your vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. A collision avoidance maneuvering support device including a control unit that performs processing.

[0108] (Note 18) Multiple waypoints may be set, The process for making the determination includes a process for determining whether or not a range where collision with other vessels is possible is detected for each of the multiple waypoints passing through each route. The collision avoidance maneuvering support device according to Appendix 17, characterized by the features described herein.

[0109] (Note 19) The control unit further performs a process to calculate an evaluation value based on the ship dynamic characteristics along each route in which no collision-prone area is detected. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support device according to Appendix 17, characterized by the features described herein.

[0110] (Note 20) The calculation process described above includes a process that calculates a good evaluation value as the curvature of the path decreases and a bad evaluation value as the curvature of the path increases. The collision avoidance maneuvering support device according to Appendix 19, characterized in that it is a collision avoidance maneuvering support device. [Explanation of Symbols]

[0111] 1. Collision Avoidance Maneuvering Support System 3 ships 10 Server devices 11. Communication Control Unit 13 Storage section 13A Map data 13M Model Data 15 Control Unit 15A Acquisition Department 15B Detection Unit 15C Setting section 15D Judgment section 15E Calculation Unit 15F Output Control Unit 30 client terminals 50 AIS

Claims

1. It detects the area where a collision between one's own vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. Let the computer perform the process, The detection process includes inputting time-series data of the other vessel's position information into a machine learning model to detect the area where a collision is possible based on time-series data of the predicted position of the other vessel output by the machine learning model and time-series data of the position information corresponding to the automatically navigated route set for the own vessel. A collision avoidance maneuvering support program characterized by the following features.

2. Multiple intermediate points are set, The process for making the determination includes a process for determining whether or not a range where collision with other vessels is possible is detected for each of the multiple waypoints along the route. The collision avoidance maneuvering support program according to feature 1.

3. The computer is further instructed to perform a process to calculate an evaluation value based on the ship's dynamic characteristics along each route where no collision-prone area is detected. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support program according to feature 1 or 2.

4. The computer is further instructed to perform a process to calculate an evaluation value based on the total distance traveled along each route for each route where no collision-prone area is detected. The output process includes a process that outputs the path with the best evaluation value. The collision avoidance maneuvering support program according to feature 1 or 2.

5. It detects the area where a collision between one's own vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. The computer performs the process, The detection process includes inputting time-series data of the other vessel's position information into a machine learning model to detect the area where a collision is possible based on time-series data of the predicted position of the other vessel output by the machine learning model and time-series data of the position information corresponding to the automatically navigated route set for the own vessel. A method for assisting vessels in avoiding collisions, characterized by the features described above.

6. It detects the area where a collision between one's own vessel and other vessels is possible, When detecting the area where a collision with another vessel is possible, a waypoint is set for the vessel to pass through between the position of the vessel at the time of detection and the destination of the vessel. Determine whether or not there is an area where collision with other vessels is possible along the route passing through the position of the vessel, the waypoint, and the destination. Outputs a path in which no collision-prone area is detected. Includes a control unit that performs processing, The detection process includes inputting time-series data of the other vessel's position information into a machine learning model to detect the area where a collision is possible based on time-series data of the predicted position of the other vessel output by the machine learning model and time-series data of the position information corresponding to the automatically navigated route set for the own vessel. A collision avoidance maneuvering support device characterized by the above.

Images