Berthing path generation method and apparatus thereof

By determining transit nodes based on a reference distance and using distinct cost functions for paths near and far from the berthing position, the method addresses collision risks in autonomous ship berthing, ensuring safe navigation.

KR103046640B1Active Publication Date: 2026-11-11SEADRONIX CORP
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
KR1020220188466
Authority / Receiving Office
KR · KR
Patent Type
Patents
Current Assignee / Owner
Priority Date
2022-08-31
Filing Date
2022-12-29
Publication Date
2026-11-11
Estimated Expiration
2042-12-29

AI Technical Summary

Technical Problem

Existing methods for generating berthing paths for ships do not adequately consider the marine environment and vessel characteristics, leading to increased collision risks due to sudden course changes near berthing facilities, especially in autonomous vessel operations.

Method used

A method and apparatus that determine transit nodes based on a reference distance from the berthing position, using different cost functions for paths within and outside this distance, considering vessel characteristics and environmental factors to generate a safe berthing path.

Benefits of technology

This approach minimizes collisions with berthing facilities by generating paths that account for vessel dynamics and environmental obstacles, enhancing the safety of autonomous ship navigation.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 112022141725389-PAT00014_ABST
    Figure 112022141725389-PAT00014_ABST
Patent Text Reader

Abstract

The present invention relates to a method for generating a berthing path for a vessel, comprising: acquiring an obstacle map including a plurality of nodes corresponding to positions at sea; selecting a current node corresponding to the current position of the vessel on the obstacle map and a berthing node corresponding to the berthing position; determining the current bow direction of the vessel at the current node and the berthing bow direction at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of a berthing facility; and determining a plurality of waypoint nodes from the current node to the berthing node on the obstacle map and an expected bow direction to be assigned to the waypoint nodes using the reference distance and a predetermined expected berthing path cost function, wherein the waypoint node corresponds to at least one of the unit nodes. The present invention relates to a method for generating a berthing path, comprising the step of generating the berthing path using the determined plurality of waypoint nodes; wherein the predetermined expected berthing path cost function includes, for a vessel located at a position farther than the reference distance from the berthing position, a first expected berthing path cost function applied to a first expected berthing path from the current node to the reference distance waypoint node, considering the current bow direction, and a second expected berthing path cost function applied to a second expected berthing path from the reference distance waypoint node to the berthing node, wherein the first expected berthing path cost function is different from the second expected berthing path cost function.
Need to check novelty before this filing date? Find Prior Art

Description

Technology Field

[0001] The present invention relates to a method and apparatus for generating a berthing path for a ship, and more specifically, to a method and apparatus for generating a berthing path that utilizes different transit node determination methods depending on whether the ship is located within a reference distance from a berthing position. Background Technology

[0002] Many accidents occur during ship operations, and the primary cause is known to be human negligence. It is expected that the commercialization of autonomous or unmanned vessels, which operate independently without human intervention, will significantly reduce maritime accidents. To this end, global companies are currently conducting autonomous vessel development projects.

[0003] To achieve the completion of autonomous vessels, it is necessary to be able to generate a route by considering the characteristics of the marine environment, the characteristics of the vessel, and the characteristics of the port. In particular, when a vessel berths, if a route is generated simply by following the shortest distance to the berthing facility, the course change section exists for a short length immediately before the berthing facility. Consequently, even a slight deviation from the route increases the risk of collision with the berthing facility, and there was a problem in that berthing along the generated route was virtually impossible when considering the characteristics of the marine environment and the vessel. The problem to be solved

[0004] One objective of the present invention is to provide a method for generating a berthing path and an apparatus thereof that utilize different transit node determination methods depending on whether a vessel is located within a reference distance from a berthing position.

[0005] Another objective of the present invention is to provide an autonomous navigation method and apparatus that perform path following so that a vessel can navigate along a generated path.

[0006] The problems that the present invention aims to solve are not limited to those described above, and problems not mentioned will be clearly understood by those skilled in the art from this specification and the attached drawings. means of solving the problem

[0007] According to one embodiment of the present invention, a method for generating a berthing path for a vessel comprises: acquiring an obstacle map including a plurality of nodes corresponding to positions at sea; selecting a current node corresponding to the current position of the vessel on the obstacle map and a berthing node corresponding to the berthing position; determining the current bow direction of the vessel at the current node and the berthing bow direction at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of a berthing facility; and determining a plurality of waypoint nodes from the current node to the berthing node on the obstacle map and an expected bow direction to be assigned to the waypoint nodes using the reference distance and a predetermined expected berthing path cost function, wherein the waypoint node corresponds to at least one of the unit nodes. A method for generating a berthing path may be provided, comprising the step of generating the berthing path using the plurality of determined transit nodes; wherein the predetermined estimated berthing path cost function includes, for a vessel located at a position farther than the reference distance from the berthing position, a first estimated berthing path cost function applied to a first estimated berthing path from the current node to the reference distance transit node considering the current bow direction, and a second estimated berthing path cost function applied to a second estimated berthing path from the reference distance transit node to the berthing node, wherein the first estimated berthing path cost function is different from the second estimated berthing path cost function.

[0008] According to another embodiment of the present invention, a device for generating a berthing path for a vessel comprises: a memory storing information about the vessel, information about a port, and a method for determining a transit node; and at least one processor; comprising: acquiring an obstacle map including a plurality of nodes corresponding to a position at sea; selecting a current node corresponding to the current position of the vessel and a berthing node corresponding to the berthing position on the obstacle map; determining the current bow direction of the vessel at the current node and the berthing bow direction at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of the berthing facility; determining a plurality of waypoint nodes from the current node to the berthing node and an expected bow direction to be assigned to the waypoint nodes on the obstacle map using the reference distance and a predetermined expected berthing path cost function - the waypoint node corresponds to at least one of the unit nodes -; generating the berthing path using the determined plurality of waypoint nodes, wherein the predetermined expected berthing path cost function is applied to a first expected berthing path from the current node to the reference distance waypoint node by considering the current bow direction for the vessel located at a position farther from the berthing position than the reference distance. A berthing path generating device may be provided, comprising a first expected berthing path cost function and a second expected berthing path cost function applied to a second expected berthing path from a reference distance passing node to a berthing node, wherein the first expected berthing path cost function is different from the second expected berthing path cost function.

[0009] The means for solving the problem of the present invention are not limited to the means for solving the problem described above, and unmentioned means for solving the problem will be clearly understood by those skilled in the art to which the present invention belongs from this specification and the attached drawings. Effects of the invention

[0010] According to the present invention, by using a method and apparatus for generating a berthing path that utilizes different transit node determination methods depending on whether the vessel is located within a reference distance from the berthing location, a path that minimizes collision with the berthing facility within the reference distance can be generated, thereby reducing the risk of collision between the vessel and the berthing facility during berthing.

[0011] According to the present invention, ship control can be performed using an autonomous navigation method and device that perform path following so that the ship can navigate along a generated path.

[0012] The effects of the present invention are not limited to the effects described above, and unmentioned effects will be clearly understood by those skilled in the art from this specification and the accompanying drawings. Brief explanation of the drawing

[0013] FIG. 1 is a drawing of an berthing guide system according to one embodiment. FIG. 2 is a block diagram showing the configuration of a path generation device according to one embodiment. FIG. 3 is a block diagram showing the configuration of a sensor module according to one embodiment. FIG. 4 is a block diagram showing the configuration of an external server according to one embodiment. FIG. 5 is a block diagram showing the configuration of a ship navigation device according to one embodiment. FIG. 6 is a diagram showing an obstacle map according to one embodiment. FIG. 7 is a diagram showing an obstacle map with assigned scores according to one embodiment. FIG. 8 is a drawing of an obstacle map including nodes corresponding to a ship according to one embodiment. FIG. 9 is a flowchart of a path generation method according to one embodiment. FIG. 10 is a diagram showing an obstacle map according to one embodiment. Figure 11 is a diagram showing a path generated by performing a conventional approach path generation method on the obstacle map of Figure 10. FIG. 12 is a drawing for explaining a reference distance according to one embodiment. FIGS. 13, 14, and 15 are drawings showing a landing path and a transit node on an obstacle map according to one embodiment. Figure 16 is an exemplary algorithm for obtaining transit nodes and paths based on the 3D A* algorithm. FIG. 17 is a flowchart of a path generation method according to one embodiment. FIG. 18 is a diagram illustrating a method for determining a reference distance via node according to one embodiment. FIG. 19 is a diagram showing each node on an obstacle map and the generated landing path according to one embodiment. FIG. 20 is a flowchart of a path following control method according to one embodiment. FIGS. 21 and FIGS. 22 are drawings for illustrating path following control according to one embodiment. FIG. 23 is a flowchart of a ship docking method using path-following control according to one embodiment. Specific details for implementing the invention

[0014] The embodiments described in this specification are intended to clearly explain the concept of the invention to those skilled in the art to which the invention pertains; therefore, the invention is not limited by the embodiments described in this specification, and the scope of the invention should be interpreted to include modifications or variations that do not depart from the concept of the invention.

[0015] The terms used in this specification have been selected to be as widely used as possible, taking into account their functions in the present invention; however, they may vary depending on the intent, custom, or emergence of new technologies of those skilled in the art to which the present invention pertains. However, if a specific term is defined and used with an arbitrary meaning, the meaning of that term will be described separately. Accordingly, the terms used in this specification should be interpreted based on their actual meaning and the content throughout this specification, rather than merely their names.

[0016] The drawings attached to this specification are intended to facilitate the explanation of the present invention. The shapes depicted in the drawings may be exaggerated as necessary to aid in understanding the present invention, and therefore the present invention is not limited by the drawings.

[0017] In this specification, if it is determined that a specific description of known configurations or functions related to the present invention may obscure the essence of the present invention, such detailed description may be omitted as necessary.

[0018] According to one embodiment of the present invention, a method for generating a berthing path for a vessel comprises: acquiring an obstacle map including a plurality of nodes corresponding to positions at sea; selecting a current node corresponding to the current position of the vessel on the obstacle map and a berthing node corresponding to the berthing position; determining the current bow direction of the vessel at the current node and the berthing bow direction at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of a berthing facility; and determining a plurality of waypoint nodes from the current node to the berthing node on the obstacle map and an expected bow direction to be assigned to the waypoint nodes using the reference distance and a predetermined expected berthing path cost function, wherein the waypoint node corresponds to at least one of the unit nodes. A method for generating a berthing path may be provided, comprising the step of generating the berthing path using the plurality of determined transit nodes; wherein the predetermined estimated berthing path cost function includes, for a vessel located at a position farther than the reference distance from the berthing position, a first estimated berthing path cost function applied to a first estimated berthing path from the current node to the reference distance transit node considering the current bow direction, and a second estimated berthing path cost function applied to a second estimated berthing path from the reference distance transit node to the berthing node, wherein the first estimated berthing path cost function is different from the second estimated berthing path cost function.

[0019] The above reference distance passing node may be one of the reference distance nodes corresponding to a location located at a distance of the above reference distance from the above docking node.

[0020] The above reference distance passing node may be a node among the above reference distance nodes located at a position that is the reference distance away from the above berthing node in the direction of the berthing bow or in the opposite direction of the above berthing bow.

[0021] The above second expected berthing path cost function may include a term that considers the berthing bow direction.

[0022] The term considering the berthing direction above may be a term considering the difference between the expected bow direction to be assigned to a transit node on the second expected berthing path and the berthing bow direction above.

[0023] The obstacle map above assigns a score based on the operational safety of the vessel to each of the plurality of nodes, and the expected berthing path cost function may include a term that considers the score.

[0024] The step of determining the plurality of transit nodes includes: determining the current speed of the vessel; and calculating the maximum turning angle of the vessel based on the current speed; and the expected berthing path cost function may include a term that considers the maximum turning angle.

[0025] According to another embodiment of the present invention, a device for generating a berthing path for a vessel comprises: a memory storing information about the vessel, information about a port, and a method for determining a transit node; and at least one processor; comprising: acquiring an obstacle map including a plurality of nodes corresponding to a position at sea; selecting a current node corresponding to the current position of the vessel and a berthing node corresponding to the berthing position on the obstacle map; determining the current bow direction of the vessel at the current node and the berthing bow direction at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of the berthing facility; determining a plurality of waypoint nodes from the current node to the berthing node and an expected bow direction to be assigned to the waypoint nodes on the obstacle map using the reference distance and a predetermined expected berthing path cost function - the waypoint node corresponds to at least one of the unit nodes -; generating the berthing path using the determined plurality of waypoint nodes, wherein the predetermined expected berthing path cost function is applied to a first expected berthing path from the current node to the reference distance waypoint node by considering the current bow direction for the vessel located at a position farther from the berthing position than the reference distance. A berthing path generating device may be provided, comprising a first expected berthing path cost function and a second expected berthing path cost function applied to a second expected berthing path from a reference distance passing node to a berthing node, wherein the first expected berthing path cost function is different from the second expected berthing path cost function.

[0026] The processor determines the plurality of transit nodes, determines the current speed of the vessel, and calculates the maximum turning angle of the vessel based on the current speed, and the expected berthing path cost function may include a term that considers the maximum turning angle.

[0027] Hereinafter, a method for generating a docking path and an apparatus according to one embodiment will be described.

[0028] 1. Anchor guide system (10)

[0029] FIG. 1 is a drawing of an eye-to-eye guide system (10) according to one embodiment.

[0030] A docking guide system (10) according to one embodiment can generate a docking path from the current position of a vessel to a docking position. To generate the docking path, an obstacle map may be obtained and a reference distance may be determined. Subsequently, a transit node may be determined from a current node on the obstacle map corresponding to the current position to a docking node on the obstacle map corresponding to the docking position, and a docking path can be generated using the current node, the docking node, and the transit node. To generate a safe docking path, when the vessel comes within a reference distance from the docking position, a path can be generated that considers the bow direction of the vessel when the vessel docks at the docking position. Meanwhile, a path may also be generated considering operational safety at sea. Additionally, the vessel may be controlled to operate by following the generated path.

[0031] More specifically, referring to FIG. 1, the docking guide system (10) may include a path generating device (100), a sensor module (200), an external server (300), and a ship navigation device (400).

[0032] Below, the path generation device (100), sensor module (200), external server (300), and ship navigation device (400) will be examined in detail. The docking guide system (10) does not have to include all of the above-described configurations, but may include some selected configurations among the path generation device (100), sensor module (200), external server (300), and ship navigation device (400). In this case, the number of one configuration among the path generation device (100), sensor module (200), external server (300), and ship navigation device (400) included in the path guide system (10) may be one or more. For example, the path guide system (10) may include one sensor module (200) or two or more sensor modules (200).

[0033] A path generation device (100) according to one embodiment can generate a path from the current position of a vessel to a docking position using data stored internally or data acquired from the outside.

[0034] More specifically, the path generation device (100) can determine a way node from the current node of the vessel to the docking node on the acquired obstacle map by using a way node determination method. The path generation device (100) can generate a docking path using the determined way nodes. The obstacle map is a map that reflects the location and object information of obstacles. Specific details regarding the obstacle map and the docking path generation method will be described later.

[0035] A sensor module (200) (Sensor device) according to one embodiment can detect the state of the vessel and surrounding environmental factors. In addition, the path generation device (100) can detect various factors necessary for generating a docking path and transmit them to the path generation device (100).

[0036] An external server (300) according to one embodiment stores at least one of information about a ship, information about a port, real-time ship status information, real-time port status information, and real-time environmental data, and can transmit data required by a path generation device (100). Specifically, if there is data required for generating a berthing path that is not stored in the path generation device (100), or if real-time data is required for generating a berthing path even if data is stored, the external server (300) can transmit data required for generating a berthing path to the path generation device (100).

[0037] A ship navigation device (400) according to one embodiment can generate a control signal to enable a ship to navigate along a berthing path generated by a path generation device (100). The generated control signal can be transmitted to a ship's propulsion device to control the ship's navigation. The control signal may include a ship speed control signal and / or a bow direction control signal.

[0038] In the following description, the path generation device (100), sensor module (200), and ship navigation device (400) are located on the ship, and the external server (300) is located in the control center.

[0039] However, it is not limited to this, and the path generation device (100) may also be located in a control center. In this case, the path generation device (100) can receive data remotely from the sensor module (200) and can remotely transmit data related to the generated path to the ship navigation device (400). Meanwhile, both the path generation device (100) and the ship navigation device (400) may be located in a control center, in which case the ship navigation device (400) can remotely transmit the generated control signal to the ship.

[0040] FIG. 2 is a block diagram showing the configuration of a path generation device (100) according to one embodiment.

[0041] Referring to FIG. 2, the path generation device (100) may include a memory (110), a processor (120), and a communication device (130).

[0042] The memory (110) can store various processing programs, parameters for performing processing of the programs, or data resulting from such processing. For example, the memory (110) can store instructions for the operation of the processor (120) to be described later, a method for determining a transit node, a transit node determination algorithm, etc.

[0043] Meanwhile, the memory (110) can store more information about the ship and information about the port.

[0044] Information about the vessel may include the length, width, volume, weight, steering performance, maximum steering angle, etc.

[0045] Information regarding the port may include a port map, port structure, location of port facilities, length of the port, location of berthing facilities, length of berthing facilities, location of obstacles, attributes of obstacles, obstacle map, berthing location of a vessel, and the bow direction of the vessel when berthing at the berthing location.

[0046] Information about the vessel and / or information about the port stored in memory (110) may be data received from an external source.

[0047] The memory (110) may be implemented as a non-volatile semiconductor memory, a hard disk, a flash memory, RAM (Random Access Memory), ROM (Read Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), or any other type of tangible non-volatile recording medium.

[0048] The processor (120) can operate according to instructions stored in memory (110), determine a transit node using a transit node determination method, and generate an piercing path using a path generation method. Unless otherwise noted, the various operations or steps of generating an piercing path disclosed below as embodiments of the present invention may be interpreted as being performed by the processor (120) of the path generation device (100) or by the control of the processor (120). The specific operation method of the processor (120) will be described later.

[0049] The processor (120) can be implemented as a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a Digital Signal Processor (DSP), a state machine, an Application Specific Integrated Circuit (ASIC), a Radio-Frequency Integrated Circuit (RFIC), and combinations thereof.

[0050] The communication device (130) can transmit data and / or information to or from the outside via wired and / or wireless communication. The communication device (130) can perform bidirectional or unidirectional communication.

[0051] For example, the communication device (130) can communicate with a sensor module (200), an external server (300), and / or a ship navigation device (400). Specifically, it can receive sensing data from the sensor module (200) and receive various data necessary for path generation from the external server (300). Additionally, it can transmit information related to a determined route node and / or information related to a generated path to the ship navigation device (400). It is not limited to this, and the communication device (130) may also communicate with other external devices.

[0052] The path generation device (100) may be installed on a vessel. It is not limited thereto, and the path generation device (100) may also be installed outside the vessel. For example, the path generation device (100) may be installed on a port control server, a terminal device for personnel, an external server, etc.

[0053] FIG. 3 is a block diagram showing the configuration of a sensor module (200) according to one embodiment.

[0054] The sensor module (200) can detect the state of the vessel and surrounding environmental factors. More specifically, the sensor module (200) can detect the position, bow direction, speed, steering angle, and / or weight of the vessel, and can also detect currents, wind direction, and wind speed of the external environment. The objects that can be detected are not limited to those described above, and the sensor module (200) can also detect various factors necessary for generating a docking path.

[0055] Referring to FIG. 3, a sensor module (200) according to one embodiment may include at least one sensor (210) and a communication device (220).

[0056] The sensor (210) may include at least one of a Global Positioning System (GPS) (211), an Automatic Identification System (AIS) (212), an ultrasonic detector (213), an Inertial Measurement Unit (IMU) (214), an Inertial Navigation System (INS) (215), a speedometer (216), a camera (217), a radar (218), a lidar (219), and a Real-Time Kinematic GPS (RTK-GPS). It is not limited to the configurations described above, and the sensor (210) may include a sensor for detecting the state of the vessel and / or a sensor for detecting the surrounding environment of the vessel.

[0057] The communication device (220) of the sensor module (200) can transmit data and / or information to the outside or receive it from the outside via wired and / or wireless communication, and can perform data communication with the path generation device (100), the external server (300), and / or the ship navigation device (400).

[0058] FIG. 4 is a block diagram showing the configuration of an external server (300) according to one embodiment.

[0059] The external server (300) stores at least one of information about a ship, information about a port, real-time ship status information, real-time port status information, and real-time environment data, and can transmit data necessary for generating a path in the path generating device (100) to the path generating device (100).

[0060] Specifically, if there is data that is not stored in the path generation device (100) but is necessary for generating a docking path, or if real-time data is needed for generating a docking path even though data is stored, the external server (300) can transmit the data necessary for generating a docking path to the path generation device (100).

[0061] For example, an external server (300) can determine the port where the vessel is located using vessel location data received from the vessel, and can transmit information about the determined port to a path generation device (100).

[0062] Meanwhile, the external server (300) can transmit data necessary for ship operation, in addition to data necessary for route generation, to the route generation device (100), sensor module (200) and / or ship operation device (400).

[0063] According to one embodiment, the external server (300) may be various types of servers, such as a control server or a cloud server.

[0064] Referring to FIG. 4, an external server (300) according to one embodiment may include memory (310), a processor (320), and a communication device (330).

[0065] The memory (310) of the external server (300) can store information about at least one port. The information about the port is not limited to the port where the vessel is currently located, but may include information about nearby ports or all ports. Since specific information about the port has been described above, a redundant description is omitted.

[0066] The memory (310) can store information about at least one vessel. The information about the vessel may be data received from the vessel, and since specific information about the vessel has been described above, a redundant description is omitted.

[0067] The memory (310) may store data received from the outside in real time by an external server (310). For example, the memory (310) may store at least one of real-time ship status information, real-time port status information, and real-time environment data.

[0068] The processor (320) of the external server (300) can determine the port where the vessel is located using data received from the vessel. For example, if the external server (300) receives GPS location data from the vessel, the processor (320) can determine the port where the vessel is located or nearby using this data.

[0069] The processor (320) can transmit an obstacle map corresponding to the determined port to the path generation device (100) and / or the ship navigation device (400).

[0070] For example, the processor (320) may generate an obstacle map including a node corresponding to the current location of the ship and a node corresponding to the docking location of the ship, or select from a plurality of obstacle maps and transmit to the path generation device (100) or ship navigation device (400) via the communication device (330) to be described later. Details regarding the obstacle map will be described later.

[0071] Meanwhile, if the external server (300) is a control server, the external server (300) can receive weather information, etc. regarding the port from a separate weather agency server and can transmit the received weather information, etc. to the route generation device (100) and / or the ship operation device (400).

[0072] The communication device (330) of the external server (300) can transmit data and / or information to the outside or receive it from the outside via wired and / or wireless communication, and can perform data communication with the path generation device (100), sensor module (200), and / or ship navigation device (400).

[0073] Meanwhile, the external server (300) can be placed outside the ship and can be located in a control center, a navigation management center, etc.

[0074] FIG. 5 is a block diagram showing the configuration of a ship navigation device (400) according to one embodiment.

[0075] The ship navigation device (400) can generate a control signal to enable the ship to navigate along a berthing path or a waypoint node received from the path generation device (100). The control signal may include a ship speed control signal and / or a bow direction control signal.

[0076] For example, a ship speed control signal may be a signal for controlling the rotational speed of a ship's propeller, a signal for controlling the number of rotations per unit time of a propeller, or an engine output control signal, but is not limited thereto, and may include various signals for controlling the ship's power system.

[0077] For example, a bow direction control signal may be a signal for controlling the rudder or wheel (helm) of a ship, but is not limited thereto, and may include various signals for controlling the direction of travel of a ship.

[0078] Referring to FIG. 5, a ship navigation device (400) according to one embodiment may include a control signal generating unit (410) and a communication device (420). The control signal generating unit (410) may include a ship speed control signal generating unit (411) and / or a bow direction control signal generating unit (412).

[0079] The ship speed control signal generation unit (411) can generate the above-described ship speed control signal and control the ship's propeller or engine, etc.

[0080] The bow direction control signal generation unit (412) can generate the bow direction control signal described above to control the rudder or steering wheel of the vessel. Specific details regarding the control signal will be described later.

[0081] The communication device (420) of the ship navigation device (400) can receive information related to a transit node or information related to a docking path from the path generation device (100). Meanwhile, the ship navigation device (400) can receive information regarding the current status of the ship and surrounding environment from the sensor module (200). Meanwhile, the ship navigation device (400) can receive weather information or navigation rules, etc. from an external server (300). Navigation rules refer to agreements or regulations that must be observed when operating a ship. For example, navigation rules may be the International Regulations for Preventing Collisions at Sea (COLREG). Meanwhile, the ship navigation device (400) can transmit the generated control signal to the ship to cause the ship to operate along the generated docking path.

[0082] 2. Obstacle Map

[0083] FIG. 6 is a drawing showing an obstacle map (600) according to one embodiment.

[0084] The obstacle map is a grid image or matrix data used in path generation, but is not limited to this and can be implemented in various forms. FIG. 6 shows an obstacle map (600) implemented as a grid image.

[0085] A path at sea can be generated by considering the location of a node (630) corresponding to an obstacle on an obstacle map (600). For example, a path generation device (100) can generate a docking path using the obstacle map (600).

[0086] Referring to FIG. 6, the obstacle map (600) may include a plurality of nodes (610). Each node (610) may correspond to a location on the sea and may also correspond to a location on land.

[0087] If the obstacle map (600) is implemented as a grid image, each node (610) may represent each area of ​​the grid image.

[0088] Meanwhile, if the obstacle map is a two-dimensional image, a 'one node' included in the obstacle map may correspond to a 'one pixel' constituting the two-dimensional image, or a 'one node' included in the obstacle map may correspond to multiple adjacent pixels constituting the two-dimensional image.

[0089] Meanwhile, when the obstacle map is implemented with matrix data, the matrix data includes multiple matrices, and some of the elements of each matrix correspond to position values ​​(e.g., x-coordinate, y-coordinate, etc.), and some of the remaining elements correspond to attribute values ​​assigned to those position values. In this case, a node of the aforementioned obstacle map may correspond to a single matrix included in the aforementioned matrix data, or a node of the obstacle map may correspond to multiple matrices that correspond to adjacent positions among the matrices included in the aforementioned matrix data.

[0090] Referring to FIG. 6, the obstacle map (600) may include nodes (620) corresponding to the sea and nodes (630) corresponding to obstacles. Referring to FIG. 6, the nodes (620) corresponding to the sea are shown in a bright color, and the nodes (630) corresponding to obstacles are shown in a dark color.

[0091] Nodes (630) corresponding to obstacles mean that a vessel cannot navigate to a location corresponding to each node. The distribution of nodes (630) corresponding to obstacles may vary depending on the type of port facilities and the type of berthing facilities. Obstacles may refer to any object that can be an obstacle to the operation of a vessel, such as terrain, buildings, islands, ports, vessels, buoys, offshore structures, breakwaters, and people.

[0092] Meanwhile, although not illustrated in FIG. 6, attribute information may be assigned to each node (610) of the obstacle map (600). The attribute information refers to information related to the object corresponding to each node, and there are no limitations on the information regarding the object.

[0093] The object may include not only obstacles that may hinder the operation of the aforementioned vessel, but also areas where the vessel can operate, such as the sea. Accordingly, information related to the sea may be assigned to the nodes (620) corresponding to the aforementioned sea, and information related to obstacles may be assigned to the nodes (630) corresponding to obstacles. Meanwhile, information related to land may be assigned to the nodes corresponding to land.

[0094] Attribute information is not limited to the presence, type, location, placement direction, movement direction, and movement speed of the object, and may also include a score based on the presence of obstacles and suitability for navigation.

[0095] FIG. 7 is a drawing showing a scored obstacle map (700) according to one embodiment. The scored obstacle map (700) may also be referred to as a cost map.

[0096] Referring to FIG. 7, some or all of the multiple nodes included in the obstacle map (700) may be assigned a score based on the presence of obstacles and suitability for navigation.

[0097] The score assigned to a specific node reflects its operational suitability, which is determined according to various criteria. Accordingly, if the score assigned to one node differs from the score assigned to another node, it means that the operational suitability determined for each node is different.

[0098] The navigability of a specific node can be determined by considering the probability that an obstacle exists at the specific node. Alternatively, the navigability of a specific node can be determined by considering the probability that the vessel will collide with an obstacle when the vessel is located at the specific node. Alternatively, the navigability of a specific node can be determined by considering the distance the specific node is from the node corresponding to the obstacle. Of course, the navigability of a specific node can be determined by a method that combines two or more of the three methods mentioned above.

[0099] High navigational suitability for a specific node may mean that the probability of a vessel colliding with an obstacle is low when passing through said specific node. Conversely, low navigational suitability for a specific node may mean that the probability of a vessel colliding with an obstacle is high when passing through said specific node.

[0100] Although not limited thereto, in this specification, a higher score is described as meaning a lower operational suitability, and a lower score is described as meaning a higher operational suitability.

[0101] The score may have a value between 0 and 255, though not limited thereto. The aforementioned range is for illustrative purposes only and is not limited to the aforementioned range. A higher score may indicate a higher probability of obstacles or unsuitability for navigation, while a lower score may indicate suitability for navigation.

[0102] Meanwhile, the score assigned to a node can be determined based on its distance from the node corresponding to the obstacle. For example, nodes that are farther from the node corresponding to the obstacle may be assigned lower scores. In this case, different scoring criteria may be applied depending on the characteristics of the obstacle.

[0103] For example, a node near a node corresponding to an obstacle that is difficult for a ship to approach, such as an island or breakwater, may be assigned a relatively higher score than a node near a node corresponding to an obstacle that is easy for a ship to approach, such as a buoy. Additionally, for a node near a node corresponding to an obstacle that is difficult for a ship to approach, the range of score reduction as the distance from the node corresponding to the obstacle increases may be smaller than the range of score reduction for a node near a node corresponding to an obstacle that is easy for a ship to approach.

[0104] In FIG. 7 according to one example, the higher the score assigned to a node, the darker the color is displayed, and the lower the score assigned to a node, the brighter the color is displayed. Referring to FIG. 7, the node (710) corresponding to the obstacle is assigned the highest score, so it is displayed the darkest. Meanwhile, regarding the nodes (720, 730, 740) corresponding to the sea, the node (720) with the lowest assigned score is displayed the brightest color, the node (730) with the medium score is displayed the medium bright color, and the node (720) with the high score is displayed the slightly bright color.

[0105] FIG. 8 is a drawing of an obstacle map (800) including a node (810) corresponding to a ship according to one embodiment.

[0106] The shape of the ship (820) is also reflected on the obstacle map (800) of Fig. 8, but is not limited thereto, and only nodes (810) corresponding to the ship may be displayed on the obstacle map (800).

[0107] Referring to FIG. 8, the bow direction (830) of a vessel located at a position on the sea corresponding to the node (810) on the obstacle map (800) can be assigned as attribute information.

[0108] Heading refers to the direction in which the bow of the vessel is pointing. Specifically, heading may refer to the angle formed by the bow-stern line and a reference line (meridian line) passing through the vessel, which is the direction in which the vessel is intended to proceed. For example, referring to FIG. 8, a value of 270 degrees or 1.5π may be assigned to the node (810) corresponding to the vessel for the heading (830).

[0109] This is not limited to this, and if a reference direction is set on an obstacle map, the bow direction may refer to the angle formed between the set reference direction and the bow-tail line.

[0110] Obstacle maps can be generated in various ways. For example, obstacle maps can be generated from electronic charts, or they can be generated using images such as satellite or aerial photographs.

[0111] For example, when generating an obstacle map by processing an image, the sea area and obstacle area reflected in the image can be identified using image segmentation, and then the obstacle map can be generated based on the identified areas. Specifically, an obstacle map can be generated by placing nodes corresponding to the sea in the sea area and nodes corresponding to obstacles in the obstacle area.

[0112] Meanwhile, obstacle maps can also be generated using LiDAR point cloud data. Specifically, obstacle maps expressed in two dimensions can be generated by projecting each point included in the LiDAR point cloud onto a reference plane. The reference plane may refer to a plane that can be assumed to be the average sea level.

[0113] To generate an obstacle map using a LiDAR point cloud, LiDAR sensors for detecting the surrounding environment may be deployed on ships or port facilities. Multiple LiDAR sensors may be deployed and installed without restrictions on their location.

[0114] Meanwhile, obstacle maps can also be generated using camera images. Specifically, an obstacle map can be generated by performing image segmentation on the image and then transforming the segmented image to a reference plane. The reference plane may refer to a plane that can be assumed to be the mean sea level.

[0115] To generate an obstacle map using camera images, cameras that capture the surrounding environment may be deployed on ships or port facilities. Multiple cameras may be deployed and installed without restriction on their location.

[0116] The method for generating obstacle maps is not limited to this, and various methods for generating port maps can be used.

[0117] An obstacle map can be generated on an external server (300). The external server (300) can generate an obstacle map using electronic charts or image data as described above. Meanwhile, the external server (300) may generate an obstacle map using LiDAR point cloud data acquired by a port facility or a vessel or captured images.

[0118] It is not limited to this, and the obstacle map may also be generated by the path generation device (100). Specifically, the path generation device (100) may generate an obstacle map using data stored in the path generation device (100) or data received from an external source.

[0119] Meanwhile, if the path generation device (100) is located on a ship, it can generate an obstacle map using LiDAR point cloud data acquired by the ship's LiDAR sensor or an image captured by the ship's camera. If the path generation device (100) is located outside the ship, the path generation device (100) can generate an obstacle map using LiDAR point cloud data acquired by the port facility or the ship or an captured image.

[0120] 3. Path Generation Method 1

[0121] FIG. 9 is a flowchart of a path generation method according to one embodiment.

[0122] Referring to FIG. 9, a path generation method according to one embodiment of the present invention may be performed by the steps of acquiring an obstacle map (S910), selecting a current node and a docking node on the obstacle map (S920), determining the current bow direction from the current node and the docking bow direction from the docking node (S930), determining a reference distance (S940), determining a plurality of transit nodes from the current node to the docking node on the obstacle map (S950), and generating a docking path using the determined transit nodes (S960). Specific details regarding the path generation method will be described later.

[0123] First, regarding the acquisition of obstacle maps, the obstacle maps may be stored in the path generation device or acquired from an external source. Even if the obstacle maps are stored in the path generation device, they may be newly acquired from an external source to update them.

[0124] The selection of the current node and the docking node on the obstacle map, and the determination of the current bow direction at the current node and the docking bow direction at the docking node, will be explained with reference to FIG. 10.

[0125] FIG. 10 is a drawing showing an obstacle map (1000) according to one embodiment.

[0126] Referring to FIG. 10, the current node (1020) may represent a node corresponding to the current position of the vessel on the obstacle map (1000). The current node (1020) may correspond to the starting position of the path.

[0127] In the obstacle map (1000) of FIG. 10, the shape of the ship is reflected at the location (1010) on the obstacle map (1000) corresponding to the ship's current location, but is not limited thereto, and the shape of the ship may not be reflected in the obstacle map.

[0128] In order to obtain information regarding the current position of a vessel, the path generation device can receive coordinates, etc. regarding the current position of the vessel through a sensor module. In addition, the path generation device can select a current node on an obstacle map using the obtained information regarding the current position of the vessel.

[0129] In order to select the current node on the obstacle map, the scale of the obstacle map and the mapping of the obstacle map to an absolute coordinate system may be performed by the path generation device.

[0130] Regarding the determination of a vessel's current position for selecting a current node, the vessel's current position may be determined based on the location of the vessel's center point. This is not limited to this, and the vessel's current position may also be determined based on any point on the vessel, such as the bow or stern.

[0131] Meanwhile, the path generation device may also obtain an obstacle map (1000) from the outside in which the current node (1020) is selected.

[0132] Referring to FIG. 10, the docking node (1050) may refer to a node corresponding to the docking position of a vessel on the obstacle map (1000). The docking node (1050) may correspond to the end position of the path.

[0133] In the obstacle map (1000) of FIG. 10, the shape of the ship is reflected at the location (1040) on the obstacle map (1000) corresponding to the docking location of the ship, but is not limited thereto, and the shape of the ship may not be reflected in the obstacle map.

[0134] The berthing location of a vessel refers to the location at the berthing facility where the vessel will berth, and can be determined based on data regarding the port stored in the route generation device or data obtained from an external server.

[0135] Regarding the determination of a vessel's berthing position for selecting a berthing node, the vessel's berthing position may be determined based on the location of the vessel's center point when the vessel is berthed at a berthing facility. This is not limited to this, and the vessel's berthing position may also be determined based on any point on the vessel, such as the bow or stern. Meanwhile, the vessel's reference position for selecting the current node and the vessel's reference position for selecting the berthing node may be set to be the same.

[0136] Meanwhile, the path generation device may also obtain an obstacle map (1000) from the outside in which the abutment node (1050) is selected.

[0137] The current bow direction (1030) of the vessel may be assigned to the selected current node (1020). The current bow direction (1030) refers to the bow direction of the vessel at the current point in time and can be determined using data obtained from the sensor module. As details regarding assigning a bow direction to a node on the obstacle map have been described above, a redundant explanation is omitted.

[0138] A berthing bow direction (1060) may be assigned to the selected berthing node (1050). The berthing bow direction (1060) refers to the bow direction when the vessel berths at the berthing facility. The berthing bow direction (1060) can be determined based on information about the port stored in the path generation device or data obtained from the outside. If only information about the berthing location is received from the outside, the berthing bow direction (1060) may be determined from the expected bow direction when the vessel is located at the berthing location based on information about the port (such as the shape of the port) on the obstacle map (1000). Since details regarding assigning a bow direction to a node on the obstacle map have been described above, a redundant explanation is omitted.

[0139] FIG. 11 is a diagram showing a path (1070) generated by performing a conventional approach path generation method on the obstacle map (1000) of FIG. 10.

[0140] Generally, a 3D A* algorithm can be used to generate a path, and FIG. 11 shows a path (1070) from the current node (1020) to the abutment node (1050) generated using only the existing 3D A* algorithm.

[0141] Referring to FIG. 11, the existing 3D A* algorithm generates the shortest path (1070) from the current node (1020) to the docking node (1050), and in the generated path (1070), a course change section (1080) exists for a short length immediately before the docking facility.

[0142] Accordingly, when a vessel is operated along a berthing path generated by a berthing path generation method using only a general 3D A* algorithm, there was a problem in that the risk of collision between the vessel and the berthing facility increased even with a small deviation from the path. To solve this, the present invention aims to generate a berthing path using a reference distance described below.

[0143] FIG. 12 is a drawing for explaining a reference distance (1110) according to one embodiment.

[0144] The reference distance (1110) means a distance that allows the vessel to turn 360 degrees and re-enter the berthing facility when the difference between the vessel's bow direction and the berthing bow direction is large, making it difficult or dangerous for the vessel to enter the berthing facility immediately.

[0145] When generating a berthing path considering a reference distance (1110), the path generating device generates a path that minimizes changes in the bow direction of the vessel within a reference distance range (1120) from the berthing node (1150), thereby reducing the risk of collision between the vessel and the berthing facility when operating the vessel along the generated path.

[0146] Specifically, the reference distance (1110) can be calculated by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of the berthing facility (1170). For example, the reference distance (1110) may be longer as the length of the vessel increases, as the width of the vessel increases, as the weight of the vessel increases, as the steering performance of the vessel decreases, and as the length of the berthing facility (1170) increases. Meanwhile, the reference distance (1110) may also be calculated by considering the turning radius of the vessel. In this case, the reference distance (1110) may be longer as the turning radius of the vessel increases. Meanwhile, the reference distance (1110) may also be calculated by considering the sum of twice the length of the berthing facility (1170) and five times the length of the vessel.

[0147] The reference distance (1110) can be calculated by the path generation device. Specifically, the path generation device can calculate the reference distance (1110) using information about ships and information about ports stored in the path generation device. In this case, the information about ships and / or information about ports may be data received from an external source.

[0148] Meanwhile, the reference distance (1110) may be calculated from an external server. Specifically, the external server may calculate the reference distance (1110) using information about the port stored in the external server and information about the vessel received from the vessel. When the reference distance is calculated from the external server, the external server may transmit the calculated reference distance to the path generation device.

[0149] Referring to FIG. 12, a reference distance node (1130), which is a node located at a position that is a reference distance (1110) away from the berthing node (1150) to generate the berthing path to be described later, may be used.

[0150] The determination of multiple transit nodes from the current node to the docking node on the obstacle map and the generation of the docking path will be explained with reference to FIGS. 13, 14, and 15.

[0151] FIGS. 13, FIGS. 14 and FIGS. 15 are drawings showing a landing path and a transit node on an obstacle map (1200) according to one embodiment.

[0152] A path can refer to an order of at least two nodes, and determining a path can mean determining the nodes and their order.

[0153] A waypoint node may refer to a node on an obstacle map corresponding to a specific location of a vessel as the vessel moves along a path from its current location to its docking location. In this case, the specific location may be the vessel's bow, stern, or center point. However, it is preferable to determine the specific location to be the same as the location used to determine the current node corresponding to the vessel's current location. For example, if the vessel's center point was used to determine the current node, it is preferable to use the vessel's center point when determining the waypoint node as well.

[0154] A method for determining a way node can be used to determine a way node on an obstacle map. A method for determining a way node according to one example may include a first method for determining a way node and a second method for determining a way node. A specific method for determining a way node is described with reference to FIG. 13.

[0155] Referring to FIG. 13, the first way node determination method is a method of determining a plurality of first way nodes (1240-1) from the current node (1210-1) to one of the reference distance nodes (1230) by considering the current direction of the current line (1220-1).

[0156] In this case, the first way node (1240-1) can be determined by taking into account the maximum turning angle of the vessel. Specifically, the first way node (1240-1) immediately following the current node (1210-1) can be determined from among nodes within the maximum turning angle based on the current bow direction (1220-1).

[0157] The method for determining the first way node can also determine the expected heading direction at each of the determined first way nodes (1240-1). Although not shown in FIG. 13, the determined expected heading direction can be assigned to the corresponding way node. The expected heading direction for a specific way node refers to the expected heading direction of a vessel at a corresponding position when assuming that a vessel moving along the expected path is at a position corresponding to the specific way node. Since the expected heading direction is assigned to each of the determined first way nodes (1240-1), the subsequent first way node immediately following the determined first way node (1240-1) can be determined from among nodes within the maximum turning angle based on the expected heading direction assigned to the determined first way node (1240-1).

[0158] The maximum turning angle of the vessel may be a value proportional to the vessel speed and inversely proportional to the turning radius. In this case, the turning radius may be set to five times the length of the vessel. To take the maximum turning angle into account when determining the first transit node (1240-1), the maximum turning angle, vessel speed, and / or turning radius at each node may be calculated.

[0159] Although not illustrated in FIG. 13, the first way node determination method may determine the first way node (1240-1) by considering the score assigned to each node of the obstacle map (1200) described above. Specifically, when determining the subsequent first way node immediately following the current node (1210-1) or the determined first way node (1240-1), the first way node may be determined by considering the score assigned to the subsequent first way node. For example, among the preliminary subsequent first way nodes, the node with the lowest score assigned to it may be determined as the subsequent first way node.

[0160] Additionally, the first transit node determination method may determine the first transit node (1240-1) by considering the remaining distance to the docking node (1280). Specifically, when determining the subsequent first transit node immediately following the current node (1210-1) or the determined first transit node (1240-1), the first transit node determination method may determine the subsequent first transit node such that the remaining distance from the subsequent first transit node to the docking node (1280) becomes smaller.

[0161] Meanwhile, in FIG. 13, the first transit nodes (1240-1) are determined such that there is a distance between the first transit nodes (1240-1), but the first transit nodes (1240-1) may also be determined continuously from the current node (1210-1) to one of the reference distance nodes (1230).

[0162] The reference distance node (1230) considered to determine the first way node (1240-1) refers to at least one node corresponding to a location located at a reference distance from the berthing node (1280). Among the reference distance nodes (1230), the node determined as the first way node (1240-1) can be set as the reference distance way node (1250-1). In this case, the bow direction when the vessel is located at the reference distance way node (1250-1) can be assigned to the reference distance way node (1250-1) as the expected bow direction (1260-1).

[0163] The first transit node determination method can determine the first transit nodes (1240-1) so that the second transit nodes (1270-1) can be determined according to the second transit node determination method described later. Specific details will be described later.

[0164] Referring to FIG. 13, the second way node determination method is a method of determining a plurality of second way nodes (1270-1) from a reference distance way node (1250-1) to a docking node (1280) by considering the docking bow direction (1290).

[0165] In this case, the second way node (1270-1) can be determined by taking into account the maximum turning angle of the vessel. Specifically, the second way node (1270-1) immediately following the reference distance way node (1250-1) can be determined from among the nodes within the maximum turning angle based on the expected heading direction (1260-1) assigned to the reference distance way node (1250-1).

[0166] The method for determining the second way node can also determine the expected heading direction at each of the determined second way nodes (1270-1). Although not shown in FIG. 13, the determined expected heading direction can be assigned to the corresponding way node. Since the expected heading direction is assigned to each of the determined second way nodes (1270-1), when determining the subsequent second way node immediately following the determined second way node (1270-1), the subsequent second way node can be determined from among the nodes within the maximum turning angle based on the expected heading direction at the determined second way node (1270-1).

[0167] Additionally, the second transit node determination method can determine the second transit nodes (1270) such that the expected bow direction to be assigned to the second transit node (1270-1) corresponding to the berthing node (1280) matches the berthing bow direction (1290).

[0168] Although not illustrated in FIG. 13, the second way node determination method may determine the second way node (1270-1) by considering the score assigned to each node of the obstacle map (1200) described above. Specifically, when determining the subsequent second way node immediately following the reference distance way node (1250-1) or the determined second way node (1270-1), the second way node may be determined by considering the score assigned to the subsequent second way node. For example, among the preliminary subsequent second way nodes, the node with the lowest assigned score may be determined as the subsequent second way node.

[0169] Additionally, the second route node determination method may determine the second route node (1270-1) by considering the remaining distance to the docking node (1280). Specifically, when determining the subsequent second route node immediately following the reference distance route node (1250-1) or the determined second route node (1270-1), the second route node determination method may determine the subsequent second route node such that the remaining distance from the subsequent second route node to the docking node (1280) becomes smaller.

[0170] Meanwhile, in FIG. 13, the second route nodes (1270-1) are determined such that there is a distance between the second route nodes (1270-1), but the second route nodes (1270-1) may be determined continuously from the reference distance route node (1250-1) to the docking node (1280).

[0171] Compared to the first method for determining a transit node, the second method for determining a transit node can determine the subsequent second transit node immediately following the reference distance transit node (1250-1) or the determined second transit node (1270-1) by considering the difference between the expected heading direction to be assigned to the subsequent second transit node and the berthing heading direction (1290). For example, among the preliminary subsequent second transit nodes, the node with the smallest difference between the expected heading direction to be assigned to the node and the berthing heading direction (1290) can be determined as the subsequent second transit node.

[0172] Meanwhile, the method for determining the second transit node may determine the subsequent second transit node by considering only the difference between the expected bow direction to be assigned to the subsequent second transit node and the berthing bow direction (1290). Alternatively, the method for determining the second transit node may determine the subsequent second transit node from among the preliminary subsequent second transit nodes the node in which the expected bow direction to be assigned to the node is the same as the berthing bow direction (1290).

[0173] That is, according to the second transit node determination method, the second transit nodes (1270-1) must be determined such that the difference between the expected bow direction to be assigned to the second transit nodes (1270-1) and the berthing bow direction (1290) is small or non-existent. Accordingly, the first transit node determination method can determine the first transit nodes (1240-1) by also considering whether the second transit nodes (1270-1) can be determined through the second transit node determination method.

[0174] Specifically, even if the first route node (1240-1) and the reference distance route node (1250-1) are determined through the first route node determination method, if the second route nodes (1270-1) from the reference distance route node (1250-1) to the docking node (1280) cannot be determined using the second path generation method, at least one of the determined first route nodes may be newly determined, or a new first route node may be additionally determined.

[0175] The determination of the first transit node is explained with reference to FIGS. 14 and FIGS. 15.

[0176] Referring to FIG. 14, when the current node (1210-2) is located close to the reference distance node (1230) and the current bow direction (1220-2) differs significantly from the berthing bow direction (1290), and when the shortest path is generated from the current node (1210-2) to one of the reference distance nodes (130) using the first path generation method, the reference distance passing node (1250-2) and the expected bow direction (1260-2) assigned to the reference distance passing node (1250-2) are inevitably determined as shown in FIG. 14 due to limitations in the steering performance of the vessel.

[0177] With the reference distance via node (1250-2) and the expected heading direction (1260-2) assigned to the reference distance via node (1250-2) determined as in FIG. 14, if the second via nodes (1270-2) are determined using the second via node determination method described above, the second via node (1270-2) cannot be generated up to the docking node (1280). That is, the second via node (1270-1) cannot be determined through the second via node determination method.

[0178] Accordingly, under the current node (1210-2) and current forward direction (1220-2) conditions as in FIG. 14, a new first transit node must be determined.

[0179] Referring to FIG. 15, the first transit node determination method can determine the first transit nodes (1240-3) so that the vessel can turn away from the reference distance node (1230) and approach the reference distance node (1230) under conditions such as when the current node (1210-2) is located close to the reference distance node (1230) and the current bow direction (1220-2) differs significantly from the berthing bow direction (1290).

[0180] Accordingly, as shown in FIG. 15, the second route node determination method can determine the second route nodes (1270-3) from the reference distance route node (1250-3) to the docking node (1280).

[0181] The above-described method for determining the transit node may also be implemented based on the 3D A* algorithm.

[0182] Specifically, to obtain the expected docking path, which is the path to be generated through the aforementioned transit node determination method, the expected docking path cost function can be set as the cost function considered in the 3D A* algorithm.

[0183] Below, we will explain a method for determining multiple transit nodes from the current node to the docking node on an obstacle map using a reference distance and an estimated docking path cost function.

[0184] Just as the transit node determination method includes a first transit node determination method and a second transit node determination method, the expected berthing path cost function may include a first expected berthing path cost function and a second expected berthing path cost function.

[0185] For the first expected berthing path that can be applied to the first expected berthing path to be generated by the first transit node determination method, the first expected berthing path cost function can be defined as follows, where g(n) and h(n) are defined in the cost function f=g+h.

[0186] g(n)=ω m *C m (n)+ ω c *C c (n)

[0187] h(n)=ω d *C d (n)

[0188] At this time, n represents the sequence number of the first intermediate node from the current node, and n at the current node can be 0.

[0189] Meanwhile, ω m , ω c , and ω d is C m , C c , and C d These are the weight values ​​for each.

[0190] C m is a score assigned to each node of the obstacle map, intended to consider locations safe from obstacles. C c is the change in angle to the next node based on the current or expected heading in radians, and is intended to reflect the vessel's limited maneuverability. C d is the remaining distance from the transit node to the docking node, and represents the heuristic value.

[0191] Using the cost function described above, the first transit node from the current node to the reference distance transit node can be determined.

[0192] For example, when determining the immediate next subsequent node (e.g., the (n+1)th via node) based on the nth via node, cost values ​​determined by a cost function can be calculated for each of the multiple subsequent node candidates based on the nth via node, and the subsequent node candidate with the smallest calculated cost value can be determined as the (n+1)th via node. That is, in determining the (n+1)th subsequent via node based on the nth via node, the score assigned to each node of the obstacle map to consider a location safe from obstacles, the change in angle to the next node based on the current or expected bow direction in radians to reflect the vessel's limited maneuverability, and the remaining distance from the via node to the berthing node can be considered. This process can be repeated from the current node to the reference distance via node to determine multiple first via nodes.

[0193] Meanwhile, for the second expected berthing path that can be applied to the second expected berthing path to be generated by the second transit node determination method, the second expected berthing path cost function can be defined as follows, where g(n) and h(n) are defined in the cost function f=g+h.

[0194] g(n)=ω m *C m (n)+ ω c *C c (n)

[0195] h(n)=ω d *C d (n)+ω b *C b (n)*A

[0196] At this time, n represents the sequence number of the second transit node, and n can be 0 at the reference distance transit node.

[0197] Meanwhile, ω m, ω c , ω d and ω b is C m , C c , C d and C b It is the weight value for each. C m , C c , C d As this has been explained above, a redundant explanation is omitted.

[0198] Cb is the difference between the expected bow direction and the berthing bow direction in radians at the transit node, and is intended to minimize the difference between the expected bow direction and the berthing bow direction.

[0199] A is a value set to increase the weighting of the difference between the expected heading and the berthing heading when using the second way node determination method. A can be assigned a maximum value in the form of a real number. For example, if an infinite value is assigned to A, C in determining the second way node b It is possible to ensure that only the value is considered. By assigning an infinite value to A (which may be the largest real number value that can be set), as described above, the second node determination method can be interpreted as determining the subsequent second way node by considering only the difference between the expected bow direction to be assigned to the subsequent second way node and the berthing bow direction (1290). However, if a reasonably large real number is assigned instead of an infinite value to A, the difference between the expected bow direction to be assigned to the subsequent second way node and the berthing bow direction (1290) is considered most significantly, while also considering the score assigned to each node of the obstacle map for considering a safe position from obstacles, the angle change amount to the next node based on the current bow direction or expected bow direction in radians to reflect the limited maneuverability of the vessel, and the remaining distance from the way node to the berthing node.

[0200] Meanwhile, if there is a significant difference between the expected direction of the vessel and the direction of the vessel at docking, the subsequent node cannot ultimately be determined. Therefore, according to the first node determination method, a 'new' set of first transit nodes can be determined, and as this loop is repeated, the objective to be achieved by the present application can ultimately be achieved, and a safe path as shown in FIG. 13 and FIG. 15 can be found instead of a path with a high risk of collision as shown in FIG. 11.

[0201] Using the cost function described above, a second transit node from the reference distance transit node to the docking node can be determined.

[0202] In summary, the estimated abutment path cost function of the transit node determination method based on the 3D A* algorithm is f=g+h, where g(n) and h(n) can be defined as follows.

[0203] g(n)=ω m *C m (n)+ ω c *C c (n)

[0204] h(n)=ω d *C d (n)+ω b *C b (n)*A

[0205]

[0206] In this case, n represents the sequence number of the intermediate node, and at the current node, n can be 0.

[0207] Consequently, the method for determining the way node (reference distance way node) placed at a reference distance from the current node and the method for determining the docking position from the reference distance way node will differ.

[0208] More specifically, the difference between the second and first method for determining a way node lies in the fact that it gives greater consideration to the difference between the expected heading angle assigned to the subsequent node and the berthing angle assigned to the berthing node. Furthermore, the difference between the second and first method for determining a way node lies in the fact that the weight value for the difference between the expected heading angle assigned to the subsequent node and the berthing angle assigned to the berthing node is set very high, thereby eliminating or significantly reducing the influence on the function value of the cost function of the values ​​considered in the first method for determining a way node (e.g., the score assigned to each node of the obstacle map to consider a safe position from obstacles, the change in angle to the next node based on the current or expected heading in radians to reflect the ship's limited maneuverability, and the remaining distance from the way node to the berthing node).

[0209] Multiple transit nodes from the current node to the docking node can be determined using the cost function described above.

[0210] Specifically, the transit nodes can be determined using the aforementioned estimated berthing path cost function and the algorithm of FIG. 16.

[0211] Figure 16 is an exemplary algorithm for obtaining transit nodes and paths based on the 3D A* algorithm.

[0212] The path generation device can use the current node, the berthing node, and the transit nodes to generate a berthing path.

[0213] Specifically, the path generation device can generate a path by sequentially connecting the current node, intermediate nodes, and berthing nodes. It is not limited to this, but the path generation device may select some intermediate nodes suitable for navigation among the intermediate nodes and generate a path by sequentially connecting the current node, the selected intermediate nodes, and the berthing nodes. When generating a path by sequentially connecting the nodes, the path generation device may consider the heading direction assigned to each node.

[0214] Meanwhile, the path generation device may generate a path by calculating an approximation curve for the via nodes. The approximation curve can be calculated to pass through the current node and the berthing node, taking into account the current bow direction and the berthing bow direction. The degree of approximation of the approximation curve for the via nodes can be determined based on information about the vessel.

[0215] Meanwhile, if the path generation device cannot determine the via nodes satisfying the above conditions using the above-described via node determination method due to the presence of obstacles within the reference distance range, etc., the path generation device may output a result indicating that it cannot generate a path.

[0216] 4. Path Generation Method 2

[0217] FIG. 17 is a flowchart of a path generation method according to one embodiment.

[0218] Referring to FIG. 17, a path generation method according to one embodiment of the present invention may be performed by the following steps: acquiring an obstacle map (S1410); selecting a current node and a docking node on the obstacle map (S1420); determining the current bow direction at the current node and the docking bow direction at the docking node (S1430); determining a reference distance (S1440); determining a reference distance transit node on the obstacle map (S1450); determining a plurality of third transit nodes from the current node to the reference distance transit node on the obstacle map (S1460); determining a plurality of fourth transit nodes from the reference distance transit node to the docking node on the obstacle map (S1470); and generating a docking path using the determined third transit node and fourth transit node (S1480). Specific details regarding the path generation method will be described later.

[0219] The details regarding the acquisition of the obstacle map, the selection of the current node and berthing node on the obstacle map, the determination of the current bow direction from the current node and the berthing bow direction from the berthing node, the determination of the reference distance, and the generation of the berthing path using the waypoint node have been described above, so a redundant explanation is omitted.

[0220] The determination of the reference distance via node on the obstacle map is explained with reference to Fig. 18.

[0221] FIG. 18 is a diagram illustrating a method for determining a reference distance via node according to one embodiment.

[0222] Referring to FIG. 15, the method for determining a reference distance passing node is a method for determining a reference distance passing node (1580) which is one of the reference distance nodes (1550) on an obstacle map (1500). Specifically, the reference distance passing node (1280) can be determined by considering at least one of the location of a berthing node (1520) on the obstacle map (1500), the berthing bow direction (1530), the reference distance (1540), the berthing threshold angle (1560), and information about the vessel.

[0223] The berthing critical angle (1560) refers to a critical angle for minimizing the change of course of the vessel within a reference distance from the berthing position.

[0224] The berthing threshold angle (1560) can be determined by considering at least one of information about the vessel and information about the port. For example, if the vessel's steering performance is high, the berthing threshold angle (1560) may be large, and if the vessel's steering performance is low, the berthing threshold angle (1560) may be small. Meanwhile, the smaller the vessel's turning radius, the larger the berthing threshold angle (1560), and the larger the turning radius, the smaller the berthing threshold angle (1560). Meanwhile, the shorter the length of the berthing facility, the larger the berthing threshold angle (1560), and the longer the length of the berthing facility, the smaller the berthing threshold angle (1560). Meanwhile, the berthing threshold angle (1560) may be determined to be 0 degrees.

[0225] For example, one of the reference distance nodes (1550) located within the berthing threshold angle range (1570) based on a line extending from the berthing node (1520) in the berthing bow direction (1530) or in the opposite direction of the berthing bow direction (1530) can be determined as the reference distance passing node (1580). It is not limited thereto, and a reference distance node (1550) located on a line extending from the berthing node (1520) in the berthing bow direction (1530) or in the opposite direction of the berthing bow direction (1530) can also be determined as the reference distance passing node (1580).

[0226] Referring to FIG. 18, a reference distance forward direction (1590) may be assigned to a determined reference distance via node (1580). The reference distance forward direction (1590) refers to the expected forward direction at the reference distance via node (1580) and may be determined by considering at least one of the location of the reference distance via node (1580), the location of the berthing node (1520), the berthing forward direction (1530), the reference distance (1540), the berthing threshold angle (1560), and information about the vessel.

[0227] For example, the reference distance forward direction (1590) may be determined as the direction from the reference distance transit node (1580) toward the docking node (1520). It is not limited to this, and the reference distance forward direction (1590) may be determined such that the difference from the docking forward direction (1530) is within the docking threshold angle (1560).

[0228] If a reference distance node (1550) on a line extending from the docking node (1520) in the docking bow direction (1530) or in the opposite direction of the docking bow direction (1530) is determined as the reference distance passing node (1580), the reference distance bow direction (1590) may be the same as the docking bow direction (1530).

[0229] The determination of multiple third way nodes from the current node to the reference distance way node on the obstacle map and the determination of multiple fourth way nodes from the reference distance way node to the docking node on the obstacle map will be explained with reference to FIG. 19.

[0230] FIG. 19 is a diagram showing each node on an obstacle map and the generated landing path according to one embodiment.

[0231] As the meanings of the current node, docking node, transit node, and reference distance transit node have been explained above, a redundant explanation is omitted.

[0232] A method for determining a way node may be used to determine a way node on an obstacle map (1600). A method for determining a way node according to one example may include a third way node determination method and a fourth way node determination method.

[0233] The third way node determination method is a method for determining multiple third way nodes (1640) from the current node (1610) to the reference distance way node (1630) by considering the location of the current node (1610), the current forward direction (1670), the location of the reference distance way node (1630), and the reference distance forward direction (1680).

[0234] Specifically, the third way nodes (1640) can be determined using a third way node determination method such that the expected direction of the third way node (1640) to be assigned to the reference distance way node (1630) matches the reference distance way node (1680).

[0235] To this end, the third way node determination method can also determine the expected direction of the lead at each of the determined third way nodes (1640). Although not shown in FIG. 19, the determined expected direction of the lead can be assigned to the corresponding way nodes.

[0236] Meanwhile, the third transit node (1240) can be determined by considering the maximum turning angle of the vessel. Specifically, the third transit node (1640) immediately following the current node (1610) can be determined from among nodes within the maximum turning angle based on the current bow direction (1670).

[0237] As described above, an expected heading direction is assigned to each of the determined third way nodes (1640). The subsequent third way node immediately following the determined third way node (1640) can be determined from among nodes within the maximum turning angle based on the expected heading direction assigned to the determined third way node (1640). Since details regarding the maximum turning angle have been described above, a redundant explanation is omitted.

[0238] Although not illustrated in FIG. 19, the third transit node determination method may determine the third transit node (1640) by considering the score assigned to each node of the obstacle map (1600) described above.

[0239] Specifically, the method for determining the third transit node may determine the third transit node by considering the score assigned to the subsequent third transit node when determining the subsequent third transit node immediately following the current node (1610) or the determined third transit node (1640). For example, among the preliminary subsequent third transit nodes, the node with the lowest score assigned to it may be determined as the subsequent third transit node.

[0240] Additionally, the third route node determination method may determine the third route node (1640) by considering the remaining distance to the reference distance route node (1630). Specifically, when determining the subsequent third route node immediately following the current node (1610) or the determined third route node (1640), the third route node determination method may determine the subsequent third route node such that the remaining distance from the subsequent third route node to the reference distance route node (1630) becomes smaller.

[0241] Additionally, the method for determining the third distance route node may determine the subsequent third route node immediately following the current node (1610) or the determined third route node (1640) by considering the difference between the expected direction of the next node to be assigned to the subsequent third route node and the reference distance direction of the next node (1680). For example, among the preliminary subsequent third route nodes, the node with the smallest difference between the expected direction of the next node to be assigned to the next node and the reference distance direction of the next node (1680) may be determined as the subsequent third route node.

[0242] Meanwhile, in FIG. 19, the third route nodes (1640) are determined such that there is a distance between the third route nodes (1640), but the third route nodes (1640) may be determined continuously from the current node (1610) to the reference distance route node (1630).

[0243] A third transit node determination method according to one embodiment can be implemented based on a 3D A* algorithm.

[0244] Specifically, in the 3D A* algorithm, the cost function considered is f=g+h, where g(n) and h(n) can be defined as follows.

[0245] g(n)=ω m *C m (n)+ ω c *C c (n)

[0246] h(n)=ω d *C d (n)+ω b *C b (n)

[0247] At this time, n represents the sequence number of the third transit node, and at the current node, n can be 0.

[0248] Meanwhile, ω m , ω c , ω d and ω b is C m , Cc , C d and C b These are the weight values ​​for each.

[0249] C m is a score assigned to each node of the obstacle map, intended to consider locations safe from obstacles. C c is the change in angle to the next node based on the current or expected heading in radians, and is intended to reflect the vessel's limited maneuverability. C d is the remaining distance from the intermediate node to the reference distance intermediate node, and represents the heuristic value. C b is the difference between the expected player direction in radians at the transit node and the reference distance player direction, and is intended to minimize the difference between the expected player direction and the reference distance player direction.

[0250] Using the cost function described above, a third transit node from the current node to the reference distance transit node can be determined.

[0251] The method for determining the fourth route node is a method for determining a plurality of fourth route nodes (1650) from the reference distance route node (1630) to the berthing node (1620) by considering the location of the reference distance route node (1630), the reference distance forward direction (1680), the location of the berthing node (1620), and the berthing forward direction (1690).

[0252] Specifically, the fourth way nodes (1640) can be determined using the fourth way node determination method such that the expected bow direction to be assigned to the fourth way node (1640) corresponding to the docking node (1630) matches the docking bow direction (1680).

[0253] To this end, the method for determining the fourth way node can also determine the expected direction of the lead at each of the determined fourth way nodes (1650). Although not shown in FIG. 19, the determined expected direction of the lead can be assigned to the corresponding way node.

[0254] Meanwhile, the method for determining the fourth way node can determine the fourth way node (1650) by considering the maximum turning angle of the vessel, the score assigned to each node of the obstacle map (1600), the remaining distance to the arrival position, which is the berthing position (1620), and the direction at the arrival position, which is the berthing bow direction (1690), just like the method for determining the third way node described above. Since the specific method has been explained in the method for determining the third way node, a redundant explanation is omitted.

[0255] A fourth transit node determination method according to one embodiment can be implemented based on a 3D A* algorithm.

[0256] Specifically, the cost function of the fourth transit node determination method may be the same as the cost function in the third transit node determination method.

[0257] However, if there is a difference between the cost function of the 4th via node determination method and the cost function of the 3rd via node determination method, C in the cost function of the 4th via node determination method d represents the remaining distance from the transit node to the docking node, and C b represents the difference between the expected heading direction in radians at the transit node and the docking heading direction.

[0258] The fourth transit node (1650) from the reference distance transit node (1630) to the docking node (1620) can be determined using the cost function described above.

[0259] Referring to FIG. 19, the docking path (1660) from the current node (1610) to the docking node (1620) can be generated using the determined third transit node (1640) and the determined fourth transit node (1650).

[0260] Specifically, the path generation device can generate a docking path (1660) by sequentially connecting the determined third way nodes (1640) from the current node (1610) on the obstacle map (1600) to the reference distance way node (1630), and sequentially connecting the determined fourth way nodes (1650) from the reference distance way node (1630) to the docking node (1620). It is not limited thereto, and the path generation device may select some way nodes suitable for navigation among the determined third way nodes (1640) and fourth way nodes (1650), and generate a docking path using the selected way nodes. In generating the path, the path generation device may consider the heading direction assigned to each node.

[0261] Meanwhile, the path generation device may generate a path by calculating an approximation curve for a waypoint node. Specifically, the path generation device may calculate a first approximation curve passing through the current node and the reference distance waypoint node by considering the current bow direction and the reference distance bow direction, and may calculate a second approximation curve passing through the reference distance waypoint node and the berthing node by considering the reference distance bow direction and the berthing bow direction, and may generate a berthing path using the first and second approximation curves. The degree of approximation of the approximation curve for the waypoint node may be determined based on information about the vessel.

[0262] Meanwhile, if the path generation device cannot determine the via nodes satisfying the above conditions using the above-described via node determination method due to the presence of obstacles within the reference distance range, etc., the path generation device may output a result indicating that it cannot generate a path.

[0263] 5. Path Following Control

[0264] Path-following control refers to generating ship control signals to enable a ship to operate along a generated path. For example, ship control signals can be generated by a ship navigation device.

[0265] FIG. 20 is a flowchart of a path following control method according to one embodiment.

[0266] Referring to FIG. 20, a path-following control method according to an embodiment of the present invention may be performed by the process of generating a first path at a first time point (S1710), generating a first ship control signal using the first path (S1720), generating a second path at a second time point later than the first time point (S1730), and generating a second ship control signal using the second path (S1740). Specific details regarding path-following control will be described later.

[0267] Regarding the generation of the first path and the generation of the first control signal at the first time point, the details will be explained with reference to FIG. 21.

[0268] FIG. 21 is a diagram illustrating path following control according to one embodiment.

[0269] Referring to FIG. 21, a first approach path (1830) can be generated using an obstacle map (1800) to perform a path-following control method. Specifically, the obstacle map (1800) may be an obstacle map obtained at a first time point, or an obstacle map obtained prior to the first time point.

[0270] A first current node (1810) corresponding to the current position at the first point in time on the obstacle map (1800) can be selected, and a docking node (1860) corresponding to the docking position can also be selected.

[0271] Subsequently, a first path (1830) can be generated using the path generation method described above. As the specific method for generating a docking path has been described above, a redundant explanation is omitted.

[0272] After a first path is generated at a first time point, a first control signal may be generated to enable the vessel to operate along the first path. The first control signal may include a first vessel direction control signal and / or a first vessel speed control signal.

[0273] The first control signal can be generated by taking into account the current heading (1820) assigned to the current node (1810) so that, for any one of the subsequent passing nodes (1840) after the current node (1810) belonging to the generated first path (1830), the heading when the actual vessel is located at the subsequent passing node (1840) can be as closely matched as possible with the expected heading (1850) assigned to the subsequent passing node.

[0274] That is, the first control signal can be generated by taking into account the current node (1810) and the current bow direction (1820) corresponding to the current position of the vessel on the generated first path (1830), at least one subsequent way node (1840) for the current node, and the expected bow direction (1850) assigned to the subsequent way node.

[0275] Specifically, the first control signal may be generated by taking into account the difference between the current heading (1820) assigned to the current node (1810) and the expected heading (1850) assigned to the subsequent transit node (1840). By taking into account that difference, a first ship direction control signal, which is a control signal for adjusting the ship's rudder or steering wheel, may be generated.

[0276] Meanwhile, the first ship speed control signal, which is a control signal for controlling the propeller rotation speed or rotational speed per unit time of the ship or controlling the output of the engine, can be generated by considering at least one of the current speed of the ship, the difference between the current bow direction (1820) and the expected bow direction (1850), the current steering performance of the ship, the direction and strength of the current current, and the current wind direction and wind speed.

[0277] The ship direction control signal and the ship speed control signal can be generated independently of each other. That is, the ship direction control signal can be generated regardless of the value of the ship speed control signal, and the ship speed control signal can be generated regardless of the value of the ship direction control signal.

[0278] This is not limited to this, and the ship direction control signal may also be generated by considering the value of the ship speed control signal. The ship speed control signal may also be generated by considering the value of the ship direction control signal. In other words, ship direction control and ship speed control may influence each other.

[0279] Meanwhile, the control signal may be generated using an artificial neural network trained to receive data regarding the ship's status and surrounding environment, such as the distance from the current node to the subsequent transit node and the difference in bow direction, and to output a ship direction control signal or a ship speed control signal.

[0280] An artificial neural network is a type of algorithm modeled after the structure of the human nervous system. It can include one or more layers containing one or more nodes or neurons, and each node can be connected through synapses. Data input into an artificial neural network can pass through nodes via synapses to become output data, through which information can be obtained.

[0281] Types of artificial neural networks include convolutional neural networks (CNNs) that extract features using filters and recurrent neural networks (RNNs) that have a structure where the output of a node is fed back as input. In addition to these, there are various other types such as restricted Boltzmann machines (RBMs), deep belief networks (DBNs), generative adversarial networks (GANs), and relational networks (RNs).

[0282] Other path following may be performed using path following algorithms. For example, algorithms such as model predictive control (MPC), pure pursuit, Stanley method, and vector pursuit, which are techniques for generating optimal control signals by receiving the location to be followed for an arbitrary time T from the current time point for path following, can be used.

[0283] Meanwhile, to perform the path following control method, a second path may be generated at a second time point, which is a time point after the first time point. The time interval between the second time point and the first time point may be a predetermined time interval. For example, the time interval may be set to 150ms to 250ms.

[0284] Regarding the generation of the second path and the generation of the second control signal at the second time point, the explanation will be given with reference to FIG. 22.

[0285] FIG. 22 is a diagram illustrating path following control according to one embodiment.

[0286] Referring to FIG. 22, a second approach path (1930) can be generated using an obstacle map (1900) to perform a path following control method.

[0287] Specifically, the obstacle map (1900) may be an obstacle map obtained at a second time point, or an obstacle map obtained at a first time point, or an obstacle map obtained at an earlier time point.

[0288] A second current node (1910) corresponding to the current position at the second point in time on the obstacle map may be selected, and a docking node (1960) corresponding to the docking position may also be selected. In this case, the docking node (1960) may be the same docking node (1860) selected at the first point in time, or a new docking node (1960) may be selected at the second point in time.

[0289] Subsequently, a second path (1930) can be generated using the path generation method described above. The generated second path (1930) may be identical to the first path (1830), or there may be differences between them.

[0290] Referring to FIG. 22, the generated second path (1930) may be different from the first path (1830) of FIG. 21.

[0291] Specifically, if there is a change in the obstacle map, for example, a change in the location or condition of the obstacle, or if the vessel fails to follow the first path between the first and second points in time due to external forces and navigational limits, the second path (1930) may differ from the first path (1830). This is not limited to this, and a second path (1930) different from the first path (1830) may also be generated due to other internal or external factors.

[0292] After the second path is generated at the second time point, a second control signal may be generated to enable the vessel to navigate along the second path. As details regarding the generation of the control signal have been described above, a redundant explanation is omitted.

[0293] The above-described path-following control method can be repeated up to the nth time point to enable the vessel to dock at the docking facility.

[0294] FIG. 23 is a flowchart of a ship docking method using path-following control according to one embodiment.

[0295] Referring to FIG. 23, a method for docking a ship using path-following control according to one embodiment of the present invention may be performed by the process of generating a path using an obstacle map (S2010), generating a control signal based on the generated path (S2020), and repeating the generation of the path and the generation of the control signal (S2030) depending on whether the ship has arrived at the docking position. Since details regarding the generation of the path and the generation of the control signal have been described above, a redundant explanation is omitted.

[0296] Meanwhile, path generation can be performed by a path generation device, and control signal generation can be generated by a ship navigation device. If the path generation device is located outside the ship, the ship navigation device may receive information regarding the berthing path and each node from the path generation device to generate ship control signals.

[0297] The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program instructions, data files, data structures, etc., either alone or in combination. The program instructions recorded on the medium may be those specifically designed and configured for the embodiment, or they may be those known and available to those skilled in the art of computer software. Examples of computer-readable recording media include magnetic media such as hard disks, floppy disks, and magnetic tapes; optical recording media such as CD-ROMs and DVDs; magneto-optical media such as floptical disks; and hardware devices specifically configured to store and execute program instructions, such as ROM, RAM, and flash memory. Examples of program instructions include machine code, such as that generated by a compiler, as well as high-level language code that can be executed by a computer using an interpreter, etc. The hardware devices described above may be configured to operate as one or more software modules to perform the operation of the embodiment, and vice versa.

[0298] The present invention described above is not limited by the embodiments and attached drawings, as various substitutions, modifications, and changes are possible within the scope of the technical concept of the invention to those skilled in the art without departing from the spirit of the invention. Furthermore, the embodiments described in this document are not limited to specific applications, and all or part of each embodiment may be selectively combined to allow for various modifications. Moreover, the steps constituting each embodiment may be used individually or in combination with the steps constituting other embodiments. Explanation of the symbols

[0299] 10 Anchor Guide System 100 Path Generation Device 200 sensor modules 300 external servers 400 ship navigation devices

Claims

Claim 1 A method for generating a berthing path for a vessel comprises: acquiring an obstacle map including a plurality of nodes corresponding to positions on the sea; selecting a current node corresponding to the current position of the vessel on the obstacle map and a berthing node corresponding to the berthing position; determining the current bow direction of the vessel at the current node; determining the berthing bow direction of the vessel at the berthing node; determining a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of the berthing facility; determining a reference distance passing node spaced apart from the berthing node by the reference distance based on the determined reference distance; generating a first berthing path from the current node to the reference distance passing node—wherein, a first expected berthing path cost function is applied, and the first expected berthing path cost function includes at least a term considering the current bow direction—; generating a second berthing path from the reference distance passing node to the berthing node—wherein, a second expected berthing path cost function different from the first expected berthing path cost function A method for generating a docking path, comprising: applying, wherein the second expected docking path cost function includes at least a term considering the docking forward direction; and generating the docking path to include first transit nodes passing along the first docking path and second transit nodes passing along the second docking path; wherein an expected forward direction is determined and assigned to each of the first transit nodes and the second transit nodes, i) the difference between the docking forward direction and ii) the expected forward direction is considered with greater weight in the second expected docking path cost function than in the first expected docking path cost function. Claim 2 A method for generating an abutment path according to claim 1, wherein the reference distance passing node is one of the reference distance nodes corresponding to a position located at a distance from the abutment node by the reference distance. Claim 3 A method for generating a docking path according to paragraph 2, wherein the reference distance passing node is a node among the reference distance nodes located at a position that is separated by the reference distance from the docking node in the direction of the docking bow or in the opposite direction of the docking bow. Claim 4 A method for generating an abutment path according to claim 1, wherein in the second expected abutment path cost function, the weight for the difference between i) the abutment forward direction and ii) the expected forward direction assigned to each of the second transit nodes is greater than the weight for the difference between i) the abutment forward direction and ii) the expected forward direction assigned to each of the first transit nodes in the first expected abutment path cost function. Claim 5 A method for generating a berthing path according to claim 1, wherein the term considering the berthing bow direction is a term considering the difference between i) the berthing bow direction and ii) the expected bow direction assigned to each of the second transit nodes. Claim 6 A method for generating a berthing path according to claim 1, wherein the obstacle map is assigned a score based on the operational safety of the vessel for each of the plurality of nodes, and at least the first expected berthing path cost function includes a term that considers the score. Claim 7 A method for generating a berthing path according to claim 1, wherein at least the first transit nodes are determined by determining the current speed of the vessel and calculating the maximum turning angle of the vessel based on the current speed, and at least the first expected berthing path cost function includes a term that considers the maximum turning angle. Claim 8 A device for generating a berthing path for a vessel, comprising: a memory storing information about the vessel, information about a port, and a method for determining a transit node; and at least one processor; wherein the processor acquires an obstacle map comprising a plurality of nodes corresponding to positions at sea, selects a current node corresponding to the current position of the vessel and a berthing node corresponding to the berthing position on the obstacle map, determines the current bow direction of the vessel at the current node, determines the berthing bow direction of the vessel at the berthing node, determines a reference distance by considering at least one of the length of the vessel, the width of the vessel, the weight of the vessel, the steering performance of the vessel, and the length of the berthing facility, and determines a reference distance passing node spaced apart from the berthing node by the reference distance based on the determined reference distance, and generates a first berthing path from the current node to the reference distance passing node - wherein a first expected berthing path cost function is applied, and the first expected berthing path cost function includes at least a term considering the current bow direction; generates a second berthing path from the reference distance passing node to the berthing node - wherein a second expected berthing path cost function different from the first expected berthing path cost function A docking path generating device that applies, wherein the second expected docking path cost function includes at least a term considering the docking forward direction; and generates the docking path to include first transit nodes passing along the first docking path and second transit nodes passing along the second docking path, wherein an expected forward direction is determined and assigned to each of the first transit nodes and the second transit nodes, i) the difference between the docking forward direction and ii) the expected forward direction is considered with a greater weight in the second expected docking path cost function than in the first expected docking path cost function. Claim 9 In claim 8, the above reference distance passing node is one of the reference distance nodes corresponding to a position located at a distance from the above docking node by the above reference distance, a docking path generating device. Claim 10 A docking path generating device according to claim 9, wherein the reference distance passing node is a node among the reference distance nodes located at a position that is separated by the reference distance from the docking node in the direction of the docking bow or in the opposite direction of the docking bow. Claim 11 In claim 8, the weight for the difference between i) the berthing forward direction and ii) the expected forward direction assigned to each of the second transit nodes in the second expected berthing path cost function is greater than the weight for the difference between i) the berthing forward direction and ii) the expected forward direction assigned to each of the first transit nodes in the first expected berthing path cost function. Claim 12 A berthing path generating device according to claim 8, wherein the term considering the berthing bow direction is a term considering the difference between i) the berthing bow direction and ii) the expected bow direction assigned to each of the second transit nodes. Claim 13 A berthing path generating device according to claim 8, wherein the obstacle map is assigned a score based on the operational safety of the vessel for each of the plurality of nodes, and at least the first expected berthing path cost function includes a term that considers the score. Claim 14 A berthing path generating device according to claim 8, wherein the processor, at least the first transit nodes determine the current speed of the vessel and calculate the maximum turning angle of the vessel based on the current speed, and at least the first expected berthing path cost function includes a term that considers the maximum turning angle. Claim 15 A computer-readable non-transient recording medium storing a method for generating an appoint path, wherein the method for generating an appoint path is a recording medium that is a method for generating an appoint path according to claim 1.

Citation Information

Patent Citations

  • Navigation device and route creation method

    JP2020008443A

  • Path planning method using obstacle map

    KR1020200027871A

  • Method for providing route of vessel

    KR102031151B1