Self-adaptive identification method for navigation scene of autonomous ship in port water area based on electronic chart

Abstract

The invention provides an electronic chart-based autonomous ship port water area navigation scene adaptive identification method. The method comprises the steps of performing system classification on port water area navigation scenes; loading an electronic chart, extracting objects in a hierarchical structure, and screening objects for assisting in distinguishing the navigation scene of the port water area according to the object identification codes; analyzing sea chart objects, and constructing a geometric model comprising port boundaries, channel lines and berth static objects; and acquiring longitude and latitude, ship speed and course information of the ship in the AIS data, and realizing port water area scene real-time identification in combination with a geometric model of a static object. According to the method, the electronic chart can be read in real time, and multi-dimensional scene judgment is carried out by combining ship dynamic parameters (navigational speed, course, longitude and latitude and the like). Therefore, the navigation environment to which the current ship belongs can be efficiently and accurately identified, and powerful support is provided for an autonomous navigation system of an intelligent ship.

Description

Technical Field

[0001] The present invention relates to the technical field of maritime traffic management, and in particular to a method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts. Background Art

[0002] Port waters, as a critical link between open waters and port nodes, present a dynamic and ever-changing navigation environment. During navigation, MASS (Maritime Autonomous Surface Ships) must dynamically adjust the type and accuracy of sensory information based on the different navigation scenarios, and adopt different navigation decision-making modes according to different scenarios. During remote monitoring, shore-based centers also need to provide relevant maritime service information based on different scenarios. However, the unmanned or low-staff nature of MASS makes it impossible to rely on traditional manual methods to determine the current navigation scenario.

[0003] In this context, the present invention develops an adaptive recognition method for autonomous ship navigation scenes in port waters based on electronic nautical charts, which enables autonomous ships to judge their navigation scenes in real time when sailing in port waters, providing a reliable environmental perception basis for the autonomous navigation of MASS. Summary of the Invention

[0004] In response to the technical problems raised above, a method for adaptively identifying navigation scenes in port waters for autonomous ships based on electronic nautical charts is provided. The present invention analyzes the S-57 standard nautical chart data to construct geometric models of static objects such as port boundaries, channel lines, and berths. It then designs multi-dimensional judgment rules based on ship dynamic parameters (speed, heading, longitude and latitude, etc.) to achieve accurate classification and real-time recognition of port water scenes. The proposed method constructs a judgment system covering eight types of scenes, which can quickly and accurately identify the current navigation scene in port waters, enhancing the adaptability of MASS to complex port environments and providing a reliable environmental perception foundation for MASS's autonomous navigation.

[0005] The technical means adopted in the present invention are as follows:

[0006] A method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts, comprising:

[0007] S1. Systematically classify navigation scenarios in port waters

[0008] S2. Load the electronic nautical chart, extract the objects in a hierarchical structure, and select the objects that assist in identifying the navigation scene in the port waters according to the object identification codes;

[0009] S3. Analyze nautical chart objects and construct a geometric model of static objects including port boundaries, channel lines, and berths;

[0010] S4. Obtain the latitude and longitude, speed, and heading information of the ship from the AIS data, and combine it with the geometric model of static objects to achieve real-time recognition of port water scenes.

[0011] Furthermore, step S1 specifically includes:

[0012] S11. Set the actual navigation route of the ship in the port waters, from berthing and unberthing, to navigation in the channel, and then to crossing the anchorage and entering the sea area;

[0013] S12. Based on the actual navigation routes of ships in port waters, the navigation scenarios are divided into eight categories: berthing, unberthing, entering the port, leaving the port, channel navigation, entering the anchorage, leaving the anchorage, and anchoring.

[0014] Furthermore, step S2 specifically includes:

[0015] The original electronic chart file is read in a hierarchical structure, and each layer is identified by a unique object code, representing a collection of the same type of objects.

[0016] Furthermore, step S3 specifically includes:

[0017] S31. Based on the analysis results of the electronic chart, the chart is divided into point objects, linear objects and surface objects. Linear objects and surface objects are abstracted into discrete object point sets as follows:

[0018]

[0019] Where t represents the number of object points on the boundary of the object;

[0020] S32. Map the latitude and longitude coordinates of the object point to a rectangular coordinate system according to the Mercator projection. The specific formula is as follows:

[0021] X n =K(L-L0)

[0022]

[0023]

[0024] Among them, X n Y is the horizontal coordinate of the object point plane; n is the vertical coordinate of the object point; L0 is the central meridian; B is the latitude, L is the longitude; a is the length of the Earth's semi-major axis; b is the length of the Earth's semi-minor axis; e is the Earth's first eccentricity; N is the radius of curvature of the eccentric circle;

[0025] S33, set a circular search circle, calculate the distance from the ship P0 (X,, Y,) to each point (X i ,Y i ,) the distance d i, the calculation formula is as follows:

[0026]

[0027] S34, if the ship P0 (X, Y) to each point (X i ,Y i ) distance d i If the search radius is less than 5 nautical miles, the azimuth information of the characteristic object to which the feature point belongs is extracted, and the distance between the characteristic object and the ship is calculated. The final object to be searched is determined based on the nearest principle, and the navigation scene to which the ship belongs is determined based on the object and the ship's AIS dynamic navigation information.

[0028] Furthermore, step S34 specifically includes:

[0029] S341: When entering or leaving a port, retrieve the surface-shaped harbor landmarks and determine the navigation scenario to which the ship belongs based on the harbor landmarks and the ship's AIS dynamic navigation information;

[0030] S342: When navigating the waterway, a linear Fairway object is retrieved, and the navigation scene to which the ship belongs is determined based on the Fairway object and the ship's AIS dynamic navigation information;

[0031] S343, when the vessel is at anchor or entering or leaving an anchorage, the surface-shaped Anchorage, Area object is retrieved as the anchorage boundary line, and the navigation scene of the vessel is determined based on the Anchorage, Area object and the vessel's AIS dynamic navigation information;

[0032] S344: When the vessel is berthing or unberthing, it retrieves a Berth object of surface type and determines the navigation scene to which the vessel belongs based on the Berth object and the vessel's AIS dynamic navigation information.

[0033] Furthermore, step S341 specifically includes:

[0034] S3411, let the point on the port area boundary be (x n ,y n ), create a polygon vertex set as follows:

[0035]

[0036] Where M represents the number of object points on the boundary;

[0037] S3412. Using the ray method, determine whether the ship is inside the polygonal port area as follows:

[0038]

[0039] Among them, x0, y0 represent the coordinates of the ship's latitude and longitude mapped to the rectangular coordinate system through Mercator projection transformation; When , it indicates that the ship is inside the polygon; when When , it indicates that the ship is outside the polygon;

[0040] S3413. Use the vector relationship between the ship and the polygon centroid to determine whether the ship enters or leaves the polygon, as follows:

[0041] S3414, take one vertex of the polygon as the origin, connect all non-adjacent vertices, divide the original n-gon into (n-2) triangles, and let the centroid of one of the triangles be O i ,(x i ,y i ,), the vertex coordinates are A1(x a ,y a ), A2(x b ,y b ), A3(x c ,y c ), then:

[0042]

[0043] Among them, s1 represents the area of ​​a triangle;

[0044] S3415, the center of mass coordinates of the polygon is obtained from the area formula of the triangle s1 as O(O x ,O y ), the formula is as follows:

[0045]

[0046] S3416, according to the obtained coordinates of the center of mass of the polygon O (O x ,O y ), and the ship coordinate P0(x0,y0) form the ship-center of mass vector With velocity vector Perform the product:

[0047]

[0048] When T1>0, it indicates that the ship is entering the polygon and the navigation state is entering the port; when T1<0, it indicates that the ship is leaving the polygon and the navigation state is leaving the port; when T1=0, it indicates that the speed vector and ship-centroid vector Vertically, select the ship's position and speed at two other moments and repeat the center of mass method process to ensure the accuracy of the judgment.

[0049] Furthermore, step S342 specifically includes:

[0050] S3421. When navigating a waterway, a linear Fairway feature can be retrieved, representing the waterway centerline. It is composed of the discrete point set formula:

[0051]

[0052] S3422, search for the nearest landmark point of the ship in the search circle, calculate the distance between the ship and the center line of the channel, and the current position of the ship is P(x o ,y o ), the closest distance is d min , the calculation formula is as follows:

[0053]

[0054] When d min When it is less than half of the channel width, it means that the ship is inside the channel, i.e. W represents the channel width, which is obtained by reading the additional fields of the chart attributes.

[0055] Furthermore, step S343 specifically includes:

[0056] S3431. As the ship's speed at anchor approaches zero, a speed threshold is set. The formula is as follows:

[0057]

[0058] Where N = 60, indicating a time window of 1 minute;

[0059] S3432: The ship's position remains relatively stable when anchored. Define the maximum drift radius R of the ship. d and location variance constraints as follows:

[0060]

[0061] As shown in the above formula, when the ship is located within the anchorage area and the speed is less than 0.5 knots, the drift radius R d <20 meters, position variance constraint When the ship is at anchor,

[0062] S3433. Since the anchorage is a polygonal area in the electronic nautical chart, the judgment method for ships entering and leaving the anchorage is similar to that for ships entering and leaving the port. First, the geometric area of ​​the anchorage is extracted according to the electronic nautical chart, and the ray method formula is used to determine whether the position of the ship is within the anchorage polygon. That is, when When the vessel is in the anchorage; when When the vessel is outside the anchorage;

[0063] S3434. Use the centroid method to determine the ship's entry and exit direction. The centroid method formula is as follows:

[0064]

[0065] When T1>0, the ship is entering the anchorage; when T1<0, the ship is leaving the anchorage.

[0066] Furthermore, step S344 specifically includes:

[0067] S3441. When a ship finds a berth within the search circle, it determines the ship's position P0 (x0, y0), and uses the centroid method to calculate the position of the berth area's centroid P1 (x1, y1), and obtains the ship's velocity vector and berth vector The vector product formula of the two is as follows:

[0068]

[0069] Where T2 represents the inner product of the velocity vector and the berth vector. T2>0 indicates that the ship is approaching the berth area; T2<0 indicates that the ship is moving away from the berth area.

[0070] S3442. To impose safety distance constraints on berthing and unberthing operations, assume that the point set within the berth is:

[0071] {(x k ,y k )} 1≤k≤M

[0072] Let d2 be the distance between the ship and the nearest point of the berth, and the safety distance constraint formula is:

[0073]

[0074] When d2>50 and T2>0, it is determined that the ship is performing berthing operations; when d2<50 and T2<0, it is determined that the ship is performing unberthing operations.

[0075] Compared with the prior art, the present invention has the following advantages:

[0076] 1. The present invention provides an adaptive recognition method for autonomous ship port navigation scenarios based on electronic nautical charts. The method has comprehensive scenario coverage, analyzes the actual navigation scenarios of ships entering and leaving the port, constructs a port landmark model based on electronic nautical charts, and accurately judges eight types of scenarios, including entering and leaving the port.

[0077] 2. The present invention provides an adaptive recognition method for autonomous ship port water navigation scenes based on electronic nautical charts. Compared with traditional ship navigation scene recognition models, the proposed model has more comprehensive discrimination factors. It constructs a geometric model of static objects such as port boundaries, channel lines, and berths, and designs multi-dimensional judgment rules based on ship dynamic parameters (speed, heading, longitude and latitude, etc.), realizing accurate classification and real-time recognition of port water scenes.

[0078] 3. The present invention provides an adaptive recognition method for autonomous ship port water navigation scenes based on electronic nautical charts. By accurately identifying the navigation environment, it effectively improves the MASS's autonomous perception and recognition capabilities of the current navigation environment, providing reliable geographic information support for the autonomous navigation system.

[0079] Based on the above reasons, the present invention can be widely promoted in fields such as marine ship transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0080] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0081] Figure 1 Flow chart of the method of the present invention.

[0082] Figure 2 Schematic diagram of the centroid method for solving the centroid of a surface object.

[0083] Figure 3 This is a diagram showing the correspondence between the object code and the specific object.

[0084] Figure 4 Schematic diagram of various ship navigation scenarios provided by embodiments of the present invention.

[0085] Figure 5 This is a schematic diagram of the ship entry and exit scenario judgment principle provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0086] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0087] It should be noted that the terms "including" and "having" and any variations thereof in the specification and claims of the present invention and the above-mentioned drawings are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products or apparatuses.

[0088] like Figure 1 As shown, the present invention provides a method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts, comprising:

[0089] S1. Systematically classify navigation scenarios in port waters

[0090] S2. Load the electronic nautical chart, extract the objects in a hierarchical structure, and select the objects that assist in identifying the navigation scene in the port waters according to the object identification codes;

[0091] S3. Analyze nautical chart objects and construct a geometric model of static objects including port boundaries, channel lines, and berths;

[0092] S4. Obtain the latitude and longitude, speed, and heading information of the ship from the AIS data, and combine it with the geometric model of static objects to achieve real-time recognition of port water scenes.

[0093] In specific implementation, as a preferred embodiment of the present invention, step S1 specifically includes:

[0094] S11. Set the actual navigation route of the ship in the port waters, from berthing and unberthing, to navigation in the channel, and then to crossing the anchorage and entering the sea area;

[0095] S12. Based on the actual navigation routes of ships in the port waters, the navigation scenarios are divided into eight categories: berthing, unberthing, entering the port, leaving the port, channel navigation, entering the anchorage, leaving the anchorage, and anchoring. Figure 2 shown.

[0096] In specific implementation, as a preferred embodiment of the present invention, step S2 specifically includes:

[0097] The original electronic chart file is read in a hierarchical structure. Each layer is identified by a unique object code, which represents a collection of the same object. The code is as follows: Figure 3 shown.

[0098] In specific implementation, as a preferred embodiment of the present invention, step S3 specifically includes:

[0099] S31. Based on the analysis results of the electronic chart, the chart is divided into point objects, linear objects and surface objects. Linear objects and surface objects are abstracted into discrete object point sets as follows:

[0100]

[0101] Where t represents the number of object points on the boundary of the object;

[0102] S32. Map the latitude and longitude coordinates of the object point to a rectangular coordinate system according to the Mercator projection. The specific formula is as follows:

[0103] X n =K(L-L0)

[0104]

[0105] Among them, X n Y is the horizontal coordinate of the object point plane; n is the vertical coordinate of the object point; L0 is the central meridian; B is the latitude, L is the longitude; a is the length of the Earth's semi-major axis; b is the length of the Earth's semi-minor axis; e is the Earth's first eccentricity; N is the radius of curvature of the eccentric circle;

[0106] S33, set a circular search circle, calculate the distance from the ship P0 (X,, Y,) to each point (X i ,Y i ,) the distance d i , the calculation formula is as follows:

[0107]

[0108] S34, if the ship P0 (X, Y) to each point (X i ,Y i ) distance d i If the search radius is less than 5 nautical miles, the azimuth information of the characteristic object to which the feature point belongs is extracted, and the distance between the characteristic object and the ship is calculated. The final object to be searched is determined based on the nearest principle, and the navigation scene to which the ship belongs is determined based on the object and the ship's AIS dynamic navigation information.

[0109] In specific implementation, as a preferred embodiment of the present invention, step S34 specifically includes:

[0110] S341: When entering or leaving a port, retrieve the surface-shaped harbor landmarks and determine the navigation scenario to which the ship belongs based on the harbor landmarks and the ship's AIS dynamic navigation information;

[0111] S342: When navigating the waterway, a linear Fairway object is retrieved, and the navigation scene to which the ship belongs is determined based on the Fairway object and the ship's AIS dynamic navigation information;

[0112] S343, when the vessel is at anchor or entering or leaving an anchorage, the surface-shaped Anchorage, Area object is retrieved as the anchorage boundary line, and the navigation scene of the vessel is determined based on the Anchorage, Area object and the vessel's AIS dynamic navigation information;

[0113] S344: When the vessel is berthing or unberthing, it retrieves a Berth object of surface type and determines the navigation scene to which the vessel belongs based on the Berth object and the vessel's AIS dynamic navigation information.

[0114] In specific implementation, as a preferred embodiment of the present invention, step S341 specifically includes:

[0115] S3411, let the point on the port area boundary be (x n ,y n ), create a polygon vertex set as follows:

[0116]

[0117] Where M represents the number of object points on the boundary;

[0118] S3412. Using the ray method, determine whether the ship is inside the polygonal port area as follows:

[0119]

[0120] Among them, x0, y0 represent the coordinates of the ship's latitude and longitude mapped to the rectangular coordinate system through Mercator projection transformation; When , it indicates that the ship is inside the polygon; when When , it indicates that the ship is outside the polygon;

[0121] S3413. Use the vector relationship between the ship and the polygon centroid to determine whether the ship enters or leaves the polygon. The schematic diagram is as follows Figure 4 As shown, the details are as follows:

[0122] S3414, take one vertex of the polygon as the origin, connect all non-adjacent vertices, divide the original n-gon into (n-2) triangles, and let the centroid of one of the triangles be O i ,(x i ,y i ,), the vertex coordinates are A1(x a ,y a ), A2(x b ,y b ), A3(x c ,y c ), then:

[0123]

[0124] Among them, s1 represents the area of ​​a triangle;

[0125] S3415, the center of mass coordinates of the polygon is obtained from the area formula of the triangle s1 as O(O x ,O y ), the formula is as follows:

[0126]

[0127] S3416, according to the obtained coordinates of the center of mass of the polygon O (O x ,O y ), and the ship coordinate P0(x0,y0) form the ship-center of mass vector With velocity vector Perform the product:

[0128]

[0129] When T1>0, it indicates that the ship is entering the polygon and the navigation state is entering the port; when T1<0, it indicates that the ship is leaving the polygon and the navigation state is leaving the port; when T1=0, it indicates that the speed vector and ship-centroid vector Vertically, select the ship's position and speed at two other moments and repeat the center of mass method process to ensure the accuracy of the judgment.

[0130] In specific implementation, as a preferred embodiment of the present invention, step S342 specifically includes:

[0131] S3421. When navigating a waterway, a linear Fairway feature can be retrieved, representing the waterway centerline. It is composed of the discrete point set formula:

[0132]

[0133] S3422, search for the nearest landmark point of the ship in the search circle, calculate the distance between the ship and the center line of the channel, and the current position of the ship is P(x o ,y o ), the closest distance is d min , the calculation formula is as follows:

[0134]

[0135] When d min When it is less than half of the channel width, it means that the ship is inside the channel, i.e. W represents the channel width, which is obtained by reading the additional fields of the chart attributes.

[0136] In specific implementation, as a preferred embodiment of the present invention, step S343 specifically includes:

[0137] S3431. As the ship's speed at anchor approaches zero, a speed threshold is set. The formula is as follows:

[0138]

[0139] Where N = 60, indicating a time window of 1 minute;

[0140] S3432: The ship's position remains relatively stable when anchored. Define the maximum drift radius R of the ship. d and location variance constraints as follows:

[0141]

[0142] As shown in the above formula, when the ship is located within the anchorage area and the speed is less than 0.5 knots, the drift radius R d <20 meters, position variance constraint When the ship is at anchor,

[0143] S3433. Since the anchorage is a polygonal area in the electronic nautical chart, the judgment method for ships entering and leaving the anchorage is similar to that for ships entering and leaving the port. First, the geometric area of ​​the anchorage is extracted according to the electronic nautical chart, and the ray method formula is used to determine whether the position of the ship is within the anchorage polygon. That is, when When the vessel is in the anchorage; when When the vessel is outside the anchorage;

[0144] S3434. Use the centroid method to determine the ship's entry and exit direction. The centroid method formula is as follows:

[0145]

[0146] When T1>0, the ship is entering the anchorage; when T1<0, the ship is leaving the anchorage.

[0147] In specific implementation, as a preferred embodiment of the present invention, step S344 specifically includes:

[0148] S3441. When a ship finds a berth within the search circle, it determines the ship's position P0 (x0, y0), and uses the centroid method to calculate the position of the berth area's centroid P1 (x1, y1), and obtains the ship's velocity vector and berth vector The vector product formula of the two is as follows:

[0149]

[0150] Where T2 represents the inner product of the velocity vector and the berth vector. T2>0 indicates that the ship is approaching the berth area; T2<0 indicates that the ship is moving away from the berth area.

[0151] S3442. Since berthing and unberthing operations are relatively delicate, safety distance constraints are required. Let the point set within the berth be:

[0152] {(x k ,y k )} 1≤k≤M

[0153] Let d2 be the distance between the ship and the nearest point of the berth, and the safety distance constraint formula is:

[0154]

[0155] When d2>50, T2>0, it is determined that the ship is berthing. When d2<50, T2<0, it is determined that the ship is leaving the berthing. The schematic diagram is as follows Figure 5 shown.

[0156] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts, characterized in that: include: S1. Systematically classify navigation scenarios in port waters; S2. Load the electronic nautical chart, extract the objects in a hierarchical structure, and select the objects that assist in identifying the navigation scene in the port waters according to the object identification codes; S3. Analyze nautical chart objects and construct a geometric model of static objects including port boundaries, channel lines, and berths; S4. Obtain the latitude and longitude, speed, and heading information of the ship from the AIS data, and combine it with the geometric model of static objects to achieve real-time recognition of port water scenes.

2. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 1, characterized in that: Step S1 specifically includes: S11. Set the actual navigation route of the ship in the port waters, from berthing and unberthing, to navigation in the channel, and then to crossing the anchorage and entering the sea area; S12. Based on the actual navigation routes of ships in port waters, the navigation scenarios are divided into eight categories: berthing, unberthing, entering the port, leaving the port, channel navigation, entering the anchorage, leaving the anchorage, and anchoring.

3. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 1 is characterized in that: Step S2 specifically includes: The original electronic chart file is read in a hierarchical structure, and each layer is identified by a unique object code, indicating a collection of the same type of objects.

4. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 1 is characterized in that: Step S3 specifically includes: S31. Based on the analysis results of the electronic chart, the chart is divided into point objects, linear objects and surface objects. Linear objects and surface objects are abstracted into discrete object point sets as follows: Where t represents the number of object points on the boundary of the object; S32. Map the latitude and longitude coordinates of the object point to the rectangular coordinate system according to the Mercator projection. The specific formula is as follows: X n =K(L-L0) Among them, X n Y is the horizontal coordinate of the object point plane; n is the vertical coordinate of the object point; L0 is the central meridian; B is the latitude, L is the longitude; a is the length of the Earth's semi-major axis; b is the length of the Earth's semi-minor axis; e is the Earth's first eccentricity; N is the radius of curvature of the eccentric circle; S33, set a circular search circle, calculate the distance from the ship P0 (X,, Y,) to each point (X i ,Y i ,) the distance d i , the calculation formula is as follows: S34, if the ship P0 (X, Y) to each point (X i ,Y i ) distance d i If the search radius is less than 5 nautical miles, the azimuth information of the characteristic object to which the feature point belongs is extracted, and the distance between the characteristic object and the ship is calculated. The final object to be searched is determined based on the nearest principle, and the navigation scene to which the ship belongs is determined based on the object and the ship's AIS dynamic navigation information.

5. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 4 is characterized in that: Step S34 specifically includes: S341: When entering or leaving a port, retrieve the surface-shaped harbor landmarks and determine the navigation scenario to which the ship belongs based on the harbor landmarks and the ship's AIS dynamic navigation information; S342: When navigating the waterway, a linear Fairway object is retrieved, and the navigation scene to which the ship belongs is determined based on the Fairway object and the ship's AIS dynamic navigation information; S343, when the vessel is at anchor or entering or leaving an anchorage, the surface-shaped Anchorage, Area object is retrieved as the anchorage boundary line, and the navigation scene of the vessel is determined based on the Anchorage, Area object and the vessel's AIS dynamic navigation information; S344: When the vessel is berthing or unberthing, it retrieves a Berth object of surface type and determines the navigation scene of the vessel based on the Berth object and the vessel's AIS dynamic navigation information.

6. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 5 is characterized in that: Step S341 specifically includes: S3411, let the point on the port area boundary be (x n ,y n ), create a polygon vertex set as follows: Where M represents the number of object points on the boundary; S3412. Using the ray method, determine whether the ship is inside the polygonal port area as follows: Among them, x0, y0 represent the coordinates of the ship's latitude and longitude mapped to the rectangular coordinate system through Mercator projection transformation; When , it indicates that the ship is inside the polygon; when When , it indicates that the ship is outside the polygon; S3413. Use the vector relationship between the ship and the polygon centroid to determine whether the ship enters or leaves the polygon, as follows: S3414, take one vertex of the polygon as the origin, connect all non-adjacent vertices, divide the original n-gon into (n-2) triangles, and let the centroid of one of the triangles be O i ,(x i ,y i ,), the vertex coordinates are A1(x a ,y a ), A2(x b ,y b ), S3(x c ,y c ), then: Among them, s1 represents the area of ​​a triangle; S3415, the center of mass coordinates of the polygon is obtained from the area formula a1 of the triangle as O(O x ,O y ), the formula is as follows: S3416, according to the obtained coordinates of the center of mass of the polygon O (O x ,O y ), and the ship coordinate P0(x0,y0) form the ship-center of mass vector With velocity vector Perform the product: When T1>0, it indicates that the ship is entering the polygon and the navigation state is entering the port; when T1<0, it indicates that the ship is leaving the polygon and the navigation state is leaving the port; when T1=0, it indicates that the speed vector and ship-centroid vector Vertically, select the ship's position and speed at two other moments and repeat the center of mass method process to ensure the accuracy of the judgment.

7. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 5 is characterized in that: Step S342 specifically includes: S3421. When navigating a waterway, a linear Fairway feature can be retrieved, representing the waterway centerline. It is composed of the discrete point set formula: S3422, search for the nearest landmark point of the ship in the search circle, calculate the distance between the ship and the center line of the channel, and the current position of the ship is P(x o ,y o ), the closest distance is d min , the calculation formula is as follows: When d min When it is less than half of the channel width, it means that the ship is inside the channel, i.e. W represents the channel width, which is obtained by reading the additional fields of the chart attributes.

8. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 5 is characterized in that: Step S343 specifically includes: S3431. As the ship's speed at anchor approaches zero, a speed threshold is set. The formula is as follows: Where N = 60, indicating a time window of 1 minute; S3432: The ship's position remains relatively stable when anchored. Define the maximum drift radius R of the ship. d and location variance constraints as follows: As shown in the above formula, when the ship is located within the anchorage area and the speed is less than 0.5 knots, the drift radius R d <20 meters, position variance constraint When the ship is at anchor, S3433. Extract the geometric area of ​​the anchorage based on the electronic chart and use the ray method formula to determine whether the ship's position is within the anchorage polygon. When the vessel is in the anchorage; when When the vessel is outside the anchorage; S3434. Use the centroid method to determine the ship's entry and exit direction. The centroid method formula is as follows: When T1>0, the ship is entering the anchorage; when T1<0, the ship is leaving the anchorage.

9. The method for adaptively identifying navigation scenes of autonomous ships in port waters based on electronic nautical charts according to claim 5 is characterized in that: Step S344 specifically includes: S3441. When a ship finds a berth within the search circle, it determines the ship's position P0 (x0, y0), and uses the centroid method to calculate the position of the berth area's centroid P1 (x1, y1), and obtains the ship's velocity vector and berth vector The vector product formula of the two is as follows: Where T2 represents the inner product of the velocity vector and the berth vector. T2>0 indicates that the ship is approaching the berth area; T2<0 indicates that the ship is moving away from the berth area. S3442. To impose safety distance constraints on berthing and unberthing operations, assume that the point set within the berth is: {(x k ,and k )} 1≤k≤M Let d2 be the distance between the ship and the nearest point of the berth, and the safety distance constraint formula is: When d2>50, t2>0, it is determined that the ship is performing berthing operations; when d2<50, T2<0, it is determined that the ship is performing unberthing operations.

Images