Bi-kmeans-based berthing planning auxiliary decision-making method

Abstract

The invention provides a berthing planning auxiliary decision-making method based on Bi-kmeans. The berthing planning auxiliary decision-making method comprises the following steps: collecting ship trajectory information by adopting binocular vision so as to construct a berthing trajectory database; when a berthing decision is executed, selecting a track set of which the end point is a specified berth from the track database, and clustering by adopting Bi-kmeans; and selecting a trajectory of which the starting point is closest to the current berthing starting point of the yacht from k trajectories formed in the centers of the k types of clusters to generate a recommended trajectory.

Description

Technical Field

[0001] The present invention belongs to the technical field of berthing planning, and in particular relates to a berthing planning auxiliary decision-making method based on Bi-kmeans. Background Art

[0002] With the rapid economic development and the continuous expansion of people's consumption demand, the marine economy has been rapidly developed. The yacht economy has become a focus of wide attention and concern. As a new growth point for the development of the marine economy, the yacht industry has entered a golden period of development and has a very broad development prospect. With the gradual warming of coastal tourism, the rapid development of the small and medium-sized yacht market has become a new hot spot. The pattern of the yacht industry has undergone new changes. The market share of small yachts has continued to increase, while the market share of large and luxury yachts has continued to decline. The yacht industry has shown a trend of mass consumption and promoted the sustainable development of the yacht economy. During the peak tourist season, yachts frequently enter and exit the dock. Many yacht docks are floating docks with dense berthing numbers. If you are not careful when docking or leaving the dock, it is easy to collide and damage the yacht, or even cause danger. Therefore, docking or leaving the dock is the most important step in yacht operation.

[0003] When berthing or leaving a pier, the yacht is in a low-speed sailing state, which is greatly affected by the wind flow around the pier, and the force on the yacht is relatively complex; the control of the yacht's movement and positioning is difficult, but the requirements are very high, which brings potential risks to berthing safety, and related maritime accidents occur from time to time. Therefore, yacht berthing planning is of great significance in ensuring navigation safety, providing convenient facilities, managing time, and improving navigation efficiency. Reasonable berthing planning can ensure the smooth sailing and docking of yachts, and improve the yacht experience and operational benefits.

[0004] At present, traditional berthing assistance decision-making only plans the location of the turning point of the track, and rarely plans the time and berthing speed. The traditional collection of ship tracks generally uses the ship automatic identification system (AIS), but the AIS system has a transmission delay, and its longitude and latitude are imported from GPS, etc., and the error of GPS can sometimes reach 100 meters, which is unacceptable for berthing. Summary of the invention

[0005] This paper mainly aims at the complex problem of yacht berthing, and is also applicable to the berthing of other types of ships. The present invention aims to provide a new berthing planning auxiliary decision-making method based on Bi-kmeans to improve the accuracy and reliability of berthing, which includes the following main design points:

[0006] (1) Use binocular vision to collect berthing trajectory data to improve accuracy;

[0007] (2) Using Bi-kmeans clustering;

[0008] (3) It not only plans the position of the trajectory turning point, but also plans the time and berthing speed, which is more perfect than the existing berthing decision-making scheme.

[0009] The technical solution specifically adopted by the present invention to solve the technical problem is:

[0010] A berthing planning auxiliary decision-making method based on Bi-kmeans uses binocular vision to collect vessel trajectory information to build a berthing trajectory database; when executing berthing decisions, a trajectory set with a terminal at a designated berth is selected from the trajectory database and clustered using Bi-kmeans; among the k trajectories formed by the centers of the k clusters, a trajectory with a starting point closest to the current berthing starting point of the yacht is selected to generate a recommended trajectory.

[0011] Furthermore, the method of collecting ship trajectory information using binocular vision is specifically as follows:

[0012] The bow position is the solution to the following system of equations:

[0013]

[0014] Where x a (t) is the horizontal coordinate of the first measurement point at time t, y a (t) is the ordinate of the first measurement point at time t; x b (t) is the horizontal coordinate of the second measurement point at time t, y b (t) is the ordinate of the second measurement point at time t; d 11 (t) is the distance from the first measurement point to the bow at time t, d 21 (t) is the distance from the second measuring point to the bow of the ship;

[0015] The stern position is the solution to the following system of equations:

[0016]

[0017] Where d 11 (t) is the distance from the first measurement point to the stern at time t, d 22 (t) is the distance from the second measurement point to the stern at time t;

[0018] The ship's bow direction at time t is:

[0019]

[0020] The speed of the ship in the forward direction at time t is:

[0021]

[0022] The transverse speed of the ship at time t is:

[0023]

[0024] The total speed of the ship at time t is:

[0025]

[0026] The trajectory state at time t is:

[0027] s(t)={t,x1(t),y1(t),x2(t),y2(t),ψ(t),v(t)} (7).

[0028] Furthermore, the trajectory database includes multiple trajectory information of multiple berths, and each trajectory information carries corresponding berth information.

[0029] Furthermore, when executing the berthing decision, according to the berth at which the vessel is currently going to berth, a trajectory set whose end point is the berth is selected from the trajectory database.

[0030] Furthermore, the implementation process of clustering using Bi-kmeans is as follows:

[0031] (1) All trajectories are considered as a cluster and the sum of squared errors (SSE) is calculated;

[0032] (2) Among all the current clusters, select the cluster with the largest SSE and divide it into two clusters using kmeans;

[0033] (3) Calculate the sum of all SSEs after the partition. If it is smaller than before, keep the partition; otherwise, cancel the partition.

[0034] (4) Repeat steps (2) and (3) until the predetermined number of clusters k is reached or the SSE cannot be further reduced.

[0035] Furthermore, after the Bi-kmeans clustering process, the k trajectories formed in the centers of the k clusters are selected, and the trajectory whose starting point is closest to the current berthing starting point of the yacht is selected; let the position set of the turning point be (P 1x ,P 1y ),(P 2x ,P 2y ),……,(P Nx ,P Ny ), the corresponding historical time is (t1, t2, …, t N );

[0036] Assuming that the starting time of the current yacht berthing is t0, the recommended trajectory is (t0, P 1x ,P 1y ),(t0+t2-t1,P 2x ,P 2y ),……,(t0+tN -t1,P Nx ,P Ny ).

[0037] And, a berthing planning auxiliary decision system based on Bi-kmeans, comprising: a trajectory database, which is constructed by collecting vessel trajectory information using binocular vision;

[0038] And, a decision module, when executing a berthing decision, is used to select a set of trajectories whose end point is a designated berth from the trajectory database, and cluster them using Bi-kmeans; among the k trajectories formed by the centers of the k clusters, a trajectory whose starting point is closest to the current berthing starting point of the yacht is selected to generate a recommended trajectory.

[0039] An electronic device comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein when the processor executes the program, the steps of the Bi-kmeans-based berthing planning auxiliary decision method as described above are implemented.

[0040] A non-transitory computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the Bi-kmeans-based berthing planning auxiliary decision-making method as described above.

[0041] Compared with the prior art, the present invention and its preferred solution adopt binocular vision to collect berthing trajectory data, thereby improving the accuracy of berthing trajectory collection; when making berthing planning decisions, the Bi-kmeans clustering solution is adopted, and the output result is better. Moreover, it not only plans the position of the trajectory turning point, but also realizes the planning time and berthing speed, which is more perfect than the existing berthing decision-making solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] The present invention is further described in detail below with reference to the accompanying drawings and specific embodiments:

[0043] Figure 1 This is a schematic diagram of a method flow chart of an embodiment of the present invention;

[0044] Figure 2 This is a schematic diagram of binocular ranging according to an embodiment of the present invention;

[0045] Figure 3 The following is a schematic diagram of a trajectory recommended by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] In order to make the features and advantages of this patent more obvious and easy to understand, the following embodiments are specifically described in detail as follows:

[0047] It should be noted that the following detailed descriptions are illustrative and are intended to provide further explanation of the present application. Unless otherwise specified, all technical and scientific terms used in this specification have the same meanings as those commonly understood by those skilled in the art to which the present application belongs.

[0048] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit the exemplary embodiments according to the present application. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that when the terms "comprise" and / or "include" are used in this specification, it indicates the presence of features, steps, operations, devices, components and / or combinations thereof.

[0049] like Figure 1 As shown, the method flow provided by the embodiment of the present invention includes the following steps:

[0050] First, binocular vision is used to collect historical trajectories and build a berthing trajectory database. Figure 2 The binocular ranging scheme of this embodiment is as follows:

[0051] The bow position is the solution to the following system of equations:

[0052]

[0053] Where x a (t) is the horizontal coordinate of the first measurement point at time t, y a (t) is the ordinate of the first measurement point at time t. b (t) is the horizontal coordinate of the second measurement point at time t, y b (t) is the ordinate of the second measurement point at time t. 11 (t) is the distance from the first measurement point to the bow at time t, d 21 (t) is the distance from the second measuring point to the bow of the ship.

[0054] The stern position is the solution to the following system of equations:

[0055]

[0056] Where d 11 (t) is the distance from the first measurement point to the stern at time t, d 22 (t) is the distance from the second measurement point to the stern at time t.

[0057] Then the ship's bow direction at time t is:

[0058]

[0059] The speed of the ship in the forward direction at time t is:

[0060]

[0061] The transverse speed of the ship at time t is:

[0062]

[0063] The total speed of the ship at time t is:

[0064]

[0065] The trajectory state at time t is:

[0066] s(t)={t,x1(t),y1(t),x2(t),y2(t),ψ(t),v(t)} (7)

[0067] This enables the precise acquisition of the ship's trajectory, and through the collection of a large amount of data, a berthing trajectory database is built as the basis for subsequent trajectory planning.

[0068] Then, for the berth where the yacht is currently going to berth, a trajectory set whose end point is the berth is selected from the trajectory database.

[0069] If kmeans is used to cluster the docking trajectories, there are problems such as it is difficult to determine the number of clusters k, it is easy to fall into the local optimal solution, and it is very sensitive to the choice of the initial cluster center.

[0070] Therefore, in this embodiment, Bi-kmeans is used to cluster the trajectory set, and the implementation process is as follows:

[0071] (1) Treat all trajectories as a cluster and calculate the sum of squared errors (SSE);

[0072] (2) Among all the current clusters, select the cluster with the largest SSE and divide it into two clusters using kmeans;

[0073] (3) Calculate the sum of all SSEs after the partition. If it is smaller than before, keep the partition; otherwise, cancel the partition.

[0074] (4) Repeat steps 2 and 3 until the predetermined number of clusters k is reached or the SSE cannot be further reduced.

[0075] After the above clustering process, among the k trajectories formed by the centers of the k clusters, the trajectory with the starting point closest to the current berthing point of the yacht is selected. Let the position set of its turning point be (P 1x ,P 1y ),(P 2x ,P 2y ),……,(P Nx ,P Ny), and its corresponding historical time is (t1, t2, …, t N ).

[0076] As a preferred solution of this embodiment, not only the position of the turning point of the trajectory is planned, but also the time and berthing speed are planned. Assuming that the starting time of the current yacht berthing is t0, the recommended trajectory is generated as (t0, P 1x ,P 1y ),(t0+t2-t1,P 2x ,P 2y ),……,(t0+t N -t1,P Nx ,P Ny ).

[0077] The following is a specific example to illustrate the implementation process of the data collection scheme of this scheme. Taking the yacht "Xiang Run Yun" as an example, its parameters are as follows:

[0078] Table 1 Main parameters of yacht "Xiang Run Yun"

[0079] MMSI 413546460 ship name Xiangrunyun Vessel length 10 meters Ship width 5 meters Call Sign MS1M

[0080] The berthing trajectory is collected using binocular vision, with the coordinates of measurement point A being (0,0) and the coordinates of measurement point B being (4m,0). The sample data for measuring the bow and stern positions are shown in the following table.

[0081] Table 2 Examples of binocular vision measurement of bow and stern positions

[0082]

[0083]

[0084] This enables the construction of a berthing trajectory database.

[0085] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment in combination with software and hardware. Moreover, the present application may adopt the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that include computer-usable program code.

[0086] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0087] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0088] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0089] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0090] The above is only a preferred embodiment of the present invention, and does not limit the present invention in other forms. Any technician familiar with the profession may use the above disclosed technical content to change or modify it into an equivalent embodiment with equivalent changes. However, any simple modification, equivalent change and modification made to the above embodiment according to the technical essence of the present invention without departing from the technical solution of the present invention still belongs to the protection scope of the technical solution of the present invention.

[0091] This patent is not limited to the above-mentioned optimal implementation mode. Anyone can derive other forms of Bi-kmeans-based berthing planning decision-making assistance methods under the inspiration of this patent. All equal changes and modifications made according to the scope of the patent application of the present invention should be covered by this patent.

Claims

1. A berthing planning decision-making aiding method based on Bi-kmeans, characterized by: Binocular vision is used to collect vessel trajectory information to build a berthing trajectory database. When executing berthing decisions, a trajectory set with the end point at the designated berth is selected from the trajectory database and clustered using Bi-kmeans. Among the k trajectories formed by the centers of k clusters, the trajectory with the starting point closest to the current berthing starting point of the yacht is selected to generate a recommended trajectory.

2. The berthing planning decision-making auxiliary method based on Bi-kmeans according to claim 1, characterized in that: The method of collecting ship trajectory information using binocular vision is specifically as follows: The bow position is the solution to the following system of equations: Where x a (t) is the horizontal coordinate of the first measurement point at time t, y a (t) is the ordinate of the first measurement point at time t; x b (t) is the horizontal coordinate of the second measurement point at time t, y b (t) is the ordinate of the second measurement point at time t; d 11 (t) is the distance from the first measurement point to the bow at time t, d 21 (t) is the distance from the second measuring point to the bow of the ship; The stern position is the solution to the following system of equations: Where d 11 (t) is the distance from the first measurement point to the stern at time t, d 22 (t) is the distance from the second measuring point to the stern at time t; the bow direction at time t is: The speed of the ship in the forward direction at time t is: The transverse speed of the ship at time t is: The total speed of the ship at time t is: The trajectory state at time t is: s(t)={t,x1(t),y1(t),x2(t),y2(t),ψ(t),v(t)} (7).

3. The berthing planning decision-making auxiliary method based on Bi-kmeans according to claim 1, characterized in that: The track database includes multiple track information of multiple berths, and each track information carries corresponding berth information.

4. The berthing planning decision-making auxiliary method based on Bi-kmeans according to claim 1, characterized in that: When executing the berthing decision, according to the berth that the ship currently intends to berth, a set of trajectories with the end point being the berth is selected from the trajectory database.

5. The berthing planning decision-making auxiliary method based on Bi-kmeans according to claim 1, characterized in that: The implementation process of clustering using Bi-kmeans is as follows: (1) All trajectories are considered as a cluster and the sum of squared errors (SSE) is calculated; (2) Among all the current clusters, select the cluster with the largest SSE and divide it into two clusters using kmeans; (3) Calculate the sum of all SSEs after the partition. If it is smaller than before, keep the partition; otherwise, cancel the partition. (4) Repeat steps (2) and (3) until the predetermined number of clusters k is reached or the SSE cannot be further reduced.

6. The berthing planning decision-making auxiliary method based on Bi-kmeans according to claim 1, characterized in that: After the Bi-kmeans clustering process, among the k trajectories formed by the centers of the k clusters, the trajectory whose starting point is closest to the current berthing starting point of the yacht is selected; let the position set of the turning point be (P 1x ,P 1y ),(P 2x ,P 2y ),……,(P Nx ,P Ny ), the corresponding historical time is (t1, t2, …, t N ); Assuming that the starting time of the current yacht berthing is t0, the recommended trajectory is (t0, P 1x ,P 1y ),(t0+t2-t1,P 2x ,P 2y ),……,(t0+t N -t1,P Nx ,P Ny ).

7. A berthing planning auxiliary decision system based on Bi-kmeans, characterized in that: include: The trajectory database is constructed by collecting the vessel trajectory information using binocular vision; And, a decision module, when executing a berthing decision, is used to select a set of trajectories whose end point is a designated berth from the trajectory database, and cluster them using Bi-kmeans; among the k trajectories formed by the centers of the k clusters, a trajectory whose starting point is closest to the current berthing starting point of the yacht is selected to generate a recommended trajectory.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the steps of the berthing planning auxiliary decision method based on Bi-kmeans are implemented as described in any one of claims 1 to 6.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the berthing planning auxiliary decision-making method based on Bi-kmeans are implemented as described in any one of claims 1 to 6.

Images