Ship route planning method

Abstract

The invention relates to a ship route planning method, and belongs to the technical field of path planning, and the method comprises the steps: S101, obtaining ship navigation starting point, terminal point and navigation sea area information, and constructing a random tree based on the starting point, the navigation sea area information comprising navigable sea areas, non-navigable sea areas and wind field information; s102, selecting a sampling point from the navigation sea area information, and selecting an adjacent point closest to the sampling point from the random tree; s103, calculating resultant force of the end point, the sampling point, the unnavigable sea area and the wind field to the adjacent points, and expanding the random tree to generate new nodes based on the direction of the resultant force; and S104, judging whether the distance between the new node and the terminal point is smaller than a threshold value or not, if so, outputting an optimal route, and if not, returning to S102. By introducing the artificial potential field method, the expansion direction of the random tree is adjusted and controlled in real time, and the convergence speed of the algorithm and the quality of the optimal solution are improved.

Description

Technical Field

[0001] The present application relates to the technical field of path planning, and in particular to a ship route planning method. Background Art

[0002] As one of the most important modes of transportation in global trade, sea transportation accounts for about 90% of global cargo transportation. As an essential tool for sea transportation, ships will encounter various complex environments and emergencies, leading to ship accidents. Therefore, ensuring the safety of ship transportation has become one of the focuses of the shipping industry. The high-risk areas for ocean-going ships mainly include areas with high risk of marine disasters. In order to improve the navigation safety level of ocean-going ships, it is urgent to carry out route planning research in high-risk areas. In the prior art, the commonly used methods for ship route planning mainly include the RRT* algorithm. The RRT* algorithm is based on the sampling principle, is suitable for high and complex environments, can quickly generate feasible paths, and has probabilistic completeness, fewer algorithm parameters, and a simple structure.

[0003] However, the RRT* algorithm is highly random, and the convergence speed of ship route planning using the RRT* algorithm is slow and it is easy to fall into the local optimal solution. Summary of the invention

[0004] In view of this, it is necessary to provide a ship route planning method to solve the problems in the prior art that the RRT* algorithm for planning ship routes has slow convergence speed and is prone to falling into local optimal solutions.

[0005] In order to solve the above problems, the present application provides a ship route planning method, comprising: S101, obtaining the starting point, end point and navigation area information of the ship, and constructing a random tree based on the starting point, wherein the navigation area information includes navigable sea area, non-navigable sea area and wind field information; S102, selecting a sampling point from the navigation area information, and selecting a neighboring point closest to the sampling point from the random tree; S103, calculating the resultant force of the end point, the sampling point, the unnavigable sea area and the wind field on the adjacent point, and based on the direction of the resultant force, expanding the random tree to generate a new node; S104, determining whether the distance between the new node and the end point is less than a threshold, if so, outputting the optimal route, if not, returning to S102.

[0006] In some possible implementations, selecting a sampling point from the navigation area information includes: Obtain random sampling probability and target bias probability, and determine whether the random sampling probability is greater than the target bias probability; If the random sampling probability is greater than the target bias probability, a random point is selected from the navigation area information, and the random point is used as a sampling point; If the random sampling probability is not greater than the target bias probability, the end point is used as the sampling point.

[0007] In some possible implementations, the target bias probability is calculated as follows:

[0008] In the formula, represents the target bias probability, Represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters. represents the probability adjustment factor, represents the initial target bias probability, Indicates the preset safe distance between the node and the unnavigable sea area. Indicates the closest Euclidean distance between the neighboring point and the unnavigable area.

[0009] In some possible implementations, the non-navigable area includes an obstacle area and a high-risk area.

[0010] In some possible implementations, the calculation formula for the resultant force is:

[0011]

[0012]

[0013]

[0014]

[0015]

[0016]

[0017]

[0018] In the formula, represents the net force on the adjacent points, represents the gravitational force on the neighboring point, represents the gravitational force of the end point on the adjacent point, represents the neighboring points, Indicates the end point, represents the distance threshold of the gravity function, and represents the gravitational gain, represents the gravitational force of the sampling point on the neighboring points, represents the sampling point, represents the repulsive force on the neighboring point, represents the repulsive force of the obstacle area on the neighboring points, represents the point in the obstacle area, and represents the repulsion gain, and represents the distance threshold of the repulsion function, represents the repulsion of the high-risk area to the neighboring points, represents points in the high-risk area, Represents wind force.

[0019] In some possible implementations, based on the direction of the resultant force, expanding the random tree to generate a new node includes: based on the direction of the resultant force, expanding the random tree by a step size to generate a new node; The calculation formula of the step length is:

[0020] In the formula, Indicates The step length of times, Indicates The step length of the represents the initial expansion step length, represents the step size adjustment factor, Represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters.

[0021] In some possible implementations, based on the direction of the resultant force, the random tree is expanded to generate a new node, including: Based on the combined force, determining an expansion direction, expanding the expansion node in the expansion direction to generate a new node, and determining whether the new node collides with the non-navigable sea area; If the new node does not collide with the unnavigable sea area, inserting the new node into the random tree; If the new node collides with the unnavigable sea area, a modification direction is calculated based on the resultant force and the unnavigable sea area information, the extended node is extended in the modification direction to generate an updated new node, and the updated new node is inserted into the random tree.

[0022] In some possible implementations, determining an expansion direction based on the combined force includes: Determining whether the resultant force is zero; If the resultant force is zero, the direction of the neighboring point pointing to the expansion node is taken as the expansion direction; If the resultant force is not zero, the direction of the resultant force is taken as the expansion direction.

[0023] In some possible implementations, calculating the modified direction based on the resultant force and the unnavigable sea area information includes: Determine the midpoint of the new node and the adjacent point, calculate the length of the line segment between the new node and the midpoint, use the length of the line segment between the new node and the midpoint as the major axis value, calculate the minor axis value, and determine an ellipse with the midpoint as the center based on the major axis value and the minor axis value; The short axis endpoint closest to the end point is selected from the ellipse, and the direction in which the adjacent point points to the short axis endpoint is used as the modification direction.

[0024] In some possible implementations, the calculation formula for the short axis value is:

[0025] In the formula, Indicates The minor axis value, Indicates The minor axis value, is the adjustment factor of the minor axis, represents the new node before updating, Indicates neighboring points.

[0026] The beneficial effects of the present application are as follows: the ship route planning method provided by the present application introduces the artificial potential field method, integrates the wind field environment of the navigation area, and adopts the real-time adjustment method of the expansion direction to control the expansion direction of the random tree, so as to overcome the deficiency of blind expansion of the RRT* algorithm and improve the slow convergence speed of the algorithm and the quality of the optimal solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 A schematic diagram of an embodiment of a ship route planning method provided in this application; Figure 2 For this application Figure 1 A schematic flow chart of an embodiment of step S102; Figure 3 A schematic diagram of the combined forces provided for this application; Figure 4 For this application Figure 1 A schematic flow chart of an embodiment of step S103; Figure 5 For this application Figure 4A schematic flow chart of an embodiment of step S401; Figure 6 A schematic diagram of the modification direction provided for this application; Figure 7 For this application Figure 4 A flowchart of an embodiment of step S403 in FIG. DETAILED DESCRIPTION

[0028] The technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0029] It should be understood that the schematic drawings are not drawn to scale. The flowcharts used in this application illustrate operations implemented according to some embodiments of the present application. It should be understood that the operations of the flowcharts may be implemented out of order, and steps without logical contextual relationships may be reversed in order or implemented simultaneously. In addition, those skilled in the art may add one or more other operations to the flowcharts, or may remove one or more operations from the flowcharts, under the guidance of the content of this application. Some of the block diagrams shown in the accompanying drawings are functional entities, and do not necessarily correspond to physically or logically independent entities. These functional entities may be implemented in software form, or implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor systems and / or microcontroller systems.

[0030] The descriptions of "first", "second", etc. involved in the embodiments of the present application are only used to describe the implicit purpose, and cannot be understood as indicating or implying their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the technical features defined as "first" and "second" may explicitly or implicitly include at least one of the features. "And / or" describes the association relationship of the associated objects, indicating that three relationships may exist, for example: A and / or B, which can represent: A exists alone, A and B exist at the same time, and B exists alone.

[0031] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0032] The present application provides a method for ship route planning, which is described below.

[0033] Figure 1 A schematic diagram of an embodiment of the ship route planning method provided in this application is as follows: Figure 1 As shown, the ship route planning method includes: S101, obtaining the starting point, end point and navigation area information of the ship, and constructing a random tree based on the starting point. The navigation area information includes navigable sea area, non-navigable sea area and wind field information; It should be noted that the RRT* algorithm is specifically used to construct the extended random tree.

[0034] S102, selecting a sampling point from the navigation area information, and selecting a neighboring point closest to the sampling point from the random tree; S103, calculating the resultant force of the end point, the sampling point, the unnavigable sea area and the wind field on the adjacent points, and based on the direction of the resultant force, expanding the random tree to generate a new node; It should be noted that the artificial potential field method is specifically used to calculate gravity.

[0035] S104, determine whether the distance between the new node and the end point is less than a threshold, if so, output the optimal route, if not, return to S102.

[0036] Compared with the prior art, this application introduces an artificial potential field method, integrates the wind field environment of the navigation area, and adopts a real-time adjustment method of the expansion direction to control the expansion direction of the random tree, so as to overcome the shortcomings of the blind expansion of the RRT* algorithm and improve the slow convergence speed of the algorithm and the quality of the optimal solution.

[0037] In order to reduce the number of sampling points, in some embodiments, a variable probability target bias strategy is introduced to guide the generation of random sampling points. Specifically, Figure 2 As shown, in step S102, sampling points are selected from the navigation area information, including: S201, obtaining a random sampling probability and a target bias probability, and determining whether the random sampling probability is greater than the target bias probability; It should be noted that the calculation formula for the target bias probability is:

[0038] In the formula, represents the target bias probability, Represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters. represents the probability adjustment factor, represents the initial target bias probability, Indicates the preset safe distance between the node and the unnavigable sea area. Indicates the closest Euclidean distance between the neighboring point and the unnavigable area.

[0039] S202: If the random sampling probability is greater than the target bias probability, a random point is selected from the navigation area information and the random point is used as a sampling point; S203: If the random sampling probability is not greater than the target bias probability, the end point is used as the sampling point.

[0040] It should be noted that when using the above method, first, set the initial value of the target bias probability. When expanding in the target direction, if the new node does not collide with the unnavigable area, the target bias probability value is gradually increased to enhance the search capability in the target direction. If the new node collides with the unnavigable area, obstacle avoidance is required, the target bias probability value should be reduced, and the target bias probability value needs to be reset to enhance the random sampling capability and avoid obstacles.

[0041] In order to better calculate the resultant force, in some embodiments, the non-navigable area includes an obstacle area and a high-risk area, and the resultant force on the adjacent points is as follows: Figure 3 As shown, Figure 3 middle, represents the sampling point, represents the neighboring points, Indicates the end point, Indicates the obstacle area. Indicates high-risk areas. represents the net force on the adjacent points, represents the gravitational force of the end point on the adjacent point, represents the gravitational force of the sampling point on the neighboring points, represents the repulsive force of the obstacle area on the neighboring points, represents the repulsion of the high-risk area to the neighboring points, Indicates wind field.

[0042] Correspondingly, the formula for calculating the resultant force is:

[0043]

[0044]

[0045]

[0046]

[0047]

[0048]

[0049]

[0050] In the formula, represents the net force on the adjacent points, represents the gravitational force on the neighboring point, represents the gravitational force of the end point on the adjacent point, represents the neighboring points, Indicates the end point, represents the distance threshold of the gravity function, and represents the gravitational gain, represents the gravitational force of the sampling point on the neighboring points, represents the sampling point, represents the repulsive force on the neighboring point, represents the repulsive force of the obstacle area on the neighboring points, represents the point in the obstacle area, and represents the repulsion gain, and represents the distance threshold of the repulsion function, represents the repulsion of the high-risk area to the neighboring points, represents points in the high-risk area, Represents wind force.

[0051] In order to improve the convergence speed of the algorithm, in some embodiments, an adaptive dynamic step size update function is designed to adjust the expansion amplitude of the random tree in real time. The calculation formula of the step size is:

[0052] In the formula, Indicates The step length of the Indicates The step length of the represents the initial expansion step length, represents the step size adjustment factor, Represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters.

[0053] It should be noted that when using the above method, the initial step size is first used for searching. When searching for a new node for the first time, if the tree does not encounter an obstacle, the step size of the next step will be increased on the original basis and accumulated in subsequent searches. When an obstacle is encountered during the expansion process, the expansion step size will be reset to reduce the probability of collision, reduce the blindness of the expansion, and speed up the expansion speed.

[0054] In order to improve the quality of the optimal solution, in some embodiments, a node update function is introduced in the collision detection. If a collision occurs, a new node is generated to replace it. Specifically, Figure 4 As shown, in step S103, based on the direction of the resultant force, the random tree is expanded to generate a new node, including: S401, based on the combined force, determine the expansion direction, expand the expansion node in the expansion direction to generate a new node, and determine whether the new node collides with the unnavigable sea area; S402, if the new node does not collide with the unnavigable sea area, insert the new node into the random tree; S403: If the new node collides with the unnavigable sea area, a modification direction is calculated based on the resultant force and the unnavigable sea area information, the extended node is extended in the modification direction to generate an updated new node, and the updated new node is inserted into the random tree.

[0055] In order to better expand based on the combined force, in some embodiments, such as Figure 5 As shown, in step S401, determining the expansion direction based on the resultant force includes: S501, determining whether the resultant force is zero; S502, if the resultant force is zero, the direction of the neighboring point pointing to the expansion node is used as the expansion direction; S503. If the resultant force is not zero, the direction of the resultant force is used as the expansion direction.

[0056] In order to determine a better modification direction, in some embodiments, the modification direction is as follows: Figure 6 As shown, Indicates the starting point, represents the neighboring points, represents the new node before updating, Indicate point and Point The midpoint of express and Point The perpendicular bisector of the line segment between Indicates non-navigable waters. Represents the new node after the update.

[0057] Correspondingly, such as Figure 7 As shown, in step S403, the modification direction is calculated based on the resultant force and the non-navigable sea area information, including: S701, determining the midpoint of the new node and the adjacent point, calculating the length of the line segment between the new node and the midpoint, taking the length of the line segment between the new node and the midpoint as the major axis value, calculating the minor axis value, and determining an ellipse with the midpoint as the center based on the major axis value and the minor axis value; It should be noted that the calculation formula for the short axis value is:

[0058] In the formula, Indicates The minor axis value, Indicates The minor axis value, is the adjustment factor of the minor axis, represents the new node before updating, Indicates neighboring points.

[0059] S702: Select the short axis endpoint closest to the end point from the ellipse, and use the direction in which the adjacent point points to the short axis endpoint as the modification direction.

[0060] The above is a detailed introduction to a ship route planning method provided by the present application. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea; at the same time, for technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0061] The above is only a preferred specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by any technician familiar with the technical field within the technical scope disclosed in the present application should be covered within the protection scope of the present application.

Claims

1. A ship route planning method, characterized in that: include: S101, obtaining the starting point, end point and navigation area information of the ship, and constructing a random tree based on the starting point, wherein the navigation area information includes navigable sea area, non-navigable sea area and wind field information; S102, selecting a sampling point from the navigation area information, and selecting a neighboring point closest to the sampling point from the random tree; S103, calculating the resultant force of the end point, the sampling point, the unnavigable sea area and the wind field on the adjacent point, and based on the direction of the resultant force, expanding the random tree to generate a new node; S104, determining whether the distance between the new node and the end point is less than a threshold, if so, outputting the optimal route, if not, returning to S102.

2. The ship route planning method according to claim 1, characterized in that: Selecting sampling points from the navigation area information includes: Obtain random sampling probability and target bias probability, and determine whether the random sampling probability is greater than the target bias probability; If the random sampling probability is greater than the target bias probability, a random point is selected from the navigation area information, and the random point is used as a sampling point; If the random sampling probability is not greater than the target bias probability, the end point is used as the sampling point.

3. The ship route planning method according to claim 2, characterized in that: The calculation formula of the target bias probability is: In the formula, represents the target bias probability, represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters. represents the probability adjustment factor, represents the initial target bias probability, Indicates the preset safe distance between the node and the unnavigable sea area. Indicates the closest Euclidean distance between the neighboring point and the unnavigable area.

4. The ship route planning method according to claim 1, characterized in that: The non-navigable areas include obstacle areas and high-risk areas.

5. The ship route planning method according to claim 4, characterized in that: The calculation formula of the resultant force is: In the formula, represents the net force on the adjacent points, represents the gravitational force on the neighboring point, represents the gravitational force of the end point on the adjacent point, represents the neighboring points, Indicates the end point, represents the distance threshold of the gravity function, and represents the gravitational gain, represents the gravitational force of the sampling point on the neighboring points, represents the sampling point, represents the repulsive force on the neighboring point, represents the repulsive force of the obstacle area on the neighboring points, represents the point in the obstacle area, and represents the repulsion gain, and represents the distance threshold of the repulsion function, represents a constant, represents the repulsion of the high-risk area to the neighboring points, represents points in the high-risk area, Represents wind force.

6. The ship route planning method according to claim 1, characterized in that: Based on the direction of the resultant force, the random tree is expanded to generate a new node, including: based on the direction of the resultant force, the random tree is expanded by a step length to generate a new node; The calculation formula of the step length is: In the formula, Indicates The step length of times, Indicates The step length of times, represents the initial expansion step length, represents the step size adjustment factor, represents a new node, represents the neighboring points, represents the vector between the new node and its neighboring points, Indicates non-navigable waters.

7. The ship route planning method according to claim 1, characterized in that: Based on the direction of the combined force, the random tree is expanded to generate new nodes, including: Based on the combined force, determining an expansion direction, expanding the expansion node in the expansion direction to generate a new node, and determining whether the new node collides with the non-navigable sea area; If the new node does not collide with the unnavigable sea area, inserting the new node into the random tree; If the new node collides with the unnavigable sea area, a modification direction is calculated based on the resultant force and the unnavigable sea area information, the extended node is extended in the modification direction to generate an updated new node, and the updated new node is inserted into the random tree.

8. The ship route planning method according to claim 7, characterized in that: Based on the combined force, determine the expansion direction, including: determining whether the resultant force is zero; If the resultant force is zero, the direction of the neighboring point pointing to the expansion node is taken as the expansion direction; If the resultant force is not zero, the direction of the resultant force is taken as the expansion direction.

9. The ship route planning method according to claim 7, characterized in that: The modification direction is calculated based on the resultant force and the unnavigable sea area information, including: Determine the midpoint of the new node and the adjacent point, calculate the length of the line segment between the new node and the midpoint, use the length of the line segment between the new node and the midpoint as the major axis value, calculate the minor axis value, and determine an ellipse with the midpoint as the center based on the major axis value and the minor axis value; The short axis endpoint closest to the end point is selected from the ellipse, and the direction in which the neighboring point points to the short axis endpoint is used as the modification direction.

10. The ship route planning method according to claim 9, characterized in that: The calculation formula of the short axis value is: In the formula, Indicates The minor axis value, Indicates The minor axis value, represents the adjustment factor of the minor axis, represents the new node before updating, Indicates neighboring points.

Images