Unmanned ship multi-point rescue route planning method and system

Abstract

According to the unmanned ship multi-point rescue route planning method and system, a weighting coefficient algorithm based on a multi-index TOPSIS algorithm of a target distance, a target speed, an included angle between a target and a ship course, a target danger level and the like and a graph data model established according to the weighting coefficient algorithm are utilized, and the minimum value of a weighting route of the graph data model is calculated in real time; and the navigation path of the unmanned ship is planned in real time based on this. According to the method and the system, rapid and efficient rescue route planning can be provided for the unmanned ship, and the intelligent rescue efficiency of the unmanned ship is effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of path planning, and in particular to a concise and practical route planning method for an unmanned ship to perform a multi-point rescue mission. Background Art

[0002] As a new type of intelligent unmanned platform, when using unmanned ships for search and rescue missions, if multiple targets are found, the search and rescue will only be carried out in the order of the found targets without intelligent path planning, which will cause back and forth situations, greatly affecting the time and effect of the search and rescue. Therefore, when carrying out rescue missions for multiple targets, it is necessary to optimize the planning according to the target information, ship driving information and actual sea conditions.

[0003] The existing unmanned boat path planning is mostly related to the research on multi-unmanned area coverage path planning, and the simulation executes the work of performing area coverage path planning tasks with unmanned boats as the main body. The present invention aims to use unmanned boats to carry out water search and rescue tasks. Therefore, its purpose is to design an efficient path for the unmanned boat to quickly reach the objects that need rescue in the environmental map, thereby fully improving the rescue efficiency. Summary of the invention

[0004] The present invention provides a method and system for planning multi-point rescue routes for an unmanned ship, so that the unmanned ship can achieve fast and efficient intelligent rescue tasks.

[0005] The unmanned boat multi-point rescue route planning method provided in the present disclosure mainly includes the following steps:

[0006] S1, real-time acquisition of information data of each target and the unmanned ship itself;

[0007] S2, using the ship platform information data, convert the target data into an absolute coordinate system;

[0008] S3, based on the converted target data and unmanned ship data, the multi-index TOPSIS algorithm is used to calculate the weights between targets and between targets and own ship, and a graph model with targets and own ship as vertices is established;

[0009] S4, planning the navigation path of the unmanned ship in real time based on the chart.

[0010] Furthermore, in step S1, the target information is acquired by using the search radar and / or the optoelectronic search turntable carried by the unmanned ship;

[0011] The ship's own information data is obtained using the ship's onboard satellite positioning system and inertial navigation equipment.

[0012] Furthermore, the method for constructing or updating the chart model in step S3 includes:

[0013] A graph data model is established with the ship and the target as vertices. The number of vertices and edges is determined according to the number of targets. An adjacency matrix is ​​established and an adjacency table is constructed using the adjacency matrix. The edge table is set to an empty table.

[0014] Based on the real-time information of the target and the unmanned ship, the result of the multi-index TOPSIS algorithm is used as the weighting coefficient, and the comprehensive weighted value is calculated between the targets and between the target and the ship, and the weighted value is used as the edge table data in the graph data structure; the indicators include: one or more of the target information, the ship heading angle, the angle between the line connecting the target and the ship and the true north, the return radius of the unmanned ship, and the drift direction;

[0015] The chart is updated immediately every time a target is rescued or a new target is searched.

[0016] Furthermore, in step S3, the specific steps of calculating the comprehensive weighted values ​​between the own ship and each target include:

[0017] (1) Normalization of each index value

[0018] Assume that the distance of target i is a low-quality index, and after converting it into a high-quality index and normalizing it, the value is:

[0019] X 1i =1 / D mi ; Where D mi (i=1, 2....n) are the distances to each target respectively; Z 1i (i=1, 2....n) is the normalized result of each target distance after transformation;

[0020] Assume that the target i speed Vmi is a high-quality index and the normalized value is:

[0021] X 2i =V mi ; Where V mi (i=1, 2....n) are the target speeds respectively; Z 2i (i=1, 2....n) is the normalized result of each target speed;

[0022] Assume that the angle between target i and the heading of the unmanned ship is a neutral indicator, and the expected value is that the angle is 0, that is, the target is on the ship's route, which is converted into a high-quality indicator and normalized to obtain the value:

[0023]

[0024] Among them A i (i=1, 2....n) are the included angles between each target and the heading of the unmanned ship; Z 3i (i=1, 2....n) is the normalized result of the angle between each target and the heading of the unmanned ship after transformation;

[0025] (2) Extreme value calculation

[0026] Determine the maximum and minimum values ​​of each normalized element based on the target element:

[0027] Z 1max =max(Z 11 ,Z 12 …,Z 1n );Z 1min =min(Z 11 ,Z 12 …,Z 1n );where Z 1max is the maximum value of the normalized target distance after all targets are transformed; Z 1min The minimum value of the normalized target distance after all target conversions;

[0028] Z 2max =max(Z 21 ,Z 22 …,Z 2n );Z 2min =min(Z 21 ,Z 22 …,Z 2n );where Z 2max is the maximum value of all target speeds normalized; Z 2min is the minimum value of all target speeds normalized;

[0029] Z 3max =max(Z 31 ,Z 32 …,Z 3n );Z 3min =min(Z 31 ,Z 32 …,Z 3n );where Z 3max is the maximum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed; Z 3min The minimum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed;

[0030] (3) Obtaining weighted values

[0031] After calculating the distance between each target and the maximum and minimum values, we can find the value after integrating all factors:

[0032]

[0033] Among them, D imax (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its maximum normalized result; Dimin (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its minimum normalized result;

[0034] D i =D imin / (D imax -D imin );

[0035] Among them, D i (i=1, 2....n) is the comprehensive weighted value of each target.

[0036] Further, the step S4 includes:

[0037] The minimum value of the weighted path with Di as the weighted coefficient from the starting point of the ship to the remaining points is calculated in real time as the planned rescue target.

[0038] Furthermore, the method further comprises the following steps:

[0039] Every time a target is rescued or a new target is found, the chart is immediately updated to plan the next unmanned boat rescue route.

[0040] An unmanned boat multi-point rescue route planning system using the above method mainly includes:

[0041] Target detection equipment is used to search, identify, locate and track targets;

[0042] The ship-borne satellite positioning system and inertial navigation equipment are used to obtain the ship platform's own information data;

[0043] The data processing equipment is used to convert the position of each searched target relative to the unmanned ship into an absolute position under the northeast celestial coordinate through coordinate transformation; and calculate the weights between targets and between targets and the ship based on the multi-index TOPSIS algorithm, establish a graph model with the targets and the ship as vertices, and plan the navigation path of the unmanned ship in real time based on the graph.

[0044] Compared with the prior art, the beneficial effects of the present invention are: (1) it provides efficient route planning for unmanned ships, so that they can quickly reach the rescue target; (2) the calculation method is simple, further improving the rescue efficiency; (3) it has good versatility for unmanned rescue platforms. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] The above and other objects, features and advantages of the present disclosure will become more apparent through a more detailed description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, wherein like reference numerals generally represent like components throughout the exemplary embodiments of the present disclosure.

[0046] Figure 1 The figure is a schematic diagram of an exemplary rescue route planning system according to the present disclosure. DETAILED DESCRIPTION

[0047] The preferred embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the preferred embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.

[0048] The present disclosure provides a method and system for planning a multi-point rescue route for an unmanned ship. Figure 1 As shown:

[0049] It mainly includes: search radar, optoelectronic search turntable, platform compass, GPS system, surface information equipment and data processor and other major equipment. Among them:

[0050] The search radar and the optoelectronic search turntable cooperate with each other to search for targets. The search radar scans various target information in the area in real time. The optoelectronic search turntable contains a tracking module that uses a template matching tracking algorithm to extract, identify and track targets under complex backgrounds. It can quickly detect targets that fall into the water and quickly locate them.

[0051] Ship platform information data obtained by ship-borne GPS system and platform compass;

[0052] The data processor converts the position of each searched target relative to the unmanned ship into an absolute position in the northeast celestial coordinate by coordinate transformation;

[0053] In addition, the data processor uses the converted target data and unmanned ship data to provide a weighted algorithm of the multi-index TOPSIS algorithm based on target distance, target speed, target movement direction, angle between target and ship heading, target danger level, etc., and a graph data model established based on this, and calculates the minimum value of the weighted path of the graph data model in real time, and uses this as a basis for real-time planning of the unmanned ship's navigation path.

[0054] Specific planning methods include:

[0055] A graph data model is established with the ship and the target as vertices. The number of vertices and edges is determined according to the number of targets. An adjacency matrix is ​​established and an adjacency table is constructed using the adjacency matrix. The edge table is set to an empty table.

[0056] The TOPSIS algorithm results based on target information, ship heading angle, angle between the target and ship line and true north, return radius of the unmanned ship, drift direction and other indicators are used as weighting coefficients, and the final weighted values ​​are calculated between targets and between the target and the ship. The weighted values ​​are used as the edge table data in the graph data structure.

[0057] The steps to calculate the comprehensive weighted value between the ship and each target are as follows:

[0058] (1) Normalization of each index value

[0059] The target i distance is a low-quality index. After being converted into a high-quality index and normalized, the value is:

[0060] X 1i =1 / D mi ; Where D mi (i=1, 2....n) are the distances to each target respectively; Z 1i (i=1, 2, ....n) is the normalized result of each target distance after transformation.

[0061] The target i speed Vmi is a high-quality index, and the normalized value is:

[0062] X 2i =V mi ; Where V mi (i=1, 2....n) are the target speeds respectively; Z 2i (i=1, 2....n) is the normalized result of each target speed.

[0063] The angle between target i and the heading of the unmanned ship is a neutral indicator, and the expected value is that the angle is 0 (that is, the target is on the ship's route). It is converted into a high-quality indicator and normalized to obtain the value:

[0064]

[0065] Among them, A i (i=1, 2....n) are the included angles between each target and the heading of the unmanned ship; Z 3i (i=1, 2....n) is the normalized result of the angle between each target and the heading of the unmanned ship after transformation.

[0066] (2) Extreme value calculation

[0067] Determine the maximum and minimum values ​​of each normalized element based on the target element:

[0068] Z 1max =max(Z 11 ,Z 12 …,Z 1n );Z1min =min(Z 11 ,Z 12 …,Z 1n );where Z 1max is the maximum value of the normalized target distance after all targets are transformed; Z 1min The minimum value of the normalized target distance after all target conversions;

[0069] Z 2max =max(Z 21 ,Z 22 …,Z 2n );Z 2min =min(Z 21 ,Z 22 …,Z 2n );where Z 2max is the maximum value of all target speeds normalized; Z 2min is the minimum value of all target speeds normalized;

[0070] Z 3max =max(Z 31 ,Z 32 …,Z 3n );Z 3min =min(Z 31 ,Z 32 …,Z 3n );where Z 3max is the maximum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed; Z 3min It is the minimum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed.

[0071] (3) Obtaining weighted values

[0072] Finally, after calculating the distance between each target and the maximum and minimum values, we can find the value after integrating all factors:

[0073]

[0074] Among them, D imax (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its maximum normalized result; D imin (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its minimum normalized result;

[0075] D i =D imin / (D imax -D imin );

[0076] Among them, D i(i=1, 2....n) is the comprehensive weighted value of each target.

[0077] The data processor calculates in real time the minimum value of the weighted path with Di as the weighting coefficient from the starting point of the ship to the remaining points traversed. The chart is updated immediately each time a target is rescued or a new target is searched. Based on this, the unmanned ship's navigation path is planned in real time to achieve the task of intelligently rescuing all targets by the unmanned ship and improve the unmanned ship's autonomous technology.

[0078] In this embodiment, multiple targets are found using search radar and optoelectronic search turntable; the data processor uses the ship platform information data to convert the target data into an absolute coordinate system, and uses the converted target data and unmanned ship data to set weights between targets and between targets and the ship; then the data processor plans and updates the unmanned ship's navigation path based on the real-time target information data, thereby enabling the unmanned ship to complete the intelligent rescue mission of all targets.

[0079] The above technical scheme is only an exemplary embodiment of the present invention. For those skilled in the art, it is easy to make various types of improvements or modifications based on the application methods and principles disclosed in the present invention, and it is not limited to the method described in the above specific embodiment of the present invention. Therefore, the method described above is only preferred and does not have a restrictive meaning.

Claims

1. A method for planning a multi-point rescue route for an unmanned ship, comprising the following steps: S1, real-time acquisition of information data of each target and the unmanned ship itself; S2, using the ship platform information data, convert the target data into an absolute coordinate system; S3, based on the converted target data and unmanned ship data, the multi-index TOPSIS algorithm is used to calculate the weights between targets and between targets and own ship, and a graph model with targets and own ship as vertices is established; S4, planning the navigation path of the unmanned ship in real time based on the chart.

2. The method according to claim 1, characterized in that In the step S1, the target information is acquired by using the search radar and / or the optoelectronic search turntable carried by the unmanned ship; The ship's own information data is obtained using the ship's onboard satellite positioning system and inertial navigation equipment.

3. The method according to claim 1 or 2, characterized in that: The method for constructing or updating the chart model in step S3 includes: A graph data model is established with the ship and the target as vertices. The number of vertices and edges is determined according to the number of targets. An adjacency matrix is ​​established and an adjacency table is constructed using the adjacency matrix. The edge table is set to an empty table. Based on the real-time information of the target and the unmanned ship, the result of the multi-index TOPSIS algorithm is used as the weighting coefficient, and the comprehensive weighted value is calculated between the targets and between the target and the ship, and the weighted value is used as the edge table data in the graph data structure; the indicators include: one or more of the target information, the ship heading angle, the angle between the line connecting the target and the ship and the true north, the return radius of the unmanned ship, and the drift direction; The chart is updated immediately every time a target is rescued or a new target is searched.

4. The method according to claim 3, characterized in that In step S3, the specific steps of calculating the comprehensive weighted values ​​between the own ship and each target include: (1) Normalization of each index value Assume that the distance of target i is a low-quality index, and after converting it into a high-quality index and normalizing it, the value is: X 1i =1 / D mi ; Where D mi (i=1, 2....n) are the distances to each target respectively; Z 1i (i=1, 2....n) is the normalized result of each target distance after transformation; Assume that the target i speed Vmi is a high-quality index and the normalized value is: X 2i =V mi ; Where V mi (i=1, 2....n) are the target speeds respectively; Z 2i (i=1, 2....n) is the normalized result of each target speed; Assume that the angle between target i and the heading of the unmanned ship is a neutral indicator, and the expected value is that the angle is 0, that is, the target is on the ship's route, which is converted into a high-quality indicator and normalized to obtain the value: Among them A i (i=1, 2....n) are the included angles between each target and the heading of the unmanned ship; Z 3i (i=1, 2....n) is the normalized result of the angle between each target and the heading of the unmanned ship after transformation; (2) Extreme value calculation Determine the maximum and minimum values ​​of each normalized element based on the target element: Z 1max =max(Z 11 ,Z 12 …,Z 1n );Z 1min =min(Z 11 ,Z 12 …,Z 1n );where Z 1max is the maximum value of the normalized target distance after all targets are transformed; Z 1min The minimum value of the normalized target distance after all target conversions; Z 2max =max(Z 21 ,Z 22 …,Z 2n );Z 2min =min(Z 21 ,Z 22 …,Z 2n );where Z 2max is the maximum value of all target speeds normalized; Z 2min is the minimum value of all target speeds normalized; Z 3max =max(Z 31 ,Z 32 …,Z 3n );Z 3min =min(Z 31 ,Z 32 …,Z 3n );where Z 3max is the maximum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed; Z 3min The minimum value of the normalized angle between the target and the heading of the unmanned ship after all targets are transformed; (3) Obtaining weighted values After calculating the distance between each target and the maximum and minimum values, we can find the value after integrating all factors: Among them, D imax (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its maximum normalized result; D imin (i=1, 2....n) is the distance value between the normalized data of all indicators of each target and its minimum normalized result; D i =D imin / (D imax -D imin ); Among them, D i (i=1, 2....n) is the comprehensive weighted value of each target.

5. The method according to claim 4, characterized in that The step S4 comprises: The minimum value of the weighted path with Di as the weighted coefficient from the starting point of the ship to the remaining points is calculated in real time as the planned rescue target.

6. The method according to claim 1, characterized in that The following steps are also included: Every time a target is rescued or a new target is found, the chart is immediately updated to plan the next unmanned boat rescue route.

7. An unmanned ship multi-point rescue route planning system using any of the methods described in claims 1-6, characterized in that: include: Target detection equipment is used to search, identify, locate and track targets; The ship-borne satellite positioning system and inertial navigation equipment are used to obtain the ship platform's own information data; The data processing equipment is used to convert the position of each searched target relative to the unmanned ship into an absolute position under the northeast celestial coordinate through coordinate transformation; and calculate the weights between targets and between targets and the ship based on the multi-index TOPSIS algorithm, establish a graph model with the targets and the ship as vertices, and plan the navigation path of the unmanned ship in real time based on the graph.

Images