Unmanned ship track planning method, device, equipment and storage medium

Abstract

The present application relates to a method, device, equipment and storage medium for trajectory planning of an unmanned ship. The method comprises: obtaining electromagnetic environment monitoring data, the number of planned monitoring points and the starting position of the unmanned ship to be planned in a preset area; using Kriging estimation based on the monitoring data to obtain the Kriging variance, and screening the location information that meets the preset threshold conditions based on the Kriging variance; using clustering to calculate based on the number of planned monitoring points and the location information that meets the preset threshold conditions to obtain the location information of the planned monitoring points; using a genetic algorithm to design a navigation route with the shortest total distance for the unmanned ship to be planned based on the starting position of the unmanned ship to be planned and the location information of each planned monitoring point. This method determines the planned monitoring points through Kriging variance estimation and clustering methods under limited resources, thereby improving the accuracy of electromagnetic spectrum map construction; the genetic algorithm is used to adaptively propose trajectory planning, which can effectively save monitoring efficiency and comprehensively improve the efficiency of electromagnetic space perception.

Description

Technical Field

[0001] The present application relates to the field of electromagnetic spectrum monitoring technology, and in particular to a method, device, equipment and storage medium for unmanned ship track planning. Background Art

[0002] With the development of artificial intelligence technology, unmanned ships can replace manual labor in some areas, reduce the cost of water detection, improve work efficiency, and become a basic ocean detection tool. Unmanned ships are dynamic, sudden, unpredictable, small, fast, and highly flexible. A momentary mistake may cause irreparable losses. How to plan the path of unmanned ships safely and effectively is very important.

[0003] Unmanned ships are relatively dependent on the infrastructure of the electromagnetic spectrum. There are great advantages in applying electromagnetic spectrum maps to drone trajectory planning. However, electromagnetic spectrum maps are sensitive to the performance, quantity and layout location of monitoring equipment. In the engineering practice of marine application scenarios, due to limited costs and the lack of conditions for the deployment of monitoring stations or other monitoring equipment, it is often impossible to obtain electromagnetic spectrum information at all locations in the area of ​​interest. Therefore, if traditional statistical principles are used to judge the valuation effect, only specific locations can be selected for measurement, and a limited number of measured values ​​can be compared with the estimated values. It can be seen from the radio wave propagation model and spatial correlation that the estimated values ​​of electromagnetic environment information near the monitoring station are often more accurate. Since fixed monitoring stations in the sea area can only be limited to islands and reefs, the cost is high and the number is small. There are often a large number of areas of interest in the sea area that do not contain monitoring stations in the neighborhood. Summary of the invention

[0004] Based on this, it is necessary to provide a track planning method, device, equipment and storage medium for an unmanned ship that can optimize the track for an unmanned ship with electromagnetic monitoring function to be planned in a sea area without monitoring stations in the neighborhood to address the above technical problems.

[0005] A method for trajectory planning of an unmanned ship, the method comprising:

[0006] Obtain electromagnetic environment monitoring data within a preset area, the number of planned monitoring points, and the starting position of the unmanned ship to be planned; the electromagnetic environment monitoring data includes location information and the receiving power of the corresponding location.

[0007] Kriging estimation is performed based on the electromagnetic environment monitoring data to obtain a Kriging variance, and location information that meets a preset threshold condition is screened based on the Kriging variance.

[0008] According to the number of proposed monitoring points and the location information satisfying the preset threshold conditions, a clustering algorithm is used to calculate and obtain the location information of the proposed monitoring points; the clustering algorithm is a hard clustering algorithm that divides data into a fixed number of clusters based on distance.

[0009] According to the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned.

[0010] A track planning device for an unmanned ship, the device comprising:

[0011] The data acquisition module is used to obtain the electromagnetic environment monitoring data, the number of planned monitoring points and the starting position of the unmanned ship to be planned in the preset area; the electromagnetic environment monitoring data includes the position information and the receiving power of the corresponding position.

[0012] The Kriging variance determination module is used to obtain the Kriging variance by using Kriging estimation according to the electromagnetic environment monitoring data, and to filter the location information that meets the preset threshold condition according to the Kriging variance.

[0013] The module for determining the location information of the proposed monitoring points is used to calculate the location information of the proposed monitoring points using a clustering algorithm based on the number of the proposed monitoring points and the location information that meets the preset threshold conditions; the clustering algorithm is a hard clustering algorithm that divides the data into a fixed number of clusters based on distance.

[0014] The track planning module is used to design a navigation route with the shortest total distance for the unmanned ship to be planned based on the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, so as to realize the track planning of the unmanned ship to be planned.

[0015] The above-mentioned unmanned ship's track planning method, device, equipment and storage medium, the method obtains the electromagnetic environment monitoring data, the number of planned monitoring points and the starting position of the unmanned ship to be planned in a preset area; Kriging estimation is used according to the electromagnetic environment monitoring data to obtain the Kriging variance, and the location information that meets the preset threshold conditions is screened according to the Kriging variance; according to the number of planned monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used for calculation to obtain the location information of the planned monitoring points; according to the starting position of the unmanned ship to be planned and the location information of each planned monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned. This method uses the Kriging variance in the geostatistical method to perform error analysis on the estimation results in the area, and reasonably selects the planned monitoring points by clustering when resources are limited, which can improve the accuracy of electromagnetic spectrum map construction; the track planning is adaptively proposed by the artificial intelligence genetic algorithm, which can effectively save the monitoring efficiency and comprehensively improve the electromagnetic space perception efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A schematic diagram of a flow chart of a method for planning a track of an unmanned ship in one embodiment;

[0017] Figure 2 A specific flow chart of a method for planning a track of an unmanned ship in another embodiment;

[0018] Figure 3 A schematic diagram of Kriging variance distribution and proposed monitoring sites in a region in an embodiment;

[0019] Figure 4 Schematic diagram of the planned monitoring sites and the track planning of the unmanned ship to be planned in another embodiment, wherein (a) is a schematic diagram of the distribution of the planned monitoring sites, and (b) is a schematic diagram of the track planning of the unmanned ship to be planned;

[0020] Figure 5 A comparison of root mean square errors of electromagnetic spectrum map construction under different deployment conditions in one embodiment;

[0021] Figure 6 A comparison of the ratio of the total distance of the unmanned ship's track and the time cost under different deployment conditions in an embodiment;

[0022] Figure 7 A structural diagram of a track planning device for an unmanned ship in one embodiment;

[0023] Figure 8 FIG. 4 is a diagram showing the internal structure of a device in one embodiment. DETAILED DESCRIPTION

[0024] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0025] In one embodiment, Figure 1 As shown, a method for trajectory planning of an unmanned ship is provided, the method comprising the following steps:

[0026] Step 100: Obtain electromagnetic environment monitoring data, the number of planned monitoring points, and the starting position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data includes location information and the receiving power of the corresponding location.

[0027] The preset area is the area of ​​interest.

[0028] The electromagnetic environment monitoring data within the preset area may be the electromagnetic environment monitoring data of fixed monitoring stations on islands and reefs.

[0029] Specifically, the unmanned ship to be planned may be an unmanned ship with electromagnetic monitoring function.

[0030] Using mathematical notation: For a limited number of electromagnetic environment monitoring datasets in the area of ​​interest, Location information, is the receiving power corresponding to the location information, where n is the serial number of the electromagnetic environment monitoring data, n is an integer greater than or equal to 1 and less than N, and N is the number of electromagnetic environment monitoring data; The monitoring order of the proposed monitoring points and location information of the proposed monitoring points Wherein, m is the serial number of the proposed monitoring point, m is an integer greater than or equal to 1 and less than M, M is the number of the proposed monitoring points, and M is an integer greater than 1.

[0031] Step 102: Kriging estimation is performed based on the electromagnetic environment monitoring data to obtain the Kriging variance, and location information that meets a preset threshold condition is screened based on the Kriging variance.

[0032] Step 104: Based on the number of proposed monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used to perform calculations to obtain the location information of the proposed monitoring points.

[0033] The clustering algorithm is a hard clustering algorithm that divides data into a fixed number of clusters based on distance.

[0034] Specifically, the clustering algorithm may be a K-Means clustering algorithm or a K-Means++ clustering algorithm.

[0035] Step 106: Based on the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned.

[0036] In the above-mentioned track planning method, the method obtains the electromagnetic environment monitoring data, the number of proposed monitoring points and the starting position of the unmanned ship to be planned in the preset area; Kriging estimation is used according to the electromagnetic environment monitoring data to obtain the Kriging variance, and the location information that meets the preset threshold conditions is screened according to the Kriging variance; According to the number of proposed monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used for calculation to obtain the location information of the proposed monitoring points; According to the starting position of the unmanned ship to be planned and the location information of each proposed monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned. This method uses the Kriging variance in the geostatistical method to perform error analysis on the estimation results in the area. Under the condition of limited resources, clustering is used to reasonably select the proposed monitoring points, which can improve the accuracy of electromagnetic spectrum map construction; the track planning is adaptively proposed by the artificial intelligence genetic algorithm, which can effectively save the monitoring efficiency and comprehensively improve the electromagnetic space perception efficiency.

[0037] In one embodiment, the preset threshold condition is that the Kriging variance is greater than the preset adaptive threshold. Step 102 includes: using Kriging estimation based on the electromagnetic environment monitoring data to obtain the Kriging variance; comparing the Kriging variance with the preset adaptive threshold, eliminating the location information whose Kriging variance is less than or equal to the preset adaptive threshold, and retaining the location information whose Kriging variance is greater than the preset adaptive threshold.

[0038] In one embodiment, the clustering algorithm in step 104 is a K-Means clustering algorithm.

[0039] In one embodiment, the clustering algorithm in step 104 is a K-Means++ clustering algorithm.

[0040] In one embodiment, step 106 includes: setting the monitoring order of the planned monitoring points; starting from the starting position of the unmanned ship to be planned, randomly designing p tracks, and using the p tracks as the current track plan population; wherein p is an integer greater than 1; selecting in the current track plan population according to a predetermined principle, The selected results are used as track offspring; the predetermined principle is the first 10% of the shortest total distance in the track plan population; crossover and mutation operations are performed on the track offspring to obtain offspring reproduction results; crossover refers to exchanging the monitoring order of two adjacent proposed monitoring points according to preset crossover parameters; mutation refers to exchanging any two points in the track planning according to preset mutation parameters; the first p routes with the shortest total distance are selected from the offspring reproduction results as the current track plan population, and enter the next round of iteration until the preset number of iterations is reached; the order of each proposed monitoring point in the track with the shortest total distance in the track plan population and the location information of the proposed monitoring points are obtained; according to the monitoring order of each proposed monitoring point and the location information of the proposed monitoring point, the navigation route with the shortest total distance of the planned object to be tested is obtained, and the track planning of the unmanned ship to be planned is realized.

[0041] The preset crossover parameters include: the probability of crossover and the order of exchanging two proposed monitoring points, the former is a set parameter, and the latter is a reasonable random integer.

[0042] The preset mutation parameters include: the probability of mutation and the order of exchanging two proposed monitoring points. The former is a set parameter and the latter is two reasonable random integers. Generally speaking, the probability of mutation is a relatively small value.

[0043] Advantages of the present invention: The present invention utilizes the characteristics of Kriging as a geostatistical method, and creatively uses Kriging variance as a reference indicator for optimizing the layout of proposed monitoring points; the present invention adaptively determines the locations of proposed monitoring points according to the number of proposed monitoring points in the area of ​​interest through Kriging variance screening and K-means or K-means++ algorithm. The present invention plans the track of the unmanned ship to be planned through an artificial intelligence genetic algorithm, solving the optimization solution of TSP-type problems. The TSP problem can be specifically searched. Generally speaking, TSP-type problems refer specifically to this type of NP-hard problem, that is, the optimal combination problem that cannot be solved by an exact algorithm.

[0044] TSP-type problem: Travelling Salesman Problem.

[0045] In one embodiment, Figure 2As shown, a method for trajectory planning of an unmanned ship is provided. The method first performs Kriging interpolation based on the monitoring data in the area to obtain the Kriging variance. As a reflection of the accuracy of Kriging estimation, the Kriging variance can be used to judge the credibility of the estimated value in the area. Therefore, the location with a large Kriging variance is the location with low estimation accuracy and needs to collect further monitoring data. According to the distribution of Kriging variance in the area, the variance with a larger value is selected by setting an adaptive threshold, and clustering is performed according to its location information and the number of proposed monitoring points. Since the number of classes needs to be controlled to be the number of proposed monitoring points, K-means is selected as the algorithm for clustering points with large variance values ​​in the area, and the center of the class in the result is the location of the proposed monitoring point. Finally, according to the starting position of the unmanned ship to be planned and the location of each proposed monitoring point, the genetic algorithm is used to optimally plan the trajectory so that the location of each proposed monitoring point can be monitored under the condition of the shortest total distance.

[0046] The specific steps of the track planning method in this embodiment are as follows:

[0047] (1) Kriging estimation based on monitoring data

[0048] Kriging estimation: First use electromagnetic environment monitoring data and The estimated value of the shadow fading component at the unknown point s0 is constructed as:

[0049]

[0050] in, is the estimated value of shadow fading at the unknown point s0; ω n is the nth Kriging weight coefficient.

[0051] To ensure that the estimation result of formula (1) is the optimal unbiased estimation, according to the second-order stationary assumption, the Kriging weight coefficient in formula (1) is obtained by the following Kriging equation system:

[0052] Kλ=M (2)

[0053] Where:

[0054]

[0055] Wherein, γ(·) is the theoretical variogram, which quantitatively describes the spatial correlation of the shadow fading component. The experimental variogram calculated from the monitoring data is fitted with the corresponding theoretical model; L is the Lagrangian coefficient.

[0056] At the same time, the estimation accuracy of formula (1) is expressed by the Kriging variance:

[0057]

[0058] Kriging variance screening: Based on the results of Kriging estimation, the Kriging variance values ​​in the region are screened. The threshold is set adaptively by the median of the Kriging variance in the region. The location information of the points with values ​​greater than the threshold is retained, and the location information of the remaining points is discarded. The location information that meets the conditions is combined into Wherein Q is the number of location information that meets the threshold condition, q is the sequence number of the location information that meets the threshold condition, and q is an integer greater than or equal to 1 and less than Q.

[0059] (2) Quasi-monitoring point estimation based on K-means clustering

[0060] Filter location information that meets the threshold condition based on Kriging variance And the number of planned monitoring points m, the location information of the planned monitoring points Perform calculations.

[0061] First, from the location information that meets the threshold condition Initialize m proposed monitoring points and determine their location information as Then perform N for the following steps Iter Iterations: (a) Initialize the cluster to {C m ,m=1,2,···,M}; (b) for For each element in {p0,m=1,2,···,M}, calculate its Euclidean distance to the center of the cluster, that is, calculate the distance from each element in {p0,m=1,2,···,M} to the current monitoring point The Euclidean distance of s q (q) Classification corresponding to the category λ with the minimum Euclidean distance q , while updating (c) For all {C m ,m=1,2,···,M} recalculate its centroid as the new proposed monitoring point; (d) when the proposed monitoring point no longer changes or the number of iterations reaches the maximum value, stop the iteration. The location information of the proposed monitoring point is output as the result. The Kriging variance distribution and the schematic diagram of the proposed monitoring site in the region are shown in Figure 3 shown.

[0062] (3) Trajectory planning based on genetic algorithm

[0063] According to the initial position of the unmanned ship to be planned and the location information of the planned monitoring point Calculate the shortest total distance and its track. First, starting from the initial position, randomly design p tracks as the size of the track plan population. Then iterate the following steps until the maximum number of iterations is met. (a) Select the top 10% with the shortest total distance from the track plan population as the preferred offspring to participate in the subsequent steps, and their number is p0; (b) Perform reproduction operations on the track offspring, namely crossover and mutation; the so-called crossover means exchanging the order of two adjacent proposed monitoring points according to the preset crossover parameters; the so-called mutation means exchanging any two points in the track planning according to the preset mutation parameters; (c) According to the reproduction results of the offspring, select the top p routes with the shortest total distance as the size of the new population; (d) Stop after reaching the iteration limit. Finally, the order of each proposed monitoring point in the track with the shortest total distance in the population is and its location information The result is output as follows. Figure 4 As shown, (a) is a schematic diagram of the distribution of the planned monitoring sites, and (b) is a schematic diagram of the track planning of the unmanned ship to be planned.

[0064] This method uses the Kriging method to obtain the Kriging variance in the region based on the electromagnetic environment monitoring data of fixed monitoring stations in the region. The Kriging variance is a measure of the error between the estimated value and the true value in the Kriging method. It can be used to judge the accuracy of the Kriging estimation in the region. By clustering the areas with large Kriging variance in the region, the locations in the sea area that need to be monitored for the next step are determined. Finally, through the artificial intelligence genetic algorithm, according to the location information to be monitored, the navigation route with the shortest total distance is designed for the unmanned ship to be planned, and the track planning of the unmanned ship to be planned is realized.

[0065] In a verification example, considering that the starting point of the track planning application for monitoring the unmanned ship to be planned is to improve the overall construction accuracy of the electromagnetic spectrum map, the root mean square error (RMSE) will be used as an indicator to judge whether the location of the proposed monitoring point has performance improvement. In addition, it is necessary to judge whether the track planning can reduce the total distance of the track and improve the overall efficiency of the monitoring station layout. Therefore, the total distance of different track schemes and the time spent on the algorithm need to be compared. According to the actual engineering application of the deployment of monitoring stations in island and reef waters, the above indicators are compared through 100 independent repeated experiments.

[0066] Figure 5The figure shows the root mean square error comparison of electromagnetic spectrum map construction under different layout conditions. The horizontal axis is the ratio of the number of planned monitoring points to the number of deployed monitoring sites, and the vertical axis is the root mean square error of the electromagnetic spectrum map construction result under the conditions of considering all monitoring data. As can be seen from the figure, after the proposed monitoring points are optimized and laid out using the present invention, the root mean square error is greater than the random layout method, which can achieve the purpose of comprehensively improving the accuracy of electromagnetic spectrum map construction and guiding the layout of proposed monitoring points. In addition, as the proportion of proposed monitoring points decreases, the performance of the present invention for layout optimization is gradually improved, which shows that under the condition that the number of proposed monitoring points is relatively sparse, the present invention can effectively improve the construction accuracy of the electromagnetic spectrum map and complete the determination of the proposed monitoring points. The construction accuracy of the electromagnetic spectrum map is positively correlated with the number of monitoring points. Under the condition that the proposed monitoring points are relatively sparse, the accuracy improvement brought by the reasonable layout of the sites is relatively high, which also fully demonstrates that the present invention has a strong application value for the estimation of proposed monitoring points in island and reef waters.

[0067] Figure 6 It is a comparison of the ratio of the total distance of the track and the time cost under different deployment conditions. The horizontal axis is the ratio of the number of planned monitoring points to the deployed monitoring sites, the vertical axis on the left is the ratio of the total distance of the track after optimization of the present invention to the total distance of the random track, and the vertical axis on the right is the time cost of the track planning stage of the present invention. It can be seen from the figure that the ratio of the total distance decreases with the increase of the proportion of the planned monitoring points, which means that the track planning of the present invention is always shorter than the random distance, and with the increase of the relative number of planned monitoring points, the optimization performance of the present invention for the total distance of the unmanned ship track to be planned is also improved. At the same time, the time cost also increases.

[0068] In summary, the present invention can realize the optimized estimation of the proposed monitoring points through screening and clustering based on Kriging variance, so as to achieve the purpose of comprehensively improving the accuracy of electromagnetic spectrum map construction, and can obtain better performance improvement when the proposed monitoring points are relatively sparse; at the same time, the track of the unmanned ship to be planned is planned through the artificial intelligence genetic algorithm, so as to achieve the minimum total track distance and the highest monitoring efficiency under the condition that the position of the proposed monitoring points remains unchanged.

[0069] Compared with the existing methods, the main features of the method of the present invention are: (1) using the estimated variance in geostatistical methods to perform error analysis on the estimated results in the region, and reasonably selecting the proposed monitoring points through clustering under the condition of limited resources. The improvement of the accuracy of electromagnetic spectrum map construction by the present invention is demonstrated through experimental comparison; (2) the trajectory planning is adaptively proposed through artificial intelligence genetic algorithm, which can effectively save monitoring efficiency and comprehensively improve the efficiency of electromagnetic space perception.

[0070] It should be understood that although Figure 1-2The steps in the flowchart are shown in sequence as indicated by the arrows, but these steps are not necessarily executed in the order indicated by the arrows. Unless otherwise specified in this document, there is no strict order restriction for the execution of these steps, and these steps can be executed in other orders. Moreover, Figure 1-2 At least part of the steps may include multiple sub-steps or multiple stages. These sub-steps or stages are not necessarily executed at the same time, but can be executed at different times. The execution order of these sub-steps or stages is not necessarily sequential, but can be executed in turn or alternately with other steps or at least part of the sub-steps or stages of other steps.

[0071] In one embodiment, Figure 7 As shown, a track planning device for an unmanned ship is provided, comprising: a data acquisition module, a Kriging variance determination module, a proposed monitoring point location information determination module and a track planning module, wherein:

[0072] The data acquisition module is used to obtain the electromagnetic environment monitoring data, the number of planned monitoring points and the starting position of the unmanned ship to be planned in the preset area; the electromagnetic environment monitoring data includes the location information and the receiving power of the corresponding location.

[0073] The Kriging variance determination module is used to obtain the Kriging variance by using Kriging estimation based on the electromagnetic environment monitoring data, and to filter the location information that meets the preset threshold conditions based on the Kriging variance.

[0074] The module for determining the location information of the proposed monitoring points is used to calculate the location information of the proposed monitoring points based on the number of proposed monitoring points and the location information that meets the preset threshold conditions using a clustering algorithm; the clustering algorithm is a hard clustering algorithm that divides data into a fixed number of clusters based on distance.

[0075] The track planning module is used to design a navigation route with the shortest total distance for the unmanned ship to be planned based on the starting position of the unmanned ship to be planned and the location information of each planned monitoring point, so as to realize the track planning of the unmanned ship to be planned.

[0076] In one embodiment, the preset threshold condition is that the Kriging variance is greater than the preset adaptive threshold. The Kriging variance determination module is also used to use Kriging estimation based on the electromagnetic environment monitoring data to obtain the Kriging variance; compare the Kriging variance with the preset adaptive threshold, eliminate the location information where the Kriging variance is less than or equal to the preset adaptive threshold, and retain the location information where the Kriging variance is greater than the preset adaptive threshold.

[0077] In one of the embodiments, the clustering algorithm in the module for determining the location information of the proposed monitoring points is a K-Means clustering algorithm.

[0078] In one of the embodiments, the clustering algorithm in the module for determining the location information of the proposed monitoring points is a K-Means++ clustering algorithm.

[0079] In one of the embodiments, the track planning module is also used to set the monitoring order of the proposed monitoring points; starting from the starting position of the unmanned ship to be planned, randomly design p tracks, and use the p tracks as the current track plan population; where p is an integer greater than 1; select from the current track plan population according to a predetermined principle, and use the selected result as the track offspring; the predetermined principle is the top 10% with the shortest total distance in the track plan population; crossover and mutation operations are performed on the track offspring to obtain offspring reproduction results; crossover refers to exchanging the monitoring order of two adjacent proposed monitoring points according to a preset crossover parameter; mutation refers to exchanging any two points in the track planning according to a preset mutation parameter; select the top p points with the shortest total distance in the offspring reproduction results The route is taken as the current track plan population and enters the next round of iteration until the preset number of iterations is reached; the order of each proposed monitoring point in the track with the shortest total distance in the track plan population and the location information of the proposed monitoring points are obtained; according to the monitoring order of each proposed monitoring point and the location information of the proposed monitoring point, the navigation route with the shortest total distance of the planned object to be tested is obtained, and the track planning of the unmanned ship to be planned is realized.

[0080] For the specific definition of the trajectory planning device, please refer to the definition of the trajectory planning method above, which will not be repeated here. The various modules in the above-mentioned trajectory planning device can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0081] In one embodiment, a device is provided. The device may be a terminal, and its internal structure diagram may be as follows: Figure 8 As shown. The device includes a processor, a memory, a network interface, a display screen and an input device connected through a system bus. Among them, the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The network interface of the device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a method for track planning of an unmanned ship is implemented. The display screen of the device can be a liquid crystal display screen or an electronic ink display screen, and the input device of the device can be a touch layer covering the display screen, or a button, trackball or touchpad set on the device housing, or an external keyboard, touchpad or mouse, etc.

[0082] Those skilled in the art will understand that Figure 8 The structure shown in the figure is merely a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the device to which the scheme of the present application is applied. The specific device may include more or fewer components than shown in the figure, or combine certain components, or have a different arrangement of components.

[0083] In one embodiment, a device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps in the above method embodiment when executing the computer program.

[0084] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiment are implemented.

[0085] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0086] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0087] The above-mentioned embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent of the present application shall be subject to the attached claims.

Claims

1. A trajectory planning method for an unmanned ship, characterized in that: The method comprises: Obtaining electromagnetic environment monitoring data within a preset area, the number of planned monitoring points, and the starting position of the unmanned ship to be planned; the electromagnetic environment monitoring data includes location information and the receiving power at the corresponding location; Using Kriging estimation based on the electromagnetic environment monitoring data to obtain Kriging variance, and screening location information that meets a preset threshold condition based on the Kriging variance; According to the number of the proposed monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used to calculate to obtain the location information of the proposed monitoring points; the clustering algorithm is a hard clustering algorithm that divides the data into a fixed number of clusters based on distance; According to the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned.

2. The method according to claim 1, characterized in that The preset threshold condition is that the Kriging variance is greater than the preset adaptive threshold; Using Kriging estimation according to the electromagnetic environment monitoring data to obtain Kriging variance, and screening location information that meets a preset threshold condition according to the Kriging variance, including: Using Kriging estimation based on the electromagnetic environment monitoring data, obtaining Kriging variance; The Kriging variance is compared with a preset adaptive threshold, the location information where the Kriging variance is less than or equal to the preset adaptive threshold is eliminated, and the location information where the Kriging variance is greater than the preset adaptive threshold is retained.

3. The method according to claim 1, characterized in that According to the number of the proposed monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used to calculate to obtain the location information of the proposed monitoring points. The clustering algorithm in the step is a K-Means clustering algorithm.

4. The method according to claim 1, characterized in that: According to the number of the proposed monitoring points and the location information that meets the preset threshold conditions, a clustering algorithm is used to calculate to obtain the location information of the proposed monitoring points. The clustering algorithm in the step is a K-Means++ clustering algorithm.

5. The method according to claim 1, characterized in that: According to the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, a genetic algorithm is used to design a navigation route with the shortest total distance for the unmanned ship to be planned, so as to realize the track planning of the unmanned ship to be planned, including: Set the monitoring order of the proposed monitoring points; Starting from the starting position of the unmanned boat to be planned, randomly design track, and the Tracks are used as the current track plan population; is an integer greater than 1; Selecting from the current track plan population according to a predetermined principle, and using the selected result as the track offspring; the predetermined principle is the first 10% of the track plan population with the shortest total distance; The offspring of the track are respectively subjected to crossover and mutation operations to obtain offspring reproduction results; the crossover refers to exchanging the monitoring order of two adjacent intended monitoring points according to a preset crossover parameter; the mutation refers to exchanging any two points in the track planning according to a preset mutation parameter; In the offspring reproduction results, select the one with the shortest total distance. The route is taken as the current track plan population and enters the next round of iteration until the preset number of iterations is reached; the order of each proposed monitoring point in the track with the shortest total distance in the track plan population and the location information of the proposed monitoring points are obtained; According to the monitoring order and location information of each planned monitoring point, the navigation route with the shortest total distance of the planned object to be tested is obtained, and the track planning of the unmanned ship to be planned is realized.

6. A track planning device for an unmanned ship, characterized in that: The device comprises: A data acquisition module is used to acquire electromagnetic environment monitoring data within a preset area, the number of planned monitoring points, and the starting position of the unmanned ship to be planned; the electromagnetic environment monitoring data includes position information and the receiving power at the corresponding position; A Kriging variance determination module, configured to obtain a Kriging variance by using Kriging estimation based on the electromagnetic environment monitoring data, and to filter location information that meets a preset threshold condition based on the Kriging variance; A module for determining the location information of proposed monitoring points, for obtaining the location information of proposed monitoring points by using a clustering algorithm to calculate according to the number of proposed monitoring points and the location information that meets a preset threshold condition; the clustering algorithm is a hard clustering algorithm that divides data into a fixed number of clusters based on distance; The track planning module is used to design a navigation route with the shortest total distance for the unmanned ship to be planned based on the starting position of the unmanned ship to be planned and the position information of each planned monitoring point, so as to realize the track planning of the unmanned ship to be planned.

7. The device according to claim 6, characterized in that The preset threshold condition is that the Kriging variance is greater than the preset adaptive threshold; The Kriging variance determination module is further used to obtain the Kriging variance by using Kriging estimation according to the electromagnetic environment monitoring data; The Kriging variance is compared with a preset adaptive threshold, the location information where the Kriging variance is less than or equal to the preset adaptive threshold is eliminated, and the location information where the Kriging variance is greater than the preset adaptive threshold is retained.

8. The device according to claim 6, characterized in that The clustering algorithm described in the module for determining the location information of the proposed monitoring points is the K-Means clustering algorithm.

9. A device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A 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 method according to any one of claims 1 to 5 are implemented.

Images