CN114690782A - Method, device, equipment and storage medium for planning flight path of unmanned ship - Google Patents
Method, device, equipment and storage medium for planning flight path of unmanned ship Download PDFInfo
- Publication number
- CN114690782A CN114690782A CN202210395527.3A CN202210395527A CN114690782A CN 114690782 A CN114690782 A CN 114690782A CN 202210395527 A CN202210395527 A CN 202210395527A CN 114690782 A CN114690782 A CN 114690782A
- Authority
- CN
- China
- Prior art keywords
- position information
- unmanned ship
- points
- planned
- kriging
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 59
- 238000003860 storage Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 136
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 62
- 230000002068 genetic effect Effects 0.000 claims abstract description 19
- 238000012216 screening Methods 0.000 claims abstract description 14
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 238000004590 computer program Methods 0.000 claims description 10
- 230000035772 mutation Effects 0.000 claims description 7
- 238000003064 k means clustering Methods 0.000 claims description 6
- 238000009395 breeding Methods 0.000 claims description 3
- 230000001488 breeding effect Effects 0.000 claims description 3
- 238000009401 outcrossing Methods 0.000 claims description 3
- 238000013461 design Methods 0.000 claims description 2
- 238000001228 spectrum Methods 0.000 abstract description 17
- 238000010276 construction Methods 0.000 abstract description 11
- 238000010586 diagram Methods 0.000 description 12
- 238000013473 artificial intelligence Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 230000008901 benefit Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000005562 fading Methods 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 241000287196 Asthenes Species 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
- 239000003643 water by type Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/0206—Control of position or course in two dimensions specially adapted to water vehicles
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Traffic Control Systems (AREA)
Abstract
The application relates to a method, a device, equipment and a storage medium for planning a flight path of an unmanned ship. The method comprises the following steps: the method comprises the steps that electromagnetic environment monitoring data, the number of monitoring points to be monitored and the starting position of an unmanned ship to be planned in a preset area are obtained; according to the monitoring data, performing kriging estimation to obtain kriging variance, and screening position information meeting a preset threshold condition according to the kriging variance; calculating by clustering according to the number of the points to be monitored and the position information meeting the preset threshold condition to obtain the position information of the points to be monitored; and designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point. The method determines the monitoring points through a kriging variance estimation and clustering method under the condition of limited resources, and improves the construction precision of the electromagnetic spectrum map; the flight path planning is adaptively proposed through a genetic algorithm, so that the monitoring efficiency can be effectively saved, and the electromagnetic space sensing efficiency is comprehensively improved.
Description
Technical Field
The application relates to the technical field of electromagnetic spectrum monitoring, in particular to a method, a device, equipment and a storage medium for planning a flight path of an unmanned ship.
Background
Along with the development of artificial intelligence technology, unmanned ship can replace manual work in some fields, reduces the detection cost in waters, has improved work efficiency, becomes a basic ocean detection instrument. The unmanned ship has the characteristics of dynamic property, burstiness, unpredictability, small volume, high speed, high flexibility and the like, and instantaneous errors can cause irreparable loss, so that how to carry out safe and effective path planning on the unmanned ship is very important.
The unmanned ship relies on the infrastructure of the electromagnetic spectrum, and the electromagnetic spectrum map has great advantages when being applied to unmanned plane track planning, but the electromagnetic spectrum map is sensitive to the performance, the quantity and the arrangement position of monitoring equipment. In the engineering practice of the marine application scene, limited by limited cost and unsatisfactory layout conditions of monitoring sites or other monitoring equipment, the electromagnetic spectrum information of all positions of an interested region cannot be obtained, so that if the estimation effect is judged by adopting the traditional statistical principle, only a specific position can be selected for measurement, and the limited number of measured values are compared with the estimated value. According to the radio wave propagation model and the spatial correlation, the electromagnetic environment information estimation value near the monitoring station is high in accuracy, the fixed monitoring stations in the sea area can only be limited to be arranged on the island, the cost is high, the number is small, and a large number of interested areas without the monitoring stations in the neighborhood exist in the sea area.
Disclosure of Invention
Based on the above, there is a need to provide a method, an apparatus, a device and a storage medium for planning a flight path of an unmanned ship, which can optimize a design flight path for the unmanned ship to be planned having an electromagnetic monitoring function in a sea area without a monitoring station in the neighborhood.
A method of flight path planning for an unmanned ship, the method comprising:
acquiring electromagnetic environment monitoring data, the number of quasi-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 received power of a corresponding location.
And performing Kriging estimation according to the electromagnetic environment monitoring data to obtain a Kriging variance, and screening position information meeting a preset threshold condition according to the Kriging variance.
Calculating by adopting a clustering algorithm according to the number of the points to be monitored and the position information meeting the preset threshold condition to obtain the position information of the points to be monitored; the clustering algorithm is a hard clustering algorithm that groups data into a fixed number of clusters based on distance.
And designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so as to realize the navigation route planning of the unmanned ship to be planned.
An apparatus for path planning for an unmanned ship, the apparatus comprising:
the data acquisition module is used for acquiring electromagnetic environment monitoring data, the number of the pseudo-monitoring points and the initial position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data includes location information and received power of a corresponding location.
And the kriging variance determining module is used for obtaining the kriging variance by adopting kriging estimation according to the electromagnetic environment monitoring data, and screening the position information meeting the preset threshold condition according to the kriging variance.
The device comprises a monitoring point position information determining module, a monitoring point position information acquiring module and a monitoring point position information acquiring module, wherein the monitoring point position information determining module is used for calculating by adopting a clustering algorithm according to the number of monitoring points and position information meeting a preset threshold value condition to obtain the monitoring point position information; the clustering algorithm is a hard clustering algorithm that classifies data into a fixed number of clusters based on distance.
And the track planning module is used for designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so that the track planning of the unmanned ship to be planned is realized.
According to the unmanned ship track planning method, the unmanned ship track planning device, the unmanned ship track planning equipment and the storage medium, the method comprises the steps of obtaining electromagnetic environment monitoring data, the number of quasi-monitoring points and the starting position of the unmanned ship to be planned in a preset area; according to the electromagnetic environment monitoring data, performing kriging estimation to obtain kriging variance, and screening position information meeting a preset threshold condition according to the kriging variance; calculating by adopting a clustering algorithm according to the number of the points to be monitored and the position information meeting the preset threshold condition to obtain the position information of the points to be monitored; and designing a navigation route with the shortest total route for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point to be planned, so as to realize the navigation route planning of the unmanned ship to be planned. According to the method, the kriging variance in the land statistics method is used, error analysis is carried out on the estimation result in the region, the monitoring points to be monitored are reasonably selected through clustering under the condition of limited resources, and the electromagnetic spectrum map construction precision can be improved; the flight path planning is adaptively proposed through an artificial intelligence genetic algorithm, so that the monitoring efficiency can be effectively saved, and the electromagnetic space sensing efficiency is comprehensively improved.
Drawings
FIG. 1 is a schematic flow chart diagram illustrating a method for planning a flight path of an unmanned ship according to an embodiment;
FIG. 2 is a detailed flow chart of a method for planning a flight path of an unmanned ship in another embodiment;
FIG. 3 is a schematic diagram of a region kriging variance distribution and a site to be monitored in an embodiment;
fig. 4 is a schematic diagram of a path planning between a site to be monitored and an unmanned ship to be planned in another embodiment, wherein (a) the site to be monitored is distributed schematically, and (b) the path planning of the unmanned ship to be planned is schematically;
FIG. 5 is a comparison of root mean square errors of electromagnetic spectrum maps constructed under different deployment conditions, in one embodiment;
FIG. 6 is a comparison of the total distance of unmanned ship's flight path versus the cost in time for different deployment conditions in one embodiment;
FIG. 7 is a diagram of a track planner for an unmanned ship according to one embodiment;
fig. 8 is an internal structural diagram of the apparatus in one embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application more apparent, the present application is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the present application and are not intended to limit the present application.
In one embodiment, as shown in fig. 1, there is provided a method for planning a flight path of an unmanned ship, the method comprising the steps of:
step 100: acquiring electromagnetic environment monitoring data, the number of monitoring points to be monitored and the initial position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data includes location information and received power for a corresponding location.
Within the preset area is a region of interest.
The electromagnetic environment monitoring data in the preset area can be electromagnetic environment monitoring data of an island reef fixed monitoring station.
Specifically, the unmanned ship to be planned may be an unmanned ship having an electromagnetic monitoring function.
Using mathematical notation:
a data set is monitored for a limited number of electromagnetic environments within a region of interest,
the information of the position of the mobile phone is,
the received power is corresponding to the position information, wherein N is the serial number of the electromagnetic environment monitoring data, N is an integer which is more than or equal to 1 and less than N, and N is the number of the electromagnetic environment monitoring data; monitoring sequence of points to be monitored
And position information of the point to be monitored
Wherein m is pseudoThe number of the monitoring points, M is an integer which is more than or equal to 1 and less than M, M is the number of the points to be monitored, and M is an integer which is more than 1.
Step 102: and performing kriging estimation according to the electromagnetic environment monitoring data to obtain kriging variance, and screening position information meeting a preset threshold condition according to the kriging variance.
Step 104: and calculating by adopting a clustering algorithm according to the number of the to-be-monitored points and the position information meeting the preset threshold condition to obtain the position information of the to-be-monitored points.
The clustering algorithm is a hard clustering algorithm that sorts data into a fixed number of clusters based on distance.
Specifically, the clustering algorithm may be a K-Means clustering algorithm or a K-Means + + clustering algorithm.
Step 106: and designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so as to realize the navigation route planning of the unmanned ship to be planned.
In the flight path planning method, electromagnetic environment monitoring data, the number of monitoring points to be monitored and the initial position of the unmanned ship to be planned in a preset area are acquired; according to the electromagnetic environment monitoring data, performing kriging estimation to obtain kriging variance, and screening position information meeting a preset threshold condition according to the kriging variance; calculating by adopting a clustering algorithm according to the number of the points to be monitored and the position information meeting the preset threshold condition to obtain the position information of the points to be monitored; and designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so as to realize the navigation route planning of the unmanned ship to be planned. According to the method, the kriging variance in the geostatistics method is used, error analysis is carried out on the estimation result in the region, the quasi-monitoring points are reasonably selected through clustering under the condition of limited resources, and the electromagnetic spectrum map construction precision can be improved; the flight path planning is adaptively proposed through an artificial intelligence genetic algorithm, so that the monitoring efficiency can be effectively saved, and the electromagnetic space sensing efficiency is comprehensively improved.
In one embodiment, the predetermined threshold condition is that the kriging variance is greater than a predetermined adaptive threshold. Step 102 comprises: performing kriging estimation according to electromagnetic environment monitoring data to obtain a kriging variance; and comparing the kriging variance with a preset adaptive threshold, rejecting the position information of which the kriging variance is less than or equal to the preset adaptive threshold, and reserving the position information of which the kriging variance is greater than the preset adaptive threshold.
In one embodiment, the clustering algorithm in step 104 is a K-Means clustering algorithm.
In one embodiment, the clustering algorithm in step 104 is a K-Means + + clustering algorithm.
In one embodiment, step 106 includes: setting a monitoring sequence of the points to be monitored; starting from the initial position of the unmanned ship to be planned, randomly designing p tracks, and taking the p tracks as a current track scheme group; wherein p is an integer greater than 1; selecting in the current track scheme population according to a preset principle, and taking the selected result as a track child; the predetermined principle is the first 10% of the shortest total route in the track scheme population; respectively carrying out crossing and mutation operations on the flight path filial generation to obtain a filial generation propagation result; the crossing refers to exchanging the monitoring sequence of two adjacent points to be monitored according to a preset crossing parameter; the variation refers to the exchange of any two points in the flight path planning according to preset variation parameters; selecting the front p flight lines with the shortest total distance from the offspring breeding results as the current flight path scheme population, and entering the next iteration until the preset iteration times are reached; obtaining the sequence of each monitoring point to be monitored in the flight path with the shortest total route in the flight path scheme population and the position information of the monitoring points to be monitored; and obtaining the navigation route with the shortest total route of the planning object to be planned according to the monitoring sequence of each monitoring point and the position information of the monitoring points, and realizing the route planning of the unmanned ship to be planned.
Wherein, presetting the cross parameter comprises: the probability of finger crossing is a set parameter, and the sequence of exchanging some two points to be monitored is a reasonable random integer.
The preset variation parameters include: the probability of variation and the order of exchanging some two points to be monitored, the former is a set parameter, and the latter is two reasonable random integers. Generally, the probability of a mutation is a relatively small value.
The invention has the advantages that: the method utilizes the characteristic that the kriging method is used as a geostatistics method, and creatively uses the kriging variance as a reference index for optimizing the layout of the monitoring points; the method adaptively determines the positions of the points to be monitored in an interested area according to the number of the points to be monitored by the kriging variance screening and the K-means or K-means + + algorithm. The invention plans the flight path of the unmanned ship to be planned through an artificial intelligent genetic algorithm, and solves the optimization solution of TSP problems. The TSP problem may be specifically searched. In general, the TSP-like problem refers to the NP-hard-like problem, i.e. the optimal combination problem that cannot be solved by the precise algorithm.
TSP-type problems: the travel Salesman Problem Problem.
In one embodiment, as shown in fig. 2, a method for planning a flight path of an unmanned ship is provided, which first performs kriging interpolation according to monitoring data in an area to obtain a kriging variance. The kriging variance is used as a reflection of the kriging estimation accuracy and can be used for judging the reliability of the estimation value in the region, so that the position with the large kriging variance is the position with the low estimation accuracy and needing to further collect monitoring data. According to the distribution of the kriging variances in the region, selecting the variance with a larger value by setting a self-adaptive threshold, clustering according to the position information and the number of the points to be monitored, and selecting K-means as an algorithm for clustering the points with the larger variance value in the region because the number of the classes needs to be controlled to be the number of the points to be monitored, wherein the center of the class in the result is the position of the points to be monitored. And finally, optimally planning the flight path through a genetic algorithm according to the initial position of the unmanned ship to be planned and the positions of the monitoring points to be planned, so that the positions of the monitoring points to be planned can be monitored under the condition of the shortest total distance.
The flight path planning method in the embodiment specifically comprises the following steps:
(1) critical estimation based on monitoring data
Kriging goldEstimating: first using electromagnetic environment monitoring data
And
construction of unknown points s0The shadow fading component estimation value is:
wherein the content of the first and second substances,
as an unknown point s0(ii) a shadow fading estimate of (d); omeganIs the nth kriging weight coefficient.
To ensure that the estimation result of equation (1) is the optimal unbiased estimation, the kriging weight coefficient in equation (1) is obtained from the following kriging equation set according to the second order stationary assumption:
Kλ＝M (2)
in the formula:
wherein gamma (-) is a theoretical variation function, the theoretical variation function quantitatively describes the spatial correlation of the shadow fading component, and the experimental variation function calculated by monitoring data is obtained by fitting a corresponding theoretical model; l is the Lagrangian coefficient.
Meanwhile, the estimation accuracy of equation (1) is represented by the kriging variance:
and (3) kriging variance screening: and screening the kriging variance values in the region according to the estimation result of the kriging method. Passing areaAnd (3) adaptively setting a threshold value for the median of the intradomain kriging variance, reserving the position information of the point where the numerical value is greater than the threshold value, and discarding the position information of the rest points. Composing position information satisfying conditions
Wherein Q is the number of location information satisfying the threshold condition, Q is the serial number of location information satisfying the threshold condition, and Q is an integer greater than or equal to 1 and less than Q.
(2) Quasi-monitoring point estimation based on K-means clustering
Screening position information meeting threshold value conditions according to kriging variance
And the number m of the quasi-monitoring points, and the position information of the quasi-monitoring points
And (6) performing calculation.
First from location information satisfying a threshold condition
M number of points to be monitored are initialized and the position information is determined as
Then the following steps are carried out by NIterAnd (4) secondary iteration: (a) initializing a cluster to { CmM ═ 1,2, ·, M }; (b) for the
Calculating the distance between each element and the center of the cluster, i.e. calculating { p }0The position of each element in M1, 2, M to the current virtual monitoring point
Distance of Ou-Do-de, will sq(q) categorizing the class λ corresponding to the minimum Euclidean distanceqAre updated simultaneously
(c) For all { CmRecalculating the centroid of the sample points in M ═ 1,2, ·, M } as new pseudo-monitoring points; (d) and stopping iteration when the point to be monitored is not changed any more or the iteration number reaches the maximum value. And outputting the position information of the point to be monitored as a result. A schematic diagram of the kriging square difference distribution and the sites to be monitored in the area is shown in fig. 3.
(3) Genetic algorithm based flight path planning
According to the initial position of the unmanned ship to be planned and the position information of the point to be monitored
And calculating the shortest total distance and the track thereof. Firstly, starting from an initial position, randomly designing p tracks as the size of a track scheme population. The following steps are then iterated until a maximum number of iterations is met. (a) Selecting the top 10% of the shortest total distance from the flight path scheme population as a preferred filial generation to participate in the subsequent steps, wherein the number of the preferred filial generation is p0(ii) a (b) Respectively carrying out propagation operations, namely crossing and mutation, on the flight path filial generation; the crossing is to carry out the exchange of the sequence of two adjacent points to be monitored according to a preset crossing parameter; the mutation is to exchange any two points in the flight path planning according to preset mutation parameters; (c) selecting the front p routes with the shortest total distance as the size of a new population according to the propagation result of the filial generation; (d) and stopping after reaching the iteration upper limit. Finally, sequencing each monitoring point in the flight path with the shortest total route in the seed group
And its position information
As a result output. A schematic diagram of the route planning between the to-be-monitored stations and the unmanned ship to be planned is shown in fig. 4, wherein (a) the schematic diagram of the distribution of the to-be-monitored stations, and (b) the schematic diagram of the route planning of the unmanned ship to be planned.
The method is based on electromagnetic environment monitoring data of fixed monitoring stations in the area, the kriging variance in the area is obtained through the kriging method, the kriging variance is used as measurement of errors between estimated values and true values in the kriging method, and the kriging variance can be used for judging the height of the estimation accuracy of the kriging in the area. And clustering the region with large Krigin variance in the region to determine the position to be monitored in the sea area. And finally, designing a navigation route with the shortest total distance for the unmanned ship to be planned according to the position information to be monitored by an artificial intelligence genetic algorithm, and realizing the flight path planning of the unmanned ship to be planned.
In a verification embodiment, considering that the starting point of the application of monitoring the flight path planning of the unmanned ship to be planned is to improve the overall construction precision of the electromagnetic spectrum map, the Root Mean-Square Error (RMSE) is used as an index for judging whether the layout position of the monitoring point has performance improvement. In addition, whether the planning of the flight path can achieve the purposes of reducing the total route distance of the flight path and improving the layout efficiency of the whole monitoring station needs to be judged, so that the total route distance of different flight path schemes and the time spent by an algorithm need to be compared. According to the practical situation of engineering application laid by the island reef sea area monitoring stations, the indexes are compared through 100 times of independent repeated experiments.
FIG. 5 is a comparison of the root mean square error of electromagnetic spectrum maps constructed under different layout conditions. The abscissa is the proportion of the number of the points to be monitored to the number of the distributed monitoring sites, and the ordinate is the root mean square error of the electromagnetic spectrum map construction result under the condition of considering all the monitoring data. According to the method, after the optimal arrangement of the to-be-monitored points is carried out, the root mean square errors are larger than those of the random arrangement, and the purposes of comprehensively improving the electromagnetic spectrum map construction precision and guiding the arrangement of the to-be-monitored points can be achieved. In addition, with the reduction of the proportion of the to-be-monitored points, the performance of the invention for layout optimization is gradually improved, which shows that under the condition that the number of the to-be-monitored points is relatively sparse, the invention can effectively improve the construction precision of the electromagnetic spectrum map and complete the determination of the to-be-monitored points. The construction precision of the electromagnetic spectrum map is in positive correlation with the number of monitoring points, the precision improvement benefit brought by reasonably arranging the stations is higher under the condition that the pseudo-monitoring points are relatively sparse, and the method has strong application value on the estimation of the pseudo-monitoring points in the island sea area.
FIG. 6 is a comparison of total track distance ratio and time cost under different layout conditions. The abscissa is the ratio of the number of the points to be monitored to the number of the distributed monitoring stations, the left ordinate is the ratio of the total path of the optimized track to the total path of the random track, and the right ordinate is the time cost of the track planning stage. The chart shows that the ratio of the total distance is reduced along with the improvement of the ratio of the monitoring points, namely, the flight path planning of the unmanned ship flight path planning method is always shorter than the random distance swing, and the optimization performance of the unmanned ship flight path planning method for the unmanned ship is improved along with the improvement of the relative number of the monitoring points. At the same time, the time cost is also increased.
In conclusion, the method can realize the optimized estimation of the points to be monitored through the screening and clustering based on the kriging variance, achieve the aim of comprehensively improving the construction precision of the electromagnetic spectrum map, and obtain better performance improvement under the condition that the points to be monitored are relatively sparse; meanwhile, the unmanned ship track to be planned is planned through an artificial intelligence genetic algorithm, so that the total track distance is minimum and the monitoring efficiency is highest under the condition that the position of the to-be-monitored point is unchanged.
Compared with the prior art, the method is mainly characterized in that (1) estimation variance in a geostatistics method is utilized, error analysis is carried out on estimation results in a region, a to-be-monitored point is reasonably selected through clustering under the condition of limited resources, and the improvement of the electromagnetic spectrum map construction precision is demonstrated through experimental comparison; (2) the flight path planning is adaptively proposed through an artificial intelligence genetic algorithm, so that the monitoring efficiency can be effectively saved, and the electromagnetic space sensing efficiency is comprehensively improved.
It should be understood that although the various steps in the flow diagrams of fig. 1-2 are shown in order as indicated by the arrows, the steps are not necessarily performed in order as indicated by the arrows. The steps are not limited to being performed in the exact order illustrated and, unless explicitly stated, may be performed in other orders. Moreover, at least some of the steps in fig. 1-2 may include multiple sub-steps or multiple stages that are not necessarily performed at the same time, but may be performed at different times, and the order of performance of the sub-steps or stages is not necessarily sequential, but may be performed in turn or alternating with other steps or at least some of the sub-steps or stages of other steps.
In one embodiment, as shown in fig. 7, there is provided a flight path planning apparatus for an unmanned ship, including: data acquisition module, kriging variance determine module, plan monitor point position information determine module and track planning module, wherein:
the data acquisition module is used for acquiring electromagnetic environment monitoring data, the number of the pseudo-monitoring points and the initial position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data includes location information and received power for a corresponding location.
And the kriging variance determining module is used for obtaining the kriging variance by adopting kriging estimation according to the electromagnetic environment monitoring data, and screening the position information meeting the preset threshold condition according to the kriging variance.
The system comprises a pseudo-monitoring point position information determining module, a data processing module and a data processing module, wherein the pseudo-monitoring point position information determining module is used for calculating by adopting a clustering algorithm according to the number of pseudo-monitoring points and position information meeting a preset threshold condition to obtain the pseudo-monitoring point position information; the clustering algorithm is a hard clustering algorithm that sorts data into a fixed number of clusters based on distance.
And the track planning module is used for designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so that the track planning of the unmanned ship to be planned is realized.
In one embodiment, the predetermined threshold condition is that the kriging variance is greater than a predetermined adaptive threshold. The kriging variance determining module is further used for obtaining the kriging variance by adopting kriging estimation according to the electromagnetic environment monitoring data; and comparing the kriging variance with a preset adaptive threshold, eliminating the position information of which the kriging variance is smaller than or equal to the preset adaptive threshold, and keeping the position information of which the kriging variance is larger than the preset adaptive threshold.
In one embodiment, the clustering algorithm in the point position information to be monitored determination module is a K-Means clustering algorithm.
In one embodiment, the clustering algorithm in the position information determination module to be monitored is a K-Means + + clustering algorithm.
In one embodiment, the track planning module is further configured to set a monitoring order of the points to be monitored; starting from the initial position of the unmanned ship to be planned, randomly designing p tracks, and taking the p tracks as a current track scheme population; wherein p is an integer greater than 1; selecting in the current track scheme population according to a predetermined principle, and taking the selected result as a track child; the predetermined principle is the first 10% of the shortest total route in the flight path scheme population; respectively carrying out crossing and mutation operations on the flight path filial generation to obtain a filial generation propagation result; the crossing refers to exchanging the monitoring sequence of two adjacent points to be monitored according to a preset crossing parameter; the variation refers to the exchange of any two points in the flight path planning according to preset variation parameters; selecting the front p routes with the shortest total distance from the offspring breeding results as the current track scheme population, and entering the next iteration until the preset iteration times are reached; obtaining the sequence of each monitoring point to be monitored in the flight path with the shortest total route in the flight path scheme population and the position information of the monitoring points to be monitored; and obtaining the navigation route with the shortest total route of the planning object to be planned according to the monitoring sequence of each monitoring point and the position information of the monitoring points, and realizing the route planning of the unmanned ship to be planned.
For the specific definition of the route planning device, reference may be made to the above definition of the route planning method, which is not described herein again. The modules in the above-mentioned route planning device can be implemented wholly or partially by software, hardware and their combination. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor calls and executes operations corresponding to the modules.
In one embodiment, a device is provided, which may be a terminal, and its internal structure diagram may be as shown in fig. 8. The device comprises a processor, a memory, a network interface, a display screen and an input device which are connected through a system bus. Wherein the processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium, 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 an operating system and computer programs in the non-volatile storage medium. The network interface of the device is used for communicating with an external terminal through network connection. The computer program is executed by a processor to implement a method of flight path planning for an unmanned ship. 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 covered on the display screen, a key, a track ball or a touch pad arranged on the shell of the device, an external keyboard, a touch pad or a mouse and the like.
Those skilled in the art will appreciate that the configuration shown in fig. 8 is a block diagram of only a portion of the configuration associated with the present application and does not constitute a limitation on the devices to which the present application applies, and that a particular device may include more or less components than those shown, or may combine certain components, or have a different arrangement of components.
In one embodiment, an apparatus is provided comprising a memory having a computer program stored thereon and a processor that when executed performs the steps of the above-described method embodiments.
In an embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which computer program, when being executed by a processor, carries out the steps of the above-mentioned method embodiments.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by hardware instructions of a computer program, which can be stored in a non-volatile computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in the embodiments provided herein may include non-volatile and/or volatile memory, among others. Non-volatile memory can include read-only memory (ROM), Programmable ROM (PROM), Electrically Programmable ROM (EPROM), Electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), Dynamic RAM (DRAM), Synchronous DRAM (SDRAM), Double Data Rate SDRAM (DDRSDRAM), Enhanced SDRAM (ESDRAM), Synchronous Link DRAM (SLDRAM), Rambus Direct RAM (RDRAM), direct bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).
The technical features of the above embodiments can be arbitrarily combined, and for the sake of brevity, all possible combinations of the technical features in the above embodiments are not described, but should be considered as the scope of the present specification as long as there is no contradiction between the combinations of the technical features.
The above-mentioned embodiments only express several embodiments of the present application, and the description thereof is more specific and detailed, but not construed as limiting the scope of the invention. It should be noted that, for a person skilled in the art, several variations and modifications can be made without departing from the concept of the present application, which falls within the scope of protection of the present application. Therefore, the protection scope of the present patent application shall be subject to the appended claims.
Claims (10)
1. A method for planning a flight path of an unmanned ship, the method comprising:
acquiring electromagnetic environment monitoring data, the number of monitoring points to be monitored and the initial position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data comprises position information and receiving power of a corresponding position;
according to the electromagnetic environment monitoring data, performing kriging estimation to obtain kriging variance, and screening position information meeting a preset threshold condition according to the kriging variance;
calculating by adopting a clustering algorithm according to the number of the points to be monitored and the position information meeting the preset threshold condition to obtain the position information of the points to be monitored; the clustering algorithm is a hard clustering algorithm which divides data into a fixed number of clusters based on distance;
and designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so as to realize the navigation route planning of the unmanned ship to be planned.
2. The method of claim 1, wherein the preset threshold condition is a kriging variance greater than a preset adaptive threshold;
according to the electromagnetic environment monitoring data, kriging estimation is adopted to obtain kriging variance, and according to the kriging variance, position information meeting a preset threshold condition is screened, wherein the method comprises the following steps:
according to the electromagnetic environment monitoring data, performing kriging estimation to obtain a kriging variance;
and comparing the kriging variance with a preset adaptive threshold, eliminating the position information of which the kriging variance is less than or equal to the preset adaptive threshold, and keeping the position information of which the kriging variance is greater than the preset adaptive threshold.
3. The method according to claim 1, wherein the position information of the to-be-monitored points is obtained by calculating with a clustering algorithm according to the number of the to-be-monitored points and the position information meeting a preset threshold condition, wherein the clustering algorithm in the step is a K-Means clustering algorithm.
4. The method according to claim 1, wherein the position information of the quasi monitoring points is obtained by calculating with a clustering algorithm according to the number of the quasi monitoring points and the position information meeting a preset threshold condition, wherein the clustering algorithm in the step is a K-Means + + clustering algorithm.
5. The method according to claim 1, wherein a genetic algorithm is adopted to design a navigation route with the shortest total distance for the unmanned ship to be planned according to the initial position of the unmanned ship to be planned and the position information of each monitoring point to be planned, so as to realize the route planning of the unmanned ship to be planned, and the method comprises the following steps:
setting a monitoring sequence of the points to be monitored;
starting from the initial position of the unmanned ship to be planned, randomly designing p tracks, and taking the p tracks as a current track scheme population; wherein p is an integer greater than 1;
selecting the current flight path scheme population according to a preset principle, and taking the selected result as a flight path child; the predetermined principle is the first 10% of the shortest total route in the track scheme population;
respectively carrying out crossing and mutation operations on the flight path filial generation to obtain a filial generation propagation result; the crossing refers to exchanging the monitoring sequence of two adjacent points to be monitored according to a preset crossing parameter; the variation refers to exchanging any two points in the flight path planning according to preset variation parameters;
selecting the front p routes with the shortest total distance from the offspring breeding results as a current track scheme population, and entering the next iteration until the preset iteration times are reached; obtaining the sequence of each monitoring point to be monitored in the flight path with the shortest total route in the flight path scheme population and the position information of the monitoring points to be monitored;
and obtaining the navigation route with the shortest total route of the planning object to be planned according to the monitoring sequence of each monitoring point and the position information of the monitoring points, and realizing the route planning of the unmanned ship to be planned.
6. An unmanned ship's track planning apparatus, the apparatus comprising:
the data acquisition module is used for acquiring electromagnetic environment monitoring data, the number of the pseudo-monitoring points and the initial position of the unmanned ship to be planned in a preset area; the electromagnetic environment monitoring data comprises position information and receiving power of a corresponding position;
the kriging variance determining module is used for obtaining the kriging variance by adopting kriging estimation according to the electromagnetic environment monitoring data, and screening the position information meeting the preset threshold condition according to the kriging variance;
the monitoring point position information determining module is used for calculating by adopting a clustering algorithm according to the number of the monitoring points and the position information meeting the preset threshold condition to obtain the position information of the monitoring points; the clustering algorithm is a hard clustering algorithm which divides data into a fixed number of clusters based on distance;
and the track planning module is used for designing a navigation route with the shortest total distance for the unmanned ship to be planned by adopting a genetic algorithm according to the initial position of the unmanned ship to be planned and the position information of each monitoring point, so that the track planning of the unmanned ship to be planned is realized.
7. The method of claim 6, wherein the preset threshold condition is a kriging variance greater than a preset adaptive threshold;
the kriging variance determining module is further used for obtaining the kriging variance by adopting kriging estimation according to the electromagnetic environment monitoring data; and comparing the kriging variance with a preset adaptive threshold, eliminating the position information of which the kriging variance is less than or equal to the preset adaptive threshold, and keeping the position information of which the kriging variance is greater than the preset adaptive threshold.
8. The method of claim 6, wherein the clustering algorithm in the module for determining location information of points to be monitored is a K-Means clustering algorithm.
9. An apparatus comprising a memory and a processor, the memory storing a computer program, wherein the processor implements the steps of the method of any one of claims 1 to 5 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method of any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210395527.3A CN114690782A (en) | 2022-04-15 | 2022-04-15 | Method, device, equipment and storage medium for planning flight path of unmanned ship |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210395527.3A CN114690782A (en) | 2022-04-15 | 2022-04-15 | Method, device, equipment and storage medium for planning flight path of unmanned ship |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114690782A true CN114690782A (en) | 2022-07-01 |
Family
ID=82142508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210395527.3A Pending CN114690782A (en) | 2022-04-15 | 2022-04-15 | Method, device, equipment and storage medium for planning flight path of unmanned ship |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114690782A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115129088A (en) * | 2022-08-26 | 2022-09-30 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle track planning and obstacle avoidance method and system based on frequency spectrum map |
-
2022
- 2022-04-15 CN CN202210395527.3A patent/CN114690782A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115129088A (en) * | 2022-08-26 | 2022-09-30 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle track planning and obstacle avoidance method and system based on frequency spectrum map |
| CN115129088B (en) * | 2022-08-26 | 2022-11-15 | 中国人民解放军国防科技大学 | Unmanned aerial vehicle track planning and obstacle avoidance method and system based on frequency spectrum map |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102611938B1 (en) | Generate integrated circuit floorplans using neural networks | |
| Di Prinzio et al. | Data-driven catchment classification: application to the pub problem | |
| US6889053B1 (en) | Likelihood-based geolocation prediction algorithms for CDMA systems using pilot strength measurements | |
| Castro et al. | Likelihood based hierarchical clustering | |
| Lichti et al. | Estimating utilization distributions with kernel versus local convex hull methods | |
| CN115315703A (en) | Generating an integrated circuit layout using a neural network | |
| CN109886388A (en) | A kind of training sample data extending method and device based on variation self-encoding encoder | |
| CN110648014B (en) | Regional wind power prediction method and system based on space-time quantile regression | |
| US20210342722A1 (en) | Air quality prediction model training method, air quality prediction method, electronic device and storage medium | |
| US20170338802A1 (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| CN110221600B (en) | Path planning method and device, computer equipment and storage medium | |
| CN107679558A (en) | A kind of user trajectory method for measuring similarity based on metric learning | |
| CN111666971A (en) | Event identification method, device and equipment based on position location and storage medium | |
| CN107194498B (en) | Hydrologic monitoring network optimization method | |
| US20220067336A1 (en) | System and process for integrative computational soil mapping | |
| CN110445567B (en) | Electromagnetic spectrum map construction method | |
| Monteil et al. | Multi-objective calibration by combination of stochastic and gradient-like parameter generation rules–the caRamel algorithm | |
| CN114690782A (en) | Method, device, equipment and storage medium for planning flight path of unmanned ship | |
| Lu et al. | Doomed run prediction in physical design by exploiting sequential flow and graph learning | |
| CN110366188B (en) | Interference measurement point deployment method, interference measurement path planning method and system | |
| CN114828026A (en) | Base station planning method, device, equipment, storage medium and program product | |
| Palacios-Rodríguez et al. | Generalized Pareto processes for simulating space-time extreme events: an application to precipitation reanalyses | |
| CN106503386A (en) | The good and bad method and device of assessment luminous power prediction algorithm performance | |
| CN117575494A (en) | Aggregation method, system, terminal and medium for multi-target REDD item area | |
| Johnson et al. | Regionalisation of rainfall statistics for the IFD Revision Project |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |