CN116989798B - Unmanned aerial vehicle track planning method - Google Patents
Unmanned aerial vehicle track planning method Download PDFInfo
- Publication number
- CN116989798B CN116989798B CN202311255289.7A CN202311255289A CN116989798B CN 116989798 B CN116989798 B CN 116989798B CN 202311255289 A CN202311255289 A CN 202311255289A CN 116989798 B CN116989798 B CN 116989798B
- Authority
- CN
- China
- Prior art keywords
- dividing
- division
- mode
- population
- optimal
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 90
- 239000013598 vector Substances 0.000 claims abstract description 47
- 238000005192 partition Methods 0.000 claims description 37
- 230000008569 process Effects 0.000 claims description 25
- 230000006870 function Effects 0.000 claims description 24
- 238000000638 solvent extraction Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 claims description 3
- 238000005215 recombination Methods 0.000 claims description 3
- 230000006798 recombination Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 11
- 238000010586 diagram Methods 0.000 description 6
- 238000004422 calculation algorithm Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 3
- 238000004088 simulation Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 239000000470 constituent Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000000523 sample Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/088—Non-supervised learning, e.g. competitive learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The invention relates to the technical field of flight path planning, in particular to an unmanned aerial vehicle flight path planning method. The method comprises the following steps: sequentially carrying out rasterization and vectorization on an environment map where the search area is located to obtain a vector raster map; setting an initial population, a maximum iteration number and a target cost function; starting from the initial population, for each generation of population, execution is performed: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the method comprises the steps of re-dividing the dividing modes of the current generation population based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and other three dividing modes selected randomly to obtain the next generation population, outputting the optimal dividing modes of all generation populations until iteration of the maximum iteration number is completed, and indicatingZAnd (5) setting up a search track of the unmanned aerial vehicle.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle track planning, in particular to an unmanned aerial vehicle track planning method.
Background
With rapid development of technology, unmanned aerial vehicles are applied to various fields such as exploration, reconnaissance and search and rescue. Due to limitations in the aspects of maneuvering range, endurance, executive capability and the like, a single unmanned aerial vehicle is difficult to independently complete complex tasks with large scale, and a plurality of unmanned aerial vehicles are clustered to form development directions and research hotspots in the current unmanned aerial vehicle field.
The cluster cooperation of a plurality of unmanned aerial vehicles means that under the support of a communication network between unmanned aerial vehicles and between the unmanned aerial vehicles and a ground station, an effective cluster mechanism is formed through information communication and fusion, and complex large-scale target search tasks are completed rapidly. However, the target searching efficiency of the multi-frame unmanned aerial vehicle is low at present.
Based on the above, the invention provides an unmanned aerial vehicle track planning method for solving the technical problems.
Disclosure of Invention
The invention describes an unmanned aerial vehicle track planning method, which can improve the target searching efficiency of a plurality of unmanned aerial vehicles.
According to a first aspect, the invention provides an unmanned aerial vehicle track planning method, comprising the following steps:
sequentially carrying out rasterization and vectorization on an environment map where the search area is located to obtain a vector raster map; the environment map comprises a search area and a non-search area, and grid vectors of the search area in the vector grid map are set to be 1-ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is set to 0, and grid vectors of non-search areas in the vector grid map are set to 0;
setting an initial population, a maximum iteration number and a target cost function; wherein the initial population comprises randomly generated search regionsNThe number of the divided areas obtained by dividing each dividing mode is equal to the number of the frames of the unmanned aerial vehicle;
starting from the initial population, for each generation of population, performing: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the method comprises the steps of carrying out re-partition on the partition modes of the current generation population based on the optimal partition mode, the suboptimal partition mode, the worst partition mode and other three partition modes selected randomly to obtain the next generation population until the iteration of the maximum iteration times is completed, and outputting the optimal partition modes of all generation populations; wherein the optimal division mode is used for indicatingZUnmanned aerial vehicle frameAnd searching for tracks.
According to a second aspect, the present invention provides an unmanned aerial vehicle track planning apparatus, comprising:
the processing unit is configured to sequentially perform rasterization and vectorization on the environment map where the search area is located, so as to obtain a vector raster map; the environment map comprises a search area and a non-search area, and grid vectors of the search area in the vector grid map are set to be 1-ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is set to 0, and grid vectors of non-search areas in the vector grid map are set to 0;
the setting unit is configured to set an initial population, a maximum iteration number and a target cost function; wherein the initial population comprises randomly generated search regionsNThe number of the divided areas obtained by dividing each dividing mode is equal to the number of the frames of the unmanned aerial vehicle;
an execution unit configured to execute, for each generation of population, starting from the initial population: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the method comprises the steps of carrying out re-partition on the partition modes of the current generation population based on the optimal partition mode, the suboptimal partition mode, the worst partition mode and other three partition modes selected randomly to obtain the next generation population until the iteration of the maximum iteration times is completed, and outputting the optimal partition modes of all generation populations; wherein the optimal division mode is used for indicatingZAnd (5) setting up a search track of the unmanned aerial vehicle.
According to a third aspect, the present invention provides an electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of the first aspect when executing the computer program.
According to a fourth aspect, the present invention provides a computer readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of the first aspect.
According to the unmanned aerial vehicle track planning method provided by the invention, the environment map where the search area is located is subjected to rasterization processing and vectorization processing in sequence to obtain the vector raster map, the initial population, the maximum iteration times and the target cost function are set, and in the iteration process of each generation of population, the next generation of population is obtained by re-dividing the division modes of the current generation of population based on the optimal division mode, the suboptimal division mode, the worst division mode and the other three division modes selected randomly, so that the diversity of the population can be increased, and the situation of being trapped in local optimum is avoided. Therefore, the target searching efficiency of the unmanned aerial vehicle can be improved through the technical scheme.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions of the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings described below are some embodiments of the present invention, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 illustrates a flow diagram of a method of unmanned aerial vehicle track planning, according to one embodiment;
FIG. 2 shows a schematic block diagram of a drone flight path planning apparatus according to one embodiment;
FIG. 3 illustrates a grid map of a search area of SAR scanning in accordance with one embodiment;
FIG. 4 illustrates a grid map of a search area of magnetic probing according to one embodiment;
FIG. 5 illustrates a schematic diagram of a division of search areas, according to one embodiment;
FIG. 6 illustrates a track schematic of five unmanned SAR scans using a unmanned aerial vehicle track planning method according to one embodiment;
fig. 7 shows a schematic diagram of a track of five unmanned aerial vehicle magnetic probes employing a unmanned aerial vehicle track planning method according to one embodiment.
Detailed Description
The scheme provided by the invention is described below with reference to the accompanying drawings.
Fig. 1 shows a flow diagram of a method of unmanned aerial vehicle track planning, according to one embodiment. It is understood that the method may be performed by any apparatus, device, platform, cluster of devices having computing, processing capabilities. As shown in fig. 1, the method includes:
step 100, sequentially carrying out rasterization and vectorization on an environment map where a search area is located to obtain a vector raster map; the environment map comprises a search area and a non-search area, and grid vectors of the search area in the vector grid map are set to be 1-ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is set to 0, and grid vectors of non-search areas in the vector grid map;
102, setting an initial population, a maximum iteration number and a target cost function; wherein the initial population comprises a random generation for the search areaNThe number of the divided areas obtained by dividing each dividing mode is equal to the number of the frames of the unmanned aerial vehicle;
step 104, starting from the initial population, for each generation of population, executing: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the method comprises the steps of carrying out re-partition on the partition modes of the current generation population based on the optimal partition mode, the suboptimal partition mode, the worst partition mode and other three partition modes selected randomly to obtain the next generation population until iteration of the maximum iteration times is completed, and outputting the optimal partition modes of all generation populations; wherein the optimal division mode is used for indicatingZAnd (5) setting up a search track of the unmanned aerial vehicle.
In this embodiment, the environment map where the search area is located is sequentially subjected to rasterization and vectorization to obtain a vector raster map, and an initial population, a maximum iteration number and a target cost function are set, and in the iteration process of each generation of population, the next generation of population is obtained by re-dividing the division manner of the current generation of population based on the optimal division manner, the suboptimal division manner, the worst division manner and other three division manners selected randomly, so that the diversity of the population can be increased, and the occurrence of local optimizations is avoided. Therefore, the target searching efficiency of the unmanned aerial vehicle can be improved through the technical scheme.
It should be noted that, at present, an algorithm of polynomial time complexity cannot be found to solve, and an optimal solution cannot be obtained in an acceptable time through an exhaustive algorithm. Therefore, the above-mentioned solution cannot guarantee that the search results in an optimal solution, but can result in a satisfactory solution, i.e. an optimal solution within a limited time range (constrained by the maximum number of iterations).
The steps are described in turn below.
For step 100:
the multi-extension-free cluster search problem firstly needs to model a search environment, namely, normalizes an environment map of a search area so as to solve a search path. The purpose of constructing the environment map is to help the drone plan an optimal search path in the search area. By using the grid map representation mode suitable for the task search environment, the storage space can be saved, and the solving efficiency of the path planning algorithm can be improved. A rasterization algorithm (not described in detail herein, as is well known to those skilled in the art) may be used to discretize the search area into a tight grid of uniform shape and size to facilitate the solution of the subsequent path planning algorithm.
The grid map obtained by the rasterization processing is a matrix, and the area to be searched is set to be 1-1%ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is 0, the area which does not need to be searched is 0, then the vector grid map is obtained through vectorization processing of the grid map, at the moment, the vector grid map contains vector information (or vector information, namely an integer set by each grid) of the searched area and the non-searched area, and indexes of the searched area are obtained, so that the searched area can be effectively divided subsequently.
For step 102:
it should be noted that, the unmanned aerial vehicle provided by the embodiment of the invention mainly refers to a fixed-wing unmanned aerial vehicle, and compared with a rotor unmanned aerial vehicle, the unmanned aerial vehicle of this type has a far greater turning cost than a direct flight cost, so that when dividing an area, grids need to be concentrated as much as possible and the number of times of turning of the unmanned aerial vehicle needs to be reduced.
In order to solve the technical problem, in one embodiment of the present invention, the objective cost function is calculated by the following formula:
；
in the method, in the process of the invention,Las a function of the cost of the object,n col andn row the number of columns and rows of search areas in the vector grid map,nfor the number of grids of the search area in the vector grid map,L t for the length of the turning path of the drone,L s is the straight path length of the unmanned aerial vehicle.
For step 104:
in one embodiment of the present invention, the optimal partitioning of the current generation population is calculated by the following formula:
；
in the method, in the process of the invention,Jfor the optimal division mode of the current generation of population (namely, the division mode of the unmanned aerial vehicle with the shortest path length in all the division modes of the first generation of population is selected as the optimal division mode of the population),L i is the firstiThe maximum value of the objective cost function of all the division areas in the division manner (i.e. the searching efficiency of the multiple unmanned aerial vehicles depends on the unmanned aerial vehicle with the longest path length).
Similarly, in one embodiment of the present invention, the optimal partitioning of all generation populations is calculated by the following formula:
；
in the method, in the process of the invention,J best for the best way of dividing the population of all generations,J i is the firstkThe optimal division mode of the generation group,Mis the maximum number of iterations.
As before, to avoid trapping in local optima, increasing the diversity of the population, such as repartitioning the manner in which each generation of population is partitioned, may be considered.
In one embodiment of the present invention, the step of "re-dividing the dividing manner of the current generation population based on the optimal dividing manner, the suboptimal dividing manner, the worst dividing manner and the other three dividing manners selected randomly" may specifically include:
based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and other three dividing modes selected randomly, two new first dividing modes are obtained through calculation;
at random, a random number is generatedr 1 When the number of the first division modes is smaller than 0.5, recombining the two new first division modes, and calculating to obtain a new second division mode;
at random, a random number is generatedr 1 When the number of the first division is not smaller than 0.5 and smaller than 1, a new third division is calculated based on the optimal division mode of the current generation population and other three randomly selected division modes;
and re-dividing the dividing mode of the current generation population based on the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population.
In this embodiment, the new second division manner and the third division manner are obtained twice sequentially, so that not only the diversity, the randomness and the local searching capability of the population can be increased, but also the situation of sinking into local optimum can be avoided.
In one embodiment of the present invention, the two new first divisions are calculated by the following formula:
；；
；
；
；；；；；；；；
；
in the method, in the process of the invention,and->Represent the firstkTwo new generations of random generationiThe division, i.e. two new first divisions, +.>Represent the firstkFirst generation groupiDivision mode(s)>Represent the firstkOptimal division of generation population,/->Represent the firstkSub-optimal partitioning of generation population, +.>Represent the firstkWorst division of generation population, +.>、/>、/>Represent the firstkThree other dividing modes for randomly selecting generation population,kis the algebra of the population of the present generation,Mfor the maximum number of iterations to be performed,ris at [0,0.5]A random number randomly generated within the range,r n to fit a random number of a standard normal distribution,r 1 is a random number randomly generated within the (0, 1) range.
In this embodiment, the above-mentioned process of obtaining the first division manner has the characteristics of not only strong optimizing capability, but also fast convergence speed.
In one embodiment of the present invention, a new second partitioning method is calculated by the following formula:
；
in the method, in the process of the invention,represent the firstkNew first generation of recombination of generation groupiThe division, i.e. a new second division,r 2 、r 3 for two random numbers selected in the (0, 1) range.
In this embodiment, the above procedure of obtaining the second division manner may increase the local searching capability of the population to generate a new better vector.
In one embodiment of the present invention, a new third partitioning method is calculated by the following formula:
；
；
in the method, in the process of the invention,represent the firstkNew generation group calculationiThe division, i.e. a new third division,v 1 、v 2 is within (0, 1)]Two random numbers selected in the range, +.>For a random number selected in the range of (0, 1),r 2 、r 3 for two random numbers selected in the (0, 1) range.
In this embodiment, the above-mentioned process of obtaining the third division manner can avoid sinking into local optimum to generate a new better vector.
In one embodiment of the present invention, the step of "repartitioning the partition mode of the current generation population based on the optimal partition mode, the new second partition mode and the new third partition mode" may specifically include:
and taking the optimal one of the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population as the optimal dividing mode after the current generation population is divided again.
In summary, by adjusting parameters to generate a new region division mode, after the new region division mode is generated, comparing with the region division mode waiting for updating, the better one is reserved and used as a region division mode in the new generation, and repeating the above operationNThe generation group is re-divided one by one (comprising a new second division mode and a new third division mode are obtained by calculation), thus generatingNAnd finally outputting the new generation population to obtain the optimal division mode of all generation populations.
It should be noted that, when updating the division manner of the current generation population in the iterative process of each generation population, the condition is based on updating the grid vector of the search area in the vector grid map, and since the random number of (0, 1) is introduced in the updating process, the updated grid vector is in the decimal condition. In order to more accurately perform region division, the inventors creatively consider: the current grid vector may be sequentially subjected to rounding and scaling, for example, to obtain a grid vector of 1.34, and then the number may be rounded up, rounded down, or rounded up to obtain an integer; and if the number after rounding is less than 1 and greater thanZIt is necessary to perform a reduction process, for example, to obtain a rounded grid vector of 0, and then consider it as 1, for example, to obtain a rounded grid vector of 1Z+1, then consider it asZ. By the processing, the division of the search area can be ensured to accord with the actual application scene in each updating iteration process.
A specific application example of the unmanned aerial vehicle track planning method is described below.
(1) Generating a grid map (vectorization results not shown)
Four search area maps of different shapes and sizes shown in fig. 3 are selected to be used as the SAR scanning cluster search simulation test map. In fig. 3, each area is actually square with a side length of 50 km, the single grid is square with a side length of 2.5 km, and the grid map behind the grid is a 20×20 matrix. The black area is a grid that does not need to be searched, and the white area is a grid that needs to be searched.
Four different shapes and sizes of the search area map shown in fig. 4 are selected to be used as the magnetic detection cluster search simulation test map. In fig. 4, the actual size of each area is a square with a side length of 50 km, the single grid is a square with a side length of 0.5 km, and the grid map behind the grid is a 100×100 matrix. The black area is a grid that does not need to be searched, and the white area is a grid that needs to be searched.
Wherein, the search area 1 shown in the figure (a) has 1985 grids to be searched, and the area is 496.25 km 2 The method comprises the steps of carrying out a first treatment on the surface of the The search area 2 shown in fig. (b) has 1747 grids to be searched and an area of 436.75 km 2 The method comprises the steps of carrying out a first treatment on the surface of the The search area 3 shown in the figure (c) has 2426 grids to be searched and the area is 606.5 km 2 The method comprises the steps of carrying out a first treatment on the surface of the The search area 4 shown in the figure (d) has 2887 grids to be searched and the area is 721.75 km 2 。
The allocation area is solved by adopting the unmanned aerial vehicle track planning method, and as illustrated in fig. 5, the area is allocated to five unmanned aerial vehicles.
(2) Searching simulation results
For four areas with different shapes of SAR scanning, the search paths of the five unmanned aerial vehicle clusters are solved by adopting the unmanned aerial vehicle track planning method, and (a), (b), (c) and (d) in FIG. 6 are search paths of the search area a, b, c, d in FIG. 3 respectively.
For the four areas with different magnetic detection shapes, the search paths of the five unmanned aerial vehicle cluster search are solved by adopting the unmanned aerial vehicle track planning method, and (a), (b), (c) and (d) in fig. 7 are search paths of the search area a, b, c, d in fig. 4 respectively.
The foregoing describes certain embodiments of the present invention. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
According to an embodiment of another aspect, the invention provides an unmanned aerial vehicle track planning device. Fig. 2 shows a schematic block diagram of a drone flight path planning apparatus according to one embodiment. It will be appreciated that the apparatus may be implemented by any means, device, platform or cluster of devices having computing, processing capabilities. As shown in fig. 2, the apparatus includes: a processing unit 200, a setting unit 202, and an executing unit 204. Wherein the main functions of each constituent unit are as follows:
the processing unit 200 is configured to sequentially perform rasterization and vectorization on the environment map where the search area is located, so as to obtain a vector raster map; the environment map comprises a search area and a non-search area, and grid vectors of the search area in the vector grid map are set to be 1-ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is set to 0, and grid vectors of non-search areas in the vector grid map are set to 0;
a setting unit 202 configured to set an initial population, a maximum number of iterations, and a target cost function; wherein the initial population comprises randomly generated search regionsNThe number of the divided areas obtained by dividing each dividing mode is equal to the number of the frames of the unmanned aerial vehicle;
an execution unit 204 configured to execute, for each generation of population, starting from the initial population: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the dividing mode of the current generation population is divided again based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and other three dividing modes selected randomly to obtain the next generation population until the iteration of the maximum iteration times is completed, and the next generation population is outputOptimal division modes of all generation populations; wherein the optimal division mode is used for indicatingZAnd (5) setting up a search track of the unmanned aerial vehicle.
As a preferred embodiment, the objective cost function is calculated by the following formula:
；
in the method, in the process of the invention,Lfor the purpose of the objective cost function,n col andn row the number of columns and the number of rows of the search area in the vector grid map,nfor the number of grids of the search area in the vector grid map,L t for the length of the turning path of the drone,L s the straight path length of the unmanned aerial vehicle;
the optimal dividing mode of the generation population is calculated by the following formula:
；
in the method, in the process of the invention,Jfor the optimal division mode of the current generation population,L i is the firstiThe maximum value of the target cost function of all the division areas in the division modes;
the optimal division mode of all generation groups is calculated by the following formula:
；
in the method, in the process of the invention,J best for the best way of dividing the population of all generations,J i is the firstkThe optimal division mode of the generation group,Mand the maximum iteration number is the maximum iteration number.
As a preferred embodiment, the re-dividing the dividing method of the current generation population based on the optimal dividing method, the suboptimal dividing method, the worst dividing method and the other three dividing methods selected randomly includes:
based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and other three dividing modes selected randomly, two new first dividing modes are obtained through calculation;
at random, a random number is generatedr 1 When the number of the first division modes is smaller than 0.5, recombining the two new first division modes, and calculating to obtain a new second division mode;
at random, a random number is generatedr 1 When the number of the first division is not smaller than 0.5 and smaller than 1, a new third division is calculated based on the optimal division mode of the current generation population and other three randomly selected division modes;
and re-dividing the dividing mode of the current generation population based on the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population.
As a preferred embodiment, the two new first divisions are calculated by the following formula:
；
；
；
；
；；
；/>；；
；；；
；
in the method, in the process of the invention,and->Represent the firstkTwo new generations of random generationiThe division, i.e. two new first divisions, +.>Represent the firstkFirst generation groupiDivision mode(s)>Represent the firstkOptimal division of generation population,/->Represent the firstkSub-optimal partitioning of generation population, +.>Represent the firstkWorst division of generation population, +.>、/>、/>Represent the firstkThree other dividing modes for randomly selecting generation population,kis the algebra of the population of the present generation,Mfor the maximum number of iterations to be described,ris at [0,0.5]A random number randomly generated within the range,r n to fit a random number of a standard normal distribution,r 1 is a random number randomly generated within the (0, 1) range.
As a preferred embodiment, a new second division is calculated by the following formula:
；
in the method, in the process of the invention,represent the firstkNew first generation of recombination of generation groupiThe division, i.e. a new second division,r 2 、r 3 for two random numbers selected in the (0, 1) range.
As a preferred embodiment, a new third division is calculated by the following formula:
；
；
in the method, in the process of the invention,represent the firstkNew generation group calculationFirst, theiThe division, i.e. a new third division,v 1 、v 2 is within (0, 1)]Two random numbers selected in the range, +.>For a random number selected in the range of (0, 1),r 2 、r 3 for two random numbers selected in the (0, 1) range. />
As a preferred embodiment, the re-dividing the current generation of the partition mode based on the optimal partition mode, the new second partition mode and the new third partition mode of the current generation of the partition mode includes:
and taking the optimal one of the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population as the optimal dividing mode after the current generation population is divided again.
According to an embodiment of another aspect, there is also provided a computer-readable storage medium having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method described in connection with fig. 1.
According to an embodiment of yet another aspect, there is also provided an electronic device including a memory having executable code stored therein and a processor that, when executing the executable code, implements the method described in connection with fig. 1.
The embodiments of the present invention are described in a progressive manner, and the same and similar parts of the embodiments are all referred to each other, and each embodiment is mainly described in the differences from the other embodiments. In particular, for the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments in part.
Those skilled in the art will appreciate that in one or more of the examples described above, the functions described in the present invention may be implemented in hardware, software, firmware, or any combination thereof. When implemented in software, these functions may be stored on or transmitted over as one or more instructions or code on a computer-readable medium.
The foregoing embodiments have been provided for the purpose of illustrating the general principles of the present invention in further detail, and are not to be construed as limiting the scope of the invention, but are merely intended to cover any modifications, equivalents, improvements, etc. based on the teachings of the invention.
Claims (4)
1. The unmanned aerial vehicle track planning method is characterized by comprising the following steps of:
sequentially carrying out rasterization and vectorization on an environment map where the search area is located to obtain a vector raster map; the environment map comprises a search area and a non-search area, and grid vectors of the search area in the vector grid map are set to be 1-ZIs an integer of one of the above,Zthe number of frames of the unmanned aerial vehicle is set to 0, and grid vectors of non-search areas in the vector grid map are set to 0;
setting an initial population, a maximum iteration number and a target cost function; wherein the initial population comprises randomly generated search regionsNThe number of the divided areas obtained by dividing each dividing mode is equal to the number of the frames of the unmanned aerial vehicle;
starting from the initial population, for each generation of population, performing: calculating each dividing mode of the current generation population by utilizing the target cost function, and determining an optimal dividing mode, a suboptimal dividing mode and a worst dividing mode of the current generation population; the method comprises the steps of carrying out re-partition on the partition modes of the current generation population based on the optimal partition mode, the suboptimal partition mode, the worst partition mode and other three partition modes selected randomly to obtain the next generation population until the iteration of the maximum iteration times is completed, and outputting the optimal partition modes of all generation populations; wherein the optimal division mode is used for indicatingZUnmanned frameSearching tracks of the machine;
the objective cost function is calculated by the following formula:
；
in the method, in the process of the invention,Lfor the purpose of the objective cost function,n col andn row the number of columns and the number of rows of the search area in the vector grid map,nfor the number of grids of the search area in the vector grid map,L t for the length of the turning path of the drone,L s the straight path length of the unmanned aerial vehicle;
the optimal dividing mode of the generation population is calculated by the following formula:
；
in the method, in the process of the invention,Jfor the optimal division mode of the current generation population,L i is the firstiThe maximum value of the target cost function of all the division areas in the division modes;
the optimal division mode of all generation groups is calculated by the following formula:
；
in the method, in the process of the invention,J best for the best way of dividing the population of all generations,J i is the firstkThe optimal division mode of the generation group,Mthe maximum iteration number is the maximum iteration number;
the method for re-dividing the current generation population based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and the other three dividing modes selected randomly comprises the following steps:
based on the optimal dividing mode, the suboptimal dividing mode, the worst dividing mode and other three dividing modes selected randomly, two new first dividing modes are obtained through calculation;
at random, a random number is generatedr 1 When the number of the first division modes is smaller than 0.5, recombining the two new first division modes, and calculating to obtain a new second division mode;
at random, a random number is generatedr 1 When the number of the first division is not smaller than 0.5 and smaller than 1, a new third division is calculated based on the optimal division mode of the current generation population and other three randomly selected division modes;
the method comprises the steps of re-dividing the dividing modes of the current generation population based on the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population;
the two new first divisions are calculated by the following formula:
；
；
；
；
；
；
；
；
；；
；；
；
in the method, in the process of the invention,and->Represent the firstkTwo new generations of random generationiThe division, i.e. two new first divisions, +.>Represent the firstkFirst generation groupiDivision mode(s)>Represent the firstkThe optimal division mode of the generation group,represent the firstkSub-optimal partitioning of generation population, +.>Represent the firstkWorst division of generation population, +.>、/>、/>Represent the firstkThree other dividing modes for randomly selecting generation population,kis the algebra of the population of the present generation,Mfor the maximum number of iterations to be described,ris at [0,0.5]A random number randomly generated within the range,r n to fit a random number of a standard normal distribution,r 1 is a random number randomly generated within the range of (0, 1);
a new second division is calculated by the following formula:
；
in the method, in the process of the invention,represent the firstkNew first generation of recombination of generation groupiThe division, i.e. a new second division,r 2 、r 3 two random numbers selected in the range of (0, 1);
a new third division is calculated by the following formula:
；
；
in the method, in the process of the invention,represent the firstkNew generation group calculationiThe division, i.e. a new third division,v 1 、v 2 is within (0, 1)]Two random numbers selected in the range, +.>For a random number selected in the range of (0, 1),r 2 、r 3 for two random numbers selected in the (0, 1) range.
2. The method of claim 1, wherein the repartitioning the partitioning of the current generation population based on the optimal partitioning of the current generation population, the new second partitioning, and the new third partitioning, comprises:
and taking the optimal one of the optimal dividing mode, the new second dividing mode and the new third dividing mode of the current generation population as the optimal dividing mode after the current generation population is divided again.
3. An electronic device comprising a memory and a processor, the memory having stored therein a computer program, the processor implementing the method of any of claims 1-2 when the computer program is executed.
4. A computer readable storage medium, having stored thereon a computer program which, when executed in a computer, causes the computer to perform the method of any of claims 1-2.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311255289.7A CN116989798B (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle track planning method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311255289.7A CN116989798B (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle track planning method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116989798A CN116989798A (en) | 2023-11-03 |
| CN116989798B true CN116989798B (en) | 2023-12-26 |
Family
ID=88523587
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311255289.7A Active CN116989798B (en) | 2023-09-27 | 2023-09-27 | Unmanned aerial vehicle track planning method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116989798B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107806877A (en) * | 2017-10-11 | 2018-03-16 | 湖北工业大学 | A kind of trajectory planning optimization method of four rotor wing unmanned aerial vehicles based on ant group algorithm |
| CN112000126A (en) * | 2020-08-12 | 2020-11-27 | 南京航空航天大学 | Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method |
| CN115435787A (en) * | 2022-07-28 | 2022-12-06 | 南京航空航天大学 | Unmanned aerial vehicle three-dimensional path planning method and system based on improved butterfly algorithm |
| CN116301048A (en) * | 2023-03-27 | 2023-06-23 | 太原市徒普斯网络科技有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and storage medium |
| CN116594425A (en) * | 2023-05-15 | 2023-08-15 | 华北电力大学（保定） | Multi-unmanned aerial vehicle path planning method based on probability map and improved genetic algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110222885B (en) * | 2019-05-24 | 2020-07-07 | 合肥工业大学 | Optimization method and system for intelligent agent autonomous path planning in unmanned system |
-
2023
- 2023-09-27 CN CN202311255289.7A patent/CN116989798B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107806877A (en) * | 2017-10-11 | 2018-03-16 | 湖北工业大学 | A kind of trajectory planning optimization method of four rotor wing unmanned aerial vehicles based on ant group algorithm |
| CN112000126A (en) * | 2020-08-12 | 2020-11-27 | 南京航空航天大学 | Whale algorithm-based multi-unmanned-aerial-vehicle collaborative searching multi-dynamic-target method |
| CN115435787A (en) * | 2022-07-28 | 2022-12-06 | 南京航空航天大学 | Unmanned aerial vehicle three-dimensional path planning method and system based on improved butterfly algorithm |
| CN116301048A (en) * | 2023-03-27 | 2023-06-23 | 太原市徒普斯网络科技有限公司 | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and storage medium |
| CN116594425A (en) * | 2023-05-15 | 2023-08-15 | 华北电力大学（保定） | Multi-unmanned aerial vehicle path planning method based on probability map and improved genetic algorithm |
Non-Patent Citations (4)
| Title |
|---|
| 基于环境建模的USV轨迹规划技术;张国栋;陈金鑫;吴鹏飞;;指挥控制与仿真(第05期);全文 * |
| 张国栋 ; 陈金鑫 ; 吴鹏飞 ; .基于环境建模的USV轨迹规划技术.指挥控制与仿真.2018,(第05期),全文. * |
| 徐利锋 ; 杨中柱 ; 黄祖胜 ; 丁维龙 ; .结合混合粒子群算法的植保无人机航线设计方法.小型微型计算机系统.2020,(第09期),全文. * |
| 结合混合粒子群算法的植保无人机航线设计方法;徐利锋;杨中柱;黄祖胜;丁维龙;;小型微型计算机系统(第09期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116989798A (en) | 2023-11-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2017116924A1 (en) | Neural network training performance optimization framework | |
| CN107330588B (en) | Task planning method for cooperative reconnaissance of multi-base heterogeneous unmanned aerial vehicle | |
| CN115485695A (en) | Method and system for hierarchical weighted sparse convolution processing | |
| CN112200300B (en) | Convolutional neural network operation method and device | |
| CN110084355B (en) | Grid scale optimization method of large-amount interaction particle motion simulation system | |
| Margaris et al. | Parallel implementations of the jacobi linear algebraic systems solve | |
| CN111738276A (en) | Image processing method, device and equipment based on multi-core convolutional neural network | |
| CN114580636A (en) | Neural network lightweight deployment method based on three-target joint optimization | |
| CN109447239B (en) | Embedded convolutional neural network acceleration method based on ARM | |
| CN106503386A (en) | The good and bad method and device of assessment luminous power prediction algorithm performance | |
| CN114138231A (en) | Method, circuit and SOC for executing matrix multiplication operation | |
| CN116989798B (en) | Unmanned aerial vehicle track planning method | |
| Bonny et al. | Time efficient segmented technique for dynamic programming based algorithms with FPGA implementation | |
| CN113094899A (en) | Random power flow calculation method and device, electronic equipment and storage medium | |
| CN116989797B (en) | Unmanned aerial vehicle track optimization method and device, electronic equipment and storage medium | |
| Hong et al. | A multi-gpu fast iterative method for eikonal equations using on-the-fly adaptive domain decomposition | |
| CN117007057B (en) | Unmanned aerial vehicle track optimization method and device | |
| Wang et al. | Learning regularity for evolutionary multiobjective search: A generative model-based approach | |
| CN116991179B (en) | Unmanned aerial vehicle search track optimization method, device, equipment and medium | |
| JP2002157237A (en) | Processor for performing preprocessing based on multilevel incomplete block decomposition | |
| Chen et al. | Efficient multi-training framework of image deep learning on GPU cluster | |
| CN114493106A (en) | Space crowdsourcing task allocation method based on geographical division | |
| CN103646282B (en) | Method for parallel processing based on hybrid optimization algorithm | |
| Gutin et al. | A selection of useful theoretical tools for the design and analysis of optimization heuristics | |
| Wu et al. | An improved genetic algorithm based on explosion mechanism |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |