CN114740890A - Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring - Google Patents
Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring Download PDFInfo
- Publication number
- CN114740890A CN114740890A CN202210385512.9A CN202210385512A CN114740890A CN 114740890 A CN114740890 A CN 114740890A CN 202210385512 A CN202210385512 A CN 202210385512A CN 114740890 A CN114740890 A CN 114740890A
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- population
- flight
- gene
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 39
- 238000005457 optimization Methods 0.000 title claims abstract description 11
- 230000002068 genetic effect Effects 0.000 claims abstract description 32
- 238000000034 method Methods 0.000 claims abstract description 22
- 108090000623 proteins and genes Proteins 0.000 claims description 46
- 230000035772 mutation Effects 0.000 claims description 14
- 238000011156 evaluation Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 9
- 210000000349 chromosome Anatomy 0.000 claims description 8
- 238000012216 screening Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 239000002344 surface layer Substances 0.000 claims description 4
- 238000010353 genetic engineering Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000010187 selection method Methods 0.000 claims description 3
- 239000012634 fragment Substances 0.000 claims description 2
- 235000012149 noodles Nutrition 0.000 claims description 2
- 239000000126 substance Substances 0.000 claims description 2
- 238000013500 data storage Methods 0.000 abstract 1
- 238000010276 construction Methods 0.000 description 4
- 238000005067 remediation Methods 0.000 description 3
- 239000010410 layer Substances 0.000 description 2
- 238000005065 mining Methods 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000002922 simulated annealing Methods 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
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Human Resources & Organizations (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Genetics & Genomics (AREA)
- General Health & Medical Sciences (AREA)
- Physiology (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention discloses an unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring, which mainly comprises the following steps: extracting flight points, initializing a population, calculating population fitness, carrying out genetic operation, iterating and outputting a result. The method is used for solving the problem of collecting land improvement graphic spot images with the characteristics of scattered distribution, different forms and the like, simulating image distribution and extracting flight points based on hardware parameters of the unmanned aerial vehicle, designing a genetic algorithm taking a greedy mechanism into consideration, efficiently calculating the optimal sequence of flight point codes, planning the flight route of the unmanned aerial vehicle, remarkably improving the monitoring efficiency of the unmanned aerial vehicle, saving the flight time of the unmanned aerial vehicle, reducing the number of acquired flight pieces, reducing the data storage pressure, and having better application value in the unmanned aerial vehicle monitoring scene in the fields of natural resources and the like.
Description
Technical Field
The invention belongs to the technical field of unmanned aerial vehicle route planning, and particularly relates to an unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring.
Background
Unmanned aerial vehicle is as the novel instrument that has integrateed high altitude shooting, remote control, telemetry, video image microwave transmission and computer information processing, can acquire high resolution image fast, and a plurality of fields such as wide application in aerial photography, agriculture, plant protection, emergency rescue, survey and drawing. The unmanned aerial vehicle is applied to natural resource monitoring, so that the defects that the space-time resolution ratio of satellite monitoring is insufficient, the tower footing monitoring coverage range is limited, and the ground inspection monitoring is highly dependent on manpower can be effectively overcome, the natural resource monitoring efficiency can be improved, and the unmanned aerial vehicle can be seen quickly, clearly and accurately.
The traditional route planning is an S-shaped route, the planning process is to plan the route by defining the aerial survey range, confirming the course and the lateral overlapping degree, confirming the aerial height and being suitable for the condition needing to be observed in the aerial survey range. But it is directed to natural resource survey patches of mixed morphology, such as: the method comprises the following steps of road distribution, narrow industrial and mining abandoned land reclamation project pattern spots, scattered village residential site reclamation project pattern spots, scattered suspected illegal construction land pattern spots, large-area covered industrial land yielding construction project pattern spots and the like, wherein the long industrial and mining abandoned land reclamation project pattern spots are distributed along a road, the scattered suspected illegal construction land pattern spots, the large-area covered industrial land yielding construction project pattern spots and the like are prone to the conditions of missing detection, redundancy, incomplete coverage and unreasonable track arrangement.
Therefore, scholars at home and abroad carry out a great deal of research work aiming at the problem of unmanned aerial vehicle track planning, for example, the K-means algorithm and the simulated annealing algorithm are adopted to carry out track planning on a multi-task multi-unmanned aerial vehicle under multiple conditions, the coverage range of a sub target area in a cruise effective area is increased, the problem of applicability and algorithm complexity of dynamic planning in a special terrain environment is solved by adopting hierarchical directional dynamic planning, the calculation efficiency is improved, the greedy MB-RRT algorithm is designed, and the speed of the unmanned aerial vehicle track planning problem is improved and the flight time is saved by sacrificing certain track quality.
Disclosure of Invention
The invention aims to: the invention aims to simulate photo distribution and extract flight points based on hardware parameters of an unmanned aerial vehicle, designs a genetic algorithm taking into account a greedy mechanism, efficiently solves the optimal sequence of flight point codes, and realizes the flight path planning of the unmanned aerial vehicle, thereby optimally solving the problem of collecting land remediation pattern spot images with the characteristics of scattered distribution, different forms and the like, improving the monitoring efficiency, reducing the collection time, and saving the storage space.
The technical scheme is as follows: the invention relates to an unmanned aerial vehicle flight path optimization algorithm for monitoring land improvement pattern spots, which comprises the following steps:
Step 2, population initialization: and calculating the distance between each flight point according to the flight point coordinates to form a distance matrix D. For any flight point SPi(i-1, 2, …, n), in SPiAs the current course LiStarting point of (2), all routes L generated by using greedy mechanism1，L2，…,LsizeA set of genetic algorithms, an initial population of genetic algorithms.
Step 5, genetic manipulation: and (5) generating the offspring individuals with excellent size genes through the processes of size time random selection, crossing, mutation and heredity based on the parent population obtained in the step (5), and entering the next generation population.
Further, in the step 1, the hybrid-form-oriented natural resource monitoring pattern spot navigation flying spot extraction method is specifically as follows:
step 1.1: and (3) calculating the ground size b corresponding to a photo shot by the unmanned aerial vehicle according to the chip width a, the focal length f and the flight height h of the unmanned aerial vehicle, and referring to the formula (1).
Step 1.2: and simulating the photo shot by the unmanned aerial vehicle during flying in the natural resource monitoring pattern spot area according to the parameter b, and forming a surface layer by the photo.
Step 1.3: and (3) performing space screening on the surface layer obtained in the step (1.2) by using the natural resource monitoring pattern spots, and screening the surface which can completely cover and has a small shooting area.
Step 1.4: and (4) extracting the center of mass of the noodle obtained in the step (1.3), namely the flight point.
Further, in step 2, the greedy mechanism is as follows: firstly, two sets S, V-S are established, a starting point and an end point are added into the S set, the flying points needing to be traversed are stored into the V-S, the point closest to the starting point is selected from the V-S and added into the set S, the point is removed from the V-S, and the circulation is continued until all the flying points are traversed, so that the final set S is obtained.
Further, in step 3, for any population of individuals Li, the substance of Li is the permutation set S of n flying spots, and the evaluation value Fi of the fitness is calculated, see formula (2).
Wherein d is a route LiThe distance between adjacent flight points.
Further, in the step 4, the number of individuals, p _ zize, of the parent population is calculated, see formula (3).
p _ size ═ n × ga _ choose _ rate formula (3)
Further, in the step 5, based on the parent population obtained in the step 4, through size sub-random selection, crossing and mutation processes, the offspring individuals with excellent size genes are obtained and enter the next generation population. The specific operation steps are as follows:
step 5.1, selection: calculating the probability P of each individual in the original population being selectediThe roulette selection method was used to randomly select 2 individuals, designated gene _ x and gene _ y. Wherein the probability P of any individual being selectediSee equation (4).
Step 5.2, crossing: based on the individuals gene _ x and gene _ y, a two-point crossing method is utilized to exchange partial chromosomes (flying spot arrangement fragments) between the individuals gene _ x and gene _ y, and partial conflict genes in the chromosomes are exchanged to ensure that no conflict genes exist, so that candidate offspring population individuals are generated and are respectively marked as gene _ x _ new and gene _ y _ new.
Step 5.3 mutation: based on the preset mutation probability ga _ multicast _ ratio, gene _ x _ new and gene _ y _ new are subjected to selective locus (flight point location) mutation, namely, partial segment inversion is carried out on a mutated chromosome.
Step 5.4 generation of progeny: and reevaluating the fitness of the gene _ x _ new and the gene _ y _ new, and adding the individuals with high fitness evaluation values into the next generation population after comparison.
Step 5.5 repeat steps 5.1 to 5.4 until the next generation population size reaches the preset size.
Has the advantages that: compared with the prior art, the invention has the following advantages:
(1) the invention introduces a greedy mechanism in the traditional genetic algorithm, provides a good initial population for the course planning process, reduces the course distance, ensures the monitoring full coverage and improves the searching efficiency compared with the traditional genetic algorithm.
(2) The method is used for solving the problem of collecting land improvement graphic spot images with the characteristics of scattered distribution, different forms and the like, simulating photo distribution and extracting flight points based on hardware parameters of the unmanned aerial vehicle, designing a genetic algorithm taking a greedy mechanism into consideration, efficiently calculating the optimal sequence of flight point codes, planning the flight route of the unmanned aerial vehicle, remarkably improving the monitoring efficiency of the unmanned aerial vehicle, saving the collecting time, the number of photos and the storage space of the unmanned aerial vehicle, and having better application value in the unmanned aerial vehicle monitoring scene in the fields of natural resources and the like.
Drawings
FIG. 1 is a flow chart of the present invention
FIG. 2 is a schematic view of flying spot extraction
FIG. 3 is a cross-sectional view
FIG. 4 is a greedy mechanism-based course planning result diagram of genetic algorithm and conventional genetic algorithm
FIG. 5 is a graph of algorithm convergence
FIG. 6 is a forward projection image of Zhangqiaomicun land remediation pattern
Detailed Description
The technical solution of the present invention is described in detail below, but the scope of the present invention is not limited to the embodiments.
In the embodiment, the land regulation map spot monitoring of Zhangcun in West of Zhangdianzhen of Jiangsu Jiangyan city is selected as experimental data, and a Dajiang unmanned aerial vehicle M300 RTK is used for carrying a Zen Si P1 camera to carry out map spot orthographic image data acquisition.
As shown in fig. 1, in the unmanned aerial vehicle flight path planning method for the mixed-form natural resource monitoring pattern spot according to the embodiment, an initialization population is generated by taking a greedy mechanism into consideration, blind search of a subsequent genetic algorithm is reduced, multiple iterative calculations are performed through the genetic algorithm, and an optimal solution of an unmanned aerial vehicle flight path is obtained while the efficiency is improved. The method specifically comprises the following steps:
step 1.1: as shown in fig. 2(b), according to the zens P1 that the chip width d is 24mm, the focal length f is 2.8mm, and the flight altitude is 270m, the corresponding size of a single image is calculated as b, and the ground size corresponding to one image shot by the unmanned aerial vehicle is about 2314 m.
Step 1.2: as shown in fig. 2(c), the shot images shot by the unmanned aerial vehicle during flying are simulated for the experimental area according to the parameter b, and the images are combined into a surface image layer.
Step 1.3: as shown in fig. 2(d), the surface image layer obtained in step 1.2 is spatially screened by using the natural resource monitoring pattern spot, and the screened surface can completely cover the surface with a small shooting area.
Step 1.4: as shown in fig. 2(e), 35 centroids of the surface obtained in step 1.3, that is, flying spots, are extracted.
Step 2, population initialization: and calculating the distance between each flight point according to the flight point coordinates to form a distance matrix D. For any flight point SPi(i ═ 1,2, …, n), by SPiAs the current course LiStarting point of (2), all routes L generated by using greedy mechanism1，L2，…,L355A set of (a), an initial population of genetic algorithms.
In particular, the greedy mechanism introduced is as follows: firstly, two sets S, V-S are established, a starting point and an end point are added into the S set, flying points needing to be traversed are stored into the V-S, points closest to the starting point are selected from the V-S and added into the set S, the points are removed from the V-S, and the circulation is continuously carried out until all the flying points are traversed, so that the final set S is obtained, namely the flight line L.
Step 5, genetic manipulation: 355 times of processes of random selection, crossing and mutation are carried out on the basis of the parent population obtained in the step 5, so that 355 excellent gene filial generation individuals are generated and enter the next generation population. The method comprises the following specific steps:
step 5.1, selection: calculating the probability P of each individual in the parent population being selected according to the formula (4)iThe roulette selection method was used to randomly select 2 individuals, designated gene _ x and gene _ y.
Step 5.2, crossing: as shown in fig. 3, based on the individuals gene _ x and gene _ y, a two-point crossover method is used to exchange part of chromosomes (flying spot arrangement segments) between the two individuals, and the genes of part of conflicting genes are exchanged to ensure that there are no conflicting genes, so as to generate candidate offspring population individuals, which are respectively designated as gene _ x _ new and gene _ y _ new.
Step 5.3 mutation: based on the preset mutation probability ga _ multicast _ ratio, gene _ x _ new and gene _ y _ new are subjected to selective locus (flight point location) mutation, namely, partial segment inversion is carried out on a mutated chromosome.
Step 5.4 generation of progeny: and reevaluating the fitness of the gene _ x _ new and the gene _ y _ new, and adding the individuals with high fitness evaluation values into the next generation population after comparison.
And step 5.5: and (5.1) repeating the steps from 5.1 to 5.4 until the number of the next generation population reaches the preset scale 355.
In order to more intuitively show the advantages of the method, the orthographic image data acquisition of the Zhangqiancun land improvement pattern spots is carried out by respectively adopting the traditional route planning and the unmanned aerial vehicle flight route planning facing the mixed form land improvement pattern spots. As shown in table 1, under the same flight parameters of the unmanned aerial vehicle, the flight path planning of the invention takes 12 minutes, the full coverage monitoring of the image spots can be realized by collecting 126 images, and the image storage space is 2.68G, whereas the flight path planning of the invention takes 30 minutes, and the full coverage monitoring of the image spots can be realized by collecting 400 images, and the image storage space is 4.55G. Obviously, the air route planning of the invention greatly improves the efficiency of the unmanned aerial vehicle in the hybrid pattern spot monitoring, saves the acquisition time by nearly 60%, reduces the number of photos by 68.5%, and saves the image storage space by nearly 41%.
TABLE 1 orthographic image acquisition experiment result of land remediation pattern spots of Zhanguan land
Fig. 6(a1) is a spot ortho-image of Zhangqiancun land improvement collected for the airline planning of the present invention, and fig. 6(b1) is a spot ortho-image of Zhangmuraun land improvement collected for the airline planning of the present invention. As shown in fig. 6(a2) and 6(b2), and fig. 6(a3) and 6(b3) are images acquired by the same pattern under two routes, respectively, it can be seen that the quality of an orthoimage acquired by using the route planning path of the present invention is not different from that of a traditional route, and the requirements of natural resource land reclamation business are met.
In conclusion, the invention introduces a greedy mechanism in the traditional genetic algorithm, provides a good initial population for the course planning process, reduces the course distance, ensures the monitoring full coverage and improves the search efficiency compared with the traditional genetic algorithm. ) The method is used for solving the problem of collecting land improvement graphic spot images with the characteristics of scattered distribution, different forms and the like, simulating photo distribution and extracting flight points based on hardware parameters of the unmanned aerial vehicle, designing a genetic algorithm taking into account a greedy mechanism, efficiently calculating the optimal sequence of flight point codes, realizing the flight route planning of the unmanned aerial vehicle, remarkably improving the monitoring efficiency of the unmanned aerial vehicle, saving the collection time by nearly 60%, reducing the number of photos by 68.5%, saving the image storage space by nearly 41%, and having better application value in the unmanned aerial vehicle monitoring scene in the fields of natural resources and the like.
Claims (6)
1. Unmanned aerial vehicle flight path optimization algorithm for monitoring land improvement pattern spots is characterized in that: the method is oriented to the scattered and non-uniform pattern spots, the greedy mechanism is considered to generate the initialization population, the blind search of the subsequent genetic algorithm is reduced, and the optimal solution of the unmanned aerial vehicle route is obtained while the efficiency is improved through repeated iterative calculation of the genetic algorithm. The method comprises the following steps:
step 1, flight point extraction: inputting a to-be-monitored pattern spot, a population size, a genetic probability ga _ choose _ ratio, a variation probability ga _ multiple _ ratio and an iteration number t. A hybrid-form-oriented land improvement pattern spot aviation flying point extraction method is designed, and framework points with the minimum quantity and uniform position distribution are selected in a pattern spot monitoring area range to serve as aviation flying points for unmanned aerial vehicles to fly, and the number of the aviation flying points is recorded as n.
Step 2, population initialization: and calculating the distance between each flight point according to the flight point coordinates to form a distance matrix D. For any flight point SPi(i ═ 1,2, …, n), by SPiAs the current course LiStarting point of (2), all routes L generated by using greedy mechanism1，L2，…,LsizeA set of genetic algorithms, an initial population of genetic algorithms.
Step 3, calculating population fitness: for any population of individuals Li(i ═ 1,2, …, size) and mixing LiThe reciprocal of the flight route distance of (a) is taken as an evaluation value of its fitness,is marked as Ai。AiThe larger the value, the higher its fitness, otherwise the lower the fitness.
Step 4, acquiring a parent population: evaluating the individual original population according to the fitness AiAnd (4) arranging the individuals according to the sequence from large to small, and screening the previous p _ size individuals as the parent population of the next generation genetic algorithm.
Step 5, genetic manipulation: and (5) generating the offspring individuals with excellent size genes through the processes of size-time random selection, crossing and mutation based on the parent population obtained in the step (5), and entering the next generation population.
Step 6, iterating and outputting a result: and (5) repeating the operations from the step (3) to the step (5) until the preset genetic iteration number t is reached, and obtaining and outputting an optimal flight point sequence, namely an optimal flight route of the unmanned aerial vehicle, through calculation and comparison of the fitness evaluation value.
2. The unmanned aerial vehicle flight path optimization algorithm for land reclamation pattern spot monitoring as recited in claim 1, wherein: in the step 1, the hybrid-form-oriented natural resource monitoring pattern spot navigation flying spot extraction method is specifically as follows:
step 1.1: and calculating the ground size b corresponding to one photo shot by the unmanned aerial vehicle according to the width a, the focal length f and the flight height h of the chip of the unmanned aerial vehicle, and referring to a formula (1).
Step 1.2: and simulating the photo shot by the unmanned aerial vehicle during flying in the natural resource monitoring pattern spot area according to the parameter b, and forming a surface layer by the photo.
Step 1.3: and (3) performing space screening on the surface layer obtained in the step (1.2) by using the natural resource monitoring pattern spots, and screening the surface which can completely cover and has a small shooting area.
Step 1.4: and (4) extracting the center of mass of the noodle obtained in the step (1.3), namely the flight point.
3. The unmanned aerial vehicle flight path optimization algorithm for land reclamation pattern spot monitoring as recited in claim 1, wherein: in the step 2, the greedy mechanism flow is as follows: firstly, two sets S, V-S are established, a starting point and an end point are added into the S set, the flying points needing to be traversed are stored into the V-S, the point closest to the starting point is selected from the V-S and added into the set S, the point is removed from the V-S, and the circulation is continued until all the flying points are traversed, so that the final set S is obtained.
4. The unmanned aerial vehicle flight path optimization algorithm for land reclamation pattern spot monitoring as recited in claim 1, wherein: in step 3, for any population of individuals Li, the substance of Li is the permutation set S of n flying spots, and the evaluation value Fi of the fitness is calculated, see formula (2).
Wherein d is a route LiThe distance between adjacent flight points.
5. The unmanned aerial vehicle flight path optimization algorithm for land reclamation pattern spot monitoring as recited in claim 1, wherein: in said step 4, the number p _ size of individuals of the parent population is calculated, see formula (3).
Formula (3) of p _ size × ga _ choose _ rate
6. The unmanned aerial vehicle flight path optimization algorithm for land reclamation pattern spot monitoring as recited in claim 1, wherein: in the step 5, based on the parent population obtained in the step 4, through size-level random selection, crossing and mutation processes, the offspring individuals with excellent size genes are obtained and enter the next generation population. The specific operation steps are as follows:
step 5.1, selection: calculating the probability P of each individual in the original population being selectediThe roulette selection method was used to randomly select 2 individuals, designated gene _ x and gene _ y. Wherein, renProbability P of an individual being selectediSee equation (4).
Step 5.2, crossing: based on the individuals gene _ x and gene _ y, a two-point crossing method is utilized to exchange partial chromosomes (flying spot arrangement fragments) between the individuals gene _ x and gene _ y, and partial conflict genes in the chromosomes are exchanged to ensure that no conflict genes exist, so that candidate offspring population individuals are generated and are respectively marked as gene _ x _ new and gene _ y _ new.
Step 5.3 mutation: based on the preset mutation probability ga _ multicast _ ratio, gene _ x _ new and gene _ y _ new are subjected to selective locus (flight point location) mutation, namely, partial segment inversion is carried out on a mutated chromosome.
Step 5.4 generation of progeny: and reevaluating the fitness of the gene _ x _ new and the gene _ y _ new, and adding the individuals with high fitness evaluation values into the next generation population after comparison.
Step 5.5 step 5.1 to step 5.5 are repeated until the next generation population size reaches the preset size.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210385512.9A CN114740890A (en) | 2022-04-13 | 2022-04-13 | Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210385512.9A CN114740890A (en) | 2022-04-13 | 2022-04-13 | Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114740890A true CN114740890A (en) | 2022-07-12 |
Family
ID=82280802
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210385512.9A Pending CN114740890A (en) | 2022-04-13 | 2022-04-13 | Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114740890A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080450A (en) * | 2022-08-22 | 2022-09-20 | 深圳慧拓无限科技有限公司 | Automatic driving test data generation method and system, electronic device and storage medium |
| CN115879603A (en) * | 2022-11-17 | 2023-03-31 | 武汉大学 | Multi-target-point-oriented multi-unmanned aerial vehicle cooperative data acquisition method and device |
| CN117213484A (en) * | 2023-06-21 | 2023-12-12 | 深圳大学 | Navigation point connection method and device based on genetic algorithm and intelligent terminal |
| CN117935625A (en) * | 2024-03-22 | 2024-04-26 | 中国民航管理干部学院 | Intelligent air traffic unmanned aerial vehicle route management system and method |
-
2022
- 2022-04-13 CN CN202210385512.9A patent/CN114740890A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115080450A (en) * | 2022-08-22 | 2022-09-20 | 深圳慧拓无限科技有限公司 | Automatic driving test data generation method and system, electronic device and storage medium |
| CN115879603A (en) * | 2022-11-17 | 2023-03-31 | 武汉大学 | Multi-target-point-oriented multi-unmanned aerial vehicle cooperative data acquisition method and device |
| CN115879603B (en) * | 2022-11-17 | 2024-05-14 | 武汉大学 | Multi-target-point-oriented multi-unmanned aerial vehicle collaborative data acquisition method and device |
| CN117213484A (en) * | 2023-06-21 | 2023-12-12 | 深圳大学 | Navigation point connection method and device based on genetic algorithm and intelligent terminal |
| CN117935625A (en) * | 2024-03-22 | 2024-04-26 | 中国民航管理干部学院 | Intelligent air traffic unmanned aerial vehicle route management system and method |
| CN117935625B (en) * | 2024-03-22 | 2024-05-24 | 中国民航管理干部学院 | Intelligent air traffic unmanned aerial vehicle route management system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114740890A (en) | Unmanned aerial vehicle flight path optimization algorithm for land improvement pattern spot monitoring | |
| CN107977743B (en) | Multi-unmanned aerial vehicle cooperative task allocation method and device | |
| CN107169608B (en) | Distribution method and device for multiple unmanned aerial vehicles to execute multiple tasks | |
| CN107807665B (en) | Unmanned aerial vehicle formation detection task cooperative allocation method and device | |
| CN107103164B (en) | Distribution method and device for unmanned aerial vehicle to execute multiple tasks | |
| Kritter et al. | On the optimal placement of cameras for surveillance and the underlying set cover problem | |
| CN109325502B (en) | Shared bicycle parking detection method and system based on video progressive region extraction | |
| CN110389595A (en) | The unmanned plane cluster of double-attribute probability graph optimization cooperates with Target Searching Method | |
| CN105841702A (en) | Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm | |
| CN110442143B (en) | Unmanned aerial vehicle situation data clustering method based on combined multi-target pigeon swarm optimization | |
| CN103390169A (en) | Sorting method of vehicle-mounted laser scanning point cloud data of urban ground objects | |
| CN105203097A (en) | Multi-robot multi-target point rescue route planning method fit for after-calamity environment | |
| Chen et al. | A modified two-part wolf pack search algorithm for the multiple traveling salesmen problem | |
| CN111598473A (en) | Multi-platform joint task planning method for complex observation task | |
| CN111121784B (en) | Unmanned reconnaissance aircraft route planning method | |
| CN104680167B (en) | Auroral oval location determining method based on deep learning | |
| CN111709318A (en) | High-resolution remote sensing image classification method based on generation countermeasure network | |
| CN111132014A (en) | Wireless sensor network node positioning method based on unmanned aerial vehicle mobile beacon | |
| CN114167898A (en) | Global path planning method and system for data collection of unmanned aerial vehicle | |
| CN111611960A (en) | Large-area ground surface coverage classification method based on multilayer perceptive neural network | |
| CN116452983B (en) | Quick discovering method for land landform change based on unmanned aerial vehicle aerial image | |
| CN107993242A (en) | Based on airborne LiDAR point cloud shortage of data zone boundary extracting method | |
| CN112434857B (en) | Unmanned aerial vehicle airport network site selection arrangement method based on GA-PSO optimization | |
| CN114467900B (en) | Accurate spraying method of lawn herbicide | |
| Liu et al. | Mars Terrain Semantic Segmentation using Zhurong Rover Imagery Based on Transfer Learning of Historical Mission Data |
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 |