CN110426043B - Unmanned aerial vehicle reconnaissance flight path planning method facing line target - Google Patents
Unmanned aerial vehicle reconnaissance flight path planning method facing line target Download PDFInfo
- Publication number
- CN110426043B CN110426043B CN201910719794.XA CN201910719794A CN110426043B CN 110426043 B CN110426043 B CN 110426043B CN 201910719794 A CN201910719794 A CN 201910719794A CN 110426043 B CN110426043 B CN 110426043B
- Authority
- CN
- China
- Prior art keywords
- unmanned aerial
- aerial vehicle
- line
- target
- chromosome
- 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
Images
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
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
Abstract
The invention provides a line target-oriented unmanned aerial vehicle reconnaissance flight path planning method aiming at the flight path planning problem of a plurality of unmanned aerial vehicle reconnaissance line targets. Firstly, on the basis of considering target characteristics, a flight path planning model of a plurality of unmanned aerial vehicle reconnaissance line targets with time cost as an objective function is established. Then, in order to ensure that all targets are spyed at most once, the coding scheme of the standard genetic algorithm is optimized. And finally, reasonably designing the cross operation and the mutation operation in order to improve the convergence speed of the algorithm. Simulation results show that the algorithm can effectively solve the problem of flight path planning of the multiple unmanned aerial vehicle reconnaissance line targets, and the convergence speed is high.
Description
Technical Field
The invention relates to the field of unmanned aerial vehicle reconnaissance, in particular to a line target-oriented unmanned aerial vehicle reconnaissance flight path planning method.
Background
The unmanned aerial vehicle flight path planning technology is a key for ensuring that multiple unmanned aerial vehicles efficiently complete tasks, and is widely concerned by scholars at home and abroad. At present, according to the difference of unmanned aerial vehicle reconnaissance objects, the problem of planning the cooperative reconnaissance flight path of multiple unmanned aerial vehicles is mainly divided into two aspects of point-to-point cooperative reconnaissance and point-to-face cooperative reconnaissance.
Point-to-point cooperative reconnaissance flight path planning, namely, reconnaissance objects are point target groups, and the unmanned aerial vehicle is required to reconnaissance the point target groups given by tasks at minimum time cost. If Liu surpasses, a multi-unmanned aerial vehicle route planning method based on an improved genetic algorithm [ J ] firepower command and control, 2019,44(1):18-22. the route planning problem of a multi-unmanned aerial vehicle reconnaissance point target group is firstly converted into a multi-traveler problem, and then the task route of each unmanned aerial vehicle is obtained by utilizing the operations of coding, crossing, variation and the like of the genetic algorithm. But the algorithm is limited to the case where the spot target size is small. In order to solve the problem of large-scale point target reconnaissance, Liu weng, Wang Yi Wan, multi-unmanned aerial vehicle collaborative search multi-target path planning problem research [ J ]. electro-optic and control, 2019,26(3):35-38. firstly, a K-means clustering algorithm is used for a point target group, a multi-traveler problem is decomposed into a single traveler problem, then, an intersection operator and a selection operator of a genetic algorithm are improved, and the solution of the rapid reconnaissance of the large-scale point target track planning problem is realized.
The point-to-surface collaborative reconnaissance flight path planning is that a reconnaissance object is a wide area target, an unmanned aerial vehicle is required to carry out covering reconnaissance on a task area without omission, and common covering modes include a scanning line method, a grid method and the like. The method comprises the steps of improving a multi-unmanned aerial vehicle collaborative area coverage search algorithm [ J ] electro-optical and control, 2016,23(1):80-84. in the case of Wuqingpo, Zhousheping, Yi Gaoyang and the like, under the premise of guaranteeing the area full coverage and meeting the dynamics constraint of unmanned aerial vehicles, the turning time and the turning position of an unmanned aerial vehicle formation are adjusted, meanwhile, a common area coverage search method is optimized, and finally, the area coverage search task can be efficiently completed. LI Y, CHEN H, MENG J E, et al, coverage path planning for UAVs based on enhanced cellular decomposition method [ J ]. Mechantronics, 2011,21(5):876 + 885, Chenhai, which front, Qianwuqi, multiple unmanned aerial vehicles cooperatively cover the path planning [ J ]. aviation bulletin, 2016,37(3):928 + 935.
Many documents and achievements exist for the flight path planning problem of the two types of targets, but the relevant document information is less for the reconnaissance problem of line targets such as railways and oil pipelines. Aiming at the problem of line target reconnaissance flight path planning, a line target-oriented unmanned aerial vehicle reconnaissance flight path planning method is provided. By establishing a multi-unmanned-plane multi-line target reconnaissance track model, then improving the coding, crossing and mutation operations of a genetic algorithm, and finally solving the reconnaissance track model by utilizing the improved genetic algorithm, the task track with the minimum time cost is obtained.
Disclosure of Invention
The invention aims to solve the technical problem of line target reconnaissance flight path planning, and provides a line target-oriented unmanned aerial vehicle reconnaissance flight path planning method.
The technical scheme adopted by the invention is as follows:
a reconnaissance flight path planning method of an unmanned aerial vehicle facing to a line target comprises the following steps:
the method comprises the following steps: establishing a flight path planning model of the unmanned aerial vehicle cooperative reconnaissance multi-line target task with time cost as an objective function according to the characteristics of the line targets, the flight speed of the unmanned aerial vehicle and the number of the line targets required to be reconnaissance by the unmanned aerial vehicle;
step two: respectively coding the unmanned aerial vehicle number, the line target number and the entry point number of the line target for multiple times by using a multi-type gene coding mode to obtain multiple chromosomes and form an initial population;
step three: calculating the fitness corresponding to each chromosome in the initial population by using an objective function of a track planning model, and recording the optimal fitness and the corresponding chromosome in the current whole population; simultaneously, chromosome in the initial population is optimized by adopting a classical roulette method to form a parent chromosome population;
step four: carrying out chromosome crossing operation on chromosomes in the parent chromosome population;
step five: carrying out chromosome variation operation on the parent chromosomes subjected to chromosome crossing operation to form a new chromosome population; taking the new chromosome population as an initial population, repeating the steps from the third step to the fifth step to a designated generation, and outputting the optimal fitness in the current whole population and the chromosome corresponding to the optimal fitness as an optimal reconnaissance sequence;
and finishing the unmanned aerial vehicle reconnaissance track planning facing the line target.
The first step specifically comprises the following steps:
is provided with m unmanned aerial vehicles and N line targets, wherein the number of the line targets required to be detected by the ith unmanned aerial vehicle is Ni；
(101) Calculating the distance L between the ith unmanned aerial vehicle and the first allocated line targeti1：
Li1＝d((xi,yi),(xi11,yi11)) (1)
Wherein, the coordinate (x)i,yi) Indicating the position, coordinate (x) of the ith dronei11,yi11) Indicating an entry point location for an ith drone to travel to the first assigned line target; d (a, b) represents the geometric distance between point a and point b;
(102) calculating the target length l of the jth line target1ij：
l1ij＝d((xij1,yij1),(xij2,yij2)) (2)
Wherein j is less than or equal to niCoordinate (x)ij1,yij1) And (x)ij2,yij2) Respectively allocating an entry point and a departure point of a jth line target to the ith unmanned aerial vehicle;
(103) calculating the target length and L of all line targets distributed to the ith unmanned aerial vehiclei2：
(104) Calculating the distance l from the current jth line target flying-off point to the next line target entry point2ij：
l2ij＝d((xij2,yij2),(xi(j+1)1,yi(j+1)1)) (4)
(105) Calculating the distance sum L between the ith unmanned aerial vehicle and all the line targetsi3:
(106) Calculating the distance L of the unmanned aerial vehicle returning to the starting point from the flying-out point of the last line targeti4Comprises the following steps:
Li4＝d((xi,yi),(xi(ni)2,yi(ni)2)) (6)
(107) calculating the overall path length D of the line target allocated for the detection of the ith unmanned aerial vehiclei：
Di＝Li1+Li2+Li3+Li4 (7)
(108) Calculating the time cost t of the ith unmanned aerial vehiclei：
Wherein ViThe speed of the ith unmanned aerial vehicle;
(109) the flight path planning model for the cooperative reconnaissance of the unmanned aerial vehicle for the multi-line target task can be expressed as follows:
an objective function:
max T (9)
constraint conditions are as follows:
wherein T ═ T1,t2,…,tm) Formula (9) shows that the overall time cost of the reconnaissance mission is determined by the unmanned aerial vehicle which takes the longest time, and formula (10) shows that all line targets are reconnaissance.
Wherein, the second step specifically comprises the following steps:
(201) unmanned aerial vehicle numbering and coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled by the serial numbers of the unmanned aerial vehicles;
(202) line object number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled with the line target numbers, and each line target number is ensured to appear only once;
(203) entry point number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein each element in the row matrix randomly takes 1 or 2; "1" indicates entry from the left side of the line object, and "2" indicates entry from the right side of the line object;
(204) repeating the steps (201) to (203) for a plurality of times to obtain a plurality of chromosomes and form an initial population, wherein s is the set population number.
The third step specifically comprises the following steps:
(301) calculating the fitness f corresponding to the h chromosome in the kth generation populationkh：
fkh＝max(Tkh) (11)
Wherein h is more than or equal to 1 and less than or equal to s, k is more than or equal to 1 and less than or equal to r, r is a genetic algebra, TkhRepresents a set of scout time costs, T, of each UAV under the scout sequence corresponding to the h chromosome in the kth generation populationkh＝(tkh1,tkh2,…,tkhm)；
(302) Calculating the best fitness g of the kth generation populationk：
gk＝min{(fk1,fk2,…fkh,…,fks)} (12)
(303) Calculating the best fitness G of the first k generations of the whole populationk：
Gk＝min{(g1,g2,…,gk)} (13)
(304) Selecting roulette: calculating the probability P that the h-th chromosome is preferred in the k-th generation populationkh：
(305) Calculating the cumulative probability q of the h chromosome in the kth generation populationkh：
qkh＝fk1+fk2+…+fkh (15)
(306) Randomly generating a number p smaller than 1 if p < qk1Then chromosome 1 in the population of the kth generation is preferred, otherwise chromosome h is selected such that q iskh＜p＜qk(h+1)And repeating the steps for s times to form a parent chromosome population.
The chromosome crossing operation in the fourth step specifically comprises the following steps:
(401) gene exchange: randomly selecting two father chromosomes A and B from the father chromosome population, randomly generating two crossed genes C1 and C2, and mutually exchanging the gene fragments of the genes C1 and C2 corresponding to the two father chromosomes A and B;
(402) and (4) checking conflict: modifying genes with the same target number to ensure that each target is detected at most once;
(403) gene inversion: and (3) respectively inverting gene segments between the genes C1 and C2 of the two parent chromosomes A and B to obtain the child chromosomes after the chromosome crossing operation.
Wherein, the chromosome mutation operation in the fifth step specifically comprises the following steps:
(501) unmanned aerial vehicle numbering variation: randomly generating a variation gene, and randomly mutating the number of the corresponding unmanned aerial vehicle into the numbers of other unmanned aerial vehicles;
(502) line target number variation: randomly generating a variant gene, randomly mutating a corresponding line target number into other target numbers, and simultaneously detecting target number conflict;
(503) entry point number variation: randomly generating a variant gene locus, and randomly mutating the corresponding entry point number to another entry point number.
Compared with the background technology, the invention has the advantages that:
the method can effectively solve the problem of flight path planning of the multiple unmanned aerial vehicle reconnaissance line targets, the planned task flight path is simple and clear, and has no cross, and compared with a standard genetic algorithm, the method provided by the invention has the advantages of high effectiveness and high algorithm convergence speed.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is a diagram of the encoding process of the present invention using multi-type gene encoding;
FIG. 3 is a diagram of the chromosome crossing process of the present invention;
FIG. 4 is a diagram illustrating the variation process of the numbering of the UAVs according to the present invention;
FIG. 5 is a diagram illustrating a process of target number variation according to the present invention;
FIG. 6 is a diagram illustrating a variation process of entry point numbering according to the present invention.
Detailed Description
The invention is further explained below with reference to the drawings. The invention relates to a line target-oriented unmanned aerial vehicle reconnaissance flight path planning method, and a flow chart refers to a figure 1. The method comprises the following steps:
the method comprises the following steps: establishing a flight path planning model for cooperatively reconnaissance of multiple unmanned aerial vehicles on a multi-line target task;
supposing that m unmanned aerial vehicles and N line targets are arranged, the number of the line targets required to be detected by the ith unmanned aerial vehicle is Ni。
(101) Calculating the distance L between the ith unmanned aerial vehicle and the first allocated line targeti1：
Li1＝d((xi,yi),(xi11,yi11)) (1)
Wherein, the coordinate (x)i,yi) Indicating the position, coordinate (x) of the ith dronei11,yi11) Indicating an entry point location for an ith drone to travel to the first assigned line target; d (a, b) represents the geometric distance between point a and point b;
(102) calculating the target length l of the jth line target1ij：
l1ij＝d((xij1,yij1),(xij2,yij2)) (2)
Wherein j is less than or equal to niCoordinate (x)ij1,yij1) And (x)ij2,yij2) Respectively allocating an entry point and a departure point of a jth line target to the ith unmanned aerial vehicle;
(103) calculating the target length and L of all line targets distributed to the ith unmanned aerial vehiclei2：
(104) Calculating the distance l from the current jth line target flying-off point to the next line target entry point2ij：
l2ij＝d((xij2,yij2),(xi(j+1)1,yi(j+1)1)) (4)
(105) Calculating the distance sum L between the ith unmanned aerial vehicle and all the line targetsi3:
(106) Calculating the distance L of the unmanned aerial vehicle returning to the starting point from the flying-out point of the last line targeti4Comprises the following steps:
Li4＝d((xi,yi),(xi(ni)2,yi(ni)2)) (6)
(107) calculating the overall path length D of the line target allocated for the detection of the ith unmanned aerial vehiclei：
Di＝Li1+Li2+Li3+Li4 (7)
(108) Calculating the time cost t of the ith unmanned aerial vehiclei：
Wherein ViThe speed of the ith unmanned aerial vehicle;
(109) then the track planning model for the cooperative reconnaissance of the multiple unmanned aerial vehicles to the multi-line target task is expressed as follows:
an objective function:
max T (9)
constraint conditions are as follows:
wherein T ═ T1,t2,…,tm)，ThAnd (3) representing a set of scouting time costs of all unmanned aerial vehicles under the corresponding scouting sequence of the h-th chromosome, wherein the formula (9) represents that the overall time cost of the scouting task is determined by the unmanned aerial vehicle which takes the longest time, and the formula (10) represents that all line targets are scouted.
Step two: when the track planning model is solved, coding is carried out by adopting a multi-type gene coding mode, and the coding mainly comprises unmanned aerial vehicle number coding, target number coding and entry point number coding;
(201) unmanned aerial vehicle numbering and coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled by the serial numbers of the unmanned aerial vehicles;
(202) line object number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled with the line target numbers, and each line target number is ensured to appear only once;
(203) entry point number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein each element in the row matrix randomly takes 1 or 2; "1" indicates entry from the left side of the line object, and "2" indicates entry from the right side of the line object;
as shown in fig. 2, 4 drones are shown to scout 6 line targets, wherein the scout sequence of drone 1 is to take off from the departure point, then enter from the right side of line target 3, then enter from the left side of line target 5, and finally return to the departure point, and so on.
Repeating the steps (201) to (203) for a plurality of times to obtain a plurality of chromosomes and form an initial population, wherein s is the set population number.
Step three: calculating the fitness corresponding to each chromosome in the initial population by using a track planning model, simultaneously recording the optimal fitness of the whole population, and preferably selecting the chromosomes in the initial population by adopting a classical roulette method to form a parent chromosome population; (first all chromosome fitness for the current generation is calculated (local optimum) and then the best fitness for all generations that have been solved is recorded (global optimum)).
(301) Calculating the fitness f corresponding to the h chromosome in the kth generation populationkh：
fkh＝max(Tkh) (11)
Wherein h is more than or equal to 1 and less than or equal to s, k is more than or equal to 1 and less than or equal to r, r is a genetic algebra, TkhRepresents a set of scout time costs, T, of each UAV under the scout sequence corresponding to the h chromosome in the kth generation populationkh＝(tkh1,tkh2,…,tkhm)；
(302) Calculating the best fitness g of the kth generation populationk：
gk＝min{(fk1,fk2,…fkh,…,fks)} (12)
(303) Calculating the best fitness G of the first k generations of the whole populationk：
Gk＝min{(g1,g2,…,gk)} (13)
(304) Selecting roulette: calculating the probability P that the h-th chromosome is preferred in the k-th generation populationkh：
(305) Calculating the cumulative probability q of the h chromosome in the kth generation populationkh：
qkh＝fk1+fk2+…+fkh (15)
(306) Randomly generating a number p smaller than 1 if p < qk1Then chromosome 1 in the population of the kth generation is preferred, otherwise chromosome h is selected such that q iskh＜p＜qk(h+1)And repeating the steps for s times to form a parent chromosome population.
Step four: carrying out chromosome crossing operation on chromosomes in the parent chromosome population;
(401) gene exchange: randomly selecting two father chromosomes A and B from the father chromosome population, randomly generating two crossed genes C1 and C2, and mutually exchanging the gene fragments of the genes C1 and C2 corresponding to the two father chromosomes A and B;
(402) and (4) checking conflict: modifying genes with the same target number to ensure that each target is detected at most once;
(403) gene inversion: and (3) respectively inverting gene segments between the genes C1 and C2 of the two parent chromosomes A and B to obtain the child chromosomes after the chromosome crossing operation.
As shown in fig. 3, for parent chromosomes a and B, the crossover genes are 2 and 4. First, the genes of the corresponding genes of the parent chromosomes A and B are exchanged. Then, it was found that the gene 1 of the parent chromosome A after gene exchange collided with the gene 4, and the target number of the gene 1 was changed to 3, and similarly, the target number of the gene 6 of the parent chromosome B after gene exchange was changed to 1. Finally, gene segments of gene 2 to gene 4 are inverted to obtain daughter chromosomes A and B.
Step five: carrying out chromosome variation operation on the parent chromosomes subjected to chromosome crossing operation to form a new chromosome population;
(501) unmanned aerial vehicle numbering variation: randomly generating a variation gene, and randomly mutating the number of the corresponding unmanned aerial vehicle into the numbers of other unmanned aerial vehicles. As shown in fig. 4, the unmanned aerial vehicle mutation gene is 3, the corresponding unmanned aerial vehicle is numbered 3, and the unmanned aerial vehicle is mutated into the unmanned aerial vehicle numbered 1;
(502) line target number variation: randomly generating a variant gene, randomly mutating the corresponding line target number into other target numbers, and simultaneously detecting the target number conflict. As shown in fig. 5, the unmanned aerial vehicle mutation gene is 4, the corresponding target number is 5, and the unmanned aerial vehicle mutation gene is mutated into a target with the number of 4, at this time, the target number of the gene conflicts with the target number of the gene 6, and the target number 4 of the gene 6 is modified into the target number 5 before the mutation of the gene 4;
(503) entry point number variation: randomly generating a variant gene locus, and randomly mutating the corresponding entry point number to another entry point number. As shown in fig. 6, the entry point variation gene is 5, and the corresponding entry point is numbered 1, which is mutated to another entry point 2.
Claims (5)
1. A reconnaissance flight path planning method for a line target-oriented unmanned aerial vehicle is characterized by comprising the following steps:
the method comprises the following steps: establishing a flight path planning model of the unmanned aerial vehicle cooperative reconnaissance multi-line target task with time cost as an objective function according to the characteristics of the line targets, the flight speed of the unmanned aerial vehicle and the number of the line targets required to be reconnaissance by the unmanned aerial vehicle;
step two: respectively coding the unmanned aerial vehicle number, the line target number and the entry point number of the line target for multiple times by using a multi-type gene coding mode to obtain multiple chromosomes and form an initial population;
step three: calculating the fitness corresponding to each chromosome in the initial population by using an objective function of a track planning model, and recording the optimal fitness and the corresponding chromosome in the current whole population; simultaneously, chromosome in the initial population is optimized by adopting a classical roulette method to form a parent chromosome population;
the method specifically comprises the following steps:
(301) calculating the fitness f corresponding to the h chromosome in the kth generation populationkh：
fkh＝max(Tkh)
Wherein h is more than or equal to 1 and less than or equal to s, k is more than or equal to 1 and less than or equal to r, r is a genetic algebra, s is a set population number, TkhRepresents a set of scout time costs, T, of each UAV under the scout sequence corresponding to the h chromosome in the kth generation populationkh＝(tkh1,tkh2,…,tkhm) M is the number of unmanned aerial vehicles;
(302) calculating the best fitness g of the kth generation populationk：
gk＝min{(fk1,fk2,…fkh,…,fks)}
(303) Calculating the best fitness G of the first k generations of the whole populationk：
Gk＝min{(g1,g2,…,gk)}
(304) Selecting roulette: calculating the probability P that the h-th chromosome is preferred in the k-th generation populationkh：
(305) Calculating the cumulative probability q of the h chromosome in the kth generation populationkh：
qkh＝fk1+fk2+…+fkh
(306) Randomly generating a number p smaller than 1 if p < qk1Then chromosome 1 in the population of the kth generation is preferred, otherwise chromosome h is selected such that q iskh＜p＜qk(h+1)Repeating the steps for s times to form a parent chromosome population;
step four: carrying out chromosome crossing operation on chromosomes in the parent chromosome population;
step five: carrying out chromosome variation operation on the parent chromosomes subjected to chromosome crossing operation to form a new chromosome population; taking the new chromosome population as an initial population, repeating the steps from the third step to the fifth step to a designated generation, and outputting the optimal fitness in the current whole population and the chromosome corresponding to the optimal fitness as an optimal reconnaissance sequence;
and finishing the unmanned aerial vehicle reconnaissance track planning facing the line target.
2. The line-target-oriented unmanned aerial vehicle reconnaissance trajectory planning method according to claim 1, wherein the first step specifically comprises the following steps:
is provided with m unmanned aerial vehicles and N line targets, wherein the number of the line targets required to be detected by the ith unmanned aerial vehicle is Ni；
(101) Calculating the distance L between the ith unmanned aerial vehicle and the first allocated line targeti1：
Li1＝d((xi,yi),(xi11,yi11)) (1)
Wherein the seat isLabel (x)i,yi) Indicating the position, coordinate (x) of the ith dronei11,yi11) Indicating an entry point location for an ith drone to travel to the first assigned line target; d (a, b) represents the geometric distance between point a and point b;
(102) calculating the target length l of the jth line target1ij：
l1ij＝d((xij1,yij1),(xij2,yij2)) (2)
Wherein j is less than or equal to niCoordinate (x)ij1,yij1) And (x)ij2,yij2) Respectively allocating an entry point and a departure point of a jth line target to the ith unmanned aerial vehicle;
(103) calculating the target length and L of all line targets distributed to the ith unmanned aerial vehiclei2：
(104) Calculating the distance l from the current jth line target flying-off point to the next line target entry point2ij：
l2ij＝d((xij2,yij2),(xi(j+1)1,yi(j+1)1)) (4)
(105) Calculating the distance sum L between the ith unmanned aerial vehicle and all the line targetsi3:
(106) Calculating the distance L of the unmanned plane from the flying-out point of the last line target to the position of the unmanned planei4Comprises the following steps:
Li4＝d((xi,yi),(xi(ni)2,yi(ni)2)) (6)
(107) calculating the overall path length D of the line target allocated for the detection of the ith unmanned aerial vehiclei：
Di＝Li1+Li2+Li3+Li4 (7)
(108) Calculating the time cost t of the ith unmanned aerial vehiclei：
Wherein ViThe speed of the ith unmanned aerial vehicle;
(109) then the flight path planning model for the unmanned aerial vehicle to cooperatively reconnoitre the multi-line target task is expressed as:
an objective function:
max T (9)
constraint conditions are as follows:
wherein T ═ T1,t2,…,tm) Formula (9) shows that the overall time cost of the reconnaissance mission is determined by the unmanned aerial vehicle which takes the longest time, and formula (10) shows that all line targets are reconnaissance.
3. The line-target-oriented unmanned aerial vehicle reconnaissance flight path planning method according to claim 1, wherein the second step specifically comprises the following steps:
(201) unmanned aerial vehicle numbering and coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled by the serial numbers of the unmanned aerial vehicles;
(202) line object number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein elements in the row matrix are randomly filled with the line target numbers, and each line target number is ensured to appear only once;
(203) entry point number coding: randomly generating a row matrix with the length equal to the number of the line targets, wherein each element in the row matrix randomly takes 1 or 2; "1" indicates entry from the left side of the line object, and "2" indicates entry from the right side of the line object;
(204) repeating the steps (201) to (203) for a plurality of times to obtain a plurality of chromosomes and form an initial population, wherein s is the set population number.
4. The line-target-oriented unmanned aerial vehicle reconnaissance flight path planning method according to claim 1, wherein the chromosome crossing operation in the fourth step specifically comprises the following steps:
(401) gene exchange: randomly selecting two father chromosomes A and B from the father chromosome population, randomly generating two crossed genes C1 and C2, and mutually exchanging the gene fragments of the genes C1 and C2 corresponding to the two father chromosomes A and B;
(402) and (4) checking conflict: modifying genes with the same target number to ensure that each target is detected at most once;
(403) gene inversion: and (3) respectively inverting gene segments between the genes C1 and C2 of the two parent chromosomes A and B to obtain the child chromosomes after the chromosome crossing operation.
5. The line-target-oriented unmanned aerial vehicle reconnaissance flight path planning method according to claim 1, wherein the chromosome mutation operation in the fifth step specifically comprises the following steps:
(501) unmanned aerial vehicle numbering variation: randomly generating a variation gene, and randomly mutating the number of the corresponding unmanned aerial vehicle into the numbers of other unmanned aerial vehicles;
(502) line target number variation: randomly generating a variant gene, randomly mutating a corresponding line target number into other target numbers, and simultaneously detecting target number conflict;
(503) entry point number variation: randomly generating a variant gene locus, and randomly mutating the corresponding entry point number to another entry point number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910719794.XA CN110426043B (en) | 2019-08-06 | 2019-08-06 | Unmanned aerial vehicle reconnaissance flight path planning method facing line target |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910719794.XA CN110426043B (en) | 2019-08-06 | 2019-08-06 | Unmanned aerial vehicle reconnaissance flight path planning method facing line target |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110426043A CN110426043A (en) | 2019-11-08 |
| CN110426043B true CN110426043B (en) | 2021-06-29 |
Family
ID=68414259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910719794.XA Active CN110426043B (en) | 2019-08-06 | 2019-08-06 | Unmanned aerial vehicle reconnaissance flight path planning method facing line target |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110426043B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111256697B (en) * | 2020-02-24 | 2022-09-27 | 哈尔滨工业大学 | Unmanned aerial vehicle flight path planning method aiming at path point clustering machine learning |
| CN112731967B (en) * | 2020-12-24 | 2021-11-19 | 中科院计算技术研究所大数据研究院 | Multi-unmanned aerial vehicle collaborative task planning method based on clustering and genetic algorithm |
| CN112859931A (en) * | 2021-01-11 | 2021-05-28 | 暨南大学 | Unmanned aerial vehicle flight path planning method, forest fire prevention system and computer readable storage medium |
| CN113110595B (en) * | 2021-05-12 | 2022-06-21 | 中国人民解放军陆军工程大学 | Heterogeneous unmanned aerial vehicle group cooperation method for target verification |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880186A (en) * | 2012-08-03 | 2013-01-16 | 北京理工大学 | Flight path planning method based on sparse A* algorithm and genetic algorithm |
| JP2014038495A (en) * | 2012-08-16 | 2014-02-27 | Toyota Central R&D Labs Inc | Three dimensional shape interpretation apparatus and program |
| CN105512769A (en) * | 2015-12-16 | 2016-04-20 | 上海交通大学 | Unmanned aerial vehicle route planning system and unmanned aerial vehicle route planning method based on genetic programming |
| CN106406346A (en) * | 2016-11-01 | 2017-02-15 | 北京理工大学 | Plan method for rapid coverage track search coordinated by multiple UAVs (Unmanned Aerial Vehicles) |
| CN106842963A (en) * | 2017-04-14 | 2017-06-13 | 合肥工业大学 | Multiple no-manned plane detection mission is distributed and trajectory planning combined optimization method and device |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107144264A (en) * | 2017-06-19 | 2017-09-08 | 北京理工大学 | A kind of aeroplane photography method that high definition pavement image is gathered for fixed-wing unmanned plane |
-
2019
- 2019-08-06 CN CN201910719794.XA patent/CN110426043B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102880186A (en) * | 2012-08-03 | 2013-01-16 | 北京理工大学 | Flight path planning method based on sparse A* algorithm and genetic algorithm |
| JP2014038495A (en) * | 2012-08-16 | 2014-02-27 | Toyota Central R&D Labs Inc | Three dimensional shape interpretation apparatus and program |
| CN105512769A (en) * | 2015-12-16 | 2016-04-20 | 上海交通大学 | Unmanned aerial vehicle route planning system and unmanned aerial vehicle route planning method based on genetic programming |
| CN106406346A (en) * | 2016-11-01 | 2017-02-15 | 北京理工大学 | Plan method for rapid coverage track search coordinated by multiple UAVs (Unmanned Aerial Vehicles) |
| CN106842963A (en) * | 2017-04-14 | 2017-06-13 | 合肥工业大学 | Multiple no-manned plane detection mission is distributed and trajectory planning combined optimization method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110426043A (en) | 2019-11-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110426043B (en) | Unmanned aerial vehicle reconnaissance flight path planning method facing line target | |
| Liu et al. | An improved ant colony algorithm for robot path planning | |
| Zhen et al. | Rotary unmanned aerial vehicles path planning in rough terrain based on multi-objective particle swarm optimization | |
| Hidalgo-Paniagua et al. | Solving the multi-objective path planning problem in mobile robotics with a firefly-based approach | |
| CN107807665B (en) | Unmanned aerial vehicle formation detection task cooperative allocation method and device | |
| CN109459026B (en) | Multi-moving-body collaborative full-coverage path planning method | |
| CN107886201B (en) | Multi-objective optimization method and device for multi-unmanned aerial vehicle task allocation | |
| CN110766254A (en) | Multi-unmanned aerial vehicle cooperative task allocation method based on improved genetic algorithm | |
| CN103267528A (en) | Multi-unmanned aerial vehicle cooperative area search method under non-flight zone limitation | |
| CN110986960B (en) | Unmanned aerial vehicle flight path planning method based on improved clustering algorithm | |
| Fu et al. | On trajectory homotopy to explore and penetrate dynamically of multi-UAV | |
| Zhang et al. | A self-heuristic ant-based method for path planning of unmanned aerial vehicle in complex 3-D space with dense U-type obstacles | |
| Tian | Research on robot optimal path planning method based on improved ant colony algorithm | |
| Xiang et al. | An effective memetic algorithm for UAV routing and orientation under uncertain navigation environments | |
| CN114399161A (en) | Multi-unmanned aerial vehicle cooperative task allocation method based on discrete mapping differential evolution algorithm | |
| CN113110517B (en) | Multi-robot collaborative search method based on biological elicitation in unknown environment | |
| Dashkevich et al. | Simulation tool for the drone trajectory planning based on genetic algorithm approach | |
| Ali et al. | Feature selection-based decision model for UAV path planning on rough terrains | |
| Ma et al. | A two-level memetic path planning algorithm for unmanned air/ground vehicle cooperative detection systems | |
| Zirong et al. | 3D Trajectory Planning of UAV Based on DPGA | |
| Duan et al. | Solving multi-objective path planning for service robot by a pareto-based optimization algorithm | |
| Bi et al. | Dynamic weighted and heat-map integrated scalable information path-planning algorithm | |
| Tian et al. | Formulation and a MOGA based approach for multi-UAV cooperative reconnaissance | |
| Zhou et al. | Real-time multi-target path prediction and planning for autonomous driving aided by fcn | |
| Wu et al. | Waiting-Time-Optimized Path Planning of Multiple Automatic Guided Vehicles Using Augmented Topology Map |
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 |