CN113703488A - Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm - Google Patents

Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm Download PDF

Info

Publication number
CN113703488A
CN113703488A CN202111122205.3A CN202111122205A CN113703488A CN 113703488 A CN113703488 A CN 113703488A CN 202111122205 A CN202111122205 A CN 202111122205A CN 113703488 A CN113703488 A CN 113703488A
Authority
CN
China
Prior art keywords
path
unmanned aerial
aerial vehicle
point
plant protection
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.)
Withdrawn
Application number
CN202111122205.3A
Other languages
Chinese (zh)
Inventor
徐止政
于全友
段纳
程义
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jiangsu Normal University
Original Assignee
Jiangsu Normal University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Jiangsu Normal University filed Critical Jiangsu Normal University
Priority to CN202111122205.3A priority Critical patent/CN113703488A/en
Publication of CN113703488A publication Critical patent/CN113703488A/en
Withdrawn legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course or altitude of land, water, air, or space vehicles, e.g. automatic pilot
    • 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

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention provides a multi-operation plant protection unmanned aerial vehicle path planning method based on an improved ant colony algorithm, which comprises the following steps: generating an operation path endpoint set of the plant protection unmanned aerial vehicle in a scanning line mode, deleting redundant operation path endpoints under the constraint condition in a root path generation algorithm, and sequentially pairwise matching adjacent operation path endpoints to form the operation path set of the plant protection unmanned aerial vehicle
Figure DEST_PATH_IMAGE002
Traversing and optimizing the course of the internally protected unmanned aerial vehicle, and selecting the operation path set with the minimum number of operation paths; and sequencing the operation paths by improving an ant colony algorithm and selecting a proper position for return voyage replenishment. The invention can quickly select the optimal path and effectively improve the working efficiency of the plant protection unmanned aerial vehicle.

Description

Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm
Technical Field
The invention relates to the field of path planning, in particular to a multi-operation plant protection unmanned aerial vehicle path planning method based on an improved ant colony algorithm.
Background
Compared with the traditional plant protection machine, the multi-rotor-wing plant protection unmanned aerial vehicle has the advantages of high efficiency, low cost, strong terrain adaptability, flexible operation and the like, and is widely applied. The traditional path planning method comprises an artificial potential field method, a Dijstra algorithm and the like. With the increase of obstacles and the continuous increase of the complexity of the problem scale, the traditional algorithm has certain limitation, so that some bionic intelligent optimization algorithms, such as an ant colony algorithm, a particle swarm algorithm, a firefly algorithm and the like, are carried forward.
When the plant protection unmanned aerial vehicle carries out spraying operation again, the operation area is large, the operation task can be completed only by replacing batteries and supplying materials for many times, the spraying route of the general plant protection unmanned aerial vehicle is a cattle-ploughing reciprocating method, and the route chart is shown in fig. 4. Plant protection unmanned aerial vehicle is probably not enough in the time of endurance of spraying operation battery, and this inevitable can involve the problem of plant protection unmanned aerial vehicle's supply of returning a journey.
The ant colony algorithm is a simulation optimization algorithm for simulating foraging behavior of ants, is suitable for processing the problem of the traveling salesman, and can obtain better node sequencing by taking the shortest transfer path as a target. The basic idea is as follows: the ant colony starts in batches, each ant selects a route traversing each node, pheromones are left on the routes, the total length of the routes is shorter, the pheromones are more, later ants select routes with higher pheromone concentration, the pheromones on the routes with shorter total length are accumulated continuously along with the increase of batches, and finally, the ant colony is concentrated on the route with the most pheromones.
The sequencing problem of the operation path considering the endurance time of the plant protection unmanned aerial vehicle is very similar to that of DTSP (dynamic station traveler problem), nodes are traversed and are not repeated, but the two differences exist, firstly, the node of the general station traveler problem is a point, the distance between the nodes is determined, the node in the sequencing of the operation path is the operation path of the plant protection unmanned aerial vehicle, the node is a line segment consisting of two points, the distance between the nodes is uncertain, and four possibilities exist. Secondly, dynamic changes of DTSP city nodes (such as city coordinate changes, inter-city path weight changes, city increase or extinction and the like) occur once every several generations in the optimization iteration process, and the number and positions of generated return points are different due to different operation path selection of the unmanned aerial vehicle, so that the method has similar characteristics to the dynamic traveler problem, but the method is essentially different from the dynamic traveler problem.
Disclosure of Invention
The invention aims to solve the problem of insufficient battery power of a plant protection unmanned aerial vehicle, provides a multi-operation plant protection unmanned aerial vehicle path planning method based on an improved ant colony algorithm, and is a method capable of obtaining a global optimal energy-saving path plan, so that the battery power of the plant protection unmanned aerial vehicle is effectively saved.
The purpose of the invention is realized by at least one of the following technical solutions.
The unmanned ship energy-saving path planning method based on the ant colony algorithm comprises the following steps:
step 1) using a group of intervals to operate wide breadth for plant protection unmanned aerial vehicle
Figure 125540DEST_PATH_IMAGE001
Scan line rotation of
Figure 476755DEST_PATH_IMAGE002
Then intersecting with the boundary of the operation area, wherein the intersection point is an operation path endpoint;
step 2) deleting the operation path end points which do not accord with the constraint conditions, pairing the adjacent operation path end points in pairs in sequence, and enabling a connecting line between each pair of intersection points to be an operation path of the plant protection unmanned aerial vehicle;
step 3)
Figure 718381DEST_PATH_IMAGE003
Traversing and optimizing the course of the plant protection unmanned aerial vehicle, and repeating the step 1) and the step 2), and selecting the plant protection unmanned aerial vehicle with the least number of operation paths as a final plant protection unmanned aerial vehicle operation path set;
step 4) ant colony algorithm parameter initialization and setting of supply points (namely starting point and end point) of plant protection unmanned aerial vehicle
Step 5) randomly selecting a starting point of an operation path of the plant protection unmanned aerial vehicle, judging whether the residual electric quantity can fly to the end point of the operation path and then can still return to a supply point, and if the residual electric quantity can fly to the end point of the operation path, turning to step 6 after the operation reaches the end point; otherwise, calculating the position of a return point in the operation path, and repeating the step 5 after the plant protection unmanned aerial vehicle returns for supply);
step 6) judging whether all the operation paths are finished, if not, selecting a starting point of the next operation path according to a transition probability formula, then judging whether the residual electric quantity can fly to the starting point of the next operation path and then still return to a supply point, and if the residual electric quantity can fly to the return point, turning to the step 5); otherwise, returning and supplying at the end point of the current operation path, and then turning to the step 5); if all the operation paths are finished, turning to step 7);
and 7) updating pheromones, finishing each iteration, calculating the pheromone concentration on the path through 3 pheromone increment matrixes from the end points of the operation paths to the operation paths and between the end points of the operation paths and the operation paths if the iteration number is less than the maximum iteration number, and outputting the final operation path sequencing optimization result if the iteration number is more than the maximum iteration number.
Further, in step 2), when the scan line intersects the polygon work area, there is a possibility that the scan line intersects the vertex, and thus two identical intersection points are generated. In this case, two points that overlap each other may be regarded as one working path end point, the left and right vertexes of the vertex may be determined, and if the vertical coordinates of the left and right vertexes are simultaneously greater than or less than the vertical coordinate of the vertex, the point may be collectively deleted from the working path end points. If not, the point is regarded as an operation path end point, and then the plant protection unmanned aerial vehicle operation path set is generated by pairing every two points in sequence.
Further, in step 6), in the improved ant colony algorithm, selecting the next operation path by using a transition probability formula, where the transition probability formula is as follows:
Figure 885182DEST_PATH_IMAGE004
wherein
Figure 200757DEST_PATH_IMAGE005
Respectively, the end point and the start point of the operation path;
Figure 801503DEST_PATH_IMAGE006
is as follows
Figure 264845DEST_PATH_IMAGE007
Only ants are selected from
Figure 796190DEST_PATH_IMAGE008
Transition probability to; is an pheromone factor;
Figure 28588DEST_PATH_IMAGE009
is a heuristic function factor;
Figure 800235DEST_PATH_IMAGE010
is at the same time
Figure 750873DEST_PATH_IMAGE011
From the end point of the time job path to the start point of the job path
Figure 571062DEST_PATH_IMAGE012
The pheromone of (a);
Figure 611961DEST_PATH_IMAGE013
is at the same time
Figure 554509DEST_PATH_IMAGE011
From the end point of the time job path to the start point of the job path
Figure 930127DEST_PATH_IMAGE012
The heuristic function of (2), the heuristic function being the reciprocal of the distance;
Figure 616323DEST_PATH_IMAGE014
is a collection of nodes that have not been visited.
Considering the battery endurance of the plant protection unmanned aerial vehicle, each ant may generate a new return point, and if the return point is located on the operation path, a new operation path end point is generated. Because a new operation path end point is generated, the distance matrix of the original heuristic function is inaccurate, and therefore the heuristic function needs to be updated in real time to ensure the accuracy of the transition probability function.
Further, in step 7), in order to improve the accuracy of finding the optimal path by the ant colony algorithm, 3 pheromone increment matrixes are adopted to calculate the pheromone concentration on the path, and the pheromone updating formula is as follows:
Figure 823314DEST_PATH_IMAGE015
Figure 123714DEST_PATH_IMAGE016
Figure 48945DEST_PATH_IMAGE017
Figure 210936DEST_PATH_IMAGE018
wherein
Figure 538012DEST_PATH_IMAGE019
Is pheromone volatilization factor;
Figure 556783DEST_PATH_IMAGE020
is the pheromone increment on the transfer path;
Figure 657726DEST_PATH_IMAGE021
is a pheromone constant;
Figure 685724DEST_PATH_IMAGE022
、
Figure 867307DEST_PATH_IMAGE023
and
Figure 322559DEST_PATH_IMAGE024
are respectively the first
Figure 956803DEST_PATH_IMAGE025
Ants are point-to-point, point-to-line, line-to-lineThe total length of the path taken.
After all ants run once, the iteration is regarded as one time, the maximum iteration times are set, and the global optimal energy-saving path planning is obtained when the maximum iteration times are reached; for paths with few ants, the pheromone is less and less, namely, the selection probability is lower and lower, and for paths with many ants, the pheromone is accumulated more and more, and the selection probability is higher and higher.
Compared with the prior art, the invention has the advantages that:
fewer job paths. The operation path set which can cover the whole operation area and has the least number is obtained through the operation path generation algorithm, and the plant protection unmanned aerial vehicle has the shortest flight path, namely consumes the least energy.
Drawings
FIG. 1 is an overall flow diagram of the present invention;
FIG. 2 is a flow chart of a path generation algorithm;
FIG. 3 is a flow chart of an improved ant colony algorithm;
FIG. 4 is a schematic diagram of a spraying route of a plant protection unmanned aerial vehicle in a rectangular area;
FIG. 5 is a cross-sectional view of a scan line and a work area;
fig. 6 is a schematic position diagram of a return point of the plant protection unmanned aerial vehicle;
fig. 7 is a plant protection unmanned aerial vehicle flight path diagram for improved ant colony algorithm planning within a regular region;
FIG. 8 is a diagram of plant protection unmanned aerial vehicle flight paths for greedy algorithm planning within a regulated area;
fig. 9 is a plant protection unmanned aerial vehicle flight path diagram for improved ant colony algorithm planning in irregular areas;
fig. 10 is a graph of plant protection unmanned aerial vehicle flight paths for greedy algorithm planning in irregular areas.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention are described in detail below with reference to the accompanying drawings.
As shown in fig. 1, the method for planning the path of the plant protection unmanned aerial vehicle for multiple operations based on the improved ant colony algorithm is mainly divided into two parts, namely a path generation algorithm and the improved ant colony algorithm. The path generation algorithm can help the plant protection unmanned aerial vehicle to find the operation path set with the least number, the improved ant colony algorithm optimizes the operation path sequencing, and the operation path sequencing with the shortest flight path of the plant protection unmanned aerial vehicle is selected.
Step 1) using a group of intervals to operate wide breadth for plant protection unmanned aerial vehicle
Figure 460597DEST_PATH_IMAGE001
Scan line rotation of
Figure 762265DEST_PATH_IMAGE002
Then intersecting with the boundary of the operation area, wherein the intersection point is an operation path endpoint;
step 2) deleting the operation path end points which do not accord with the constraint conditions, pairing the adjacent operation path end points in pairs in sequence, and enabling a connecting line between each pair of intersection points to be an operation path of the plant protection unmanned aerial vehicle;
as shown in fig. 5, when the scanning line intersects the polygon work area, there is a possibility that the scanning line intersects the vertex, and therefore two identical intersections occur. The scanning line S1 and the boundary of the polygon area
Figure 388418DEST_PATH_IMAGE026
And a boundary
Figure DEST_PATH_IMAGE027
All intersect at a point
Figure 696909DEST_PATH_IMAGE028
And a boundary
Figure 66710DEST_PATH_IMAGE029
And
Figure 222885DEST_PATH_IMAGE030
intersect at a point
Figure 19940DEST_PATH_IMAGE031
And a boundary
Figure 628776DEST_PATH_IMAGE032
And
Figure 474372DEST_PATH_IMAGE033
intersect at a point
Figure 485053DEST_PATH_IMAGE034
And a boundary
Figure 141425DEST_PATH_IMAGE035
、
Figure 237557DEST_PATH_IMAGE036
And
Figure 949161DEST_PATH_IMAGE037
intersect at a point
Figure 814349DEST_PATH_IMAGE038
、
Figure 890889DEST_PATH_IMAGE039
And
Figure 474317DEST_PATH_IMAGE040
. When the two points are coincident, the coincident two points are regarded as an operation path end point, and then paired in sequence, so that a line segment can be obtained
Figure 989612DEST_PATH_IMAGE041
、
Figure 896257DEST_PATH_IMAGE042
And
Figure 206016DEST_PATH_IMAGE043
wherein the effective operation path is a line segment
Figure 276740DEST_PATH_IMAGE043
To do so
Figure 267830DEST_PATH_IMAGE041
And
Figure 107610DEST_PATH_IMAGE042
it is outside the polygon working area and this is clearly incorrect.
In order to solve the above problem, it is necessary to determine the left and right vertexes of the intersection point located at the vertex of the working area, and if the vertical coordinates of the left and right vertexes are simultaneously greater than or less than the vertical coordinate of the vertex, the point is centrally deleted from the working path end point. If not, the point is regarded as the end point of the operation path. Then, the two unmanned aerial vehicles are paired in sequence to form a re-heading angle of the plant protection unmanned aerial vehicle
Figure 588270DEST_PATH_IMAGE002
The following set of job paths.
Step 3)
Figure 146290DEST_PATH_IMAGE003
In that
Figure 737808DEST_PATH_IMAGE044
Traversing and optimizing the course of the plant protection unmanned aerial vehicle, and repeating the step 1) and the step 2), and selecting the plant protection unmanned aerial vehicle with the least number of operation paths as a final plant protection unmanned aerial vehicle operation path set;
Figure 120510DEST_PATH_IMAGE003
starting from 0 DEG, take
Figure 37651DEST_PATH_IMAGE045
Turning to step 1) for step traversal mode, calculating the next operation path set, and comparing each operation path set with the minimum number of operation paths
Figure 817388DEST_PATH_IMAGE046
To determine a heading angle and a set of work paths for the plant protection drone.
Step 4) ant colony algorithm parameter initialization and setting of supply points (namely starting point and end point) of plant protection unmanned aerial vehicle
Initialization parameter, number of ants
Figure 212597DEST_PATH_IMAGE047
Pheromone importance factor
Figure 964652DEST_PATH_IMAGE048
Factor of importance of heuristic function
Figure 787115DEST_PATH_IMAGE049
Pheromone volatility coefficient
Figure 54148DEST_PATH_IMAGE050
Intensity coefficient of pheromone
Figure 253048DEST_PATH_IMAGE051
Number of iterations
Figure 921927DEST_PATH_IMAGE052
And the like. The starting point, the terminal point and the supply point of the plant protection unmanned aerial vehicle are set as one point.
Step 5) randomly selecting a starting point of an operation path of the plant protection unmanned aerial vehicle, judging whether the residual electric quantity can fly to the end point of the operation path and then can still return to a supply point, and if the residual electric quantity can fly to the end point of the operation path, turning to step 6 after the operation reaches the end point; otherwise, calculating the position of a return point in the operation path, and repeating the step 5 after the plant protection unmanned aerial vehicle returns for supply);
selecting a starting point of a working path of the plant protection unmanned aerial vehicle, judging the number of the end point of the working path according to the odd-even number of the starting point, and if the starting point is odd, taking the number of the end point as the starting point number + 1; if the starting point number is an even number, the end point number is the starting point number-1.
As shown in FIG. 6, the working paths and the transfer paths are arranged alternately, and the working paths are
Figure DEST_PATH_IMAGE053
Figure 39925DEST_PATH_IMAGE054
The transfer path is
Figure 794254DEST_PATH_IMAGE055
Figure 531266DEST_PATH_IMAGE056
. The consumption of the battery of the plant protection unmanned aerial vehicle is closely related to the accumulated flight distance, and the residual electric quantity is converted into the residual flight distance of the plant protection unmanned aerial vehicle on the assumption that the electric quantity consumed by the plant protection unmanned aerial vehicle per kilometer is the same. When the plant protection unmanned aerial vehicle carries out the operation task, need carry out the residual capacity monitoring to the arbitrary point of each airline.
To have
Figure 743067DEST_PATH_IMAGE057
Model of a work path, flying to waypoints in order
Figure 172911DEST_PATH_IMAGE058
For accumulated mileage
Figure 414537DEST_PATH_IMAGE059
To indicate, from the waypoint
Figure 689660DEST_PATH_IMAGE058
The return journey replenishment route is
Figure 333131DEST_PATH_IMAGE060
The total single flight path of the plant protection unmanned aerial vehicle is
Figure 605981DEST_PATH_IMAGE061
Of 1 at
Figure 521853DEST_PATH_IMAGE062
For a working path
Figure 600667DEST_PATH_IMAGE063
Is shown in which
Figure 98645DEST_PATH_IMAGE064
The number of the starting point of the operation path,
Figure 870292DEST_PATH_IMAGE065
for the operation path end point number, the flight distance of the plant protection unmanned aerial vehicle before returning is as follows:
Figure 758613DEST_PATH_IMAGE066
wherein
Figure 641119DEST_PATH_IMAGE067
Is a rounded up symbol;
if the accumulated distance of the plant protection unmanned aerial vehicle meets the requirement
Figure 993602DEST_PATH_IMAGE068
Then the return journey program is executed immediately, the return journey point is called
Figure 636285DEST_PATH_IMAGE069
. When in use
Figure 74220DEST_PATH_IMAGE070
When the route is the starting point of the operation route, the route returns from the end point of the previous operation route; when in use
Figure 494837DEST_PATH_IMAGE071
When the operation path is at the end point, the return point is positioned on the current operation path through a formula
Figure 905089DEST_PATH_IMAGE072
To determine the return point
Figure 18539DEST_PATH_IMAGE073
Specific location of
Step 6) judging whether all the operation paths are finished, if not, selecting a starting point of the next operation path according to a transition probability formula, then judging whether the residual electric quantity can fly to the starting point of the next operation path and then still return to a supply point, and if the residual electric quantity can fly to the return point, turning to the step 5); otherwise, returning and supplying at the end point of the current operation path, and then turning to the step 5); if all the operation paths are finished, turning to step 7);
in the improved ant colony algorithm, the next operation path is selected through a transition probability formula, wherein the transition probability formula is as follows:
Figure 943770DEST_PATH_IMAGE004
wherein
Figure 168077DEST_PATH_IMAGE005
Respectively, the end point and the start point of the operation path;
Figure 229574DEST_PATH_IMAGE006
is as follows
Figure 638559DEST_PATH_IMAGE007
Only ants are selected from
Figure 51086DEST_PATH_IMAGE008
To
Figure 79085DEST_PATH_IMAGE074
The transition probability of (2);
Figure 260667DEST_PATH_IMAGE075
is an pheromone factor;
Figure 138756DEST_PATH_IMAGE009
is a heuristic function factor;
Figure 38579DEST_PATH_IMAGE010
is at the same time
Figure 604689DEST_PATH_IMAGE011
Time operation path end point
Figure 906357DEST_PATH_IMAGE076
To the starting point of the operation path
Figure 266932DEST_PATH_IMAGE012
The pheromone of (a);
Figure 591734DEST_PATH_IMAGE013
is at the same time
Figure 961535DEST_PATH_IMAGE011
Time operation path end point
Figure 852131DEST_PATH_IMAGE076
To the starting point of the operation path
Figure 649186DEST_PATH_IMAGE012
Of a heuristic function of
Figure 444972DEST_PATH_IMAGE005
The reciprocal of the distance;
Figure 618464DEST_PATH_IMAGE014
is a collection of nodes that have not been visited.
And 7) updating pheromones, finishing each iteration, calculating the pheromone concentration on the path through 3 pheromone increment matrixes from the end points of the operation paths to the operation paths and between the end points of the operation paths and the operation paths if the iteration number is less than the maximum iteration number, and outputting the final operation path sequencing optimization result if the iteration number is more than the maximum iteration number.
In order to improve the accuracy of finding the optimal path by the ant colony algorithm, 3 pheromone increment matrixes are adopted to calculate the pheromone concentration on the path, and a pheromone updating formula is as follows:
Figure 629146DEST_PATH_IMAGE077
Figure 597102DEST_PATH_IMAGE015
Figure 693234DEST_PATH_IMAGE016
Figure 342521DEST_PATH_IMAGE017
Figure 207709DEST_PATH_IMAGE018
wherein
Figure 34982DEST_PATH_IMAGE019
Is pheromone volatilization factor;
Figure 618410DEST_PATH_IMAGE020
is the pheromone increment on the transfer path;
Figure 805809DEST_PATH_IMAGE021
is a pheromone constant;
Figure 791082DEST_PATH_IMAGE022
、
Figure 100841DEST_PATH_IMAGE023
and
Figure 171565DEST_PATH_IMAGE024
are respectively the first
Figure 411922DEST_PATH_IMAGE025
Only ants take the total length of the path from point to point, from point to line, and from line to line.
After all ants run once, the iteration is regarded as one time, the maximum iteration times are set, and the global optimal energy-saving path planning is obtained when the maximum iteration times are reached; for paths with few ants, the pheromone is less and less, namely, the selection probability is lower and lower, and for paths with many ants, the pheromone is accumulated more and more, and the selection probability is higher and higher.
Firstly, tests are carried out in a regular area, and the experimental results are shown in fig. 7 and fig. 8, the improved ant colony algorithm greatly reduces the turning times and the flight distance of the unmanned aerial vehicle compared with a single greedy algorithm, the improved ant colony algorithm avoids blindness and has good positive feedback at the initial searching stage, the convergence rate of the algorithm is improved, and an optimal solution is obtained.
In order to further verify the adaptability and effectiveness of the improved ant colony algorithm in the complex environment, a plurality of complex polygonal operation areas are adopted for experiments, the experimental results are shown in fig. 9 and 10, and the improved ant colony algorithm is about 11% better than the greedy algorithm in flight distance.
The present invention is not limited to the above-mentioned embodiments, and based on the technical solutions disclosed in the present invention, those skilled in the art can make some substitutions and modifications to some technical features without creative efforts according to the disclosed technical contents, and these substitutions and modifications are all within the protection scope of the present invention.

Claims (4)

1. A multi-operation plant protection unmanned aerial vehicle path planning method based on an improved ant colony algorithm is characterized by comprising the following steps:
step 1) using a group of intervals to operate wide breadth for plant protection unmanned aerial vehicle
Figure 887266DEST_PATH_IMAGE001
Scan line rotation of
Figure 194751DEST_PATH_IMAGE002
Then intersecting with the boundary of the operation area, wherein the intersection point is an operation path endpoint;
step 2) deleting the operation path end points which do not accord with the constraint conditions, pairing the adjacent operation path end points in pairs in sequence, and enabling a connecting line between each pair of intersection points to be an operation path of the plant protection unmanned aerial vehicle;
step 3) in
Figure 85346DEST_PATH_IMAGE003
Carrying out course traversal optimization on the built-in protected unmanned aerial vehicle, and repeating the step 1) and the step 2), wherein the number of the selected operation paths is minimumAs a final plant protection unmanned aerial vehicle operation path set;
step 4) ant colony algorithm parameter initialization and setting of supply points (namely starting point and end point) of plant protection unmanned aerial vehicle
Figure 882401DEST_PATH_IMAGE004
；
Step 5) randomly selecting a starting point of an operation path of the plant protection unmanned aerial vehicle, judging whether the residual electric quantity can fly to the end point of the operation path and then can still return to a supply point, and if the residual electric quantity can fly to the end point of the operation path, turning to step 6 after the operation reaches the end point; otherwise, calculating the position of a return point in the operation path, and repeating the step 5 after the plant protection unmanned aerial vehicle returns for supply);
step 6) judging whether all the operation paths are finished, if not, selecting a starting point of the next operation path according to a transition probability formula, then judging whether the residual electric quantity can fly to the starting point of the next operation path and then still return to a supply point, and if the residual electric quantity can fly to the return point, turning to the step 5); otherwise, returning and supplying at the end point of the current operation path, and then turning to the step 5); if all the operation paths are finished, turning to step 7);
and 7) updating pheromones, finishing each iteration, calculating the pheromone concentration on the path through 3 pheromone increment matrixes from the end points of the operation paths to the operation paths and between the end points of the operation paths and the operation paths if the iteration number is less than the maximum iteration number, and outputting the final operation path sequencing optimization result if the iteration number is more than the maximum iteration number.
2. The method for planning the path of the plant protection unmanned aerial vehicle with multiple operations according to claim 1, wherein in step 2), when the scan line intersects with the polygonal operation area, there is a possibility that the scan line intersects with the vertex, so that two identical intersection points are generated, for this case, two coincident points can be regarded as an operation path end point, and then the left and right vertices of the vertex are determined, if the vertical coordinates of the left and right vertices are simultaneously greater than or less than the vertical coordinate of the vertex, the point is deleted from the operation path end point set, if not, the point is regarded as the operation path end point, and then the operation path sets of the plant protection unmanned aerial vehicle are generated by pairwise pairing.
3. The method for planning the path of the unmanned aerial vehicle for multiple operations and plant protection based on the improved ant colony algorithm of claim 1, wherein in the step 6), the next operation path is selected by a transition probability formula in the improved ant colony algorithm, and the transition probability formula is as follows:
Figure 865138DEST_PATH_IMAGE005
wherein
Figure 38630DEST_PATH_IMAGE006
Respectively, the end point and the start point of the operation path;
Figure 49312DEST_PATH_IMAGE007
is as follows
Figure 954951DEST_PATH_IMAGE008
Only ants are selected from
Figure 51083DEST_PATH_IMAGE009
To
Figure 762687DEST_PATH_IMAGE010
The transition probability of (2);
Figure 627875DEST_PATH_IMAGE011
is an pheromone factor; is a heuristic function factor;
Figure 766732DEST_PATH_IMAGE012
to end the working path at the time
Figure 287843DEST_PATH_IMAGE009
Pheromones to the start of the job path;
Figure 475242DEST_PATH_IMAGE013
to end the working path at the time
Figure 460516DEST_PATH_IMAGE009
To the starting point of the operation path
Figure 770274DEST_PATH_IMAGE010
Of a heuristic function of
Figure 280146DEST_PATH_IMAGE006
The reciprocal of the distance;
Figure 333553DEST_PATH_IMAGE014
for a set of nodes that have not been visited,
considering the battery endurance of the plant protection unmanned aerial vehicle, each ant may generate a new return point, if the return point is located on the operation path, a new operation path end point is generated,
because a new operation path end point is generated, the distance matrix of the original heuristic function is inaccurate, and therefore the heuristic function needs to be updated in real time to ensure the accuracy of the transition probability function.
4. The method for planning the path of the unmanned aerial vehicle for multiple operations and plant protection based on the improved ant colony algorithm as claimed in claim 1, wherein in step 7), in order to improve the accuracy of the improved ant colony algorithm in finding the optimal path, 3 pheromone increment matrixes are adopted to calculate the pheromone concentration on the path, and the pheromone updating formula is as follows:
Figure 111016DEST_PATH_IMAGE015
wherein
Figure 591676DEST_PATH_IMAGE016
Figure 884117DEST_PATH_IMAGE017
Figure 741215DEST_PATH_IMAGE018
Figure 373184DEST_PATH_IMAGE019
Wherein
Figure 24746DEST_PATH_IMAGE020
Is pheromone volatilization factor;
Figure 7745DEST_PATH_IMAGE021
is the pheromone increment on the transfer path;
Figure 402954DEST_PATH_IMAGE022
is a pheromone constant;
Figure 387966DEST_PATH_IMAGE023
、
Figure 476007DEST_PATH_IMAGE024
and are respectively the first
Figure 743041DEST_PATH_IMAGE025
Only ants take the total length of the path from point to point, from point to line, and from line to line.
CN202111122205.3A 2021-09-24 2021-09-24 Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm Withdrawn CN113703488A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202111122205.3A CN113703488A (en) 2021-09-24 2021-09-24 Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111122205.3A CN113703488A (en) 2021-09-24 2021-09-24 Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm

Publications (1)

Publication Number Publication Date
CN113703488A true CN113703488A (en) 2021-11-26

Family

ID=78661752

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111122205.3A Withdrawn CN113703488A (en) 2021-09-24 2021-09-24 Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm

Country Status (1)

Country Link
CN (1) CN113703488A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114326804A (en) * 2021-12-28 2022-04-12 广州极飞科技股份有限公司 Route planning method, operation control method and related device
CN114764251A (en) * 2022-05-13 2022-07-19 电子科技大学 Energy-saving method for multi-agent collaborative search based on energy consumption model

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114326804A (en) * 2021-12-28 2022-04-12 广州极飞科技股份有限公司 Route planning method, operation control method and related device
CN114326804B (en) * 2021-12-28 2023-06-09 广州极飞科技股份有限公司 Route planning method, operation control method and related devices
CN114764251A (en) * 2022-05-13 2022-07-19 电子科技大学 Energy-saving method for multi-agent collaborative search based on energy consumption model
CN114764251B (en) * 2022-05-13 2023-10-10 电子科技大学 Multi-agent collaborative search energy-saving method based on energy consumption model

Similar Documents

Publication Publication Date Title
CN110941261B (en) Autonomous underwater vehicle multi-zone traversal path planning method
CN103699135B (en) The flight path automatic planning in depopulated helicopter pesticide spraying farmland operation region
CN110530388B (en) Multi-AGV path planning method and system
CN113703488A (en) Multi-operation plant protection unmanned aerial vehicle path planning method based on improved ant colony algorithm
CN112650229B (en) Mobile robot path planning method based on improved ant colony algorithm
CN107622327A (en) Multiple no-manned plane path planning method based on cultural ant colony search mechanisms
CN105841702A (en) Method for planning routes of multi-unmanned aerial vehicles based on particle swarm optimization algorithm
CN109357685A (en) Airway net generation method, device and storage medium
CN108413963A (en) Bar-type machine people's paths planning method based on self study ant group algorithm
Li et al. Mobile robot path planning based on improved genetic algorithm with A-star heuristic method
CN111189455B (en) Unmanned aerial vehicle route planning method, system and storage medium
CN115454132A (en) Unmanned aerial vehicle inspection three-dimensional path planning method and system for mountain photovoltaic power station
Yu et al. Balanced multi-region coverage path planning for unmanned aerial vehicles
Gu et al. Robot path planning of improved adaptive Ant Colony System Algorithm based on Dijkstra
CN113649206A (en) Track generation optimization method for ship body construction paint spraying
Wang et al. Autonomous vehicles path planning with enhanced ant colony optimization
Gao et al. Competitive self-organizing neural network based UAV path planning
Huang et al. A Multi-robot Coverage Path Planning Algorithm Based on Improved DARP Algorithm
Cheng et al. Route planning of mixed ant colony algorithm based on Dubins path
CN114911254A (en) Unmanned aerial vehicle penetration path planning method based on Laguerre graph
Kang et al. A research on area coverage algorithm for robotics
CN111896001A (en) Three-dimensional ant colony track optimization method
Zhang et al. Research on complete coverage path planning for unmanned surface vessel
CN113589841A (en) Unmanned aerial vehicle route generation method, unmanned aerial vehicle and computer readable storage medium
CN113625771A (en) Shadow following single unmanned aerial vehicle area coverage path planning method

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
WW01 Invention patent application withdrawn after publication

Application publication date: 20211126

WW01 Invention patent application withdrawn after publication