CN116518982B - Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method - Google Patents
Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method Download PDFInfo
- Publication number
- CN116518982B CN116518982B CN202310796607.4A CN202310796607A CN116518982B CN 116518982 B CN116518982 B CN 116518982B CN 202310796607 A CN202310796607 A CN 202310796607A CN 116518982 B CN116518982 B CN 116518982B
- Authority
- CN
- China
- Prior art keywords
- path
- aerial vehicle
- unmanned aerial
- objective
- sample points
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 54
- 238000012544 monitoring process Methods 0.000 title claims abstract description 21
- 239000013598 vector Substances 0.000 claims abstract description 60
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 238000013178 mathematical model Methods 0.000 claims abstract description 17
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000004364 calculation method Methods 0.000 claims abstract description 8
- 230000004083 survival effect Effects 0.000 claims description 11
- 238000005070 sampling Methods 0.000 claims description 6
- 238000005265 energy consumption Methods 0.000 claims description 3
- 230000035772 mutation Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012804 iterative process Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 208000034699 Vitreous floaters Diseases 0.000 description 1
- 230000004888 barrier function Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000001172 regenerating effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The application discloses a multi-target planning method for a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path, which relates to the technical field of low-altitude remote sensing unmanned aerial vehicle path planning and comprises the following steps: s10, establishing a Maklink three-dimensional graph theory model of the unmanned aerial vehicle path environment based on initial environment information; obtaining a specific single path scheme based on the Maklink three-dimensional graph theory model; s20, establishing a mathematical model of path multi-objective optimization based on an objective function and a constraint function of the unmanned aerial vehicle travelling along the path; s30, generating a mathematical space formed by upper and lower limits of the objective function, namely a decision space according to an objective function forming a mathematical model of path multi-objective optimization, and generating a group of reference vectors for improving multi-objective optimization efficiency and accuracy in the decision space, S40, performing self-adaptive adjustment on the reference vectors based on an iteration process of path planning, and finally iterating to obtain a pareto optimal solution set of the path scheme. The application improves the calculation efficiency and the accuracy.
Description
Technical Field
The application relates to the technical field of low-altitude remote sensing unmanned aerial vehicle path planning, in particular to a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method.
Background
Different from the large-scale high altitude forestry remote sensing monitoring of main through high altitude satellite image and assist cavity aviation image supplementary key region, the resource monitoring in the woodland belongs to low altitude forestry monitoring field, leads to traditional monitoring means unable to carry out the fine monitoring to the woodland. The low-altitude remote sensing unmanned aerial vehicle is a small-sized aircraft operated by using radio remote control equipment and an onboard program control device, has the advantages of small size, low manufacturing cost, convenient use, strong environmental adaptability and the like, and can carry out fine monitoring in a low airspace. Meanwhile, the unmanned aerial vehicle application low-altitude remote sensing field has the characteristics of quick response, high image resolution, strong expansion capability, low operation cost and the like, and has wide application prospect in the resource monitoring management under forests.
When the low-altitude remote sensing unmanned aerial vehicle is in operation, one key constraint factor is the planning of a flight path. In the low-altitude remote sensing environment, fixed barriers (such as trees, buildings and the like) exist in the application scene of the unmanned aerial vehicle, various emergency conditions (such as flying birds, balloons, environmental wind and the like) exist at the same time, and the advantages and disadvantages of the flight path directly determine the task execution efficiency of the low-altitude remote sensing unmanned aerial vehicle, so that a reasonable and efficient path needs to be planned in a three-dimensional complex space.
Traditional unmanned plane path planning is mainly based on a visual method, an A-algorithm and a Dijkstra algorithm: according to the map data acquired in advance, an initial path scheme is acquired by utilizing the algorithm, then the change of the running environment is ascertained in real time, and local adjustment is performed on the basis of the initial path scheme, so that a final running path is acquired. However, the conventional path planning method has extremely high requirements on an initial map, and if the detailed topography of a task scene and the map information of the environment cannot be obtained in advance, the initial path scheme cannot be set effectively; meanwhile, the traditional method has low calculation efficiency, so that when instantaneous and complex environment changes occur in an application scene, a subsequent path cannot be effectively and quickly adjusted. In a low-altitude remote sensing scene, the unmanned aerial vehicle is difficult to acquire detailed three-dimensional initial map information, and is also easy to suffer from environmental interference factors such as birds, floaters, crosswinds and the like in the task execution process. Therefore, aiming at the unmanned aerial vehicle path planning problem in the low-altitude remote sensing application scene, the rapid path planning independent of a fine preset map needs to be carried out.
When the unmanned aerial vehicle runs along the planned path, the energy used during running along the path, the time consumed and the survival rate of the unmanned aerial vehicle are all indexes for evaluating the path quality, and complex mutual coupling relations exist among the indexes, so that the indexes cannot be synthesized to serve as an index to measure the path quality through a conventional decoupling means. Therefore, the multi-objective optimization method can be used for rapidly solving the path planning, and the planning efficiency and the planning precision of the final path scheme are improved.
Disclosure of Invention
In order to overcome the defects of the prior art, the application provides a multi-target planning method for a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path, which solves the problems of low efficiency and low precision in the current low-altitude remote sensing unmanned aerial vehicle path planning process and improves the calculation efficiency and accuracy.
The technical scheme adopted for solving the technical problems is as follows: a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method, comprising the following steps:
s10, establishing a Maklink three-dimensional graph theory model of the unmanned aerial vehicle path environment based on initial environment information; obtaining a specific single path scheme based on the Maklink three-dimensional graph theory model; the initial environment information comprises an initial position of the unmanned aerial vehicle, a task target position and available three-dimensional map information;
s20, establishing a mathematical model of path multi-objective optimization based on an objective function and a constraint function of the unmanned aerial vehicle travelling along the path; the objective function comprises time required by the unmanned aerial vehicle when travelling along a path, consumed energy and survival rate of the unmanned aerial vehicle; the constraint function is an interference operation factor in the unmanned plane path; the specific steps of establishing the mathematical model of path multi-objective optimization are as follows:
s201, acquiring space information by using preset map information and an unmanned aerial vehicle through an onboard camera, dividing a three-dimensional space grid after finishing physical space modeling of the unmanned aerial vehicle through SLAM means, setting up a path on the three-dimensional space grid based on Maklink graph theory, and converting a path scheme into a mathematical form:wherein->Refers to the kth design variable of the path scheme;
s202, according to task details and an operation environment, regarding obstacles in the operation environment as constraint functions in path multi-objective optimization planning, and setting time required by the unmanned aerial vehicle to travel along a pathConsumed energyAnd self-survival->As a multi-objective function for judging paths, determining upper and lower limits of design variables of the path scheme mathematical form X; wherein (1)>Refers to the actual path length obtained by integrating the length of the path scheme X, +.>Refers to a path length infinitesimal obtained by differentiating a certain point of a path,/or->Speed expression referring to path scheme X, < >>Refers to instantaneous speed infinitesimal obtained by differentiating a certain point of a path,/for>Refers to the energy consumption calculated based on the instantaneous speed infinitesimal at a certain point of the path,/->Indicating that the survival of the unmanned aerial vehicle is proportional to the reciprocal of the constraint violation amount G in the path X, ++>The survival rate control number;
s203, initializing a design variable space omega based on upper and lower limits of the design variable to form a multi-objective optimized mathematical model of path planning; the multi-objective optimized mathematical model of the path planning is as follows:
,
the constraint function is:wherein n denotes the number of constraint functions, X denotes the mathematical form of the path scheme, ++>Refers to the ith constraint function, and specifically includes obstacles encountered by the unmanned aerial vehicle when the unmanned aerial vehicle travels along the path,/->Refers to the control coefficient of the ith constraint function;
the method for calculating the multi-objective function and the constraint function value of the initial path comprises the following steps: according to the path scheme when the unmanned aerial vehicle operatesPerforming optimized Latin hypercube sampling in a determined design variable space omega, wherein the sampling number is 3k+2 sample points, and the sample points form a population of the path multi-objective optimization planning; every sample point->Converting into an initial path according to the method in the step S201, and calculating corresponding multi-objective function and constraint function values; where i=1, 2, …,3k+2;
s30, generating a mathematical space formed by the upper limit and the lower limit of the objective function, namely a decision space according to the objective function of the mathematical model forming the path multi-objective optimization, and forming the decision spaceInternally generating a group of reference vectors for improving the efficiency and the precision of multi-objective optimization; the specific method is as follows: determining a decision space according to the upper and lower extremum of the three multi-objective function values of all the sample points calculated in the step S202, and generating a group of initial reference vectors based on a standard boundary crossing method in the decision space, wherein the number of the reference vectors is as followsWhere k is the design variable dimension;
s40, performing self-adaptive adjustment on the reference vector based on an iteration process of path planning, and finally iterating to obtain a pareto optimal solution set of the path scheme; the specific steps of the self-adaptive adjustment of the reference vector are as follows:
s401, evolving the sample points under the jurisdiction of all the reference vectors by utilizing the operations of crossing, mutation and selection in a differential evolution algorithm to generate a new group of standby offspring sample points;
s402, iterating the population according to the pareto criterion;
s403, recalculating the size of the decision space based on the new population, and generating a group of reference vectors in the new decision space;
s404, circulating S401, S402 and S403, if the number of times of calculating paths satisfying the Maklink graph theory reaches a set value, terminating the circulation, and outputting the current population as a multi-objective solution; otherwise, the loops S401, S402, and S403 are continued.
Further, each sample point in the populationCorresponding multiple objective function value->And attaching each sample point to the reference vector corresponding to the minimum value according to the minimum value of the included angle between the sample point and all the reference vectors in the decision space.
Further, in step S401, the specific method for evolving the sample points under the jurisdiction of all the reference vectors includes: firstly, placing sample points governed by each reference vector into a blank evolution pool, then finding out adjacent reference vectors of the reference vectors, adding the sample points governed by the adjacent reference vectors into a previous evolution pool, and performing differential evolution on the evolution pool to obtain sample points with the same scale as the evolution pool; and finally, storing the sample points into a standby child sample point set.
Further, in step S402, the specific ways of iterating the population include: and merging the parent and standby child sample points, performing pareto dominant sorting, and reserving sample points which are sorted forward and have the same population scale according to the sorting result, wherein the reserved sample points are used as new populations.
Further, in step S403, the method for generating the reference vector is the same as the method for generating the reference vector in S30.
The beneficial effects of the application are as follows: according to the scheme, the multi-target planning method for the low-altitude forestry monitoring remote sensing unmanned aerial vehicle path effectively solves the problems of low efficiency and low precision in the multi-target planning process of the low-altitude remote sensing unmanned aerial vehicle path, and therefore calculation efficiency and accuracy are improved.
Drawings
Fig. 1 is a flow chart of a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method.
Detailed Description
The application will be further described with reference to the drawings and examples.
The conception, specific structure, and technical effects produced by the present application will be clearly and completely described below with reference to the embodiments and the drawings to fully understand the objects, features, and effects of the present application. It is apparent that the described embodiments are only some embodiments of the present application, but not all embodiments, and that other embodiments obtained by those skilled in the art without inventive effort are within the scope of the present application based on the embodiments of the present application. In addition, all the connection relation related to the application does not directly connect the single-finger components, but means that a better connection structure can be formed by adding or reducing connection accessories according to specific implementation conditions. The technical features in the application can be interactively combined on the premise of no contradiction and conflict.
Referring to fig. 1, the application discloses a low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method, which comprises the following steps:
s10, establishing a Maklink three-dimensional graph theory model of the unmanned aerial vehicle path environment based on initial environment information; obtaining a specific single path scheme based on the Maklink three-dimensional graph theory model; the initial environment information comprises an initial position of the unmanned aerial vehicle, a task target position and available three-dimensional map information;
s20, establishing a mathematical model of path multi-objective optimization based on an objective function and a constraint function of the unmanned aerial vehicle travelling along the path; the objective function comprises time required by the unmanned aerial vehicle when travelling along a path, consumed energy and survival rate of the unmanned aerial vehicle; the constraint function is an interference operation factor in the unmanned plane path; the specific steps of establishing the mathematical model of path multi-objective optimization are as follows:
s201, acquiring space information of the unmanned aerial vehicle through an onboard camera by utilizing preset map information and the unmanned aerial vehicle, completing physical space modeling of the unmanned aerial vehicle through SLAM and other means, dividing a three-dimensional space grid, setting up a path on the three-dimensional space grid based on a Maklink graph theory, and converting a path scheme into a mathematical formWherein->Refers to the kth design variable of the path scheme;
s202, according to task details and an operation environment, regarding obstacles and the like in the operation environment as constraint functions in path multi-objective optimization planning, and setting time required by the unmanned aerial vehicle to travel along a pathConsumed energyAnd itselfSurvival rate->As a multi-objective function for judging paths, determining upper and lower limits of design variables of the path scheme mathematical form X; wherein (1)>Refers to the actual length of the path obtained by integrating the length of the path scheme X,refers to a path length infinitesimal obtained by differentiating a certain point of a path,/or->Speed expression referring to path scheme X, < >>Refers to instantaneous speed infinitesimal obtained by differentiating a certain point of a path,/for>Refers to the energy consumption calculated based on the instantaneous speed infinitesimal at a certain point of the path,/->Indicating that the survival of the unmanned aerial vehicle is proportional to the reciprocal of the constraint violation amount G in the path X, ++>The survival rate control number;
s203, initializing a design variable space omega based on upper and lower limits of the design variables to form a multi-objective optimized mathematical model of path planning; the multi-objective optimized mathematical model of the path planning is as follows:
,
the constraint function is:wherein n denotes the number of constraint functions, X denotes the mathematical form of the path scheme, ++>Refers to the ith constraint function, and specifically includes obstacles encountered by an unmanned aerial vehicle when traveling along a path, etc., -a constraint function of +.>Refers to the control coefficient of the ith constraint function.
In addition, the calculation method of the multi-objective function and the constraint function value of the initial path is as follows: according to the path scheme when the unmanned aerial vehicle operatesPerforming optimized Latin hypercube sampling in a determined design variable space omega, wherein the sampling number is 3k+2 sample points, and the sample points form a population of the path multi-objective optimization planning; every sample point->Converting into an initial path according to the method in the step S201, and calculating corresponding multi-objective functions and constraint function values; where i=1, 2, …,3k+2.
S30, generating a mathematical space formed by upper and lower limits of three objective functions, namely a decision space, according to the three objective functions forming the path multi-objective optimization mathematical model; because the population is generated in the calculation process of the multi-objective function and the constraint function value of the initial path, a single individual in the population corresponds to three objective function values, wherein the single individual is in a single path scheme, therefore, three objective functions of the whole population correspondingly have three upper and lower value limit ranges, the three value ranges generate a three-dimensional decision space ψ, and a group of reference vectors for improving multi-objective optimization efficiency and precision are generated in the three-dimensional decision space ψ, and the specific modes are as follows: determining a decision space according to the upper and lower extremum of the three multi-objective function values of all the sample points calculated in step S202, generating a set of initial reference vectors based on a standard boundary crossing method in the decision space,the number of reference vectors isWhere k is the design variable dimension; wherein each sample point in the population is +.>Corresponding multiple objective function value->The included angle value between the sample points and all the reference vectors in the decision space is the minimum value, and each sample point is attached to the reference vector corresponding to the minimum value according to the minimum value of the included angle, in other words, the sample points are attached to specific reference vectors in the decision space, and the sample points with different amounts are administered under the specific reference vectors; in addition, in the single-objective problem, one X corresponds to one Y, and in the multi-objective problem of the present embodiment, one X corresponds to a plurality of Y, for example, here one X corresponds to Y1, Y2, Y3, and then the upper and lower limits of X correspond to 3 upper and lower limits of Y1, Y2, Y3, and 3 upper and lower limits of Y1, Y2, Y3 generate a decision space; in the corresponding attaching process of the sample point and the reference vector, if the number of the sample points governed by a certain reference vector is zero, any sample point is regulated to the reference vector from the reference vector governing a plurality of sample points.
S40, performing self-adaptive adjustment on the reference vector based on an iterative process of path planning; the method comprises the following specific steps:
s401, evolution is carried out on sample points under the jurisdiction of all the reference vectors, wherein the sample points under the jurisdiction of all the reference vectors are marked as parent sample points; generating a new set of standby child sample points by utilizing crossover, mutation and selection operations in a differential evolution algorithm, and generating N standby child sample points by setting the number of parent sample points as N and N parent sample points; the specific method comprises the following steps: firstly, placing sample points governed by each reference vector into a blank evolution pool, then finding out adjacent reference vectors of the reference vectors, adding the sample points governed by the adjacent reference vectors into a previous evolution pool, and performing differential evolution on the evolution pool to obtain sample points with the same scale as the evolution pool; and finally, storing the sample points into a standby child sample point set.
S402, iterating the population according to the pareto criterion; in this embodiment, the specific way of iterating the population includes: and merging the parent sample points and the standby child sample points, wherein the number of the sample points is 2N, performing pareto dominant sorting, and reserving the sample points which are ranked forward and have the same population scale according to the sorting result, namely selecting the N sample points forward as new populations, and taking the reserved sample points as the new populations.
S403, recalculating the size of the decision space based on the new population, and generating a group of new reference vectors in the new decision space; the decision space is determined by a population objective function, and the generation method of the reference vector is the same as the generation method in S30, and is a standard boundary crossing method;
s404, looping S401, S402 and S403, namely, iterating the path scheme, if the convergence condition is met, terminating the loop, and outputting the current population as a multi-objective solution; otherwise, the process continues to loop S401, S402 and S403, where the convergence condition is that the number of times of calculating the path by the Maklink graph theory reaches a set value, and the set value in this embodiment is 500 times.
When solving the multi-objective problem, the obtained final result is a group of pareto optimal solution sets, which are not single optimal solutions; the path generated by the initial random is either pareto optimal, or the optimal solution set is obtained by iteration; in the iterative process, the decision space is continuously refined; if the decision space changes, the corresponding reference vector needs to be regenerated, and the process globally looks like that the reference vector changes in the optimization process, namely, the reference vector self-adaptively adjusts.
In the embodiment, the low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-objective planning method takes time and consumed energy and survival rate of the unmanned aerial vehicle as multi-objective functions in path planning, and obtains a multi-party balanced optimized path scheme by utilizing multi-objective solution, so that the overall efficiency of the unmanned aerial vehicle is optimal in running; by establishing a reference vector in the decision space, the population can be converged more quickly in the multi-objective solving process, and the optimization speed is improved; based on the updated population at the end of each iteration, regenerating the decision space and correspondingly updating the reference vector to finish the self-adaptive adjustment of the reference vector, thereby realizing the balance between the efficiency and the precision of the solving result. The method effectively solves the problems of low efficiency and low precision in the low-altitude remote sensing unmanned aerial vehicle path planning process, and improves the calculation efficiency and accuracy.
While the preferred embodiment of the present application has been described in detail, the present application is not limited to the embodiments, and those skilled in the art can make various equivalent modifications or substitutions without departing from the spirit of the present application, and the equivalent modifications or substitutions are included in the scope of the present application as defined in the appended claims.
Claims (5)
1. The method for planning the multiple targets of the path of the remote sensing unmanned aerial vehicle monitored by low-altitude forestry is characterized by comprising the following steps of:
s10, establishing a Maklink three-dimensional graph theory model of the unmanned aerial vehicle path environment based on initial environment information; obtaining a specific single path scheme based on the Maklink three-dimensional graph theory model; the initial environment information comprises an initial position of the unmanned aerial vehicle, a task target position and available three-dimensional map information;
s20, establishing a mathematical model of path multi-objective optimization based on an objective function and a constraint function of the unmanned aerial vehicle travelling along the path; the objective function comprises time required by the unmanned aerial vehicle when travelling along a path, consumed energy and survival rate of the unmanned aerial vehicle; the constraint function is an interference operation factor in the unmanned plane path; the specific steps of establishing the mathematical model of path multi-objective optimization are as follows:
s201, acquiring space information by using preset map information and an unmanned aerial vehicle through an onboard camera, dividing a three-dimensional space grid after finishing physical space modeling of the unmanned aerial vehicle through SLAM means, setting up a path on the three-dimensional space grid based on Maklink graph theory, and converting a path scheme into a mathematical form:wherein->Refers to the kth design variable of the path scheme;
s202, according to task details and an operation environment, regarding obstacles in the operation environment as constraint functions in path multi-objective optimization planning, and setting time required by the unmanned aerial vehicle to travel along a pathConsumed energyAnd self-survival->As a multi-objective function for judging paths, determining upper and lower limits of design variables of the path scheme mathematical form X; wherein (1)>Refers to the actual path length obtained by integrating the length of the path scheme X, +.>Refers to a path length infinitesimal obtained by differentiating a certain point of a path,/or->Speed expression referring to path scheme X, < >>Refers to instantaneous speed infinitesimal obtained by differentiating a certain point of a path,/for>Refers to the energy consumption calculated based on the instantaneous speed infinitesimal calculation of a certain point of a pathQuantity (S)>Indicating that the survival of the unmanned aerial vehicle is proportional to the reciprocal of the constraint violation amount G in the path X, ++>The survival rate control number;
s203, initializing a design variable space omega based on upper and lower limits of the design variable to form a multi-objective optimized mathematical model of path planning; the multi-objective optimized mathematical model of the path planning is as follows:
,
the constraint function is:wherein n denotes the number of constraint functions, X denotes the mathematical form of the path scheme, ++>Refers to the ith constraint function, and specifically includes obstacles encountered by the unmanned aerial vehicle when the unmanned aerial vehicle travels along the path,/->Refers to the control coefficient of the ith constraint function;
the method for calculating the multi-objective function and the constraint function value of the initial path is as follows: according to the path scheme when the unmanned aerial vehicle operatesPerforming optimized Latin hypercube sampling in a determined design variable space omega, wherein the sampling number is 3k+2 sample points, and the sample points form a population of the path multi-objective optimization planning; every sample point->Converting into an initial path according to the method in the step S201, and calculating corresponding multi-objective function and constraint function values; where i=1, 2, …,3k+2;
s30, generating a mathematical space formed by upper and lower limits of the objective function, namely a decision space according to an objective function of a mathematical model forming path multi-objective optimization, and generating a group of reference vectors for improving multi-objective optimization efficiency and precision in the decision space; the specific method is as follows: determining a decision space according to the upper and lower extremum of the three multi-objective function values of all the sample points calculated in the step S202, and generating a group of initial reference vectors based on a standard boundary crossing method in the decision space, wherein the number of the reference vectors is as followsWhere k is the design variable dimension;
s40, performing self-adaptive adjustment on the reference vector based on an iteration process of path planning, and finally iterating to obtain a pareto optimal solution set of the path scheme; the specific steps of the self-adaptive adjustment of the reference vector are as follows:
s401, evolving the sample points under the jurisdiction of all the reference vectors by utilizing the operations of crossing, mutation and selection in a differential evolution algorithm to generate a new group of standby offspring sample points;
s402, iterating the population according to the pareto criterion;
s403, recalculating the size of the decision space based on the new population, and generating a group of reference vectors in the new decision space;
s404, circulating S401, S402 and S403, if the number of times of calculating paths satisfying the Maklink graph theory reaches a set value, terminating the circulation, and outputting the current population as a multi-objective solution; otherwise, the loops S401, S402, and S403 are continued.
2. A low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method according to claim 1, wherein each sample point in the populationCorresponding multiple objective function value->And attaching each sample point to the reference vector corresponding to the minimum value according to the minimum value of the included angle between the sample point and all the reference vectors in the decision space.
3. The method for multi-objective planning of a path of a remote sensing unmanned aerial vehicle for low-altitude forestry monitoring according to claim 2, wherein in step S401, the specific method for evolving the sample points under the jurisdiction of all the reference vectors comprises: firstly, placing sample points governed by each reference vector into a blank evolution pool, then finding out adjacent reference vectors of the reference vectors, adding the sample points governed by the adjacent reference vectors into a previous evolution pool, and performing differential evolution on the evolution pool to obtain sample points with the same scale as the evolution pool; and finally, storing the sample points into a standby child sample point set.
4. A low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method according to claim 3, wherein in step S402, the specific way of iterating the population comprises: and merging the parent and standby child sample points, performing pareto dominant sorting, and reserving sample points which are sorted forward and have the same population scale according to the sorting result, wherein the reserved sample points are used as new populations.
5. A low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method according to claim 3, wherein in step S403, the reference vector generation method is the same as the reference vector generation method in S30.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310796607.4A CN116518982B (en) | 2023-07-03 | 2023-07-03 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310796607.4A CN116518982B (en) | 2023-07-03 | 2023-07-03 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116518982A CN116518982A (en) | 2023-08-01 |
CN116518982B true CN116518982B (en) | 2023-09-19 |
Family
ID=87403279
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310796607.4A Active CN116518982B (en) | 2023-07-03 | 2023-07-03 | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116518982B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN117387634B (en) * | 2023-12-13 | 2024-02-27 | 江西啄木蜂科技有限公司 | Color-changing wood forest zone unmanned aerial vehicle path multi-target planning method based on user preference |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106970648A (en) * | 2017-04-19 | 2017-07-21 | 北京航空航天大学 | Unmanned plane multi-goal path plans combined method for searching under the environment of city low latitude |
CN109631900A (en) * | 2018-12-24 | 2019-04-16 | 中国矿业大学 | A kind of no-manned plane three-dimensional track multi-objective particle swarm Global Planning |
CN111026126A (en) * | 2019-12-27 | 2020-04-17 | 哈尔滨工程大学 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
WO2022007376A1 (en) * | 2020-07-08 | 2022-01-13 | 北京航空航天大学 | Multi-objective multimodal particle swarm optimization method based on bayesian adaptive resonance |
CN114237282A (en) * | 2021-11-29 | 2022-03-25 | 南京邮电大学 | Intelligent unmanned aerial vehicle flight path planning method for intelligent industrial park monitoring |
CN115903896A (en) * | 2022-11-22 | 2023-04-04 | 中国人民解放军国防科技大学 | Multi-unmanned aerial vehicle path planning method based on proxy model optimization |
CN116126032A (en) * | 2023-04-17 | 2023-05-16 | 华南农业大学 | Unmanned aerial vehicle group path planning method based on improved multi-objective evolutionary algorithm |
CN116255986A (en) * | 2023-02-22 | 2023-06-13 | 中国人民解放军海军工程大学 | Multi-unmanned aerial vehicle collaborative reconnaissance flight path planning method based on decision maker preference |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107504972B (en) * | 2017-07-27 | 2018-08-07 | 北京航空航天大学 | A kind of aircraft's flight track method and device for planning based on dove group's algorithm |
-
2023
- 2023-07-03 CN CN202310796607.4A patent/CN116518982B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106970648A (en) * | 2017-04-19 | 2017-07-21 | 北京航空航天大学 | Unmanned plane multi-goal path plans combined method for searching under the environment of city low latitude |
CN109631900A (en) * | 2018-12-24 | 2019-04-16 | 中国矿业大学 | A kind of no-manned plane three-dimensional track multi-objective particle swarm Global Planning |
CN111026126A (en) * | 2019-12-27 | 2020-04-17 | 哈尔滨工程大学 | Unmanned ship global path multi-target planning method based on improved ant colony algorithm |
WO2022007376A1 (en) * | 2020-07-08 | 2022-01-13 | 北京航空航天大学 | Multi-objective multimodal particle swarm optimization method based on bayesian adaptive resonance |
CN114237282A (en) * | 2021-11-29 | 2022-03-25 | 南京邮电大学 | Intelligent unmanned aerial vehicle flight path planning method for intelligent industrial park monitoring |
CN115903896A (en) * | 2022-11-22 | 2023-04-04 | 中国人民解放军国防科技大学 | Multi-unmanned aerial vehicle path planning method based on proxy model optimization |
CN116255986A (en) * | 2023-02-22 | 2023-06-13 | 中国人民解放军海军工程大学 | Multi-unmanned aerial vehicle collaborative reconnaissance flight path planning method based on decision maker preference |
CN116126032A (en) * | 2023-04-17 | 2023-05-16 | 华南农业大学 | Unmanned aerial vehicle group path planning method based on improved multi-objective evolutionary algorithm |
Non-Patent Citations (3)
Title |
---|
基于协同多目标算法的多机器人路径规划;万逸飞;彭力;;信息与控制(第02期);全文 * |
复合形引导蜂群寻优的无人机航迹多目标规划;刘刚;裴红蕾;;机械设计与制造(第04期);全文 * |
面向交通监控的动态无人飞机路径多目标优化;王亮;刘晓锋;刘少堂;耿杰;高婷婷;;数学的实践与认识(第22期);全文 * |
Also Published As
Publication number | Publication date |
---|---|
CN116518982A (en) | 2023-08-01 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110428111B (en) | UAV/UGV (unmanned aerial vehicle/user generated Union vector) cooperative long-time multitask operation trajectory planning method | |
CN112116830B (en) | Unmanned aerial vehicle dynamic geo-fence planning method based on airspace meshing | |
CN110544296B (en) | Intelligent planning method for three-dimensional global track of unmanned aerial vehicle in uncertain enemy threat environment | |
Tang et al. | Dynamic reallocation model of multiple unmanned aerial vehicle tasks in emergent adjustment scenarios | |
Lin et al. | An algorithm for trajectory prediction of flight plan based on relative motion between positions | |
CN106970648A (en) | Unmanned plane multi-goal path plans combined method for searching under the environment of city low latitude | |
CN105045274B (en) | A kind of intelligent shaft tower connected graph construction method for unmanned plane inspection trajectory planning | |
CN116518982B (en) | Low-altitude forestry monitoring remote sensing unmanned aerial vehicle path multi-target planning method | |
CN116257082B (en) | Distributed active cooperative detection method for multiple unmanned aerial vehicles | |
CN115060263A (en) | Flight path planning method considering low-altitude wind and energy consumption of unmanned aerial vehicle | |
CN113268087A (en) | Flight path planning method for cooperative work of multiple unmanned aerial vehicles based on improved ant colony algorithm in multi-constraint complex environment | |
CN114740899B (en) | Gridding airspace distribution and collaborative search planning method | |
CN115903888A (en) | Rotor unmanned aerial vehicle autonomous path planning method based on longicorn swarm algorithm | |
CN116954233A (en) | Automatic matching method for inspection task and route | |
CN115185303A (en) | Unmanned aerial vehicle patrol path planning method for national parks and natural protected areas | |
CN110986954A (en) | Military transport plane route planning method based on wolf optimization algorithm | |
Ma et al. | Volcanic Ash Region Path Planning Based on Improved A‐Star Algorithm | |
CN108596397B (en) | Hydrological model-based multi-aircraft route planning method | |
Jiang et al. | Research on method of trajectory prediction in aircraft flight based on aircraft performance and historical track data | |
CN116954239B (en) | Unmanned aerial vehicle track planning method and system based on improved particle swarm optimization | |
CN116518979B (en) | Unmanned plane path planning method, unmanned plane path planning system, electronic equipment and medium | |
CN116822362B (en) | Unmanned aerial vehicle conflict-free four-dimensional flight path planning method based on particle swarm optimization | |
CN117521932A (en) | Unmanned aerial vehicle inspection management system based on meshing division | |
CN112214930A (en) | Multi-machine collaborative route planning method and system based on collaborative particle swarm optimization algorithm | |
Huang et al. | On the 3D track planning for electric power inspection based on the improved ant colony optimization and algorithm |
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 |