CN116257057A - Agricultural machinery operation path planning method and system based on region division - Google Patents
Agricultural machinery operation path planning method and system based on region division Download PDFInfo
- Publication number
- CN116257057A CN116257057A CN202310093745.6A CN202310093745A CN116257057A CN 116257057 A CN116257057 A CN 116257057A CN 202310093745 A CN202310093745 A CN 202310093745A CN 116257057 A CN116257057 A CN 116257057A
- Authority
- CN
- China
- Prior art keywords
- area
- sub
- agricultural machinery
- nodes
- taking
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000013439 planning Methods 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 49
- 230000004888 barrier function Effects 0.000 claims abstract description 8
- 239000002245 particle Substances 0.000 claims description 63
- 238000004422 calculation algorithm Methods 0.000 claims description 47
- 238000005265 energy consumption Methods 0.000 claims description 37
- 230000010365 information processing Effects 0.000 claims description 4
- 230000001133 acceleration Effects 0.000 claims description 3
- 238000004590 computer program Methods 0.000 claims description 3
- 230000008569 process Effects 0.000 description 17
- 238000010845 search algorithm Methods 0.000 description 7
- 238000004891 communication Methods 0.000 description 5
- 238000000354 decomposition reaction Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 238000005457 optimization Methods 0.000 description 4
- 230000005484 gravity Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 241000283153 Cetacea Species 0.000 description 2
- 238000004387 environmental modeling Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 230000002068 genetic effect Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000013316 zoning Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010899 nucleation Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
- G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
- G05D1/0219—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory ensuring the processing of the whole working surface
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)
- Feedback Control In General (AREA)
Abstract
The invention relates to an agricultural machinery operation path planning method and system based on region division, comprising the following steps: acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area; taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information; obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
Description
Technical Field
The invention relates to the technical field of agricultural equipment, in particular to an agricultural machinery operation path planning method and system based on region division.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Modern agriculture starts to combine unmanned technology into the use of agricultural machinery to realize autonomous navigation function, unmanned operation is realized in the operations of farmland, seeding and the like, but after crops are harvested, the work content of the part transported back to a warehouse still needs to be completed by means of manual driving agricultural machinery.
The unmanned autonomous navigation of the agricultural machinery is to be realized on the basis of realizing unmanned autonomous navigation of the agricultural machinery, which is a core problem of ensuring that the agricultural machinery can realize accurate path planning, and the agricultural machinery can carry out accurate operation.
Aiming at the problems, the conventional path planning method can find a feasible path from a starting point to a target point in a short time when the path planning is carried out, but redundant nodes are generated in the planning process, so that the length of the feasible path and the time of the path planning are increased, and the working cost of agricultural machinery operation is indirectly increased; some intelligent algorithms are also often applied to path planning algorithm researches, such as genetic algorithm, ant colony algorithm, whale algorithm and the like, and can solve a globally optimal feasible path, but the performance is weaker when local path searching is performed, and early convergence is easy to occur, so that the final feasible path accuracy is reduced.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides an agricultural machinery operation path planning method and system based on region division, which are applied to a period of transporting crops back to a warehouse after harvesting, obtain a group of initial feasible paths according to a particle swarm algorithm, combine the characteristics of obstacles in an environment map and the number of intersection points of the initial paths and circle center lines, decompose the environment map into a plurality of subareas through a region division method, reduce the search range of the feasible paths, reduce the complexity of searching, avoid the problem of local optimal solution easily generated during global searching, and improve the efficiency of refined searching in the next stage. In the fine searching stage, fractional calculus is introduced into a mixed algorithm combining particle swarm and gravity searching, global convergence of the algorithm is enhanced, energy consumption constraint is considered, when an obstacle is met, dynamic parameters are introduced to adjust searching step length, and a route which can be exhausted as low as possible can be planned according to the energy consumption constraint.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
the first aspect of the invention provides an agricultural machinery operation path planning method based on region division, comprising the following steps:
acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area;
taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information;
obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
The area division is realized, specifically:
defining a connecting line between every two circle centers of obstacles in the environment map information as a circle center line, taking the position of an end point coordinate as a father node, and taking the obstacles at the two ends of the circle center line with the most intersection point with the feasible path group as child nodes of the father node; the child node serves as a parent node in the next level node and extends until reaching the final node, which is the start coordinate.
Except for a start coordinate point and an end coordinate point, each node can only be used as a child node of a father node; each node traverses to the point that the decomposed sub-area space is a single connected area.
When the child node of the parent node is just the initial coordinate point, but the connecting line is blocked by other connected nodes, the boundary line of the operation area is used as the connecting line between the nodes to form a new sub-area.
And taking the set radius around the obstacle as a reference, forming safety areas around the obstacle, wherein each safety area has a set energy consumption weight.
The initial feasible path group from the initial coordinate to the final coordinate is obtained through a standard particle swarm algorithm.
Carrying out path search in the subareas to obtain optimal paths in the subareas, and obtaining final needed optimal feasible paths through comparison, wherein the method specifically comprises the following steps:
obtaining an optimal path in the subarea through a particle swarm algorithm;
updating a speed item of a particle swarm algorithm by utilizing fractional calculus;
updating the position information of the particle swarm algorithm in the position updating item through the set energy consumption weight;
and obtaining the optimal path in the subarea through speed updating and position updating, and obtaining the final optimal feasible path when the requirement or the maximum iteration is met.
A second aspect of the present invention provides a system for implementing the above method, comprising:
an information acquisition module configured to: acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area;
an information processing module configured to: taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information;
a path planning module configured to: obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
A third aspect of the invention provides a computer device.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the region division based agricultural work path planning method as described above when the program is executed.
Compared with the prior art, the above technical scheme has the following beneficial effects:
1. the environment area for path planning is divided into a plurality of sub-areas through area division, the optimal paths in the sub-areas are obtained through fine search of the sub-areas, and the final optimal feasible paths are obtained through comparison, so that the problem of local optimization of an algorithm can be avoided, meanwhile, the complexity of search is reduced, and the search efficiency is improved.
2. In the area dividing process, except for a starting coordinate and an ending coordinate, each node can only be used as a child node of a father node, so that a closed area is prevented; meanwhile, each node needs to traverse, namely the decomposed subarea space is a single communication area, so that the occurrence of multiple communication areas is avoided, and all barriers are ensured to participate in area decomposition.
3. In the region dividing process, in order to avoid the occurrence of multiple communication regions, the boundary line of the operation region is considered, and when the child node of the parent node is just the initial coordinate point but is blocked by other connected nodes in the connecting line, the boundary line of the operation region is considered to form a complete sub-region.
4. When the sub-regions are finely searched after the region division, the particle swarm algorithm is combined with the gravity search algorithm, so that the searching capability of the particle swarm algorithm can be effectively improved, and meanwhile, the particle search speed is updated by combining the memory characteristics of fractional calculus, so that the convergence performance of the algorithm is improved; and taking the energy consumption factor into consideration in the path planning constraint, and adjusting the particle searching step length through dynamic parameters so as to obtain a feasible path with lower energy consumption.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the invention.
FIG. 1 is a schematic flow diagram of an agricultural work path planning process based on zoning provided by one or more embodiments of the present invention;
FIGS. 2 (a) -2 (c) are each a schematic view of zoning during an agricultural machine path planning process according to one or more embodiments of the present invention;
FIGS. 3 (a) -3 (b) are two non-viable states, respectively, of sub-region division in an agricultural implement path planning process provided by one or more embodiments of the present invention;
FIGS. 4 (a) -4 (b) are schematic diagrams illustrating two divisions of an agricultural machine path planning process with boundary lines considered in accordance with one or more embodiments of the present invention;
FIG. 5 is a schematic illustration of energy consumption grading during an agricultural machinery path planning process provided by one or more embodiments of the present invention;
FIG. 6 is a schematic diagram of an agricultural machinery path planning system provided by one or more embodiments of the present invention.
Detailed Description
The invention will be further described with reference to the drawings and examples.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the present invention. As used herein, the singular is also intended to include the plural unless the context clearly indicates otherwise, and furthermore, it is to be understood that the terms "comprises" and/or "comprising" when used in this specification are taken to specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof.
As described in the background art, in the conventional path planning method, a feasible path from a starting point to a target point can be found in a short time when path planning is performed, but redundant nodes are generated in the planning process, so that the feasible path length and the path planning time are increased, and the working cost of agricultural machinery operation is indirectly increased; some intelligent algorithms are also often applied to path planning algorithm researches, such as genetic algorithm, ant colony algorithm, whale algorithm and the like, and can solve a globally optimal feasible path, but the performance is weaker when local path searching is performed, and early convergence is easy to occur, so that the final feasible path accuracy is reduced.
The particle swarm algorithm is widely applied to optimization problem research, has fewer parameters, simple rules and easy realization, and obtains good effect when being applied to path planning, but has slower post convergence speed and is easy to generate local optimal solution. Therefore, the following embodiment provides an agricultural machinery operation path planning method and system based on region division, a group of initial feasible paths are obtained according to a particle swarm algorithm, the environment map is divided into a plurality of subareas by combining the characteristics of obstacles in the environment map and the number of intersection points of the initial paths and circle center lines through a region division method, the search range of the feasible paths is reduced, the complexity of search is reduced, the problem of local optimal solution easily generated during global search is avoided, and the efficiency of refined search in the next stage is improved. In the fine searching stage, fractional calculus is introduced into a mixed algorithm combining particle swarm and gravity searching, global convergence of the algorithm is enhanced, energy consumption constraint is considered, when an obstacle is met, dynamic parameters are introduced to adjust searching step length, and a route which can be exhausted as low as possible can be planned according to the energy consumption constraint.
Embodiment one:
as shown in fig. 1, the agricultural machinery operation path planning method based on region division comprises the following steps:
step1: collecting environmental map information (including the size of an area and obstacles in the area) through a sensor and an image collecting module on the agricultural machinery;
step2: converting the collected environmental information into a two-dimensional image, carrying out environmental modeling, and determining that the agricultural machinery position information is set as a starting coordinate and the end point is set as a warehouse position through a GPS positioning system;
step3: obtaining a group of initial feasible paths through a particle swarm algorithm, and dividing an environment map into different subareas by combining a regional division method;
step4: the particle swarm algorithm is combined with the gravitation search algorithm, fractional calculus and energy consumption constraint are introduced in particle updating, a fractional particle swarm gravitation search algorithm is formed, and path searching is carried out on the sub-region;
step5: initializing information such as particle group velocity, position, quality and the like;
step6: calculating fitness value, and updating particle acceleration, mass and the like;
step7: updating the position and the speed of the particle swarm;
step8: and finishing the iteration, searching the optimal feasible path, and finishing path planning.
According to the process, through region division, an environment region for path planning is divided into a plurality of sub-regions, so that fine search is realized, the problem of local optimization of an algorithm can be avoided, meanwhile, the complexity of search is reduced, and the search efficiency is improved; the particle swarm algorithm is combined with the gravitation search algorithm, so that the searching capability of the particle swarm algorithm can be effectively improved, and meanwhile, the particle searching speed is updated by combining the memory characteristic of fractional calculus, so that the convergence performance of the algorithm is improved; and taking the energy consumption factor into consideration in the path planning constraint, and adjusting the particle searching step length through dynamic parameters so as to obtain a feasible path with lower energy consumption.
Specific:
environmental modeling information collection
Before a path search is performed and a path is planned, environmental information of all the work areas is acquired. In order to enable the environment information to be more accurate and real, the first step of environment modeling is carried out, a laser radar and a machine vision system are installed on the unmanned agricultural machinery to form an environment information acquisition module, and the machine vision can acquire an environment image by means of a camera and process the image. The unmanned agricultural machinery and the acquisition system are used for acquiring information of an operation area to acquire overall environmental information, the overall size of an environmental map and some obstacles in the area are included, the acquired information is converted into a two-dimensional image by means of the information processing module, the laser radar can achieve a ranging function, the information of the obstacles in the area including boundaries and the area is accurately acquired, such as the distance between the boundaries of the obstacles and the area, the coordinate information of the obstacles and the like, the laser ranging radar is installed on the agricultural machinery, the image acquisition module and the GPS positioning system module can be used for judging the position of the unmanned agricultural machinery in real time, the distance between the laser ranging radar and the obstacles is needed, when the planned path reaches the area with the obstacles, whether the unmanned agricultural machinery enters the high-energy area (the area near the obstacles) is judged, when the planned path does not meet the current requirement, the planned path is re-planned by the path planning module to obtain a feasible path meeting the requirement, and the automatic transportation operation of the unmanned agricultural machinery is completed.
Region optimized decomposition
1. Region decomposition
For the division of the space subareas, the division methods are different according to different actual requirements. When the sub-areas are divided by connection, when the connection points of the area dividing lines are at geometric vertexes, geometric boundaries or arc tangent points of the obstacles, the number of the obstacles in the sub-areas is large, even the situation that no obstacle exists in the individual sub-areas occurs, so that the search performance in the areas is large. According to the embodiment, the obstacle in the environment map is set to be a circular obstacle, the coordinates of the center of the obstacle are regarded as connecting nodes of the region boundary in the region division, the connecting nodes extend from the initial node to the next-stage node, and the space region is decomposed by connecting the initial node with each extending node. The division of the regions in this way avoids the mentioned phenomenon of no obstacle in the region.
As shown in the schematic region division diagrams of fig. 2 (a) -2 (c), black filled circles in the diagrams represent obstacles, boxes represent starting positions of unmanned agricultural machinery, and target positions are represented by five-pointed stars.
In the initial stage of region division, a set of feasible path groups from a starting point to a target point are obtained by adopting a standard particle swarm algorithm (shown by a dotted line in fig. 2 (a)), a connecting line between every two circle centers of obstacles is defined as a circle center line (shown by a black solid line in fig. 2 (b)), the position of the target point is taken as an initial node (defined as a father node in the embodiment, the extended next node is defined as a child node), two obstacles with the largest circle center line with the feasible path group intersection point are taken as child nodes (such as child node 1 and child node 2) of the father node to form a child region, the two child nodes are taken as father nodes in the next group of nodes and are connected with the next node, and the initial coordinate point is the final node (shown by the black arrow pointing in fig. 2 (c)).
Wherein each node can only act as a child node of a parent node (except for the start point and the target point), thus preventing the occurrence of a closed region (not including the start point) in the process, as shown in fig. 3 (a); meanwhile, each node needs to traverse, namely the decomposed subarea space is a single communication area, so that the occurrence of multiple communication areas (shown in fig. 3 (b)) is avoided, and all barriers in the graph can participate in area decomposition.
2. Consideration of spatial boundary line
In the region decomposition process, in order to avoid the occurrence of multiple connected regions, boundary lines of the space regions are considered, and when child nodes of a parent node are just starting points, but are blocked by other connected nodes in the connecting line, the boundary lines are considered, so that a new sub-region form is formed, and the occurrence of the situation is avoided. As shown in fig. 4 (a) -4 (b), considering the division manner of the boundary line, wherein fig. 4 (a) cannot form a feasible sub-area due to the fact that the connecting line (black dotted line) is to pass through the obstacle, the boundary area should be considered at this time, as shown by the black solid line in fig. 4 (b), so that a complete space sub-area is formed.
After the area division, a finer searching range can be obtained, the complexity of path searching is reduced, and the fine searching is performed, so that some interference of the local optimal position under the global searching can be avoided to a certain extent, and the searching efficiency and capacity are improved.
3. Energy consumption grading treatment
In the process of planning and searching a feasible path, generally, in the vicinity of an obstacle, the agricultural machinery needs to perform obstacle avoidance processing, the turning cost of the agricultural machinery is considered, and the like, compared with the situation that the energy consumption in an obstacle-free area is higher, in order to reduce the energy consumption of the agricultural machinery as much as possible, a safety area is set around the obstacle, the energy consumption of the agricultural machinery, caused by obstacle avoidance, is taken into consideration, the energy consumption levels of the safety area are divided, the energy consumption values in different ranges are determined, and the energy consumption factors are taken into consideration in the constraint condition of particle updating, so that the particles are searched under the constraint of multiple factors, and a better search result is obtained. Thus, for the content of this section, it is mainly defined in two aspects (energy consumption grading is exemplified by circular obstacles):
according to the characteristics of the selected space obstacle, the radius (r) of the obstacle is taken as a reference, and the maximum influence area reaches 0.5r on the basis of the radius, namely the maximum periphery of the safety area. The widths of the safety regions (circular ring region in FIG. 5) are sequentially 0.2r,0.3r and 0.5r, and the region boundary line is sequentially defined as L 1 ,L 2 ,L 3 ；
Setting energy consumption weights: in the range of (r, L) 1 ) Energy consumption weighting coefficient K 1 The method comprises the steps of carrying out a first treatment on the surface of the In the range of (L) 1 ,L 2 ) Energy consumption weighting coefficient K 2 ；(L 2 ,L 3 ) Coefficient of energy consumption K 3 The method comprises the steps of carrying out a first treatment on the surface of the In the range of (L) 3 Outside) is normal driving energy consumption; when the obstacle is within the radius r of the obstacle, the obstacle avoidance fails, and a feasible path cannot be formed.
The energy consumption calculation formula:
wherein ,e0 Representing the energy consumption coefficient, K, of the non-obstacle region i Energy consumption coefficients, L, representing the individual energy consumption partitions around the obstacle path Representing the total path length of the agricultural machine in the non-obstacle region, L ob Representing the path length within the obstacle region.
When the obstacle region is other geometric bodies, the distance from the geometric center to the obstacle boundary is taken as a reference distance by taking the geometric center as the center, and the corresponding energy consumption region is set.
Particle swarm gravitation search algorithm based on fractional order
After the environment map is refined through the area dividing method, in order to further improve the global convergence and searching capability of searching, a particle swarm algorithm is combined with an gravitation searching algorithm in a refined searching stage, and the speed item of the particle swarm algorithm is updated by introducing fractional calculus, so that the global convergence is improved; introducing an energy consumption problem into a position updating item, and dynamically adjusting and updating the position information of a particle swarm algorithm; and carrying out refined search on each subarea to obtain an optimal path in the subarea, and obtaining a final global feasible path through comparison.
The standard particle swarm algorithm speed update and the position update are as follows:
in the above, v i Indicating particle velocity, c 1 ，c 2 Is a particle learning factor, r 1 、r 2 Representing the random number between (0, 1).
If it is assumed that there is an attractive force between particles, the force is proportional to the mass of the particles and inversely proportional to the distance between the particles, the force can make the particles with good adaptability attract other particles to approach each other, and search iteration is performed towards the globally optimal position, so that a particle gravitation search algorithm is formed, and the speed update formula is as follows:
wherein ,
is each with mass->
Particle acceleration of>
f t Is the fitness, f best And f worst The best and worst fitness among the particle swarms are indicated, respectively. />
For other particles to be the force of the current particle, epsilon is a random number, L ij Is the Euclidean distance between particles, +.>
Is a gravitational constant depending on constants g and α, and in addition, T and T represent the current number of iterations and the maximum number of iterations, respectively.
By shifting the term, the formula (4) is converted into the following form:
the inertia weight ω is a random number belonging to the range between 0,1, and when the value thereof is 1, the left side of the formula (5) can be developed by means of fractional calculus, as shown in the following formula:
in the above formula, α is a random coefficient, and as a method for updating particles, a good performance of convergence can be obtained by selecting a value between 0 and 1.
The particle velocity at the next time is calculated in the above equation by introducing fractional calculus into the velocity update term, correlating the particle velocity update to historical terms at the first four times, which helps to improve global convergence.
For the improved algorithm, in the process of searching, proper increase or decrease of step length is required to enable the space searching to obtain a more accurate solution, and meanwhile, in the process of iteration, a dynamic parameter beta is introduced in the embodiment, and the particle updating searching step length is dynamically adjusted, wherein the dynamic parameter beta is as shown in the following formula:
wherein ,E(xid ) For the energy consumption of the current position, E (x id ) avg Is the average energy consumption.
At this time, the particle position update term is:
according to the process, through region division, an environment region for path planning is divided into a plurality of sub-regions, so that fine search is realized, the problem of local optimization of an algorithm can be avoided, meanwhile, the complexity of search is reduced, and the search efficiency is improved; the particle swarm algorithm is combined with the gravitation search algorithm, so that the searching capability of the particle swarm algorithm can be effectively improved, and meanwhile, the particle searching speed is updated by combining the memory characteristic of fractional calculus, so that the convergence performance of the algorithm is improved; and taking the energy consumption factor into consideration in the path planning constraint, and adjusting the particle searching step length through dynamic parameters so as to obtain a feasible path with lower energy consumption.
Embodiment two:
as shown in fig. 6, a system for implementing the above method includes:
an information acquisition module configured to: acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area;
an information processing module configured to: taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information;
a path planning module configured to: obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
Through regional division, the environment region for path planning is divided into a plurality of sub-regions, so that fine search is realized, the problem of local optimum of an algorithm can be avoided, meanwhile, the complexity of search is reduced, and the search efficiency is improved.
Embodiment III:
the present embodiment provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps in the method for planning an agricultural machine operation path based on region division according to the above embodiment when executing the program.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. The agricultural machinery operation path planning method based on region division is characterized by comprising the following steps:
acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area;
taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information;
obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
2. The regional division-based agricultural machinery operation path planning method of claim 1, wherein the regional division is implemented specifically as follows:
defining a connecting line between every two circle centers of obstacles in the environment map information as a circle center line, taking the position of an end point coordinate as a father node, and taking the obstacles at the two ends of the circle center line with the most intersection point with the feasible path group as child nodes of the father node; the child node serves as a parent node in the next level node and extends until reaching the final node, which is the start coordinate.
3. The agricultural machinery working path planning method based on area division according to claim 2, wherein each node can only be a child node of one parent node except for a start coordinate point and an end coordinate point when the area division is realized; each node traverses to the point that the decomposed sub-area space is a single connected area.
4. The method for planning an agricultural machine operation path based on regional division according to claim 2, wherein when the regional division is realized, when the child node of the parent node is just the starting coordinate point but the connecting line is blocked by other connected nodes, the boundary line of the operation region is used as the connecting line between the nodes to form a new sub-region.
5. The agricultural machinery working path planning method based on area division according to claim 2, wherein when the area division is realized, safety areas around the obstacle are formed with a set radius around the obstacle as a reference, and each safety area has a set energy consumption weight.
6. The method for planning a path of an agricultural operation based on regional division according to claim 1, wherein the initial feasible path group from the start coordinate to the end coordinate is obtained by a standard particle swarm algorithm.
7. The regional division-based agricultural machinery operation path planning method of claim 1, wherein the path searching is performed in the subareas to obtain the optimal paths in the subareas, and the final required optimal feasible paths are obtained through comparison, specifically:
obtaining an optimal path in the subarea through a particle swarm algorithm;
updating a speed item of a particle swarm algorithm by utilizing fractional calculus;
updating the position information of the particle swarm algorithm in the position updating item through the set energy consumption weight;
and obtaining the optimal path in the subarea through speed updating and position updating, and obtaining the final optimal feasible path when the requirement or the maximum iteration is met.
8. The regional division based agricultural implement path planning method of claim 7, wherein the velocity update is represented by the following formula:
wherein ,
is each with mass->
Particle acceleration of>
f t Is the fitness, f best And f worst The best and worst fitness among the particle swarms are indicated, respectively. />
For other particles to be the force of the current particle, epsilon is a random number, L ij Is the Euclidean distance between particles, +.>
Is a gravitational constant depending on constants g and α, and in addition, T and T represent the current number of iterations and the maximum number of iterations, respectively.
9. Agricultural machinery operation route planning system based on regional division, characterized by comprising:
an information acquisition module configured to: acquiring the size of an agricultural machinery operation area and the information of an environment map formed by barriers in the area;
an information processing module configured to: taking the agricultural machinery position as a starting coordinate, taking the warehouse position as an end coordinate, and carrying out environment modeling according to the acquired environment map information;
a path planning module configured to: obtaining an initial feasible path group from the initial coordinates to the final coordinates, regarding the obstacles in the environment map information as circular obstacles, taking the center coordinates as connecting nodes of the boundaries of all sub-areas in the area division, taking the final coordinates as initial nodes to extend to the next node, connecting the initial nodes with all the extending nodes to realize the area division, obtaining a plurality of groups of sub-areas, searching paths in the sub-areas, obtaining the optimal paths in the sub-areas, and updating to obtain the final optimal feasible paths.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the area division based agricultural work path planning method of any one of claims 1-8 when the program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093745.6A CN116257057A (en) | 2023-02-03 | 2023-02-03 | Agricultural machinery operation path planning method and system based on region division |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310093745.6A CN116257057A (en) | 2023-02-03 | 2023-02-03 | Agricultural machinery operation path planning method and system based on region division |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116257057A true CN116257057A (en) | 2023-06-13 |
Family
ID=86683706
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310093745.6A Pending CN116257057A (en) | 2023-02-03 | 2023-02-03 | Agricultural machinery operation path planning method and system based on region division |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116257057A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117315514A (en) * | 2023-11-27 | 2023-12-29 | 华南农业大学 | Unmanned agricultural machinery man-machine cooperation mode working area division method |
| CN117407606A (en) * | 2023-12-14 | 2024-01-16 | 青岛理工大学 | Tourist route recommendation method based on large language model and knowledge graph |
-
2023
- 2023-02-03 CN CN202310093745.6A patent/CN116257057A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117315514A (en) * | 2023-11-27 | 2023-12-29 | 华南农业大学 | Unmanned agricultural machinery man-machine cooperation mode working area division method |
| CN117315514B (en) * | 2023-11-27 | 2024-03-19 | 华南农业大学 | Unmanned agricultural machinery man-machine cooperation mode working area division method |
| CN117407606A (en) * | 2023-12-14 | 2024-01-16 | 青岛理工大学 | Tourist route recommendation method based on large language model and knowledge graph |
| CN117407606B (en) * | 2023-12-14 | 2024-03-05 | 青岛理工大学 | Tourist route recommendation method based on large language model and knowledge graph |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116257057A (en) | Agricultural machinery operation path planning method and system based on region division | |
| CN109254588B (en) | Unmanned aerial vehicle cluster cooperative reconnaissance method based on cross variation pigeon swarm optimization | |
| CN108594853B (en) | Unmanned aerial vehicle formation control method | |
| Goel et al. | Three dimensional path planning for UAVs in dynamic environment using glow-worm swarm optimization | |
| CN107807665B (en) | Unmanned aerial vehicle formation detection task cooperative allocation method and device | |
| CN107168380B (en) | Multi-step optimization method for coverage of unmanned aerial vehicle cluster area based on ant colony algorithm | |
| Reshamwala et al. | Robot path planning using an ant colony optimization approach: a survey | |
| Ali et al. | Cooperative path planning of multiple UAVs by using max–min ant colony optimization along with cauchy mutant operator | |
| CN112684807A (en) | Unmanned aerial vehicle cluster three-dimensional formation method | |
| CN108829140B (en) | Multi-unmanned aerial vehicle cooperative target searching method based on multi-colony ant colony algorithm | |
| Levine et al. | Information-rich path planning with general constraints using rapidly-exploring random trees | |
| Ma et al. | Improved ant colony algorithm for global optimal trajectory planning of UAV under complex environment. | |
| CN111638725A (en) | Unmanned aerial vehicle formation reconstruction system and method based on ant colony algorithm and artificial potential field method | |
| CN114020031B (en) | Unmanned aerial vehicle cluster collaborative dynamic target searching method based on improved pigeon colony optimization | |
| CN111381600A (en) | UUV path planning method based on particle swarm optimization | |
| CN111880561A (en) | Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment | |
| CN114895707B (en) | Agricultural unmanned aerial vehicle path planning method and system based on variable frequency bat algorithm | |
| CN114967680B (en) | Mobile robot path planning method based on ant colony algorithm and convolutional neural network | |
| Gangadharan et al. | Ant colony optimization and firefly algorithms for robotic motion planning in dynamic environments | |
| CN115686057A (en) | Multi-unmanned aerial vehicle path planning method based on whale optimization algorithm | |
| Bai et al. | Design and Simulation of a Collision-free Path Planning Algorithm for Mobile Robots Based on Improved Ant Colony Optimization. | |
| Wang et al. | Trajectory planning for an unmanned ground vehicle group using augmented particle swarm optimization in a dynamic environment | |
| Gao et al. | Ant colony optimization for UAV-based intelligent pesticide irrigation system | |
| CN114839982A (en) | Automatic transportation equipment-oriented path planning method and system | |
| Wang et al. | Full coverage path planning methods of harvesting robot with multi-objective constraints |
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 |