CN113155132B - Unmanned aerial vehicle path planning method and system for greenhouse - Google Patents
Unmanned aerial vehicle path planning method and system for greenhouse Download PDFInfo
- Publication number
- CN113155132B CN113155132B CN202110415238.0A CN202110415238A CN113155132B CN 113155132 B CN113155132 B CN 113155132B CN 202110415238 A CN202110415238 A CN 202110415238A CN 113155132 B CN113155132 B CN 113155132B
- Authority
- CN
- China
- Prior art keywords
- preset
- data information
- greenhouse
- expansion
- unmanned aerial
- 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 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 103
- 238000000605 extraction Methods 0.000 claims abstract description 16
- 239000011159 matrix material Substances 0.000 claims description 12
- 230000011218 segmentation Effects 0.000 claims description 9
- 230000009466 transformation Effects 0.000 claims description 8
- 238000013075 data extraction Methods 0.000 claims description 5
- 230000004888 barrier function Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000575 pesticide Substances 0.000 abstract description 6
- 238000005507 spraying Methods 0.000 abstract description 6
- 230000007246 mechanism Effects 0.000 description 19
- 230000008569 process Effects 0.000 description 9
- 238000013499 data model Methods 0.000 description 5
- 238000003825 pressing Methods 0.000 description 5
- 238000002474 experimental method Methods 0.000 description 4
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 230000000452 restraining effect Effects 0.000 description 2
- 239000007921 spray Substances 0.000 description 2
- 238000012800 visualization Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 230000000916 dilatatory effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003780 insertion Methods 0.000 description 1
- 230000037431 insertion Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000149 penetrating effect Effects 0.000 description 1
- 230000010152 pollination Effects 0.000 description 1
- 238000010845 search algorithm Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 235000013311 vegetables Nutrition 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
- G01C21/206—Instruments for performing navigational calculations specially adapted for indoor navigation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C21/00—Navigation; Navigational instruments not provided for in groups G01C1/00 - G01C19/00
- G01C21/20—Instruments for performing navigational calculations
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
- G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
- G05B13/04—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators
- G05B13/042—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric involving the use of models or simulators in which a parameter or coefficient is automatically adjusted to optimise the performance
-
- 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
- G05D1/0088—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
- G05D1/106—Change initiated in response to external conditions, e.g. avoidance of elevated terrain or of no-fly zones
Landscapes
- Engineering & Computer Science (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Automation & Control Theory (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Business, Economics & Management (AREA)
- Game Theory and Decision Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
Abstract
The invention relates to the technical field of unmanned aerial vehicle path planning, and provides an unmanned aerial vehicle path planning method for a greenhouse. The method comprises the steps of: modeling the internal structure of the greenhouse; according to the acquired internal structure model data information, a preset obstacle expansion algorithm, a preset ground extraction algorithm and a preset module division rule, carrying out module division on the internal structure model to acquire nodes corresponding to each module, and numbering each node; and selecting preset initial position information and preset final position information from the numbers, and combining a preset A-algorithm and a preset 2-opt algorithm to obtain a second preset shortest route which traverses all nodes and returns to the preset initial position after starting from the preset initial position. By adopting the method, the unmanned aerial vehicle is used for fertilizing or spraying pesticide to the crops in the greenhouse, so that the unmanned aerial vehicle can select the shortest route for operation.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle path planning, in particular to an unmanned aerial vehicle path planning method and system for a greenhouse and an unmanned aerial vehicle.
Background
Greenhouse cultivation plants are a common technology in modern agriculture, in the prior art, spraying of pesticide and water and other liquids of plants in the greenhouse is mainly performed manually, a large amount of manpower is consumed, the manpower cost is high, and the automation degree is low.
In order to solve the problems, the following schemes are adopted at present, for example, unmanned aerial vehicles are used for spraying pesticides or water, but the unmanned aerial vehicles are required to be manually involved in the spraying process, and the unmanned aerial vehicles are prevented from colliding with plants or obstacles in a greenhouse; or a fixed flight orbit is arranged, and the unmanned aerial vehicle is controlled to spray pesticide or water according to the flight orbit. However, the method still wastes manpower, has large manual operation ratio in the flying process, low automation degree and low intellectualization; the method of fixing the flight orbit is high in cost, when the planted crops are changed, the flight route of the unmanned aerial vehicle is not changed, and when liquid needed by spraying is needed, the flight orbit is replaced, so that the cost is high. Meanwhile, the existing unmanned aerial vehicle battery is usually built-in and not detachable, and the unmanned aerial vehicle battery can be used continuously after waiting for charging after the unmanned aerial vehicle battery is exhausted.
Therefore, how to intelligent in the greenhouse at present, the unmanned aerial vehicle is automatically controlled to carry out corresponding spraying or monitoring work, and the unmanned aerial vehicle convenient to replace the battery is provided.
Disclosure of Invention
The technical problem to be solved by the invention is that the unmanned aerial vehicle with high reliability can select an optimal route to fertilize, spray pesticide and monitor vegetables in the greenhouse after avoiding obstacles in the greenhouse and keeping flying at a certain height with planted plants. In order to solve the problems, the invention provides an unmanned aerial vehicle path gauge method and system for a greenhouse. The invention is realized by the following technical scheme: an unmanned aerial vehicle path planning method for a greenhouse, comprising the following steps:
s1: modeling the internal structure of the greenhouse according to a preset modeling algorithm, and acquiring data information of an internal structure model;
s2: according to the obtained internal structure model data information and a preset obstacle expansion algorithm, obtaining obstacle expansion layout data information corresponding to the internal structure model of the greenhouse;
s3: according to a preset ground extraction algorithm, ground data extraction is carried out on the obstacle expansion layout data information, and corresponding ground structure layout data information in the obstacle expansion layout data information is obtained;
S4: according to the obtained obstacle expansion layout data information and a preset module division rule, carrying out module division on the internal structure model after the expansion of the obstacle, obtaining nodes corresponding to each module, and numbering each node;
s5: selecting preset initial position information and preset final position information from the numbers according to the numbers of the modules in the step S4, and acquiring a first preset shortest route between the preset initial position and the preset final position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
s6: and (3) combining the number in the step S4 with the first preset shortest route between the preset starting position and the preset ending position acquired in the step S5 and a preset 2-opt algorithm, and acquiring a second preset shortest route which traverses all nodes after starting from the preset starting position and returns to the preset starting position.
Further, the step S2 of acquiring the obstacle expansion layout data information according to the preset obstacle expansion algorithm specifically includes the steps of:
s21: acquiring three-dimensional data information corresponding to the unmanned aerial vehicle;
s22: and expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
Further, the step S22 specifically includes the steps of:
s221: according to the acquired width information of the unmanned aerial vehicle, performing width expansion on preset initial structure layout data information;
s222: according to the acquired height information of the unmanned aerial vehicle, performing height expansion on the data subjected to the width expansion in the step S221 according to a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
s223: and (3) acquiring the layout data information of the expanded structure according to the expanded data with the margin coefficient subtracted in the step S222, and storing the layout data information in a background server.
Further, in step S3, ground data extraction is performed on the obstacle expansion layout data information, and specific ground structure layout data information corresponding to the obstacle expansion layout data information is obtained
The method comprises the following steps:
s31: carrying out space horizontal segmentation on the internal structure of the greenhouse, and acquiring horizontal plane data information of the internal structure of the greenhouse;
s32: acquiring preset bottom surface data information in the horizontal surface data information;
s33: according to a preset flood filling algorithm, expanding from the preset bottom surface of the greenhouse to a plurality of preset directions, and expanding according to a preset step value;
S34: and extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
Further, a distance transformation algorithm is further included between the step S5 and the step S4, and specifically includes the steps of:
a1: obtaining a distance matrix corresponding to an internal structure model of the greenhouse according to a preset distance transformation algorithm; the value of the preset position point in the distance matrix is a preset minimum distance value of the position from a preset height plane of an internal structure of the greenhouse;
a2: and assigning infinity to the empty space in the internal structure model of the greenhouse, assigning a to the preset ground in the internal structure model of the greenhouse, and assigning b to the preset barrier in the internal structure model of the greenhouse.
Further, in step S5, a preset originating position and a preset destination position are obtained through a preset a-algorithm
Shortest distance between devices, comprising the steps of:
s51: acquiring a preset first path between a preset starting position and a preset end position through a preset estimated cost function, wherein the preset estimated cost function is as follows:
f(n)＝g(n)+h(n)
wherein g (n) is the distance estimation cost from the preset initial position to the current point position;
h (n) is the distance cost value from the preset initial position to the preset final position;
f (n) is the distance estimation cost from the preset initial position to the preset final position through the current point position;
wherein the calculation formula of h (n) is as follows:
h(n)＝√(Xend-Xn)2+(Yend-Yn)2+(Zend-Zn)2
wherein (Xend, yend, yend) is the three-dimensional coordinates of the preset end point position, and (Xn, yn, zn) is the three-dimensional coordinates of the current point position.
S52: and (3) acquiring a second preset shortest distance between the preset initial position and the preset end position of the unmanned aerial vehicle according to the route data information from the preset initial position to the preset end position calculated in the step (S51) and by combining the distance matrix data information of the internal structure of the greenhouse acquired by the preset distance conversion algorithm.
An unmanned aerial vehicle path planning system for a warmhouse booth, comprising:
the modeling module is used for modeling the internal structure of the greenhouse according to a preset modeling algorithm and obtaining data information of an internal structure model;
the obstacle expansion module is used for acquiring obstacle expansion layout data information corresponding to the internal structure model of the greenhouse according to the acquired internal structure model data information and a preset obstacle expansion algorithm;
the ground extraction module is used for extracting ground data of the obstacle expansion layout data information according to a preset ground extraction algorithm and acquiring corresponding ground structure layout data information in the obstacle expansion layout data information;
The node numbering module is used for carrying out module division on the internal structure model after the expansion of the obstacle according to the acquired information of the expansion layout data of the obstacle and a preset module division rule, acquiring nodes corresponding to each module and numbering each node;
acquiring a preset two-point distance module, selecting preset initial position information and preset end position information from the numbers, and acquiring a first preset shortest route between the preset initial position and the preset end position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
the module for obtaining the traversing optimal route is used for obtaining a second preset shortest route which traverses all nodes after starting from a preset starting position and returns to the preset starting position according to a preset 2-opt algorithm.
Further, the obstacle dilating module comprises:
the method comprises the steps of obtaining a three-dimensional data unit, wherein the three-dimensional data unit is used for obtaining three-dimensional data information corresponding to an unmanned aerial vehicle;
and the obstacle expansion layout unit is used for expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
Further, the obstacle expanding layout unit includes:
the width expanding unit is used for expanding the width of the preset initial structure layout data information according to the acquired width information of the unmanned aerial vehicle;
the height expansion unit is used for carrying out height expansion on the data subjected to the width expansion according to the acquired height information of the unmanned aerial vehicle and a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
and acquiring an expansion data unit, which is used for acquiring the expansion structure layout data information by subtracting the expanded data of the margin coefficient and storing the expansion structure layout data information to a background server.
Further, the ground extraction module includes:
the horizontal plane segmentation unit is used for carrying out space horizontal plane segmentation on the internal structure of the greenhouse, acquiring horizontal plane data information of the internal structure of the greenhouse and acquiring preset bottom surface data information in the horizontal plane data information;
the expansion unit is used for expanding from the preset bottom surface of the greenhouse to a plurality of preset directions according to a preset flood filling algorithm and expanding according to a preset step value;
and acquiring a ground data information unit, wherein the ground data information unit is used for extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
By adopting the technical scheme, the invention has at least the following beneficial effects:
(1) The unmanned aerial vehicle path planning method for the greenhouse can be used for carrying out corresponding modeling according to the internal structure of the greenhouse, so that the unmanned aerial vehicle path planning is carried out according to the built indoor structure model of the greenhouse.
(2) According to the unmanned aerial vehicle path planning method for the greenhouse, obstacle expansion can be carried out on the built internal structure model of the greenhouse according to the size of the unmanned aerial vehicle, so that the unmanned aerial vehicle cannot strike the obstacle in the flight process.
(3) The unmanned aerial vehicle path planning method for the greenhouse can divide the horizontal plane inside the greenhouse and extract the ground in the horizontal plane, and the ground comprises a ground plane and a stair step plane, so that the unmanned aerial vehicle can be planned to carry out flight adjustment in the height direction.
(4) According to the unmanned aerial vehicle path planning method for the greenhouse, the model established by the internal structure of the greenhouse is divided into modules, each module is numbered in advance, so that the unmanned aerial vehicle path planning can be realized, and whether the planned route of the unmanned aerial vehicle is correct can be analyzed.
(5) According to the unmanned aerial vehicle path planning method for the greenhouse, a 2-opt algorithm is executed on each node of the obtained internal structure of the greenhouse to obtain the optimal combination of the unmanned aerial vehicle in the greenhouse, then two points in the optimal path are respectively set as a starting point and an ending point according to the sequence of the nodes, an A algorithm is executed once, the optimal path length is finally obtained, and the visualization is performed in preset software.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flowchart of a method for planning a path of an unmanned aerial vehicle for a greenhouse;
FIG. 2 is a flow chart II of the unmanned aerial vehicle path planning method for the greenhouse;
FIG. 3 is a flowchart III of the unmanned aerial vehicle path planning method for a greenhouse;
fig. 4 is a distance transformation algorithm diagram in the unmanned aerial vehicle path planning method for a greenhouse;
FIG. 5 is a first block diagram of an unmanned aerial vehicle path planning system for a greenhouse;
FIG. 6 is a second block diagram of the unmanned aerial vehicle path planning system for a greenhouse;
fig. 7 is a schematic view of a structure of a drone according to an exemplary embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Example 1:
the embodiment of the invention provides a path planning method for an unmanned aerial vehicle in a greenhouse, which comprises the following steps of:
s1: modeling the internal structure of the greenhouse according to a preset modeling algorithm, and acquiring data information of an internal structure model;
the application adopts a three-dimensional raster data model method to model the internal structure of the greenhouse, and the specific modeling algorithm is as follows:
The imported raw house model is such a binary three-dimensional raster data model matrix. The space in which the original house model is located has three dimensions of X, Y, Z axes, with the data units, i.e. voxels, being considered as a grid of cubes. The values of the voxels in the original house model are only two of 0 and 128, representing the empty region and the non-passing region, respectively. The non-passing area comprises walls, roofs, floors, stairs, furniture and other obstacles in the house model, and is an area which does not support the unmanned aerial vehicle model to pass through at the position of the voxel. In contrast, the empty region indicates that the voxel is free of obstructions and can support the unmanned aerial vehicle model to pass through.
S2: according to the obtained internal structure model data information and a preset obstacle expansion algorithm, obtaining obstacle expansion layout data information corresponding to the internal structure model of the greenhouse;
further, the step S2 of acquiring the obstacle expansion layout data information according to the preset obstacle expansion algorithm specifically includes the steps of:
s21: acquiring three-dimensional data information corresponding to the unmanned aerial vehicle;
s22: and expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
Further, the step S22 specifically includes the steps of:
s221: according to the acquired width information of the unmanned aerial vehicle, performing width expansion on preset initial structure layout data information;
s222: according to the acquired height information of the unmanned aerial vehicle, performing height expansion on the data subjected to the width expansion in the step S221 according to a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
s223: and (3) acquiring the layout data information of the expanded structure according to the expanded data with the margin coefficient subtracted in the step S222, and storing the layout data information in a background server.
Namely: because the unmanned aerial vehicle is taken as an abstracted point in the three-dimensional grid house data model, occupies a small volume, and the unmanned aerial vehicle has a certain volume, the sizes of all boundaries and obstacle object elements of the three-dimensional grid house data model have certain limitations on the capability of restraining the flight track in the flight process, and obstacles (walls, floors and other obstacles) in the model cannot well play a role in restraining the passing unmanned aerial vehicle. Therefore, the obstacle in the data model is expanded outwards by a certain width in the experiment, so that the unmanned aerial vehicle can smoothly pass through the channel capable of completely accommodating the volume of the unmanned aerial vehicle.
Due to the working reasons of the unmanned aerial vehicle, the safety of the unmanned aerial vehicle in the flight process is ensured when pesticide or water is sprayed or monitoring or pollination is performed in the greenhouse. The safety distance from the unmanned aerial vehicle to the obstacle needs to be set according to the size of the unmanned aerial vehicle model. And the planned indoor path distance of the unmanned aerial vehicle is shortest.
Aiming at the unmanned aerial vehicle indoor path planning method provided herein, the following parameters need to be provided for an algorithm: the length and width of the aircraft, the altitude of the aircraft and the step size in the vertical direction.
Length and width and altitude of the aircraft: the algorithm herein simulates unmanned aerial vehicle flight in a three-dimensional room model, and therefore, for an aircraft model, it is also an object with three dimensions of length, width and height. In the experiments herein, the model of the drone is defined as a cylinder, whose length and width are the diameter of the cylinder and whose height is the height of the cylinder. Thus, in the experiments herein, the length and width of the aircraft are equal.
Step size in vertical direction: the step length in the vertical direction is defined as the maximum value that the aircraft can move at each change in altitude in the vertical direction. In the experiments herein, the step value in the vertical direction is considered to be greater than or equal to the height of one step of a staircase in a house model.
I.e. in the present application the obstacle-dilating algorithm is geometrically dilated around and downwards to a degree depending on the aircraft, i.e. the size of the unmanned aerial vehicle in this context. Specifically, the expansion radius in the horizontal direction is equal to the size of the unmanned aerial vehicle model, and the degree of expansion downward is the height of the unmanned aerial vehicle model minus 1.
S3: according to a preset ground extraction algorithm, ground data extraction is carried out on the obstacle expansion layout data information, and corresponding ground structure layout data information in the obstacle expansion layout data information is obtained;
according to the method, the ground is extracted, and the unmanned aerial vehicle is guaranteed to fly stably along a designated height as much as possible. This designated height refers to the height of the drone from the ground. The specific algorithm is as follows: first, the ground position of the internal structural model of the greenhouse is determined. Then, only the obstacles and the non-obstacles are included in the given internal structure model, wherein the obstacles include the ground, the stairs, the wall, the roof and the like, so that the ground (including the stairs) is necessary to be distinguished and extracted from other obstacles. The differentiation between the ground (including stairs) and other obstacles is achieved by utilizing different characteristics between the ground and other obstacles.
The specific preset ground extraction algorithm comprises the following steps:
s31: carrying out space horizontal segmentation on the internal structure of the greenhouse, and acquiring horizontal plane data information of the internal structure of the greenhouse;
s32: acquiring preset bottom surface data information in the horizontal surface data information;
s33: according to a preset flood filling algorithm, expanding from the preset bottom surface of the greenhouse to a plurality of preset directions, and expanding according to a preset step value;
s34: and extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
Through presetting the ground extraction algorithm, the flying height of the unmanned aerial vehicle can be guaranteed.
S4: according to the obtained obstacle expansion layout data information and a preset module division rule, carrying out module division on the internal structure model after the expansion of the obstacle, obtaining nodes corresponding to each module, and numbering each node;
s5: selecting preset initial position information and preset final position information from the numbers according to the numbers of the modules in the step S4, and acquiring a first preset shortest route between the preset initial position and the preset final position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
S6: and (3) combining the number in the step S4 with the first preset shortest route between the preset starting position and the preset ending position acquired in the step S5 and a preset 2-opt algorithm, and acquiring a second preset shortest route which traverses all nodes after starting from the preset starting position and returns to the preset starting position.
By adopting the technical scheme, the unmanned aerial vehicle can start from any point in the model of the internal structure of the greenhouse, traverses each point one by one, only accesses once, does not repeat and finally returns to the original point.
Further, a distance transformation algorithm is further included between the step S5 and the step S4, and specifically includes the steps of:
a1: obtaining a distance matrix corresponding to an internal structure model of the greenhouse according to a preset distance transformation algorithm; the value of the preset position point in the distance matrix is a preset minimum distance value of the position from a preset height plane of an internal structure of the greenhouse;
a2: and assigning infinity to the empty space in the internal structure model of the greenhouse, assigning a to the preset ground in the internal structure model of the greenhouse, and assigning b to the preset barrier in the internal structure model of the greenhouse.
In the application, a distance transformation algorithm is adopted to obtain a distance matrix of a space of an internal structure model of the greenhouse, the value of each position point in the matrix represents the distance value of the position, namely the minimum distance value from the element to a plane with a designated height in the house model, and the minimum distance value is used as the consumption value passing through the element.
All the empty spaces (except the ground, stairs and obstacles in the internal structure model) are assigned infinity (in the actual algorithm implementation process, a large value is assigned to represent infinity), and two different smaller values are respectively assigned to the ground (including stairs) and the obstacles in the internal structure model, so that the ground (including stairs) and the obstacles in the internal structure model can be accurately identified in the later distance conversion algorithm implementation process. As shown in fig. 4.
Further, the method comprises the steps of,
in step S5, the most significant between the preset initial position and the preset final position is obtained by the preset a-algorithm
Short distance comprising the steps of:
s51: acquiring a preset first path between a preset starting position and a preset end position through a preset estimated cost function, wherein the preset estimated cost function is as follows:
f(n)＝g(n)+h(n)
wherein g (n) is the distance estimation cost from the preset initial position to the current point position;
h (n) is the distance cost value from the preset initial position to the preset final position;
f (n) is the distance estimation cost from the preset initial position to the preset final position through the current point position;
wherein the calculation formula of h (n) is as follows:
h(n)＝√(Xend-Xn)2+(Yend-Yn)2+(Zend-Zn)2
Wherein (Xend, yend, yend) is the three-dimensional coordinates of the preset end point position, and (Xn, yn, zn) is the three-dimensional coordinates of the current point position.
The method comprises the following specific steps:
the algorithm A is a heuristic search algorithm, and is a direct search method which is most effective in solving the shortest path in a static road network and an effective algorithm for solving a plurality of search problems due to higher flexibility and adaptability of the algorithm.
The algorithm A combines Dijkstra algorithm and BFS algorithm to make up for the advantages and disadvantages. The heuristic function of the a-algorithm is as follows:
f(n)＝g(n)+h(n)
g (n) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -, a distance from the starting point to the current point n to be estimated cost).
h (n) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -stem) s of the current point n to the.
f (n) - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -, a distance from the starting point to the ending point to be estimated through the current point n.
In case the starting point and the ending point are both determined, given a current point n, the value of h (n) is fixed, remains unchanged, and g (n) can be updated.
In order to obtain the optimal path, the value of h (n) is smaller than or equal to the actual distance from the current point n to the end point, wherein h (n) is a heuristic function in the path search planning algorithm.
In general, h (n) is obtained by calculating the euclidean distance from the current point n to the termination point, expressed in a two-dimensional plane as:
In the solution herein, the problem is extended to the three-dimensional space coordinate system model, and h (n) is defined as the euclidean distance from the current point n to the termination point in the three-dimensional space model, namely:
(x end ,y end ,z end ) Is the coordinate of the termination point in a three-dimensional space coordinate system, (x) n ,y n ,z n ) Is the coordinates of the current point n in the three-dimensional space coordinate system.
The specific steps of the algorithm are: firstly, an OpenList table and a CloseList table are created, nodes to be detected are stored in the OpenList during path planning, and detected grids are stored in the CloseList.
Setting a preset starting position as A and setting a preset finishing position as B;
firstly, adding a starting point A into an OpenList table, and setting the starting point A as a parent node of other 8 grids around. Searching 8 adjacent points of the starting point A, if the adjacent points are points which are not in the OpenList table or the CloseList table, calculating the f (n) value of the point, putting the point A into the CloseList table, judging whether the OpenList table is empty at the moment, if the OpenList table is not empty, indicating that all possible path points are found before reaching the end point, searching paths fails, and ending the algorithm; otherwise, continuing to take out a point with the minimum f (n) value from the OpenList table as the next step of path finding. And judging whether the point is an end point, if so, successfully searching the path, otherwise, continuously setting the point as a starting point A, and then operating the surrounding adjacent points of the A.
S52: and (3) acquiring a second preset shortest distance between the preset initial position and the preset end position of the unmanned aerial vehicle according to the route data information from the preset initial position to the preset end position calculated in the step (S51) and by combining the distance matrix data information of the internal structure of the greenhouse acquired by the preset distance conversion algorithm.
According to the method, the unmanned aerial vehicle is enabled to start from any point in the space of the greenhouse through the route planning, the preset points appointed in each area are traversed in sequence, each point is visited only once, obstacle avoidance is considered in the flight process, the shortest flight path is selected, and finally the unmanned aerial vehicle returns to the original point; therefore, to check the above-mentioned two-point route planning problem, the problem can be expanded into the problem of the tourist.
The method comprises the following specific steps: starting from a certain point of n preset nodes in the internal structure of the greenhouse, traversing the n nodes, traversing each node only once, and finally returning to the original node to obtain the shortest node traversing sequence. Namely:
S min ＝(s 1 ，s 2 ，s 3 …，s n )
wherein s is t Is a node, d (s t ，s t+1 ) Representing node s i Sum node s i+1 The length between the nodes, when the TSP problem contains n nodes, (n-1) is present-! 2 path order.
Because a great deal of operation can be carried out by solving with a fine algorithm, the application adopts a 2-opt algorithm also called a two-element optimization algorithm to solve the problem of a traveling company, and the specific steps are as follows:
step 1: randomly selecting a route, setting the route as a route one (A- > B- > C- > D- > E- > F- > G), and assuming that the route is the shortest path, wherein the path is min;
step 2: randomly selecting two unconnected nodes in a route, turning over the route between the two nodes to obtain a new route, and if the node B and the node E are randomly selected, the new route is A- > (E- > -D- > -C- > -B) - > -F- > -G, () and the part is the turned-over route;
if the new path is shorter than the min path, setting the new path as the shortest path min, setting the counter COUNT value to 0, and returning to the step 2; otherwise, adding 1 to the counter COUNT value, ending the algorithm when the counter is greater than or equal to the COUNT value, wherein the min is the shortest path, otherwise, returning to the step 2.
The method is used for planning the shortest path between two points through an A-algorithm, so that an unmanned aerial vehicle can find the shortest path and safely pass through indoor barriers; and the 2-opt algorithm is used for solving the problem of the tourist in the indoor inspection path planning. Firstly, respectively writing a Python program script for an A algorithm and a 2-opt algorithm, so as to realize effective combination of the two algorithms, firstly, executing the 2-opt algorithm on all house nodes to obtain an optimal path combination, then respectively setting two points in the optimal path as a starting point and an ending point according to a node sequence, executing the A algorithm once, finally obtaining the total optimal path length, and carrying out visualization in Paraview software.
Example 2:
the embodiment of the invention provides a path planning system for a greenhouse unmanned aerial vehicle, which comprises the following steps: the modeling module is used for modeling the internal structure of the greenhouse according to a preset modeling algorithm and obtaining data information of an internal structure model;
the obstacle expansion module is used for acquiring obstacle expansion layout data information corresponding to the internal structure model of the greenhouse according to the acquired internal structure model data information and a preset obstacle expansion algorithm;
the ground extraction module is used for extracting ground data of the obstacle expansion layout data information according to a preset ground extraction algorithm and acquiring corresponding ground structure layout data information in the obstacle expansion layout data information;
the node numbering module is used for carrying out module division on the internal structure model after the expansion of the obstacle according to the acquired information of the expansion layout data of the obstacle and a preset module division rule, acquiring nodes corresponding to each module and numbering each node;
acquiring a preset two-point distance module, selecting preset initial position information and preset end position information from the numbers, and acquiring a first preset shortest route between the preset initial position and the preset end position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
The module for obtaining the traversing optimal route is used for obtaining a second preset shortest route which traverses all nodes after starting from a preset starting position and returns to the preset starting position according to a preset 2-opt algorithm.
Further, the obstacle expanding module includes:
the method comprises the steps of obtaining a three-dimensional data unit, wherein the three-dimensional data unit is used for obtaining three-dimensional data information corresponding to an unmanned aerial vehicle;
and the obstacle expansion layout unit is used for expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
Further, the obstacle expanding layout unit includes:
the width expanding unit is used for expanding the width of the preset initial structure layout data information according to the acquired width information of the unmanned aerial vehicle;
the height expansion unit is used for carrying out height expansion on the data subjected to the width expansion according to the acquired height information of the unmanned aerial vehicle and a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
and acquiring an expansion data unit, which is used for acquiring the expansion structure layout data information by subtracting the expanded data of the margin coefficient and storing the expansion structure layout data information to a background server.
Further, the ground extraction module includes:
the horizontal plane segmentation unit is used for carrying out space horizontal plane segmentation on the internal structure of the greenhouse, acquiring horizontal plane data information of the internal structure of the greenhouse and acquiring preset bottom surface data information in the horizontal plane data information;
the expansion unit is used for expanding from the preset bottom surface of the greenhouse to a plurality of preset directions according to a preset flood filling algorithm and expanding according to a preset step value;
and acquiring a ground data information unit, wherein the ground data information unit is used for extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
The system can be used for realizing corresponding modeling according to the internal structure of the greenhouse, so that the path planning of the unmanned aerial vehicle is carried out according to the built indoor structure model of the greenhouse. The built internal structure model of the greenhouse is expanded according to the size of the unmanned aerial vehicle, so that the unmanned aerial vehicle cannot strike the obstacle in the flight process. The horizontal plane inside the greenhouse is divided, the ground in the horizontal plane is extracted, and the ground comprises a ground plane and a stair step plane, so that the unmanned aerial vehicle can be planned to carry out flight adjustment in the height direction. The model after the internal structure of the greenhouse is built is divided into modules, and each module is numbered in advance, so that the planning of the route planning of the unmanned aerial vehicle can be realized, and whether the planned route of the unmanned aerial vehicle is correct can be analyzed. And executing a 2-opt algorithm on each node of the obtained internal structure of the greenhouse to obtain the optimal combination of the unmanned aerial vehicle in the greenhouse, setting two points in the optimal path as a starting point and an ending point according to the node sequence, executing an A-time algorithm, finally obtaining the optimal path length, and visualizing in preset software.
Example 3:
referring to fig. 7, an unmanned aerial vehicle convenient to change battery, unmanned aerial vehicle includes organism 2 and battery package 1, and battery package 1 includes battery case 11 and locates the electric core in the battery case 11, is equipped with the latch groove on the battery case 11, organism 2 is equipped with the battery compartment 30 that holds battery package 1, is equipped with in the battery compartment 30 and presses the pop-up mechanism, and battery compartment 30 has an export, presses the one end that the pop-up mechanism installed and be relative setting with battery compartment 30 export, and battery package 1 pluggable installs in battery compartment 30, and battery package 1 realizes the incorporable battery compartment 30 inside and pops out battery compartment 30 along with pressing the circulation.
The pressing and ejecting mechanism adopts a ball-point pen-like pressing and ejecting mechanism and comprises a sliding base, wherein a beveled heart-shaped stop block is arranged on the side surface or below the sliding base, and a sliding rail is arranged around the stop block; the sliding rail is formed by sequentially and smoothly connecting a first sliding rail, a second sliding rail, a third sliding rail, a fourth sliding rail and a fifth sliding rail, wherein the first sliding rail and the fourth sliding rail are respectively positioned at two sides below the stop block, the second sliding rail and the third sliding rail are respectively positioned at two sides above the stop block, the fifth sliding rail is positioned below the first sliding rail and the fourth sliding rail, and the fifth sliding rail is connected with the fourth sliding rail into a straight line; a loop bar is arranged in the sliding rail, and the other end of the loop bar is movably connected in the unmanned aerial vehicle; the unmanned aerial vehicle is internally provided with an elastic piece for pushing the sliding base to slide up and down, and the other end of the elastic piece is connected above the side, below the side or below the sliding base. The elastic member is a compression spring when located under or below the side of the slide base. The inclined cutting step is arranged between the sliding rail IV and the sliding rail V, the sliding rail IV is higher than the sliding rail V, the sliding rail V is smoothly communicated with the sliding rail I, and the top end of the loop bar is ensured to slide unidirectionally according to a preset track when the sliding mechanism is used. The guide protrusion I is arranged above the second slide rail and the third slide rail, and is biased to one side of the second slide rail, so that the sleeve rod slides into the third slide rail instead of the second slide rail when sliding in the second slide rail; ensure the one-way sliding of the loop bar in the sliding rail. Further, the top end of the fourth sliding rail is provided with a concave wedge-shaped slope relative to the third sliding rail, so that the sleeve rod can slide from the third sliding rail to the fourth sliding rail smoothly and cannot slide reversely. Further, a wedge-shaped guiding protrusion II with guiding function is arranged above the first sliding rail, the tail end of the guiding protrusion II is located above the second sliding rail, and after the user releases hands by pressing, the loop bar smoothly slides into the space between the second sliding rail and the third sliding rail.
The pressing and ejecting mechanism further comprises a locking mechanism, the locking mechanism comprises a lock tongue, the loop bar is located at the joint of the second slide rail and the third slide rail when the battery pack is inside the unmanned aerial vehicle, the bottom surface of the battery pack is flush with the outlet end face of the battery compartment, the lock tongue is matched with a latch groove on the surface of the battery pack to lock the battery pack inside the battery compartment of the unmanned aerial vehicle, when the battery pack needs to be replaced, the bottom surface of the battery pack is pressed by a finger, one end of the loop bar slides into the fourth slide rail from the third slide rail, the finger is loosened, under the action of the elastic piece, the elastic piece pushes the battery pack to move outwards to eject the battery compartment, and one end of the loop bar moves from the fourth slide rail to the tail end of the fifth slide rail.
Example 4:
a battery-facilitated replacement unmanned aerial vehicle, comprising: the battery pack comprises a battery shell and a battery core arranged in the battery shell, a positioning hole is formed in the side wall of the battery shell, a battery cavity structure is arranged on the side wall of the battery shell, the battery cavity structure comprises a battery bin capable of accommodating and supplying power to the battery for extraction and insertion, an ejection mechanism and a locking mechanism, the battery bin is provided with an outlet, the ejection mechanism is arranged at one end opposite to the outlet of the battery bin, the locking mechanism is used for limiting the battery pack arranged in the battery bin so as to limit the battery pack from falling out from the outlet of the battery bin, the battery pack is arranged in the battery bin in a pluggable manner, the ejection mechanism is arranged near the locking mechanism, and the ejection mechanism is a push-type ejection mechanism, so that the battery can be taken in the battery bin and the battery bin can be ejected along with the push-type circulation;
The locking structure is arranged at one end opposite to the outlet of the battery compartment and comprises a sleeve, a sliding base and a lock tongue arranged on the sliding base, a notch is arranged on the sleeve, when the lock tongue on the sliding base slides to the notch, the lock tongue is separated from a positioning hole on the battery pack, the battery pack can be moved out of the battery compartment, and when the lock tongue is far away from the notch, the lock tongue is matched with the positioning hole on the battery pack after being extruded by the sleeve so as to fix the battery pack in the battery compartment;
the ejecting mechanism comprises a fixed block arranged on the sliding base, the fixed block is fixedly connected with the upper end of the sleeve, a beveled heart-shaped stop block is arranged on the side face of the fixed block, the ejecting mechanism further comprises a moving piece penetrating through the sliding base and matched with the stop block on the fixed block, one end of the moving piece is abutted against the battery pack, and the other end of the moving piece is matched with the stop block. The spring mechanism further comprises an elastic piece which is arranged in the fixed block and used for pushing the sliding base to slide up and down, and the elastic piece drives the sliding base to move up and down, so that the locking tongue is controlled to be matched with the positioning hole on the battery pack, and the battery is locked or unlocked. The fixed block and the sliding base are provided with mutually matched connecting structures, and the fixed block can only move in a certain stroke relative to the sliding base.
The foregoing description of the preferred embodiments of the invention is not intended to limit the invention to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the invention are intended to be included within the scope of the invention.
Claims (10)
1. The unmanned aerial vehicle path planning method for the greenhouse is characterized by comprising the following steps of:
s1: modeling the internal structure of the greenhouse according to a preset modeling algorithm, and acquiring data information of an internal structure model;
s2: according to the obtained internal structure model data information and a preset obstacle expansion algorithm, obtaining obstacle expansion layout data information corresponding to the internal structure model of the greenhouse;
s3: according to a preset ground extraction algorithm, ground data extraction is carried out on the obstacle expansion layout data information, and corresponding ground structure layout data information in the obstacle expansion layout data information is obtained;
s4: according to the obtained obstacle expansion layout data information and a preset module division rule, carrying out module division on the internal structure model after the expansion of the obstacle, obtaining nodes corresponding to each module, and numbering each node;
s5: selecting preset initial position information and preset final position information from the numbers according to the numbers of the modules in the step S4, and acquiring a first preset shortest route between the preset initial position and the preset final position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
S6: and (3) combining the number in the step S4 with the first preset shortest route between the preset starting position and the preset ending position acquired in the step S5 and a preset 2-opt algorithm, and acquiring a second preset shortest route which traverses all nodes after starting from the preset starting position and returns to the preset starting position.
2. The unmanned aerial vehicle path planning method for a greenhouse according to claim 1, wherein the step S2 of acquiring the obstacle expansion layout data information according to a preset obstacle expansion algorithm specifically comprises the steps of:
s21: acquiring three-dimensional data information corresponding to the unmanned aerial vehicle;
s22: and expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
3. The unmanned aerial vehicle path planning method for a greenhouse according to claim 2, wherein the step S22 specifically comprises the steps of:
s221: according to the acquired width information of the unmanned aerial vehicle, performing width expansion on preset initial structure layout data information;
S222: according to the acquired height information of the unmanned aerial vehicle, performing height expansion on the data subjected to the width expansion in the step S221 according to a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
s223: and (3) acquiring the layout data information of the expanded structure according to the expanded data with the margin coefficient subtracted in the step S222, and storing the layout data information in a background server.
4. The unmanned aerial vehicle path planning method for a greenhouse according to claim 1, wherein in step S3, ground data extraction is performed on the obstacle expansion layout data information, and the corresponding ground structure layout data information in the obstacle expansion layout data information is obtained, specifically comprising the steps of:
s31: carrying out space horizontal segmentation on the internal structure of the greenhouse, and acquiring horizontal plane data information of the internal structure of the greenhouse;
s32: acquiring preset bottom surface data information in the horizontal surface data information;
s33: according to a preset flood filling algorithm, expanding from the preset bottom surface of the greenhouse to a plurality of preset directions, and expanding according to a preset step value;
s34: and extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
5. The unmanned aerial vehicle path planning method for a greenhouse according to claim 1, wherein a distance transformation algorithm is further included between the step S5 and the step S4, and the method specifically includes the steps of:
a1: obtaining a distance matrix corresponding to an internal structure model of the greenhouse according to a preset distance transformation algorithm; the value of the preset position point in the distance matrix is a preset minimum distance value of the position from a preset height plane of an internal structure of the greenhouse;
a2: and assigning infinity to the empty space in the internal structure model of the greenhouse, assigning a to the preset ground in the internal structure model of the greenhouse, and assigning b to the preset barrier in the internal structure model of the greenhouse.
6. The unmanned aerial vehicle path planning method for a greenhouse of claim 5, wherein the shortest distance between the preset starting position and the preset final position is obtained in step S5 through a preset a-algorithm, comprising the steps of:
s51: acquiring a preset first path between a preset starting position and a preset end position through a preset estimated cost function, wherein the preset estimated cost function is as follows:
f(n)＝g(n)+h(n)
wherein g (n) is the distance estimation cost from the preset initial position to the current point position;
h (n) is the distance cost value from the preset initial position to the preset final position;
f (n) is the distance estimation cost from the preset initial position to the preset final position through the current point position;
wherein the calculation formula of h (n) is as follows:
h(n)＝√(Xend-Xn)2+(Yend-Yn)2+(Zend-Zn)2
wherein (Xend, yend, yend) is the three-dimensional coordinate of the preset end point position, and (Xn, yn, zn) is the three-dimensional coordinate of the current point position;
s52: and (3) acquiring a second preset shortest distance between the preset initial position and the preset end position of the unmanned aerial vehicle according to the route data information from the preset initial position to the preset end position calculated in the step (S51) and by combining the distance matrix data information of the internal structure of the greenhouse acquired by the preset distance conversion algorithm.
7. An unmanned aerial vehicle path planning system for a warmhouse booth, comprising:
the modeling module is used for modeling the internal structure of the greenhouse according to a preset modeling algorithm and obtaining data information of an internal structure model;
the obstacle expansion module is used for acquiring obstacle expansion layout data information corresponding to the internal structure model of the greenhouse according to the acquired internal structure model data information and a preset obstacle expansion algorithm;
The ground extraction module is used for extracting ground data of the obstacle expansion layout data information according to a preset ground extraction algorithm and acquiring corresponding ground structure layout data information in the obstacle expansion layout data information;
the node numbering module is used for carrying out module division on the internal structure model after the expansion of the obstacle according to the acquired information of the expansion layout data of the obstacle and a preset module division rule, acquiring nodes corresponding to each module and numbering each node;
acquiring a preset two-point distance module, selecting preset initial position information and preset end position information from the numbers, and acquiring a first preset shortest route between the preset initial position and the preset end position by combining a preset A-type algorithm, obstacle expansion layout data information and ground structure layout data information;
the module for obtaining the traversing optimal route is used for obtaining a second preset shortest route which traverses all nodes after starting from a preset starting position and returns to the preset starting position according to a preset 2-opt algorithm.
8. The unmanned aerial vehicle path planning system for a warmhouse booth of claim 7, wherein the obstacle expansion module comprises:
The method comprises the steps of obtaining a three-dimensional data unit, wherein the three-dimensional data unit is used for obtaining three-dimensional data information corresponding to an unmanned aerial vehicle;
and the obstacle expansion layout unit is used for expanding the preset initial structure layout data information of the internal structure of the greenhouse according to the acquired length data information, width data information and height data information corresponding to the unmanned aerial vehicle, and acquiring the obstacle expansion layout data information of the internal structure of the greenhouse.
9. The unmanned aerial vehicle path planning system for a greenhouse of claim 8, wherein the obstacle-dilating layout unit comprises:
the width expanding unit is used for expanding the width of the preset initial structure layout data information according to the acquired width information of the unmanned aerial vehicle;
the height expansion unit is used for carrying out height expansion on the data subjected to the width expansion according to the acquired height information of the unmanned aerial vehicle and a preset height expansion algorithm, and subtracting a margin coefficient from the expanded data information;
and acquiring an expansion data unit, which is used for acquiring the expansion structure layout data information by subtracting the expanded data of the margin coefficient and storing the expansion structure layout data information to a background server.
10. The unmanned aerial vehicle path planning system for a greenhouse of claim 7, wherein the ground extraction module comprises:
The horizontal plane segmentation unit is used for carrying out space horizontal plane segmentation on the internal structure of the greenhouse, acquiring horizontal plane data information of the internal structure of the greenhouse and acquiring preset bottom surface data information in the horizontal plane data information;
the expansion unit is used for expanding from the preset bottom surface of the greenhouse to a plurality of preset directions according to a preset flood filling algorithm and expanding according to a preset step value;
and acquiring a ground data information unit, wherein the ground data information unit is used for extracting preset ground data information of the internal structure of the greenhouse according to the endowed value corresponding to the expanded obstacle and a preset comparison algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110415238.0A CN113155132B (en) | 2021-04-18 | 2021-04-18 | Unmanned aerial vehicle path planning method and system for greenhouse |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110415238.0A CN113155132B (en) | 2021-04-18 | 2021-04-18 | Unmanned aerial vehicle path planning method and system for greenhouse |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113155132A CN113155132A (en) | 2021-07-23 |
| CN113155132B true CN113155132B (en) | 2024-04-12 |
Family
ID=76868290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110415238.0A Active CN113155132B (en) | 2021-04-18 | 2021-04-18 | Unmanned aerial vehicle path planning method and system for greenhouse |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113155132B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117151596B (en) * | 2023-11-01 | 2023-12-29 | 领先未来科技集团有限公司 | Logistics management method, system and storage medium for storage AGVs (automatic guided vehicle) through Internet of things |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105091884A (en) * | 2014-05-08 | 2015-11-25 | 东北大学 | Indoor moving robot route planning method based on sensor network dynamic environment monitoring |
| CN206528646U (en) * | 2017-02-24 | 2017-09-29 | 深圳市大疆创新科技有限公司 | Battery compartment and unmanned vehicle |
| WO2017173990A1 (en) * | 2016-04-07 | 2017-10-12 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
| CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
| CN110909961A (en) * | 2019-12-19 | 2020-03-24 | 盈嘉互联（北京）科技有限公司 | BIM-based indoor path query method and device |
-
2021
- 2021-04-18 CN CN202110415238.0A patent/CN113155132B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105091884A (en) * | 2014-05-08 | 2015-11-25 | 东北大学 | Indoor moving robot route planning method based on sensor network dynamic environment monitoring |
| WO2017173990A1 (en) * | 2016-04-07 | 2017-10-12 | 北京进化者机器人科技有限公司 | Method for planning shortest path in robot obstacle avoidance |
| CN206528646U (en) * | 2017-02-24 | 2017-09-29 | 深圳市大疆创新科技有限公司 | Battery compartment and unmanned vehicle |
| CN108444482A (en) * | 2018-06-15 | 2018-08-24 | 东北大学 | A kind of autonomous pathfinding barrier-avoiding method of unmanned plane and system |
| CN110909961A (en) * | 2019-12-19 | 2020-03-24 | 盈嘉互联（北京）科技有限公司 | BIM-based indoor path query method and device |
Non-Patent Citations (1)
| Title |
|---|
| 基于IGWO-A~*算法的无人机农田喷洒航迹规划;李靖;杨帆;;沈阳农业大学学报(第02期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113155132A (en) | 2021-07-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| MacAllister et al. | Path planning for non-circular micro aerial vehicles in constrained environments | |
| Cao et al. | Autonomous exploration development environment and the planning algorithms | |
| Marder-Eppstein et al. | The office marathon: Robust navigation in an indoor office environment | |
| Chestnutt et al. | Planning biped navigation strategies in complex environments | |
| Bekris et al. | Greedy but safe replanning under kinodynamic constraints | |
| Frey et al. | Locomotion policy guided traversability learning using volumetric representations of complex environments | |
| US20190082582A1 (en) | Scouting systems | |
| Schmid et al. | A unified approach for autonomous volumetric exploration of large scale environments under severe odometry drift | |
| US7519457B2 (en) | Path generator for mobile object | |
| CN114119920A (en) | Three-dimensional point cloud map construction method and system | |
| CN114219910A (en) | Automatic driving vehicle livestock-raising cleaning method integrating laser radar and machine vision | |
| CN113155132B (en) | Unmanned aerial vehicle path planning method and system for greenhouse | |
| CN114442621A (en) | An autonomous exploration and mapping system based on a quadruped robot | |
| Williams et al. | Online 3D frontier-based UGV and UAV exploration using direct point cloud visibility | |
| CN108958285A (en) | It is a kind of that path planning method is cooperateed with based on the efficient multiple no-manned plane for decomposing thought | |
| AU2020336151B2 (en) | System and method of control for autonomous or remote-controlled vehicle platform | |
| Aguiar et al. | Localization and mapping on agriculture based on point-feature extraction and semiplanes segmentation from 3D LiDAR data | |
| Choi et al. | Improved CNN-based path planning for stairs climbing in autonomous UAV with LiDAR sensor | |
| CN112327927A (en) | Multi-angle strike track planning method for formation unmanned aerial vehicles based on grid planning algorithm | |
| Benenson et al. | Integrating perception and planning for autonomous navigation of urban vehicles | |
| de Lima et al. | Air-ground collaborative localisation in forests using lidar canopy maps | |
| CN111427341A (en) | A Probabilistic Map-Based Target Search Method for Robots with Shortest Expected Time | |
| CN118243127A (en) | A path planning method for a wheeled plant protection robot | |
| CN107970610B (en) | Planning method and device for 3D scene vertical space flight route | |
| Cladera et al. | Challenges and Opportunities for Large-Scale Exploration with Air-Ground Teams using Semantics |
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 |