CN116661502B - Intelligent agricultural unmanned aerial vehicle path planning method - Google Patents

Intelligent agricultural unmanned aerial vehicle path planning method Download PDF

Info

Publication number
CN116661502B
CN116661502B CN202310913709.XA CN202310913709A CN116661502B CN 116661502 B CN116661502 B CN 116661502B CN 202310913709 A CN202310913709 A CN 202310913709A CN 116661502 B CN116661502 B CN 116661502B
Authority
CN
China
Prior art keywords
aerial vehicle
unmanned aerial
obstacle
nodes
representing
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
Application number
CN202310913709.XA
Other languages
Chinese (zh)
Other versions
CN116661502A (en
Inventor
李健
张伟健
于维霖
卢健
付鸿鲲
王海瑞
秦杰
关路
张安阳
丁鹏
王嘉玮
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Jilin Agricultural University
Original Assignee
Jilin Agricultural University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Jilin Agricultural University filed Critical Jilin Agricultural University
Priority to CN202310913709.XA priority Critical patent/CN116661502B/en
Publication of CN116661502A publication Critical patent/CN116661502A/en
Application granted granted Critical
Publication of CN116661502B publication Critical patent/CN116661502B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G05D1/10—Simultaneous control of position or course in three dimensions
    • G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Automation & Control Theory (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

The application provides an intelligent agricultural unmanned aerial vehicle path planning method, which relates to the technical field of path planning, and the method firstly takes an unmanned aerial vehicle as a center and carries out obstacle avoidance by using an artificial potential field method of giving a repulsive potential field to an obstacle and giving a attractive potential field to a target point: when the obstacle is small or the situation is simple, the obstacle is directly avoided; when the obstacle is too large or the situation is complex, the problems that the artificial potential field method is easy to fall into local optimum are effectively solved by establishing a three-dimensional grid map, screening nodes by utilizing jump point searching and introducing an A-star algorithm to carry out path planning, so that real-time and accurate obstacle avoidance is realized. Meanwhile, the method effectively solves the problems of huge calculation amount, high calculation complexity, long calculation time, long path length planning and the like of the A-star algorithm, completes path planning with high precision and few nodes in a short time, and saves calculation resources.

Description

Intelligent agricultural unmanned aerial vehicle path planning method
Technical Field
The application relates to the technical field of path planning, in particular to an intelligent agricultural unmanned aerial vehicle path planning method.
Background
Along with the development of science and technology, the development and application of various types of robots are increasingly mature; the unmanned aerial vehicle is widely applied to the fields of agriculture and forestry, geographic information systems, geological survey, disaster relief, military and the like. The unmanned aerial vehicle for agriculture and forestry in China is widely applied, and the unmanned aerial vehicle can not meet obstacles such as trees, telegraph poles, shoals, houses and the like when in field operation, so that the unmanned aerial vehicle can not reach a preset place, and further the production purpose of agriculture and forestry can not be achieved.
Aiming at the problems, a plurality of scientific researchers research a plurality of path planning and obstacle avoidance algorithms, so that the unmanned aerial vehicle can efficiently operate in the agriculture and forestry fields, and meanwhile, the safety of the unmanned aerial vehicle in the operation process is ensured. For example: yue Gaofeng et al propose a bi-directional smoothing A-star algorithm in its published "bi-directional smoothing A-star algorithm for mobile robot navigation planning" (China science: technical science, 2021, 51 (04): 459-468), which can reduce path length and computation time and increase safety distance; zhang et al extract a three-dimensional artificial potential field method based on a pilot following method from "Fixed-Wing UAV Formation Control Design With Collision Avoidance Based on an Improved Artificial Potential Field" (IEEE Access,2018, 6:78342-78351) published by Zhang et al, and solve the problem that an unmanned aerial vehicle falls into a limit value in the obstacle avoidance process.
In the method, although an A-star algorithm and/or an artificial potential field method are adopted to carry out path planning and obstacle avoidance on the unmanned aerial vehicle, and meanwhile, the obstacle avoidance on the artificial potential field method is greatly improved; however, when unmanned aerial vehicles perform field operations of agriculture and forestry, obstacles difficult to avoid by an artificial potential field method are encountered in some cases, for example: when the unmanned plane, the robot and the obstacle are on the same straight line, the resultant force of the unmanned plane at a certain special position is zero, so that the unmanned plane can stop in situ or shake violently; when the distance between the obstacle and the target point is too close, the repulsive force of the obstacle can be larger than the attractive force of the target point at a certain position of the repulsive force of the obstacle, so that the unmanned aerial vehicle oscillates or stops back and forth near the target point, and the problem that the target point cannot be reached is generated; when the obstacle is too large or the obstacle is complex, the unmanned aerial vehicle may shake and cannot reach the target point. In the above cases, the unmanned aerial vehicle may fail to avoid the obstacle accurately, so that the unmanned aerial vehicle may be damaged, the target point may not be reached, or the planned quality may be reduced (i.e., the planned path length is increased, the unmanned aerial vehicle energy consumption is increased, the planned path security is low, etc.), etc.; in addition, large or complex obstacles can promote the calculation complexity of the A-star algorithm in the three-dimensional space, so that the problems of huge calculation amount, low planning efficiency and long planning time of path planning are caused.
Disclosure of Invention
Aiming at the problems in the prior art, the application aims to provide an intelligent agricultural unmanned aerial vehicle path planning method for solving the problems in the prior art.
The aim of the application is achieved by the following technical scheme:
the intelligent agricultural unmanned aerial vehicle path planning method specifically comprises the following steps:
firstly, taking the current position of the unmanned aerial vehicle as a starting point, taking the position of a target point as a terminal point, adding an artificial potential field for an obstacle and the target point between the starting point and the terminal point, and simulating the running track of the unmanned aerial vehicle from the starting point to the terminal point through an artificial potential field method;
then, judging whether the unmanned aerial vehicle reaches a target point: if the target point is reached, path planning is completed;
if the target point is not reached, detecting in the detection area, and judging whether the resultant force is zero or the oscillation condition occurs in the unmanned aerial vehicle flight process: if the result is not generated (the resultant force is zero or the vibration condition), judging whether the unmanned aerial vehicle reaches the target point again, and if the cycle is not jumped out of the cycle for a plurality of times, outputting an alarm instruction;
if the situation occurs (the resultant force is zero or the vibration situation), the node where the current unmanned plane is located is taken as an initial node, the first node of the half plane in the flying direction after the obstacle is avoided is taken as a termination node, and the map in the detection area is rasterized; presetting screening conditions, and obtaining alternative nodes meeting the screening conditions through a jump point searching algorithm;
and finally, optimizing the starting point, the target point and the alternative nodes by adopting an A-star algorithm, screening the optimal alternative node (namely the jump point), and completing the mobile path planning of the unmanned aerial vehicle.
As a preferable scheme of the application, the specific steps of adding artificial potential fields for the obstacle and the target point between the starting point and the end point are as follows:
first, construct a gravitational potential field function：
；
Wherein:representing gravitational coefficient, ++>Indicating the position of the drone (i.e. the starting point,) in +.>Indicating the location of the target point (i.e., endpoint); />Representing the distance between the drone (i.e., start point) and the target point (i.e., end point);
representing gravitational potential field factors: when->When (I)>A potential field with the target point as the center and the size inversely proportional to the distance; when->When (I)>Is parabolic-like in function shape;
negative gradient of the gravitation potential field function +.>The method comprises the following steps:
；
the attraction potential field generates attraction to the unmanned aerial vehicle, and under the action of the attraction, the unmanned aerial vehicle goes to a target point (namely an endpoint);
construction of repulsive potential field function：
；
Wherein:representing the repulsive force coefficient, +.>Representing the distance between the drone (i.e., the origin) and the obstacle;the repulsive force radiation radius of the obstacle is represented and is obtained by judging the specific obstacle;
negative gradient of repulsive potential field function>The method comprises the following steps:
；
when the unmanned aerial vehicle is in the influence radius of the obstacle, the repulsive force potential field generates repulsive force to the unmanned aerial vehicle, so that the unmanned aerial vehicle is far away from the obstacle.
As a preferable scheme of the application, the specific steps for judging whether the resultant force is zero or the vibration condition occurs in the unmanned aerial vehicle flight process are as follows:
first, an R5DOS model of the unmanned aerial vehicle is defined:
；
wherein: a represents an unmanned aerial vehicle body area, B represents a detection area of the unmanned aerial vehicle, and C represents an obstacle;respectively indicate->Is formed inside of (a); />Respectively indicate->Is outside of (a);
wherein five planes are inserted in the whole space, expressed as:
，/>the whole space is divided into 16 areas, and s1NE, s2NE, s1EN, s2EN, s3WN, s4WN, s3NW, s4NW, s5ES, s6ES, s5SE, s6SE, s7SW, s8SW, s7WS and s8WS are respectively used for representing the north east area of the first hanging limit, the north east area of the second hanging limit, the northwest area of the third hanging limit, the northwest area of the fourth hanging limit, the southeast area of the fifth hanging limit, the southeast area of the sixth hanging limit, the southeast area of the seventh hanging limit, the southeast area of the eighth hanging limit, the southeast area of the seventh hanging limit and the southeast area of the eighth hanging limit;
the respective hanging limits within the DOS layer are defined as:
；
wherein:representing the value distribution in the spatial coordinate system in the corresponding hanging limit, < >>Representing the angular distribution in the space coordinate system in the corresponding hanging limit;
meanwhile, for the DOS layer, it is defined as:
；
wherein: DOS is any hanging limit of s1NE, s2NE, s1EN, s2EN, s3WN, s4WN, s3NW, s4NW, s5ES, s6ES, s5SE, s6SE, s7SW, s8SW, s7WS and s8 WS;
in the constructed artificial potential field, the resultant force F of attraction force and repulsion force is as follows:
；
when (when)Or the obstacle appears in four or more than four hemispherical DOS layers in the flight direction of the unmanned aerial vehicle, namely +.>When the unmanned plane is in flight, judging that the resultant force is zero or the situation of oscillation occurs; otherwise, this does not occur.
As a preferable scheme of the application, the unmanned aerial vehicle does not have the situation of zero resultant force or oscillation and does not reach the target point for at least 3 times, and after an alarm instruction is output, the system is overhauled manually immediately, and the error result and reason are stored.
As a preferred scheme of the application, the specific steps of the map rasterizing and screening candidate nodes are as follows:
firstly, dividing a movable space of the unmanned aerial vehicle into 16 areas through a constructed R5DOS model, and establishing eight cube areas by taking eight hanging limits in the space as main points; all vertexes of the unmanned aerial vehicle and other adjacent hanging limits are used as adjacent nodes of the current node, namely searching nodes of the next time, so that 26 searching nodes in the grid map are obtained;
then, the vertexes in the grid map are used as searching nodes, and obstacle areas are marked for useA representation; defining that the barrier grid value is 1, the common grid value is 0, and the connecting line between the unmanned aerial vehicle and the target point is +.>；
Obtaining an evaluation function for each search node：
；
Representing a square area connected with the three-dimensional grid search node;
thereafter, a screening condition is set:
a、is defined by a plurality of search nodes;
b、；
wherein n represents an obstacle node,；/>representing obstacle nodes and->Is a distance of (2);
representing search nodes beside obstacle nodes, i.e. condition b being the distance required to find the movement of the drone beside the obstacle nodesThe shortest searching node;
all search nodes in the grid map are searched, and when the screening conditions a and b are simultaneously met, the search nodes are regarded as alternative nodes, namely jump points.
As a preferred scheme of the application, the specific steps for completing path planning by adopting the A-star algorithm are as follows:
constructing a cost function to search path nodes, wherein the cost functionThe method comprises the following steps:
；
wherein:an estimated cost function representing the shortest path between the n-th candidate node to the target node,/->A movement cost function representing the shortest path between the starting point to the n-th candidate node;
calculating the movement cost between two nodes through Euclidean distance, wherein the function expression is as follows:
；
wherein:、/>respectively represent the first node->Second node->Is defined by the coordinates of (a).
The following technical effects are provided by the technical scheme:
according to the scheme, firstly, an unmanned aerial vehicle is taken as a center, a repulsive force row function is given to an obstacle detected by the unmanned aerial vehicle, and a gravitation potential field is given to a target point, when the obstacle is smaller or the situation is simpler, the obstacle avoidance of the unmanned aerial vehicle is directly completed by using an improved artificial potential field method, and the path planning from the starting point of the unmanned aerial vehicle to the target point is realized; when the obstacle detected by the unmanned aerial vehicle is too large or the situation is too complex (such as the unmanned aerial vehicle, the obstacle is on a straight line, the resultant force of the unmanned aerial vehicle at a certain special position is zero, and the unmanned aerial vehicle stops in situ or violently oscillates, the distance between the obstacle and the target point is too close, the repulsive force of the obstacle is larger than the attractive force of the target point at a certain position, the unmanned aerial vehicle oscillates or stops back and forth near the target point, the obstacle is too large, and the unmanned aerial vehicle violent oscillates, and the like), the resultant force of the attractive force and the repulsive force received by the unmanned aerial vehicle is zero, and oscillation is caused, and the three-dimensional grid map is established around the obstacle, namely, the A-star algorithm is improved by introducing a jump point search algorithm, so that path planning is completed, firstly, the problems of unmanned aerial vehicle damage caused by obstacle avoidance failure are effectively improved, secondly, path planning time is shortened, high-efficiency work of the unmanned aerial vehicle is realized, thirdly, the calculated amount and the complexity of the path planning are effectively reduced, and the problem of local optimum caused by the artificial potential field method is avoided.
The scheme of the application can generate effective unmanned aerial vehicle running paths, and has the advantages of few access nodes, small path length and short calculation time; in general, the path planning time and the traversing nodes of the unmanned aerial vehicle can be effectively reduced, the unmanned aerial vehicle is prevented from sinking into local optimum, and the accuracy and instantaneity of operation control are improved.
Drawings
Fig. 1 is a flowchart of a path planning method according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of defining 16 regions of the DOS layer according to an embodiment of the present application.
FIG. 3 is a schematic diagram of two situations in which an obstacle cannot be avoided by using an artificial potential field method; fig. 3 (a) is a schematic diagram of the situation where the resultant force is zero, and fig. 3 (b) is a schematic diagram of the situation where the obstacle is too large; c1 represents a first obstacle, C2 represents a second obstacle, C3 represents a third obstacle, M1 represents a first target point, M2 represents a second target point; UAV represents an unmanned aerial vehicle.
Fig. 4 is a distribution diagram of 26 search nodes in a spatial region obtained in an embodiment of the present application.
Fig. 5 is a schematic diagram of a jump point search in a grid map according to an embodiment of the present application.
FIG. 6 is a schematic diagram of a path-finding simulation using path planning in an embodiment of the present application, where RAPA is the path planning of the present application and AS is the path planning using a conventional A-star algorithm.
Detailed Description
The technical solutions of the embodiments of the present application will be clearly and completely described below in conjunction with the detailed description, and it is apparent that the described embodiments are only some embodiments of the present application, not all embodiments.
Example 1:
as shown in fig. 1: the intelligent agricultural unmanned aerial vehicle path planning method specifically comprises the following steps:
firstly, taking the current position of the unmanned aerial vehicle as a starting point and the position of a target point as a terminal point, adding an artificial potential field for an obstacle and the target point between the starting point and the terminal point, as shown in fig. 3:
construction of the gravitation potential field function：
；
Wherein:representing gravitational coefficient, ++>Indicating the position of the drone (i.e. the starting point,) in +.>Indicating the location of the target point (i.e., endpoint); />Representing the distance between the drone (i.e., start point) and the target point (i.e., end point);
representing gravitational potential field factors: when->When (I)>A potential field with the target point as the center and the size inversely proportional to the distance; when->When (I)>Is parabolic-like in function shape;
negative gradient of the gravitation potential field function +.>The method comprises the following steps:
；
the attraction potential field generates attraction to the unmanned aerial vehicle, and under the action of the attraction, the unmanned aerial vehicle goes to a target point (namely an endpoint);
construction of repulsive potential field function：
；
Wherein:representing the repulsive force coefficient, +.>Representing the distance between the drone (i.e., the origin) and the obstacle;the repulsive force radiation radius of the obstacle is represented and is obtained by judging the specific obstacle;
negative gradient of repulsive potential field function>The method comprises the following steps:
；
when the unmanned aerial vehicle is in the influence radius of the obstacle, the repulsive force potential field generates repulsive force to the unmanned aerial vehicle, so that the unmanned aerial vehicle is far away from the obstacle.
Simulating a running track from a starting point to an end point of the unmanned aerial vehicle through a manual potential field method;
then, judging whether the unmanned aerial vehicle reaches a target point: if the target point is reached, path planning is completed;
if the target point is not reached, detecting in the detection area, and judging whether the resultant force is zero or the vibration condition occurs in the unmanned aerial vehicle flight process, wherein the judging method specifically comprises the following steps:
defining an R5DOS model of the unmanned aerial vehicle:
；
wherein: a represents an unmanned aerial vehicle body area, B represents a detection area of the unmanned aerial vehicle, and C represents an obstacle;respectively indicate->Is formed inside of (a); />Respectively indicate->Is outside of (a);
wherein five planes are inserted in the whole space, expressed as:
，/>the whole space is divided into 16 areas (as shown in fig. 2), and s1NE, s2NE, s1EN, s2EN, s3WN, s4WN, s3NW, s4NW, s5ES, s6ES, s5SE, s6SE, s7SW, s8SW, s7WS, s8WS represent north east area of the first hanging limit, north east area of the second hanging limit, north east area of the first hanging limit, north west area of the second hanging limit, north west area of the third hanging limit, south east area of the fourth hanging limit, south east area of the fifth hanging limit, south east area of the sixth hanging limit, south west area of the seventh hanging limit, south west area of the eighth hanging limit, south west area of the seventh hanging limit, and west area of the eighth hanging limit are adopted respectively;
the respective hanging limits within the DOS layer are defined as:
；
wherein:representing the value distribution in the spatial coordinate system in the corresponding hanging limit, < >>Representing the angular distribution in the space coordinate system in the corresponding hanging limit;
meanwhile, for the DOS layer, it is defined as:
；
wherein: DOS is any hanging limit of s1NE, s2NE, s1EN, s2EN, s3WN, s4WN, s3NW, s4NW, s5ES, s6ES, s5SE, s6SE, s7SW, s8SW, s7WS and s8 WS;
in the constructed artificial potential field, the resultant force F of attraction force and repulsion force is as follows:
；
when (when)Or the four or more hemispherical DOS layers in the flight direction of the unmanned aerial vehicle have no obstacle, namely +.>And judging that the resultant force is zero or the condition of oscillation does not occur in the flight process of the unmanned plane at the moment: judging whether the unmanned aerial vehicle reaches a target point again, and outputting an alarm instruction if the unmanned aerial vehicle does not jump out of the cycle for 3 times; and after the alarm instruction is output, the system is overhauled manually immediately, and the error result and the cause (the error instruction is collected and used as a subsequent reference) are stored.
When (when)Or the obstacle appears in four or more than four hemispherical DOS layers in the flight direction of the unmanned aerial vehicle, namely +.>And when the unmanned aerial vehicle is in flight, judging that the resultant force is zero or the situation of oscillation occurs: taking the node where the current unmanned plane is located as an initial node, and avoiding the flying direction after the obstacleIs (i.e.)>) The first node of (a) is a termination node, and the map in the detection area is rasterized; presetting screening conditions, and obtaining alternative nodes meeting the screening conditions through a jump point searching algorithm; the method comprises the following steps:
firstly, through the constructed R5DOS model, as shown in fig. 4, a movable space of the unmanned aerial vehicle is divided into 16 areas, and eight cube areas are established by taking eight hanging limits in the space as main points; all vertexes of the unmanned aerial vehicle and other adjacent hanging limits are used as adjacent nodes of the current node, namely searching nodes of the next time, so that 26 searching nodes in the grid map are obtained;
in the process of searching once, 26 searching nodes are required to be accessed, so that the calculation difficulty and calculation time are greatly increased, and the real-time performance of judgment and the efficiency of path planning are reduced; therefore, after 26 search nodes are obtained, the jump point screening is carried out on the 26 search nodes; the method comprises the following steps:
as shown in fig. 5: vertices (e.g., parent nodes) in the grid map) As search node and mark obstacle region, with +.>A representation; defining that the barrier grid value is 1, the common grid value is 0, and the connecting line between the unmanned aerial vehicle and the target point is；
Obtaining an evaluation function for each search node：
；
Representing a square area connected with the three-dimensional grid search node; as described above, the three-dimensional space region includes eight hanging limits in total, i.e., a region around a node where an obstacle may exist is 8 at most, and thus, inside the obstacle, there is a +.>Belonging to [0,8 ]]；
Thereafter, a screening condition is set:
a、is defined by a plurality of search nodes;
b、；
wherein n represents an obstacle node,；/>representing obstacle nodes and->Distance (of the link between the drone and the target point);
representing a search node beside the obstacle node, a point with a larger diameter as shown in fig. 5, namely, a search node with the shortest distance required for searching the unmanned aerial vehicle to move beside the obstacle node is provided with a condition b;
all search nodes in the grid map are searched, and when the screening conditions a and b are simultaneously met, the search nodes are regarded as alternative nodes, namely jump points.
Through the screening, when barriers exist around the searching nodes, the special nodes are screened out and used as jumping points, and other searching nodes are ignored as unnecessary nodes;
finally, optimizing the starting point, the target point and the alternative nodes by adopting an A-star algorithm, screening the optimal alternative node (namely the jump point), and completing the mobile path planning of the unmanned aerial vehicle, wherein the method specifically comprises the following steps:
constructing a cost function to search path nodes, wherein the cost functionThe method comprises the following steps:
；
wherein:an estimated cost function representing the shortest path between the n-th candidate node to the target node,/->A movement cost function (which may be calculated by the following euclidean distance formula) representing the shortest path between the starting point to the n-th candidate node;
calculating the movement cost between two nodes through Euclidean distance, wherein the function expression is as follows:
；
wherein:、/>respectively represent the first node->Second node->Is defined by the coordinates of (a).
Based on the path planning algorithm, a simulation environment is created in MATLAB2022a, wherein the simulation experiment is performed in a computer with a CPU of Intel (R) Core (TM) i7-8750H CPU @ 2.20GHz 2.21 GHz and a GPU of NVIDIA GTX 1060 Max-Q6 GB, the simulation environment is performed in a map with a length of 200m, a width of 200m and a height of 40m, the method is respectively compared with the path planning of the traditional A-star algorithm, and meanwhile, the method is simulated under the general condition and the special condition (the special condition is the condition that a large obstacle exists and the unmanned aerial vehicle is caused to vibrate), and the following is needed to be explained: the simulation experiments were all performed 50 times, the simulation results were averaged, the simulation diagram is shown in fig. 6, and the simulation results are shown in table 1 below:
table 1, simulation test results:
as can be seen from the above table 1 and fig. 6 of the drawings of the specification:
the method can effectively avoid the obstacle and reach the target point, and can effectively avoid the obstacle when encountering a large obstacle or when the resultant force is zero, and has timeliness, safety and accuracy; meanwhile, compared with an A-star algorithm of a three-dimensional space, the method has the advantages of less path length, less planning time and less access nodes, and has faster average speed and shorter time consumption;
as can be obtained from table 1 above, the present application reduces the planning time by 97.74% (general case), 95.47% (special case), 15.24% (general case), 14.28% (special case), and 99.69% (general case), 99.53% (special case) for the a-star, respectively, and the path length, respectively.
Example 2:
in the above embodiment 1, the detection of the obstacle (i.e. the size, height, etc. of the obstacle) may be implemented by a camera provided on the unmanned aerial vehicle, using an existing imaging method, as will be understood by those skilled in the art.

Claims (2)

1. An intelligent agricultural unmanned aerial vehicle path planning method is characterized in that: the method specifically comprises the following steps:
firstly, taking the current position of the unmanned aerial vehicle as a starting point, taking the position of a target point as a terminal point, adding an artificial potential field for an obstacle and the target point between the starting point and the terminal point, and simulating the running track of the unmanned aerial vehicle from the starting point to the terminal point through an artificial potential field method;
the artificial potential field is added specifically as follows:
first, construct a gravitational potential field function：
；
Wherein:representing gravitational coefficient, ++>Indicating the location of the unmanned aerial vehicle, +.>Representing the position of the target point; />Representing a distance between the unmanned aerial vehicle and the target point;
representing gravitational potential field factors: when->When (I)>Is a potential field with the target point as the center and the magnitude inversely proportional to the distanceThe method comprises the steps of carrying out a first treatment on the surface of the When->When (I)>Is parabolic-like in function shape;
negative gradient of the gravitation potential field function +.>The method comprises the following steps:
；
the attraction potential field generates attraction to the unmanned aerial vehicle, and the unmanned aerial vehicle goes to a target point under the action of the attraction;
construction of repulsive potential field function：
；
Wherein:representing the repulsive force coefficient, +.>Representing a distance between the unmanned aerial vehicle and the obstacle; />The repulsive force radiation radius of the obstacle is represented and is obtained by judging the specific obstacle;
negative gradient of repulsive potential field function>The method comprises the following steps:
；
when the unmanned aerial vehicle is within the influence radius of the obstacle, the repulsive force potential field generates repulsive force to the unmanned aerial vehicle, so that the unmanned aerial vehicle is far away from the obstacle;
then, judging whether the unmanned aerial vehicle reaches a target point: if the target point is reached, path planning is completed;
if the target point is not reached, detecting in the detection area, and judging whether the resultant force is zero or the oscillation condition occurs in the unmanned aerial vehicle flight process: if the circulation is not performed, judging whether the unmanned aerial vehicle reaches the target point again, and if the circulation is not performed for a plurality of times, outputting an alarm instruction;
judging whether the resultant force is zero or the vibration condition occurs in the flight process of the unmanned aerial vehicle specifically comprises the following steps:
first, an R5DOS model of the unmanned aerial vehicle is defined:
；
wherein: a represents an unmanned aerial vehicle body area, B represents a detection area of the unmanned aerial vehicle, and C represents an obstacle;respectively indicate->Is formed inside of (a); />Respectively indicate->Is outside of (a);
wherein five planes, respectively denoted as，The whole space is divided into 16 areas respectivelys1NE、s2NE、s1EN、s2EN、s3WN、s4WN、s3NW、s4NW、s5ES、s6ES、s5SE、s6SE、s7SW、s8SW、s7WS、 s8WSThe north east region representing the first ceiling, the north east region representing the second ceiling, the north west region representing the third ceiling, the north west region representing the fourth ceiling, the south east region representing the fifth ceiling, the south east region representing the sixth ceiling, the south west region representing the fifth ceiling, the south west region representing the seventh ceiling, the south west region representing the eighth ceiling, the southwest region representing the seventh ceiling, the southwest region representing the eighth ceiling;
the respective hanging limits within the DOS layer are defined as:
；
wherein:representing the value distribution in the spatial coordinate system in the corresponding hanging limit, < >>Representing the angular distribution in the space coordinate system in the corresponding hanging limit;
meanwhile, for the DOS layer, it is defined as:；
wherein: DOS iss1NE、s2NE、s1EN、s2EN、s3WN、s4WN、s3NW、s4NW、s5ES、s6ES、s5SE、s6SE、 s7SW、s8SW、s7WS、s8WSAny hanging limit;
in the constructed artificial potential field, the resultant force of attraction force and repulsion forceFThe method comprises the following steps:
；
when (when)Or the four or more hemispherical DOS layers in the flight direction of the unmanned aerial vehicle are provided with barriers, namelyWhen the unmanned plane is in flight, judging that the resultant force is zero or the situation of oscillation occurs; otherwise, the method does not appear;
if the situation occurs, the node where the current unmanned plane is located is taken as an initial node, the first node of the half plane in the flying direction after avoiding the obstacle is taken as a termination node, and the map in the detection area is rasterized; presetting screening conditions, and obtaining alternative nodes meeting the screening conditions through a jump point searching algorithm; the method comprises the following steps:
firstly, dividing a movable space of the unmanned aerial vehicle into 16 areas through a constructed R5DOS model, and establishing eight cube areas by taking eight diagrams in the space as main points; all vertexes of the unmanned aerial vehicle and other adjacent trigrams are used as adjacent nodes of the current node, namely searching nodes of the next time, so that 26 searching nodes in the grid map are obtained;
then, the vertexes in the grid map are used as searching nodes, and obstacle areas are marked for useA representation; defining that the barrier grid value is 1, the common grid value is 0, and the connecting line between the unmanned aerial vehicle and the target point is +.>；
Obtaining an estimation function for each node：
；
Representing square areas where three-dimensional grid nodes are connected;
thereafter, a screening condition is set:
a、is defined by the network, is a node of the network;
b、；
wherein n represents an obstacle node,；/>representing obstacle nodes and->Is a distance of (2); />Representing nodes next to the obstacle node;
searching all search nodes in the grid map, and when the screening conditions a and b are simultaneously met, taking the nodes as alternative nodes, namely jump points;
and finally, optimizing the starting point, the target point and the alternative nodes by adopting an A-star algorithm, screening the optimal alternative node and completing the mobile path planning of the unmanned aerial vehicle.
2. The intelligent agricultural unmanned aerial vehicle path planning method of claim 1, wherein: the specific steps for completing path planning by adopting the A-star algorithm are as follows:
constructing a cost function to search path nodes, wherein the cost functionThe method comprises the following steps:
；
wherein:represent the firstnEstimated cost function of shortest path between each candidate node to target node, +.>Representing the starting point to the firstnA movement cost function of the shortest path between the candidate nodes;
calculating the movement cost between two nodes through Euclidean distance, wherein the function expression is as follows:
；
wherein:、/>respectively represent the first node->Second node->Is defined by the coordinates of (a).
CN202310913709.XA 2023-07-25 2023-07-25 Intelligent agricultural unmanned aerial vehicle path planning method Active CN116661502B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310913709.XA CN116661502B (en) 2023-07-25 2023-07-25 Intelligent agricultural unmanned aerial vehicle path planning method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310913709.XA CN116661502B (en) 2023-07-25 2023-07-25 Intelligent agricultural unmanned aerial vehicle path planning method

Publications (2)

Publication Number Publication Date
CN116661502A CN116661502A (en) 2023-08-29
CN116661502B true CN116661502B (en) 2023-10-10

Family

ID=87717353

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310913709.XA Active CN116661502B (en) 2023-07-25 2023-07-25 Intelligent agricultural unmanned aerial vehicle path planning method

Country Status (1)

Country Link
CN (1) CN116661502B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111781948A (en) * 2020-06-18 2020-10-16 南京非空航空科技有限公司 Unmanned aerial vehicle formation shape transformation and online dynamic obstacle avoidance method
CN114047767A (en) * 2021-11-24 2022-02-15 山东建筑大学 Robot jumping point searching algorithm based on artificial potential field method
CN116400679A (en) * 2023-02-25 2023-07-07 吉林大学 Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method
CN219330029U (en) * 2022-09-27 2023-07-14 吉林农业大学 Fruit tree fertilization robot

Family Cites Families (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11231715B2 (en) * 2018-05-22 2022-01-25 King Fahd University Of Petroleum And Minerals Method and system for controlling a vehicle

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111781948A (en) * 2020-06-18 2020-10-16 南京非空航空科技有限公司 Unmanned aerial vehicle formation shape transformation and online dynamic obstacle avoidance method
CN114047767A (en) * 2021-11-24 2022-02-15 山东建筑大学 Robot jumping point searching algorithm based on artificial potential field method
CN219330029U (en) * 2022-09-27 2023-07-14 吉林农业大学 Fruit tree fertilization robot
CN116400679A (en) * 2023-02-25 2023-07-07 吉林大学 Ship formation algorithm combining rapid travel leveling method and virtual obstacle potential field method

Non-Patent Citations (9)

* Cited by examiner, † Cited by third party
Title
A real-time local path planning algorithm for the wave glider based on time-stamped collision detection and improved artificial potential field.Ocean Engineering.2023,1-23. *
Jian Li ,等.UAV Path Planning Model Based on R5DOS Model Improved A-Star Algorithm.applied sciences.2022,1-15. *
Jian Li,等.Leader-Follower UAV FormationModel Based on R5DOS-Intersection Model.Computers,Materials & Continua.2021,第69卷(第2期),2493-2511. *
Jian Li,等.Representation and Reasoning of Three-Dimensional Spatial Relationships Based on R5DOS-Intersection Model Representation and Reasoning Based on R5DOS Model.Complexity.2020,1-15. *
RJA-Star Algorithm for UAV Path Planning Based on Improved R5DOS Model;Jian Li，等;Applied Sciences;1-16 *
Uav Path Planning Based on Improved Artificial Potential Field Method;Yuhong Sun，等;2022 International Conference on Computer Network, Electronic and Automation;95-100 *
基于改进A*和Lattice算法的自动驾驶汽车路径规划研究;任书宇，吴钦木，周还籍;计算机与数字工程;第51卷(第2期);342-347 *
基于改进跳点搜索法的移动机器人路径规划;侯宇翔，等;组合机床与自动化加工技术(第3期);54-58 *
机械臂关节空间B 样条曲线轨迹规划;王幼民;安徽机电学院学报;第15卷(第2期);21-26 *

Also Published As

Publication number Publication date
CN116661502A (en) 2023-08-29

Similar Documents

Publication Publication Date Title
CN109916393B (en) Multi-grid-value navigation method based on robot pose and application thereof
CN112179351B (en) Three-dimensional obstacle avoidance track planning method based on pre-planned path optimization RRT algorithm
Xuexi et al. SLAM algorithm analysis of mobile robot based on lidar
CN106017472B (en) Global route planning method, global route planning system and unmanned plane
Yaoming et al. A newly bio-inspired path planning algorithm for autonomous obstacle avoidance of UAV
CN105865449A (en) Laser and vision-based hybrid location method for mobile robot
CN108958282A (en) Three-dimensional path planing method based on dynamic spherical window
Stojkoska et al. Indoor localization of unmanned aerial vehicles based on RSSI
CN104406589B (en) Flight method of aircraft passing through radar area
CN112947594B (en) Unmanned aerial vehicle-oriented track planning method
CN114296474A (en) Unmanned aerial vehicle path planning method and system based on path time cost
Liu et al. A variable-step RRT* path planning algorithm for quadrotors in below-canopy
Yuan et al. Improved lazy theta∗ algorithm based on octree map for path planning of UAV
Liu et al. Application of dijkstra algorithm in path planning for geomagnetic navigation
CN117406771B (en) Efficient autonomous exploration method, system and equipment based on four-rotor unmanned aerial vehicle
Wu et al. A Non-rigid hierarchical discrete grid structure and its application to UAVs conflict detection and path planning
Ma et al. Volcanic ash region path planning based on improved A-star algorithm
CN116661502B (en) Intelligent agricultural unmanned aerial vehicle path planning method
Han et al. Research on UAV indoor path planning algorithm based on global subdivision grids
CN107843261A (en) A kind of method and system based on laser scanning data positioning robot position
CN112015199A (en) Flight path planning method and device applied to underground coal mine intelligent inspection unmanned aerial vehicle
Chen et al. Real-time active detection of targets and path planning using UAVs
CN115686064A (en) Air-drop aircraft path planning method and system based on improved A-star algorithm
Qiu et al. Improved F‐RRT∗ Algorithm for Flight‐Path Optimization in Hazardous Weather
CN114879716A (en) Law enforcement unmanned aerial vehicle path planning method for countering low-altitude airspace aircraft

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