CN113190017A - Harvesting robot operation path planning method based on improved ant colony algorithm - Google Patents

Harvesting robot operation path planning method based on improved ant colony algorithm Download PDF

Info

Publication number
CN113190017A
CN113190017A CN202110562995.0A CN202110562995A CN113190017A CN 113190017 A CN113190017 A CN 113190017A CN 202110562995 A CN202110562995 A CN 202110562995A CN 113190017 A CN113190017 A CN 113190017A
Authority
CN
China
Prior art keywords
path
distance
line
harvester
farmland
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.)
Granted
Application number
CN202110562995.0A
Other languages
Chinese (zh)
Other versions
CN113190017B (en
Inventor
王立辉
刘明杰
祝文星
任元
许宁徽
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.)
Southeast University
Original Assignee
Southeast 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 Southeast University filed Critical Southeast University
Priority to CN202110562995.0A priority Critical patent/CN113190017B/en
Publication of CN113190017A publication Critical patent/CN113190017A/en
Application granted granted Critical
Publication of CN113190017B publication Critical patent/CN113190017B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0221—Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving a learning process
    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02—Control of position or course in two dimensions
    • G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0276—Control of position or course in two dimensions specially adapted to land vehicles using signals provided by a source external to the vehicle

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 invention discloses a harvesting robot operation path planning method based on an improved ant colony algorithm, which comprises the following steps: 1. establishing a mathematical model of the trapezoid farmland, and determining the optimal operation direction under the conditions of the minimum turning times and the maximum vertical degree of an operation line and a boundary; 2. abstracting farmland full-coverage path planning into a Vehicle Route Problem (VRP), and establishing a corresponding VRP model according to different grain unloading position distribution; 3. designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint condition; 4. and solving the expression of each path according to the traversal sequence of the operation lines and the farmland model to generate a farmland full-coverage path and provide reference for path tracking of the harvester. The method can design a farmland full-coverage path with the minimum full-load driving distance according to different grain unloading position distribution conditions.

Description

Harvesting robot operation path planning method based on improved ant colony algorithm
Technical Field
The invention belongs to the field of intelligent harvester operation path planning, and particularly relates to a harvester robot operation path planning method based on an improved ant colony algorithm, in particular to a method for designing a full-coverage path by utilizing the improved ant colony algorithm according to the grain bin capacity of a harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint conditions.
Background
The farmland full-coverage path planning is a key technology for realizing the autonomous operation of the harvester, can provide a reasonable path for the field operation of the harvester, effectively improves the problems of repeated operation and missed operation, and improves the operation efficiency of the harvester. At present, no mature and universal method exists in the field full-coverage path planning aspect. In practical application, there are two main ways for planning a full-coverage path of a farmland: one is that the driver stipulates an initial operation path and realizes the full coverage of the farmland by continuously translating the operation path; the other is to operate in a shuttle or spiral manner in a specific field environment, such as a rectangular field. The two path planning modes have lower intelligent degree, adaptability to different farmlands and operation efficiency. Therefore, a work path planning method needs to be studied.
By analyzing the current research situation at home and abroad of the full coverage path planning algorithm, the optimal operation path is designed by taking the driving distance, the effective operation area ratio, the operation time, the energy consumption and the like as optimization targets and utilizing optimization algorithms such as a greedy algorithm, an ant colony algorithm and the like. The full-load running distance and the grain unloading position distribution have great influence on the planning of the operation path of the agricultural machinery, and the specific research is relatively less when the two factors are comprehensively considered. Therefore, when performing full coverage path planning, the following two factors need to be considered: the large harvester has heavy weight and large rolling compaction on the land, and the running distance of the full-load harvester in the field is required to be reduced; in actual operation, an intermittent grain unloading mode exists, a grain transporting vehicle cannot enter a field and only can stop at the edge of the field, the position distribution of grain unloading points needs to be fully considered, and different covering paths are designed independently.
Disclosure of Invention
Aiming at the problems of low effectiveness and weak universality of autonomous path planning of a harvester, the invention provides a harvesting robot operation path planning method based on an improved ant colony algorithm, a farmland model is established, a distance model of an operation line and a grain unloading position is established according to distribution conditions of five grain unloading positions, the grain bin capacity, the total travel distance and the full load travel distance of the harvester are taken as constraint conditions, the operation line traversal sequence is solved by utilizing the improved ant colony algorithm, an operation path is planned, the rolling degree of the land is reduced, and the adaptability of the path planning algorithm to different grain unloading position distributions is improved.
The invention provides a harvesting robot operation path planning method based on an improved ant colony algorithm, which is characterized by comprising the following steps of:
step 1, establishing a farmland model;
setting four vertexes of the farmland as A, B, C and D, knowing coordinates of the four points, respectively solving mathematical expressions of boundaries to complete preliminary modeling of the farmland, determining an operation direction under the conditions that the number of turns is minimum and the vertical degree of an operation line and the boundaries is maximum, and respectively taking edges and diagonal lines of a quadrangle as the operation direction to solve the number of turns required by each of the four vertexes;
when the AD is taken as the operation direction, the cutting width of the harvester is set as lcut_widthA series of parallel lines is then represented as
Figure BDA0003079717050000021
Wherein k isADIs the slope of the AD side, bADThe intercept is AD edge intercept, i is the serial number of the operation line;
respectively solving the intersection points of the group of parallel lines and the quadrilateral boundary, if two intersection points exist, adding one to the turn times until no intersection point exists, and keeping the current turn times as the result of the operation direction;
similarly, respectively using AB, BC, CD, AC and BD as operation directions, solving corresponding turning times, wherein the operation direction with the minimum turning times is obtained by comparison, if a plurality of groups of operation directions all meet the requirement of the minimum turning times, comparing the included angle between the operation direction and the boundary, selecting the operation direction with the included angle close to 90 degrees because the turning complexity and the turning distance are smaller under the vertical condition, and finally solving to obtain the mathematical expression of each operation line so as to perfect the farmland model;
step 2, abstracting the farmland full-coverage path planning into a vehicle route problem, and establishing a corresponding VRP model according to different grain unloading position distribution;
step 3, designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint condition;
and 4, solving the expression of each path according to the traversal sequence of the operation lines and the farmland model to generate a farmland full-coverage path and provide reference for path tracking of the harvester.
Further, the step 2 abstracts the farmland full-coverage path planning into a vehicle route problem, and establishes a corresponding VRP model according to different grain unloading position distributions, comprising the following steps:
(2.1) defining five grain unloading position distribution conditions:
based on intermittent type formula mode of unloading is studied, and the fortune grain car can not travel in the farmland, need berth at the roadside, divide into following five kinds of condition according to the position and the figure of unloading:
"a": only one grain unloading position S1At the head or tail of the operation line;
"b": only one grain unloading position S1On a side road parallel to the work line;
"c": with two grain unloading positions S1、S2Respectively at the head and tail of the operation line;
"d": with two grain unloading positions S1、S2On the two side roads parallel to the operation line;
"e": with two grain unloading positions S1、S2One at the head or tail of the line and one on a road parallel to the line;
(2.2) establishing a VRP model:
the farmland full-coverage path planning means that the operation path of the harvester is planned to traverse the whole farmland, each operation line only passes once, the loading capacity of the harvester cannot exceed the capacity of the harvester,when the machine is fully loaded or nearly fully loaded, the machine needs to unload grains at the grain unloading position, and the set of path points is set as E, wherein the set of path points comprises a head end point i of each operation lineupEnd point idownPosition S for unloading grain1、S2Each job row having a length of liAnd grain volume V that can be harvestediTwo attributes, starting from the grain unloading position, traversing each operation line in a certain sequence, and finally returning to the grain unloading position, and setting the capacity of the harvester as VgranaryThe sequence number of the operation line is i, j, wherein i, j belongs to [1, n ]line]Unloading point S1A distance to the head end of the working line of
Figure BDA0003079717050000031
To the tail end of the working line at a distance of
Figure BDA0003079717050000032
Grain unloading point S2A distance to the head end of the working line of
Figure BDA0003079717050000033
To the tail end of the working line at a distance of
Figure BDA0003079717050000034
The turning distance between the working lines is
Figure BDA0003079717050000035
According to the distribution conditions of the five grain unloading positions, a distance model between an operation line and the grain unloading positions is respectively established as follows:
(2.2.1) unloading the harvester at the head of the working line:
Figure BDA0003079717050000036
wherein liIs the length of the ith job row;
(2.2.2) the harvester unloads on the side parallel to the working line:
Figure BDA0003079717050000037
wherein w is the working line width, θupIs the angle between the upper boundary and the line of operation, θdownIs the included angle between the lower boundary and the operation line;
(2.2.3) the harvester can be unloaded at both the head and tail ends of the work line:
Figure BDA0003079717050000038
(2.2.4) the harvester can unload on both sides parallel to the working line:
Figure BDA0003079717050000039
wherein n islineIs the number of operation lines;
(2.2.5) harvester unloading at work line head end and left side:
Figure BDA0003079717050000041
the turning distance between the working lines is
Figure BDA0003079717050000042
Is composed of
Figure BDA0003079717050000043
Wherein S isTTurning distance in T-turn mode, SΩTurning distance in omega-type turning mode, SUThe turning distance of the U-shaped turning mode.
Further, the step 3 is to design an optimal operation row traversal sequence by adopting an improved ant colony algorithm according to the harvester capacity, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint conditions, and specifically comprises the following steps:
(3.1) ant colony algorithm initialization:
setting the ant colony scale as M, the important degree factor of the left pheromone as alpha, the important degree factor of the heuristic function as beta, the pheromone volatilization factor as rho, the total pheromone released by the ant in one iteration as Q, and the maximum iteration number as Imax；
In the first iteration, the initial pheromone content on each path is the same, the ant colony starts from a grain unloading point, a reasonable path is selected according to the pheromone content and the heuristic function of each path, and the heuristic function of each section of path pq is
Figure BDA0003079717050000044
The smaller the distance, the larger the function value;
(3.2) path selection:
calculating the probability that the mth ant transfers from the current point p to the next point q in the nth iteration as
Figure BDA0003079717050000045
Wherein, taupq(n) is the pheromone of path pq in the nth iteration;
selecting the path with the maximum transition probability as a target path, judging whether the capacity constraint is exceeded or not, if so, not adding the point, and continuously searching the next target point; if not, it is added to the current path. Repeating the steps until all the operation lines are traversed, completing one iteration, and recording the path node of each ant
Figure BDA0003079717050000046
And recording the total path length
Figure BDA0003079717050000047
By contrast, the minimum total path length is obtained
Figure BDA0003079717050000048
And corresponding path
Figure BDA0003079717050000049
(3.3) adjusting the route length based on the weight factor:
the accumulation of pheromones has a direct relation with the length of a route, the searching process of an ant colony algorithm is influenced by changing the content of the pheromones by changing the length of the route, in the current path planning algorithm, the total distance of driving is taken as a cost function, a feasible solution for enabling the function to reach the minimum value is obtained by solving through an optimization algorithm, except for considering the total driving distance, a full load distance constraint is added, when an ant passes through an operation line, the grain volume harvested by the ant is updated, the value is associated with the length of the route, the ant is guided to search for the optimization according to the full load distance constraint, and the distance of the route is improved as follows:
Figure BDA0003079717050000051
wherein, lightmassIs a weight factor, VnowFor the grain volume currently harvested, VgranaryIs the volume of the granary, kmWhen ants pass through a certain path with larger weight, the recorded distance of the path is larger than the real distance, so that pheromone of the path is reduced, and the ants are induced to search for a shorter path under the condition of full load;
(3.4) update pheromone:
every time an ant passes a path, it leaves a pheromone on that path. On the next iteration, the pheromone content of path pq is
τpq(n+1)＝(1-ρ)τpq(n)+Δτpq
Wherein (1-rho). taupq(n) pheromones remaining after volatilization, Δ τpqThe pheromones left for all ants passing through this path in this iteration are:
Figure BDA0003079717050000052
wherein, the content of the pheromone left by each ant is as follows:
Figure BDA0003079717050000053
the value is determined by the distance of the path traversed, the shorter the distance, the higher the pheromone content;
(3.5) judging whether to terminate the iteration:
if the ant colony algorithm end condition is met, the path traveled by the iterative ants is the operation line traversal sequence, and the step 4 is carried out;
and if the ant colony algorithm ending condition is not met, enabling the iteration number i to be i +1, and jumping to the step (3.2) to continue to search the next path.
Further, the ant colony algorithm end condition is as follows:
the current iteration number I is more than ImaxOr the optimal solution meets the accuracy requirement:
Figure BDA0003079717050000061
wherein,
Figure BDA0003079717050000062
the shortest path length obtained after the ith iteration is shown, and xi is a preset precision threshold.
Further, in the step 4, according to the traversal order of the operation lines and the farmland model, the expression of each path is solved, a farmland full-coverage path is generated, and a reference is provided for path tracking of the harvester, specifically as follows:
and (3) designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint conditions in the step 3, and linking the operation line expressions obtained by the step 1 by utilizing the traversal sequence to form a path expression covering the whole farmland.
Has the advantages that: compared with the prior art, the harvesting robot operation path planning method based on the improved ant colony algorithm has the following advantages: five grain unloading positions are provided, and a distance model between an operation line and the grain unloading positions is correspondingly established, so that the adaptability of a path planning algorithm to different operation environments is improved; the ant colony algorithm is used for path search, so that the robustness is strong, and the global search capability is stronger; the path length is adjusted by using the weight factor, the ant colony algorithm is improved, the full-load running distance can be reduced, the rolling degree of the harvester on the land is reduced, and the operation efficiency is improved.
Drawings
Fig. 1 is a flowchart of a harvesting robot working path planning method based on an improved ant colony algorithm disclosed by the invention.
Detailed Description
The invention is described in further detail below with reference to the following detailed description and accompanying drawings:
the invention provides a harvesting robot operation path planning method based on an improved ant colony algorithm, which comprises the steps of establishing a farmland model, establishing a distance model between an operation line and a grain unloading position according to distribution conditions of five grain unloading positions, solving an operation line traversing sequence by using the improved ant colony algorithm under the constraint conditions of grain bin capacity, total travel distance and full load travel distance of a harvester, planning an operation path, reducing the grinding degree of the land and improving the adaptability of the path planning algorithm to different grain unloading position distributions.
As shown in fig. 1, the invention discloses a harvesting robot working path planning method based on an improved ant colony algorithm, comprising the following steps:
step 1, establishing a farmland model:
and (3) setting the four vertexes of the farmland as A, B, C and D, knowing the coordinates of the four points, respectively solving the mathematical expressions of the boundary, and completing the preliminary modeling of the farmland. And determining the operation direction under the conditions that the turn times are minimum and the vertical degree of the operation line and the boundary is maximum, and respectively taking the sides and the diagonal lines of the quadrangle as the operation direction to solve the turn times required by each.
When the AD is taken as the operation direction, the cutting width of the harvester is set as lcut_widthThen a series of parallel lines can be represented as
Figure BDA0003079717050000063
Wherein k isADIs the slope of the AD side, bADThe intercept is AD edge intercept, i is the serial number of the operation line;
and respectively solving the intersection points of the group of parallel lines and the quadrilateral boundary, if two intersection points exist, adding one to the turn times until no intersection point exists, and keeping the current turn times as the result of the operation direction.
And similarly, respectively using AB, BC, CD, AC and BD as operation directions to solve corresponding turning times. By comparison, the working direction with the minimum turning frequency is the demand. And if a plurality of groups of operation directions all meet the requirement of minimum turning times, comparing the included angles between the operation directions and the boundary. Because the bending complexity and the bending distance are smaller under the vertical condition, the operation direction with the included angle close to 90 degrees is selected. And finally, solving to obtain a mathematical expression of each operation line, and perfecting the farmland model.
And 2, abstracting the farmland full-coverage path planning into a vehicle route problem, and establishing a corresponding VRP model according to different grain unloading position distribution. The method comprises the following steps:
(2.1) defining the distribution of five grain unloading positions
The invention is researched based on an intermittent grain unloading mode, and the grain transporting vehicle cannot run in the farmland and needs to be parked at the roadside. The following five conditions can be divided according to the positions and the number of grain unloading:
"a": only one grain unloading position S1At the head (or tail) of the job line;
"b": only one grain unloading position S1On a side road parallel to the work line;
"c": with two grain unloading positions S1、S2Respectively at the head and tail of the operation line;
"d": with two grain unloading positionsPut S1、S2On the two side roads parallel to the operation line;
"e": with two grain unloading positions S1、S2One at the head (or tail) of the line and one on a road parallel to the line.
(2.2) establishing a VRP model
The farmland full-coverage path planning means that the operation path of the harvester is planned to traverse the whole farmland, each operation line only passes once, and the loading capacity of the harvester cannot exceed the capacity of the harvester. When the machine is fully loaded or nearly fully loaded, the machine needs to move to a grain unloading position to unload grains. Let E be a set of waypoints including a head point i for each lineupEnd point idownPosition S for unloading grain1、S2. Each job row having a length of liAnd grain volume V that can be harvestediTwo attributes. The harvester starts from the grain unloading position, traverses each operation line in a certain sequence and finally returns to the grain unloading position. Set the capacity of the harvester as VgranaryThe sequence number of the operation line is i, j (i, j is E [1, n ]line]) Unloading point S1A distance to the head end of the working line of
Figure BDA0003079717050000071
To the tail end of the working line at a distance of
Figure BDA0003079717050000072
Grain unloading point S2A distance to the head end of the working line of
Figure BDA0003079717050000073
To the tail end of the working line at a distance of
Figure BDA0003079717050000074
The turning distance between the working lines is
Figure BDA0003079717050000075
According to the distribution conditions of the five grain unloading positions, a distance model between an operation line and the grain unloading positions is respectively established as follows:
(2.2.1) unloading of harvester at head of working line
Figure BDA0003079717050000076
Wherein liIs the length of the ith job row.
(2.2.2) unloading of the harvester on the side parallel to the working line
Figure BDA0003079717050000081
Wherein w is the working line width, θupIs the angle between the upper boundary and the line of operation, θdownIs the angle between the lower boundary and the operation line.
(2.2.3) the harvester can be unloaded at both the head and tail ends of the working line
Figure BDA0003079717050000082
(2.2.4) the harvester can be unloaded on both sides parallel to the working line
Figure BDA0003079717050000083
Wherein n islineIs the number of operation lines.
(2.2.5) harvester unloading at work line head end and left side
Figure BDA0003079717050000084
The turning distance between the working lines is
Figure BDA0003079717050000085
Is composed of
Figure BDA0003079717050000086
Wherein S isTTurning distance in T-turn mode, SΩTurning distance in omega-type turning mode, SUThe turning distance of the U-shaped turning mode.
And 3, designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint condition. The method specifically comprises the following steps:
(3.1) Ant colony Algorithm initialization
Setting the ant colony scale as M, the important degree factor of the left pheromone as alpha, the important degree factor of the heuristic function as beta, the pheromone volatilization factor as rho, the total pheromone released by the ant in one iteration as Q, and the maximum iteration number as Imax。
In the first iteration, the initial pheromone content on each path is the same. And the ant colony starts from the grain unloading point, and a reasonable path is selected according to the pheromone content and the heuristic function of each route. The heuristic function of each path pq is
Figure BDA0003079717050000091
The smaller the distance, the larger the function value.
(3.2) Path selection
Calculating the probability that the mth ant transfers from the current point p to the next point q in the nth iteration as
Figure BDA0003079717050000092
Wherein, taupq(n) is the pheromone of path pq in the nth iteration.
Selecting the path with the maximum transition probability as a target path, judging whether the capacity constraint is exceeded or not, if so, not adding the point, and continuously searching the next target point; if not, it is added to the current path. Repeating the steps until all the operation lines are traversed, completing one iteration, and recording the path section of each antDot
Figure BDA0003079717050000093
And recording the total path length
Figure BDA0003079717050000094
By contrast, the minimum total path length is obtained
Figure BDA0003079717050000095
And corresponding path
Figure BDA0003079717050000096
(3.3) adjusting the route length based on the weight weighting factor
The accumulation of pheromones has a direct relation with the length of the route, and the content of the pheromones can be changed by changing the length of the route, so that the optimization process of the ant colony algorithm is influenced. In the current path planning algorithm, the total distance of driving is mostly used as a cost function, and a feasible solution for enabling the function to reach the minimum value is obtained through an optimization algorithm. In addition to considering the total distance traveled, a full load distance constraint is added. To reduce the compaction of the ground by the harvester under full load, a weight weighting factor is added to the true distance of the path. When the ants pass through one operation row, the grain volume harvested by the ants is updated, the value is correlated with the length of the path, and the ants are guided to carry out optimization according to the full load distance constraint. The distance of the path is improved as follows:
Figure BDA0003079717050000097
wherein, lightmassIs a weight factor, VnowFor the grain volume currently harvested, VgranaryIs the volume of the granary, kmIs a scale factor. When ants pass through a certain path with larger weight, the recorded distance of the path is larger than the real distance, so that the pheromone of the path is reduced, and the ants are induced to search for a shorter path under the condition of full load.
(3.4) updating pheromones
Every time an ant passes a path, it leaves a pheromone on that path. On the next iteration, the pheromone content of path pq is
τpq(n+1)＝(1-ρ)τpq(n)+Δτpq
Wherein (1-rho). taupq(n) pheromones remaining after volatilization, Δ τpqFor all ants passing through this path in this iteration, the pheromone is left as
Figure BDA0003079717050000101
Wherein each ant retains pheromone with content of
Figure BDA0003079717050000102
This value is determined by the distance of the path traversed, the shorter the distance the higher the pheromone content.
(3.5) determining whether to terminate the iteration
If the ant colony algorithm end condition is met, the path traveled by the iterative ants is the operation line traversal sequence, and the step 4 is carried out;
and if the ant colony algorithm ending condition is not met, enabling the iteration number i to be i +1, and jumping to the step (3.2) to continue to search the next path.
The ant colony algorithm end condition is as follows:
the current iteration number I is more than ImaxOr the optimal solution meets the accuracy requirement:
Figure BDA0003079717050000103
wherein,
Figure BDA0003079717050000104
is the shortest path length obtained after the ith iteration, and xi is the preset precisionAnd (4) a threshold value.
And 4, solving the expression of each path according to the traversal sequence of the operation lines and the farmland model to generate a farmland full-coverage path and provide reference for path tracking of the harvester. The method comprises the following specific steps:
and (3) connecting the expression of each operation line obtained by the solution in the step (1) by using the optimal traversal sequence of the operation lines obtained by the solution in the step (3) to form a path expression covering the whole farmland.
The above description is only one of the preferred embodiments of the present invention, and is not intended to limit the present invention in any way, but any modifications or equivalent variations made in accordance with the technical spirit of the present invention are within the scope of the present invention as claimed.

Claims (5)

1. The harvesting robot operation path planning method based on the improved ant colony algorithm is characterized by comprising the following steps of:
step 1, establishing a farmland model:
setting the four vertexes of the farmland as A, B, C and D, knowing the coordinates of the four points, solving the mathematical expression of the boundary, completing the preliminary modeling of the farmland, determining the operation direction under the conditions of the minimum turning times and the maximum vertical degree of the operation line and the boundary, and respectively taking the sides and the diagonal lines of the quadrangle as the operation direction to solve the required turning times;
when the AD is taken as the operation direction, the cutting width of the harvester is set as lcut_widthThen a series of parallel operation behaviors
Figure FDA0003079717040000011
Wherein k isADIs the slope of the AD side, bADThe intercept is AD edge intercept, i is the serial number of the operation line;
respectively solving the intersection points of the group of parallel lines and the quadrilateral boundary, if two intersection points exist, adding one to the turn times until no intersection point exists, and keeping the current turn times as the result of the operation direction;
similarly, respectively using AB, BC, CD, AC and BD as operation directions, solving corresponding turning times, wherein the operation direction with the minimum turning times is obtained by comparison, if a plurality of groups of operation directions all meet the requirement of the minimum turning times, comparing the included angle between the operation direction and the boundary, selecting the operation direction with the included angle close to 90 degrees because the turning complexity and the turning distance are smaller under the vertical condition, and finally solving to obtain the mathematical expression of each operation line so as to perfect the farmland model;
step 2, abstracting the farmland full-coverage path planning into a vehicle route problem, and establishing a corresponding VRP model according to different grain unloading position distribution;
step 3, designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint condition;
and 4, solving the expression of each path according to the traversal sequence of the operation lines and the farmland model to generate a farmland full-coverage path and provide reference for path tracking of the harvester.
2. The harvesting robot working path planning method based on the improved ant colony algorithm according to claim 1, wherein the step 2 abstracts the farmland full coverage path planning into a vehicle route problem, and establishes a corresponding VRP model according to different grain unloading position distributions, and comprises the following steps:
(2.1) defining five grain unloading position distribution conditions:
based on intermittent type formula mode of unloading is studied, and the fortune grain car can not travel in the farmland, need berth at the roadside, divide into following five kinds of condition according to the position and the figure of unloading:
"a": only one grain unloading position S1At the head or tail of the operation line;
"b": only one grain unloading position S1On a side road parallel to the work line;
"c": with two grain unloading positions S1、S2Respectively at the head and tail of the operation line;
"d": with two grain unloading positions S1、S2On the two side roads parallel to the operation line;
"e": with two grain unloading positions S1、S2One at the head or tail of the line and one on a road parallel to the line;
(2.2) establishing a VRP model:
the farmland full-coverage path planning means that the operation path of the harvester is planned to traverse the whole farmland, each operation line only passes through once, the loading capacity of the harvester cannot exceed the capacity of the harvester, when the harvester is fully loaded or nearly fully loaded, the harvester needs to unload grains at the grain unloading position, the set of path points is E, wherein the set of path points comprises a head end point i of each operation lineupEnd point idownPosition S for unloading grain1、S2Each job row having a length of liAnd grain volume V that can be harvestediTwo attributes, starting from the grain unloading position, traversing each operation line in a certain sequence, and finally returning to the grain unloading position, and setting the capacity of the harvester as VgranaryThe sequence number of the operation line is i, j, wherein i, j belongs to [1, n ]line]Unloading point S1A distance to the head end of the working line of
Figure FDA0003079717040000021
To the tail end of the working line at a distance of
Figure FDA0003079717040000022
Grain unloading point S2A distance to the head end of the working line of
Figure FDA0003079717040000023
To the tail end of the working line at a distance of
Figure FDA0003079717040000024
The turning distance between the working lines is
Figure FDA0003079717040000025
According to five grain unloading positionsAnd (3) setting distribution conditions, and respectively establishing a distance model between an operation line and a grain unloading position as follows:
(2.2.1) unloading the harvester at the head of the working line:
Figure FDA0003079717040000026
wherein liIs the length of the ith job row;
(2.2.2) the harvester unloads on the side parallel to the working line:
Figure FDA0003079717040000027
wherein w is the working line width, θupIs the angle between the upper boundary and the line of operation, θdownIs the included angle between the lower boundary and the operation line;
(2.2.3) the harvester can be unloaded at both the head and tail ends of the work line:
Figure FDA0003079717040000028
(2.2.4) the harvester can unload on both sides parallel to the working line:
Figure FDA0003079717040000029
wherein n islineIs the number of operation lines;
(2.2.5) harvester unloading at work line head end and left side:
Figure FDA0003079717040000031
the turning distance between the working lines is
Figure FDA0003079717040000032
Is composed of
Figure FDA0003079717040000033
Wherein S isTTurning distance in T-turn mode, SΩTurning distance in omega-type turning mode, SUThe turning distance of the U-shaped turning mode.
3. The method for planning the operation path of the harvesting robot based on the improved ant colony algorithm as claimed in claim 1, wherein the step 3 is to design an optimal operation traversal order by using the improved ant colony algorithm according to the constraints of the harvester capacity, the total travel distance, the full-load travel distance and the grain unloading position distribution, and specifically comprises the following steps:
(3.1) ant colony algorithm initialization:
setting the ant colony scale as M, the important degree factor of the left pheromone as alpha, the important degree factor of the heuristic function as beta, the pheromone volatilization factor as rho, the total pheromone released by the ant in one iteration as Q, and the maximum iteration number as Imax；
In the first iteration, the initial pheromone content on each path is the same, the ant colony starts from a grain unloading point, a reasonable path is selected according to the pheromone content and the heuristic function of each path, and the heuristic function of each section of path pq is
Figure FDA0003079717040000034
The smaller the distance, the larger the function value;
(3.2) path selection:
calculating the probability that the mth ant transfers from the current point p to the next point q in the nth iteration as
Figure FDA0003079717040000035
Wherein, taupq(n) is the pheromone of path pq in the nth iteration;
selecting the path with the maximum transition probability as a target path, judging whether the capacity constraint is exceeded or not, if so, not adding the point, and continuously searching the next target point; if not, it is added to the current path. Repeating the steps until all the operation lines are traversed, completing one iteration, and recording the path node of each ant
Figure FDA0003079717040000041
And recording the total path length
Figure FDA0003079717040000042
By contrast, the minimum total path length is obtained
Figure FDA0003079717040000043
And corresponding path
Figure FDA0003079717040000044
(3.3) adjusting the route length based on the weight factor:
the accumulation of pheromones has a direct relation with the length of a route, the searching process of an ant colony algorithm is influenced by changing the content of the pheromones by changing the length of the route, in the current path planning algorithm, the total distance of driving is taken as a cost function, a feasible solution for enabling the function to reach the minimum value is obtained by solving through an optimization algorithm, except for considering the total driving distance, a full load distance constraint is added, when an ant passes through an operation line, the grain volume harvested by the ant is updated, the value is associated with the length of the route, the ant is guided to search for the optimization according to the full load distance constraint, and the distance of the route is improved as follows:
Figure FDA0003079717040000045
wherein, lightmassIs a weight factorSeed, VnowFor the grain volume currently harvested, VgranaryIs the volume of the granary, kmWhen ants pass through a certain path with larger weight, the recorded distance of the path is larger than the real distance, so that pheromone of the path is reduced, and the ants are induced to search for a shorter path under the condition of full load;
(3.4) update pheromone:
every time an ant passes a path, it leaves a pheromone on that path. On the next iteration, the pheromone content of path pq is
τpq(n+1)＝(1-ρ)τpq(n)+Δτpq
Wherein (1-rho). taupq(n) pheromones remaining after volatilization, Δ τpqThe pheromones left for all ants passing through this path in this iteration are:
Figure FDA0003079717040000046
wherein, the content of the pheromone left by each ant is as follows:
Figure FDA0003079717040000047
the value is determined by the distance of the path traversed, the shorter the distance, the higher the pheromone content;
(3.5) judging whether to terminate the iteration:
if the ant colony algorithm end condition is met, the path traveled by the iterative ants is the operation line traversal sequence, and the step 4 is carried out;
and if the ant colony algorithm ending condition is not met, enabling the iteration number i to be i +1, and jumping to the step (3.2) to continue to search the next path.
4. A harvesting robot working path planning method based on improved ant colony algorithm according to claim 3, characterized in that the ant colony algorithm end condition is:
the current iteration number I is more than ImaxOr the optimal solution meets the accuracy requirement:
Figure FDA0003079717040000051
wherein,
Figure FDA0003079717040000052
the shortest path length obtained after the ith iteration is shown, and xi is a preset precision threshold.
5. The method for planning the operation path of the harvesting robot based on the improved ant colony algorithm as claimed in claim 1, wherein the step 4 is to solve the expression of each path according to the traversal sequence of the operation lines and the farmland model to generate a farmland full-coverage path, and provide a reference for path tracking of the harvester, and specifically comprises the following steps:
and (3) designing an optimal operation line traversal sequence by adopting an improved ant colony algorithm according to the capacity of the harvester, the total travel distance, the full-load travel distance and the grain unloading position distribution constraint conditions in the step 3, and linking the operation line expressions obtained by the step 1 by utilizing the traversal sequence to form a path expression covering the whole farmland.
CN202110562995.0A 2021-05-24 2021-05-24 Harvesting robot operation path planning method based on improved ant colony algorithm Active CN113190017B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202110562995.0A CN113190017B (en) 2021-05-24 2021-05-24 Harvesting robot operation path planning method based on improved ant colony algorithm

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202110562995.0A CN113190017B (en) 2021-05-24 2021-05-24 Harvesting robot operation path planning method based on improved ant colony algorithm

Publications (2)

Publication Number Publication Date
CN113190017A true CN113190017A (en) 2021-07-30
CN113190017B CN113190017B (en) 2022-02-15

Family

ID=76984817

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202110562995.0A Active CN113190017B (en) 2021-05-24 2021-05-24 Harvesting robot operation path planning method based on improved ant colony algorithm

Country Status (1)

Country Link
CN (1) CN113190017B (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113848880A (en) * 2021-08-30 2021-12-28 中车大连电力牵引研发中心有限公司 Agricultural machinery path optimization method based on improved Q-learning
CN114378828A (en) * 2022-01-30 2022-04-22 哈尔滨工业大学 Task planning method for nuclear industry detection robot
CN114545930A (en) * 2022-01-21 2022-05-27 江苏徐工工程机械研究院有限公司 Agricultural machinery path planning method and system
CN114879669A (en) * 2022-04-28 2022-08-09 贵州民族大学 Robot control method based on multi-target path planning and intelligent picking
CN115067061A (en) * 2022-05-18 2022-09-20 江苏大学 Grain box grain unloading return position monitoring system and method and harvester
CN117308965A (en) * 2023-11-28 2023-12-29 华南农业大学 Harvester robot autonomous grain unloading path planning method based on sliding window algorithm

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020106108A1 (en) * 2001-02-02 2002-08-08 The Board Of Trustees Of The University Method and apparatus for automatically steering a vehicle in an agricultural field using a plurality of fuzzy logic membership functions
US20050075784A1 (en) * 2003-10-07 2005-04-07 Gray Sarah Ann Modular path planner
CN104714551A (en) * 2015-03-23 2015-06-17 中国科学技术大学 Indoor area covering method suitable for vehicle type mobile robot
CN107272679A (en) * 2017-06-15 2017-10-20 东南大学 Paths planning method based on improved ant group algorithm
CN107807644A (en) * 2017-10-30 2018-03-16 洛阳中科龙网创新科技有限公司 A kind of farm machinery consumption minimization trajectory path planning method
CN110319836A (en) * 2019-04-09 2019-10-11 华东理工大学 A kind of path planning control method and device with the minimum target of energy loss
CN111026126A (en) * 2019-12-27 2020-04-17 哈尔滨工程大学 Unmanned ship global path multi-target planning method based on improved ant colony algorithm
DE102019202107B3 (en) * 2019-02-18 2020-04-23 Zf Friedrichshafen Ag Collision avoidance of an autonomous agricultural machine

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20020106108A1 (en) * 2001-02-02 2002-08-08 The Board Of Trustees Of The University Method and apparatus for automatically steering a vehicle in an agricultural field using a plurality of fuzzy logic membership functions
US20050075784A1 (en) * 2003-10-07 2005-04-07 Gray Sarah Ann Modular path planner
CN104714551A (en) * 2015-03-23 2015-06-17 中国科学技术大学 Indoor area covering method suitable for vehicle type mobile robot
CN107272679A (en) * 2017-06-15 2017-10-20 东南大学 Paths planning method based on improved ant group algorithm
CN107807644A (en) * 2017-10-30 2018-03-16 洛阳中科龙网创新科技有限公司 A kind of farm machinery consumption minimization trajectory path planning method
DE102019202107B3 (en) * 2019-02-18 2020-04-23 Zf Friedrichshafen Ag Collision avoidance of an autonomous agricultural machine
CN110319836A (en) * 2019-04-09 2019-10-11 华东理工大学 A kind of path planning control method and device with the minimum target of energy loss
CN111026126A (en) * 2019-12-27 2020-04-17 哈尔滨工程大学 Unmanned ship global path multi-target planning method based on improved ant colony algorithm

Cited By (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113848880A (en) * 2021-08-30 2021-12-28 中车大连电力牵引研发中心有限公司 Agricultural machinery path optimization method based on improved Q-learning
CN113848880B (en) * 2021-08-30 2023-12-22 中车大连电力牵引研发中心有限公司 Agricultural machinery path optimization method based on improved Q-learning
CN114545930A (en) * 2022-01-21 2022-05-27 江苏徐工工程机械研究院有限公司 Agricultural machinery path planning method and system
CN114378828A (en) * 2022-01-30 2022-04-22 哈尔滨工业大学 Task planning method for nuclear industry detection robot
CN114378828B (en) * 2022-01-30 2024-02-20 哈尔滨工业大学 Task planning method for nuclear industry detection robot
CN114879669A (en) * 2022-04-28 2022-08-09 贵州民族大学 Robot control method based on multi-target path planning and intelligent picking
CN114879669B (en) * 2022-04-28 2024-05-28 贵州民族大学 Robot control method based on multi-target path planning and intelligent pickup
CN115067061A (en) * 2022-05-18 2022-09-20 江苏大学 Grain box grain unloading return position monitoring system and method and harvester
CN115067061B (en) * 2022-05-18 2024-04-09 江苏大学 Grain unloading and returning position monitoring system and method for grain tank and harvester
CN117308965A (en) * 2023-11-28 2023-12-29 华南农业大学 Harvester robot autonomous grain unloading path planning method based on sliding window algorithm
CN117308965B (en) * 2023-11-28 2024-03-12 华南农业大学 Harvester robot autonomous grain unloading path planning method based on sliding window algorithm

Also Published As

Publication number Publication date
CN113190017B (en) 2022-02-15

Similar Documents

Publication Publication Date Title
CN113190017B (en) Harvesting robot operation path planning method based on improved ant colony algorithm
Jin et al. Optimal coverage path planning for arable farming on 2D surfaces
CN106969778B (en) Path planning method for cooperative pesticide application of multiple unmanned aerial vehicles
Spekken et al. Optimized routing on agricultural fields by minimizing maneuvering and servicing time
US8498788B2 (en) Method and system for determining a planned path of a vehicle
CN108154254A (en) Logistic distribution vehicle dispatching method based on modified A* algorithms
CN110515380B (en) Shortest path planning method based on turning weight constraint
CN111103880B (en) Collaborative navigation operation path planning system and method for unmanned grain combine harvester
CN111880561A (en) Unmanned aerial vehicle three-dimensional path planning method based on improved whale algorithm in urban environment
KR102296542B1 (en) Task assigning method and task assigning system for two heterogeneous robots
Wang et al. Full coverage path planning methods of harvesting robot with multi-objective constraints
CN110954124A (en) Adaptive path planning method and system based on A-PSO algorithm
EP3589107B1 (en) System and method of bale collection
CN115829230A (en) Heterogeneous unmanned aerial vehicle group cooperative attack task allocation method
CN110986951B (en) Path planning method based on penalty weight, navigation grid and grid map
CN113625772B (en) Shadow following multi-unmanned aerial vehicle area coverage path planning method
CN116929356A (en) Urban low-altitude unmanned aerial vehicle route planning method, device and storage medium
CN113110431A (en) Real-time planning method for field test path of unmanned target vehicle
CN113050635A (en) Task allocation and path planning method for orchard picking and transporting multiple robots
CN115686068B (en) Collaborative path planning method under multi-threat environment
CN115046557B (en) AGV path planning method combining B spline curve and A star algorithm
Ding et al. Path Planning of Omnidirectional mobile vehicle based on road condition
CN101739508A (en) Quantum derivative simulated annealing algorithm adopting arbitrary initial rotation angle step length
CN117308965B (en) Harvester robot autonomous grain unloading path planning method based on sliding window algorithm
CN116843262B (en) Intelligent medicine logistics distribution path planning method based on big data

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