CN115034466A - Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof - Google Patents
Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof Download PDFInfo
- Publication number
- CN115034466A CN115034466A CN202210630037.7A CN202210630037A CN115034466A CN 115034466 A CN115034466 A CN 115034466A CN 202210630037 A CN202210630037 A CN 202210630037A CN 115034466 A CN115034466 A CN 115034466A
- Authority
- CN
- China
- Prior art keywords
- mushroom
- picking
- mushrooms
- target
- neighborhood
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- A—HUMAN NECESSITIES
- A01—AGRICULTURE; FORESTRY; ANIMAL HUSBANDRY; HUNTING; TRAPPING; FISHING
- A01G—HORTICULTURE; CULTIVATION OF VEGETABLES, FLOWERS, RICE, FRUIT, VINES, HOPS OR SEAWEED; FORESTRY; WATERING
- A01G18/00—Cultivation of mushrooms
- A01G18/70—Harvesting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- Biophysics (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Strategic Management (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Physiology (AREA)
- Genetics & Genomics (AREA)
- Mycology (AREA)
- Environmental Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof, comprising the following steps: A. designing a reciprocating pushing picking mode for separating mushrooms from a culture medium; B. a method for determining the optimal pushing direction of the nondestructive picking of mature mushrooms; C. and (3) optimizing a mature mushroom picking path planning algorithm by considering a double-target without damaging the picking pushing direction and the optimal path. The method optimizes the mushroom picking path problem. The invention realizes the optimization of the multi-target problem after the mushroom reciprocating pushing picking is combined with the optimal path, and well avoids the damage to the current mushroom to be picked and the surrounding mushrooms when the mushrooms are picked through the determination of the lossless picking direction and the planning of the picking path, thereby effectively improving the success rate of the lossless picking of the mushrooms and improving the picking efficiency. The invention is not only limited to the picking of edible mushrooms such as mushrooms, straw mushrooms and the like, but also is suitable for the directed picking and the trajectory planning of other cluster fruits.
Description
Technical Field
The invention relates to the technical field of picking machinery, in particular to the field of mushroom picking, and particularly relates to a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof.
Background
With the continuous development of mushroom cultivation technology, mushroom cultivation has already formed industrial production. Due to the fact that the mushroom picking operation period is long, and a large amount of labor force needs to be invested for a long time to guarantee timely harvesting, the mushroom picking operation is the most time-consuming and painstakingly-demanding link in the whole production chain. Manual work is currently the most dominant picking mode. The mushroom picking labor intensity is high, the environment is humid, a large amount of physical consumption of picking personnel can be caused by long-time picking, and certain influence is caused to health. Meanwhile, because of the shortage of green and strong labor in rural areas, the production mode of the traditional mushroom artificial picking becomes an important bottleneck restricting the development of the mushroom planting industry. Therefore mushroom picking needs to be automated as soon as possible.
In the existing mushroom automatic picking mode, mushroom picking is mainly completed by the fact that an end effector sucks or clamps a pileus and then rotates to separate a sporocarp from a culture medium. However, field experiments show that, on one hand, the rotation separation picking mode is easy to cause separation between the stipe and the cap (namely, broken root damage) under the condition that the bonding force between the fruiting body and the culture medium is large, and on the other hand, a plurality of mushrooms are possibly adhered and adhered around one mushroom due to the fact that the mushrooms grow to have anisotropic and uneven density and density. In this case, picking by grasping or rotating is difficult to adapt to the mushrooms which are gathered and grown, and is easy to damage the surrounding mushrooms, which seriously affects the picking quality.
Therefore, the intelligent lossless mushroom picking is a key technical problem to be solved urgently by the fruit and vegetable picking robot. There is a need for a mushroom reciprocating non-destructive picking method and a path planning method thereof.
Disclosure of Invention
The invention aims to solve the problem of high fruiting body picking damage rate in the existing mushroom automatic intelligent picking technology, and provides a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof, which not only effectively improve the success rate of nondestructive picking of mature mushrooms, particularly gathered mushrooms, but also optimize the length of a picking path to improve the picking efficiency, thereby realizing nondestructive picking of the mushrooms and simultaneously obtaining an optimal picking path.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof mainly comprise the following steps:
a: designing a reciprocating pushing picking mode for separating mushrooms from a culture medium;
b: a method for determining the optimal pushing direction of the nondestructive picking of the mature mushrooms;
c: and (3) optimizing a mature mushroom picking path planning algorithm by considering a double-target without damaging the picking pushing direction and the optimal path.
Preferably, a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof specifically comprise the following steps:
a: designing a reciprocating pushing picking mode for separating mushrooms from a culture medium;
step A1: clamping or adsorbing the mushroom by using an end effector;
step A2: pushing the mushrooms to and fro along the optimal pushing direction of the mushrooms to realize the separation of the mushrooms from the culture medium;
b: a method for determining the optimal pushing direction of the nondestructive picking of mature mushrooms;
step B1: acquiring mushroom central coordinates, mushroom cap radius and mushroom height data in a mushroom distribution image, and storing the data as mushroom data characteristics;
step B2: utilizing mushroom data characteristics to search out neighborhood mushrooms and secondary neighborhood mushrooms around the target mushroom;
step B3: calculating a neighborhood mushroom solution set and a secondary neighborhood mushroom solution set and determining the optimal pushing direction of the mushrooms;
c: a double-objective optimization mature mushroom picking path planning algorithm considering the lossless picking pushing direction and the optimal path;
step C1: constructing a multi-objective optimization model of the mushroom picking path:
step C1.1: constructing a mushroom reciprocating pushing picking failure rate function, and calculating the picking failure rate of a picking sequence;
step C1.1.1: judging the reciprocating pushing picking of the target mushrooms;
step C1.1.2: calculating the picking failure rate of the mushroom picking sequence;
step C1.2: constructing a mushroom path length calculation function, and calculating the path length of the picking sequence;
step C1.3: establishing a multi-objective optimization model according to the established mushroom reciprocating pushing picking failure rate function and the path length function;
step C2: after the model construction in the step C1 is completed, solving the model by using an improved NSGA-II algorithm to obtain a Pareto non-dominating set;
step C2.1: chromosome coding of population individuals;
step C2.2: initializing a population;
step C2.3: injecting an extreme value of the length of a single target picking path in the initial population and calculating p of all individuals in the population failure 、dist sum Function values;
step C2.4: selecting a parent population by an elite strategy;
step C2.5: selection, crossover and mutation operations:
step C2.6: merging parent and offspring populations and performing duplicate removal operation;
step C2.7: selecting offspring populations by adopting an elite strategy added with a cyclic congestion sorting algorithm;
step C2.7.1: two boundary individuals 1 in the non-dominant hierarchy d 、n d Set the congestion degree of (1) as inf, sort the individuals in the non-dominated hierarchy from high to low in the congestion degree, and delete the individual with the smallest congestion degree;
step C2.7.2: recalculating the crowding degrees of the remaining individuals in the hierarchy, and deleting the individuals with the minimum crowding degrees again;
step C2.7.3: and iterating in sequence until the specified number of solutions are screened.
Step C2.8: repeating the steps C2.5-C2.8 to a target genetic algebra, and jumping out of the current loop;
step C2.9: and selecting an optimal solution from the non-dominated solution set according to the weight coefficient and outputting the optimal solution.
Preferably, the step a specifically includes:
step A1: clamping or adsorbing the mushroom by using an end effector;
step A2: and pushing the mushrooms to and fro along the optimal pushing direction of the mushrooms to realize the separation of the mushrooms from the culture medium.
Preferably, the optimal pushing direction of the mature mushrooms in the step A2 is determined based on the method for determining the optimal pushing direction of the mature mushrooms in the step B without damage in picking, and the method specifically comprises the following steps:
step B1: acquiring mushroom central coordinates, mushroom cap radius and mushroom height data in a mushroom distribution image, and storing the data as mushroom data characteristics;
step B2: utilizing mushroom data characteristics to search out neighborhood mushrooms and secondary neighborhood mushrooms around the target mushroom; mushrooms that intersect or are tangent to the target mushroom are called neighborhoods, and mushrooms that are separated from the target mushroom but still interfere with the reciprocating push space of the target mushroom are called sub-neighborhoods;
judging the suspicious mushroom as the evaluation index of the neighborhood mushroom, wherein the determination form is as follows:
0<a oi ≤r oi
wherein a is oi Representing the center distance between the target mushroom and the ith suspect mushroom; r is oi A mushroom cap radius sum representing the target and the ith suspect mushroom; i is e [1, …, n-1 ]]N is the total number of mushrooms;
judging the suspicious mushroom as the evaluation index of the next neighborhood mushroom, wherein the determination form is as follows:
r oi <a oi ≤d o +r i
wherein r is i Radius of cap of suspect mushroom, d o Representing the reciprocating pushing range of the target mushroom, the formula is as follows:
in the formula h o And r o Respectively representing the height of the target mushroom and the radius of the mushroom cap, k is the coefficient of the pushing picking range, and k belongs to (0, 1)]；
Step B3: calculating a neighborhood mushroom solution set and a secondary neighborhood mushroom solution set and determining the optimal pushing direction of the mushrooms; whether the target mushroom is surrounded by the neighboring mushrooms is compared with the relation between the point and the polygon, and the relation between the point and the polygon is judged by utilizing an improved cross multiplication judgment method so as to determine whether the target mushroom is surrounded by the neighboring mushrooms; assuming that the number of neighborhood mushrooms is m, the target mushroom mass point p o And each neighborhood mushroom particle p i Make a vector between
Wherein i ∈ [1,2,3, …, m ∈ ]]M is the total number of the neighborhood mushrooms; selecting any one of the vectors as selected
And as a base vector, the rest other vectors are called neighborhood vectors, and the neighborhood vectors and the base vector are subjected to cross multiplication and point multiplication operations in sequence, wherein the specific formula is as follows:
where f is the directional coefficient, θ 2,i Is a vector included angle with a direction;
all neighborhood vectors and base vectors are sequentially subjected to cross multiplication and point multiplication to obtain results, the results are arranged in an ascending order, and the maximum value theta in the results is selected max With a minimum value theta min (ii) a The specific formula for judging the relationship between the points and the polygon is as follows:
when the points are on and outside the polygon, the target mushroom is considered to be not surrounded by its neighborhood mushrooms; recording the neighborhood mushroom solution A, wherein the specific expression form is as follows:
A＝360°-(|θ max |+|θ min |)
the calculation formula for calculating the internal common tangent angle between the target mushroom and a certain secondary neighborhood mushroom by using the internal common tangent theorem is as follows:
wherein n is the number of the mushroom in the next neighborhood, alpha oi Is the angle alpha of the common tangent line formed by the target mushroom and the next adjacent mushroom oi Is the center distance r between the target mushroom and the next adjacent mushroom o ，r i Respectively the radius of the cap of the target mushroom and the radius of the cap of the next adjacent mushroom;
the inner common tangent angle is a complementary angle beta within the range of 0-360 DEG oi Called a sub-neighborhood mushroom individual solution set; angle of compensation beta oi The calculation formula is as follows:
β oi ＝360°-α oi ，i∈[1，…，n]
the existence situations of neighborhood mushrooms and sub-neighborhood mushrooms around the picked target mushrooms are mainly divided into three situations:
1) neighborhood mushrooms and sub-neighborhood mushrooms do not exist around the target mushroom;
2) both neighborhoods and sub-neighborhoods are present around the target mushroom;
3) only one of neighborhoods mushroom and secondary neighborhoods mushroom exists around the target mushroom;
for the first case, in order to avoid invalid calculations, the picking push direction of the target mushroom for this case is defaulted to 180 °; in the second case, the neighborhood mushroom solution A and the next neighborhood mushroom individual solution beta should be sequentially combined oi Performing intersection operation, if the intersection appears, the intersection is an empty set
If so, judging that the target mushroom fails to be picked by reciprocating pushing, and quitting the judgment of the picking algorithm; if the intersection is not an empty set after all the intersection taking operations are finished, reserving the intersection and using the intersection for determining a feasible pushing direction; for the third case, when only neighborhood mushrooms exist around the target mushroom, a neighborhood mushroom solution set obtained in the judgment of the relationship between the target mushroom and the neighborhood mushrooms is used for determining a feasible pushing direction; when only the next neighbourhood mushroom exists around the target mushroom, all the next neighbourhood mushroom individuals are collected oi The intersection of the two adjacent mushroom solutions is the final feasible direction-promoting solution set of the target mushroom after the target mushroom is interfered by all the adjacent mushroom solutions, which is called an adjacent mushroom solution set B, and the specific expression form is as follows:
when the next neighborhood mushroom solution B is an empty set, the target mushroom is not subjected to reciprocating pushing picking and is considered to be failed in picking, and when the next neighborhood mushroom solution B is not an empty set, the target mushroom is subjected to reciprocating pushing picking and is considered to be successfully picked;
selecting a solution set with the largest angle range from the obtained feasible pushing direction solution sets as a solution set of the optimal pushing direction; solving formula of optimal pushing direction:
wherein theta is down 、θ up The lower and upper bounds of the solution set are respectively.
Preferably, especially for the actual case of mushroom mass growth, in order to achieve a non-destructive picking of the mature mushrooms therein, step C, in combination with step B, comprises in particular the following steps:
step C1: constructing a multi-objective optimization model of mushroom reciprocating pushing picking paths:
step C2: after the model construction in the step C1 is completed, solving the model by using an improved NSGA-II algorithm to obtain a Pareto non-dominating set;
step C3: and according to the result obtained in the step C2, carrying out sorting based on the weight value on the obtained Pareto non-dominating set.
Preferably, the step C1 specifically includes the following steps:
step C1.1: constructing a mushroom reciprocating pushing picking failure rate function, and calculating the picking failure rate of a picking sequence;
b, searching out the total number of the mushrooms which fail to be picked in a complete picking sequence by utilizing the step B and recording the total number; calculating the picking failure rate of the mushroom picking sequence, wherein the determination form is as follows:
wherein n is failure Total number of mature mushrooms failing to pick by reciprocating push under the picking path, n sum The total number of mature mushrooms is calculated;
step C1.2: constructing a mushroom path length calculation function, and calculating the path length of the picking sequence; the path length calculation function is specifically formed as follows:
wherein n is the total number of the mature mushrooms, and x and y are respectively the abscissa and the ordinate of the mushrooms;
step C1.3: establishing a multi-objective optimization model according to the established mushroom reciprocating pushing picking failure rate function and the path length function; the optimization target of the multi-target optimization model is as follows:
the multi-objective optimization model sets two optimization objectives, the first objective is to minimize picking failure rate and the second objective is to minimize picking path length.
Preferably, in the step C2, the process of solving the multi-objective optimization model based on the NSGA-II method specifically includes the following steps:
step C2.1: chromosome coding of population individuals;
step C2.2: initializing a population and calculating p for individuals in the population failure 、dist sum Function values;
step C2.3: injecting an extreme value of the length of a single target picking path into the initial population;
step C2.4: selecting a parent population by an elite strategy;
step C2.5: selecting, crossing and mutating;
step C2.6: merging parent and offspring populations and performing duplicate removal operation;
step C2.7: selecting offspring populations by adopting an elite strategy of adding a cycle congestion sorting algorithm;
step C2.8: repeating the steps C2.5-C2.7 to a target genetic algebra, and jumping out of the current loop;
step C2.9: and selecting an optimal solution from the non-dominated solution set according to the weight coefficient and outputting the optimal solution.
Preferably, in the step C2.7, the loop congestion ordering algorithm mainly includes the following steps:
step C2.7.1: two boundary individuals 1 in the non-dominant hierarchy d 、n d Set the congestion degree of (2) as inf, sort the individuals in the non-dominated hierarchy from high to low in the congestion degree, and delete the individual with the smallest congestion degree;
step C2.7.2: recalculating the crowding degrees of the remaining individuals in the hierarchy, and deleting the individuals with the minimum crowding degrees again;
step C2.7.3: and iterating in sequence until the specified number of solutions are screened.
According to a further technical scheme, in the step A, the step A2: the optimal pushing direction in the separation of the mushrooms from the medium by pushing the mushrooms back and forth along the optimal pushing direction of the mushrooms is realized by utilizing the step B: the method for determining the optimal pushing direction of the mature mushrooms in the nondestructive picking is determined.
In a further technical scheme, the step C1.1 is carried out in the following step C1.1.1: the reciprocating pushing picking judgment of the target mushroom is based on the following steps:
and B, determining whether the target mushroom can be subjected to reciprocating push picking or not by using a determination method of the optimal push direction of the mature mushroom.
In a further technical scheme, the specific mode of the population individual chromosome coding in the step C2.1 under the step C2 is as follows:
the coding adopts an integer permutation coding method. If M mature mushrooms are screened out, the chromosome is divided into M sections, wherein each section is the number corresponding to one mature mushroom, and when 10 mature mushrooms {1,2,3,4,5,6,7,8,9,10} are screened out, then {10,5,3,4,7,6,9,8,2,1} is a legal chromosome.
In a further technical solution, the crossing manner of the particle group algorithm in step C2.3 in step C2 is specifically described as follows:
the crossing mode of the particle swarm algorithm adopts sequential crossing (OX), namely starting and ending positions are randomly selected in two parent chromosomes, genes in the region of the parent chromosome 1 are copied to the same position of the offspring 1, and then genes lacking in the offspring 1 are filled in sequence on the parent chromosome 2. Another child is obtained in a similar manner.
In a further technical scheme, in the step C2, the elite strategy in the step C2.4 selects the parent population mainly based on two items, i.e., a non-dominated level and a crowding degree. And selecting the individuals with higher priority in sequence, and selecting the individuals with the same level by adopting the crowdedness. The calculation formula of the congestion degree is as follows:
where n is the number of individuals in the current level, f m (i) An mth objective function value representing an ith chromosome in the current hierarchy,
respectively the maximum and minimum of the mth objective function in the current level;
in a further technical solution, the specific formula of the cross probability adjusted in stages in step C2.6 in step C2 is as follows:
wherein T is the maximum evolutionary algebra, T 1 ＝αT，T 2 (1- α) T, typically α is 0.382 or 0.258; beta is the regulating coefficient of the cross probability at the later stage of evolution, and beta belongs to (0, 1)]The setting of the coefficient can ensure that the cross probability is asymptotic to a value other than 0 at the later stage of evolution.
In a further technical solution, the detailed description of the repetitive individual control strategy in step C2.7 under step C2 is as follows:
in the NSGA-ii algorithm, a new population s (t) is generated by applying an elite strategy to the population after the parent population p (t) is merged with the child population r (t). In the process of selection, crossing and mutation of the parent population P (t), when the probability of crossing and mutation is not 1, some individuals are not crossed and mutated. Therefore, after the parent population and the offspring population are combined, repeated individuals appear. When the new population s (t) is subsequently subjected to non-dominated sorting, the repeated individuals are not dominated by each other, and the partially repeated individuals are selected into a new parent population P (t + 1). After such generations, the new parent is occupied by more and more repeated solutions, resulting in very few non-dominant solutions in the final Pareto solution set.
The specific steps of repeating the individual control strategy are as follows:
(1) deleting the repeat individuals in the parent P (t) and the child R (t) after combination;
(2) and (3) judging whether the number of the deduplicated population is smaller than the number of the population P (t), if so, continuing to perform championship selection, crossing, mutation and population merging, returning to the step (1), otherwise, performing rapid non-dominated sorting on the population, and selecting N individuals as a new parent population P (t + 1).
Compared with the prior art, the technical scheme of the invention has prominent substantive characteristics and obvious advantages:
1. in order to realize the nondestructive picking of mushrooms, the invention provides a reciprocating pushing nondestructive picking method, in particular to a trajectory planning method for determining the optimal pushing direction and picking sequence suitable for the nondestructive picking of mushrooms through reciprocating pushing, aiming at dense mushrooms;
2. the invention uses the relation between the point and the polygon in the graph theory to simulate the relation between the picked mushroom and the surrounding mushrooms in the actual growing environment, and uses the improved cross-product discrimination method and the result calculated by the internal common tangent theorem to determine whether the picked mushroom can be pushed and picked in a reciprocating way or not and the optimal pushing direction when the picked mushroom can be picked, and then uses the improved NSGA-II algorithm to optimize the lossless picking success rate and the path length of the picking path of the mature mushroom;
3. in order to improve the optimization efficiency of the algorithm, methods such as population quality improvement operation on the initial population and injection of the initial population into a single-target extreme value are adopted, so that the convergence and the diversity distribution of the algorithm are effectively improved, the algorithm can obtain an approximate Pareto optimal solution set which is more uniform in distribution and wider in coverage range while ensuring convergence to the real Pareto front edge;
4. the invention realizes the optimization of the multi-target problem after the reciprocating pushing picking of the mushrooms is combined with the optimal path, overcomes the phenomenon that mushroom caps and mushroom stems are separated in the prior picking technology, and well avoids the damage to other mushrooms when the mushrooms are picked through the determination of the lossless picking direction and the planning of the picking road strength, thereby effectively improving the success rate of the lossless picking of the mushrooms;
5. the method is not only limited to the picking of edible mushrooms such as mushrooms and straw mushrooms, but also is suitable for directional picking and trajectory planning of other cluster fruits.
Drawings
FIG. 1 is a flow chart of a preferred embodiment of the method of the present invention.
Fig. 2 is a schematic view of reciprocating pushing picking in the second embodiment of the present invention.
Fig. 3 is a flowchart of the mature mushroom picking judgment according to the second embodiment of the present invention.
Fig. 4 is a flowchart of a mushroom picking path planning algorithm according to a third embodiment of the present invention.
Fig. 5 is an image of the actual distribution of mushrooms according to the third embodiment.
Fig. 6 is the optimal picking path diagram of the mature mushrooms of the third embodiment.
Fig. 7 is a schematic view of the direction of picking and pushing mature mushrooms in the third embodiment.
Detailed Description
For a better understanding of the present invention, reference is made to the following detailed description taken in conjunction with the accompanying drawings and examples.
Example one
In this embodiment, referring to fig. 1, a mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof specifically include:
a: designing a reciprocating pushing picking mode for separating mushrooms from a culture medium;
step A1: clamping or adsorbing the mushroom by using an end effector;
step A2: pushing the mushrooms to and fro along the optimal pushing direction of the mushrooms to realize the separation of the mushrooms from the culture medium;
b: a method for determining the optimal pushing direction of the nondestructive picking of mature mushrooms;
step B1: acquiring mushroom central coordinates, mushroom cap radius and mushroom height data in a mushroom distribution image, and storing the data as mushroom data characteristics;
step B2: utilizing mushroom data characteristics to search out neighborhood mushrooms and secondary neighborhood mushrooms around the target mushroom;
step B3: calculating a neighborhood mushroom solution set and a secondary neighborhood mushroom solution set and determining the optimal pushing direction of the mushrooms;
c: a double-target optimized mature mushroom picking path planning algorithm considering the lossless picking pushing direction and the optimal path;
step C1: constructing a multi-objective optimization model of the mushroom picking path:
step C1.1: constructing a mushroom reciprocating pushing picking failure rate function, and calculating the picking failure rate of a picking sequence;
step C1.1.1: judging the reciprocating pushing picking of the target mushrooms;
step C1.1.2: calculating the picking failure rate of the mushroom picking sequence;
step C1.2: constructing a mushroom path length calculation function, and calculating the path length of the picking sequence;
step C1.3: establishing a multi-objective optimization model according to the established mushroom reciprocating pushing picking failure rate function and the path length function;
step C2: after the model construction in the step C1 is completed, solving the model by using an improved NSGA-II algorithm to obtain a Pareto non-dominating set;
step C2.1: chromosome coding of population individuals;
step C2.2: initializing a population;
step C2.3: injecting an extreme value of the length of a single target picking path in the initial population and calculating p of all individuals in the population failure 、dist sum Function values;
step C2.4: selecting a parent population by an elite strategy;
step C2.5: selection, crossover and mutation operations:
step C2.6: merging parent and offspring populations and performing duplicate removal operation;
step C2.7: selecting offspring populations by adopting an elite strategy of adding a cycle congestion sorting algorithm;
step C2.7.1: two boundary individuals 1 in the non-dominant hierarchy d 、n d Set the congestion degree of (1) as inf, sort the individuals in the non-dominated hierarchy from high to low in the congestion degree, and delete the individual with the smallest congestion degree;
step C2.7.2: recalculating the crowding degrees of the remaining individuals in the hierarchy, and deleting the individuals with the minimum crowding degrees again;
step C2.7.3: and iterating in sequence until the specified number of solutions are screened.
Step C2.8: repeating the steps C2.5-C2.8 to a target genetic algebra, and jumping out of the current loop;
step C2.9: and selecting an optimal solution from the non-dominated solution set according to the weight coefficient and outputting the optimal solution.
The mushroom reciprocating pushing lossless picking mode and the path planning method thereof effectively improve the success rate of lossless picking of mature mushrooms, particularly gathered mushrooms, and optimize the length of a picking path to improve the picking efficiency, thereby realizing lossless picking of the mushrooms and simultaneously obtaining an optimal picking path.
Example two
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in this embodiment, as shown in fig. 1 to fig. 3, the optimal pushing direction of the ripe mushroom in the step a2 is determined based on the method for determining the optimal pushing direction of the ripe mushroom in the step B without damage, and the method specifically includes:
step B1: acquiring mushroom central coordinates, mushroom cap radius and mushroom height data in a mushroom distribution image, and storing the data as mushroom data characteristics;
step B2: utilizing mushroom data characteristics to search out neighborhood mushrooms and secondary neighborhood mushrooms around the target mushroom; mushrooms which intersect or are tangent to the target mushroom are called neighborhoods, and mushrooms which are separated from the target mushroom but still cause interference to the reciprocating push space of the target mushroom are called secondary neighborhoods;
judging the suspicious mushroom as the evaluation index of the neighborhood mushroom, wherein the determination form is as follows:
0<a oi ≤r oi
wherein a is oi Representing the center distance between the target mushroom and the ith suspect mushroom; r is oi The sum of the radius of the cap representing the target and the ith suspect mushroom; i is e [1, …, n-1 ]]N is the total number of mushrooms;
and judging the suspicious mushroom as an evaluation index of the mushroom in the next neighborhood, wherein the determination form is as follows:
r oi <a oi ≤d o +r i
wherein r is i Radius of cap of suspect mushroom, d o Representing the reciprocating pushing range of the target mushroom, the formula is as follows:
in the formula h o And r o Respectively representing the height of the target mushroom and the radius of the mushroom cap, k is the coefficient of the pushing picking range, and k belongs to (0, 1)]；
Step B3: calculating a neighborhood mushroom solution set and a sub-neighborhood mushroom solution set and determining the optimal push direction of the mushrooms; whether the target mushroom is surrounded by the neighboring mushrooms is compared with the relation between the point and the polygon, and the relation between the point and the polygon is judged by utilizing an improved cross multiplication judgment method so as to determine whether the target mushroom is surrounded by the neighboring mushrooms; assuming that the number of neighborhood mushrooms is m, the target mushroom particle p o With each neighborhood mushroom dot p i Make a vector between
Wherein i ∈ [1,2,3, …, m ∈ ]]M is the total number of the neighborhood mushrooms; selecting any one of the vectors as selected
And as a base vector, the rest vectors are called neighborhood vectors, and the neighborhood vectors and the base vector sequentially perform cross multiplication and dot multiplication operations, wherein the specific formula is as follows:
where f is the directional coefficient, θ 2,i Is a vector included angle with a direction;
all neighborhood vectors and base vectors are sequentially subjected to cross multiplication and point multiplication to obtain results, the results are arranged in an ascending order, and the maximum value theta in the results is selected max With a minimum value theta min (ii) a The specific formula for judging the relationship between the points and the polygon is as follows:
when the points are on and outside the polygon, the target mushroom is considered to be not surrounded by its neighborhood mushrooms; recording the neighborhood mushroom solution A, wherein the specific expression form is as follows:
A＝360°-(|θ max |+|θ min |)
the calculation formula for calculating the internal common tangent angle between the target mushroom and a certain secondary neighborhood mushroom by using the internal common tangent theorem is as follows:
wherein n is the number of the mushroom in the next neighborhood, alpha oi Is the internal common tangent angle formed by the target mushroom and the next adjacent mushroom, a oi Is the center distance r between the target mushroom and the next adjacent mushroom o ，r i Respectively the radius of the cap of the target mushroom and the radius of the cap of the next adjacent mushroom;
the inner common tangent angle is a complementary angle beta within the range of 0-360 DEG oi Called a sub-neighborhood mushroom individual solution set; angle of compensation beta oi The calculation formula is as follows:
β oi ＝360°-α oi ，i∈[1，…，n]
the existence situations of neighborhood mushrooms and sub-neighborhood mushrooms around the picked target mushrooms are mainly divided into three situations:
1) neighborhood mushrooms and secondary neighborhood mushrooms do not exist around the target mushroom;
2) both neighborhoods and sub-neighborhoods are present around the target mushroom;
3) only one of neighborhoods mushroom and secondary neighborhoods mushroom exists around the target mushroom;
for the first case, in order to avoid invalid calculations, the picking push direction of the target mushroom for this case is defaulted to 180 °; in the second case, the neighborhood mushroom solution A and the next neighborhood mushroom individual solution beta should be sequentially combined oi Performing intersection operation, if the intersection appears, the intersection is an empty set
If so, judging that the target mushroom fails to be picked by reciprocating pushing, and quitting the judgment of the picking algorithm; if the intersection is not an empty set after all the intersection taking operations are finished, reserving the intersection and using the intersection for determining a feasible pushing direction; for the third case, when only neighborhood mushrooms exist around the target mushroom, a neighborhood mushroom solution set obtained in the judgment of the relationship between the target mushroom and the neighborhood mushrooms is used for determining a feasible pushing direction; when only the next mushroom exists around the target mushroom, all the next mushroom individuals are collected oi The intersection of the two adjacent mushroom solutions is the final feasible direction-promoting solution set of the target mushroom after the interference of all the adjacent mushroom solutions, namely the adjacent mushroom solution set B, and the specific expression form is as follows:
when the next neighborhood mushroom solution B is an empty set, the target mushroom is not subjected to reciprocating pushing picking and is considered to be failed in picking, and when the next neighborhood mushroom solution B is not an empty set, the target mushroom is subjected to reciprocating pushing picking and is considered to be successfully picked;
selecting a solution set with the largest angle range from the obtained feasible pushing direction solution sets as a solution set of the optimal pushing direction; solving formula of optimal pushing direction:
wherein theta is down 、θ up The lower and upper bounds of the solution set are respectively.
In order to realize the lossless picking of the mushrooms, the embodiment utilizes a reciprocating pushing lossless picking method, utilizes the relation between points and polygons in graph theory to compare the relation between the picked mushrooms and the surrounding mushrooms in the actual growth environment, and utilizes an improved cross-multiplication discrimination method and results calculated by an internal common tangent theorem to determine whether the picked mushrooms can be subjected to reciprocating pushing picking and the optimal pushing direction when the mushrooms can be picked.
EXAMPLE III
This embodiment is substantially the same as the above embodiment, and is characterized in that:
in this embodiment, as shown in fig. 4-7, in the step C, a dual-objective optimization algorithm for mature mushroom picking path planning is adopted, taking into account the lossless picking pushing direction and the optimal path.
In order to realize the lossless picking of the mature mushrooms, the step C specifically comprises the following steps in combination with the step B:
step C1: constructing a multi-objective optimization model of the mushroom picking path:
step C1.1: constructing a mushroom reciprocating pushing picking failure rate function, and calculating the picking failure rate of a picking sequence;
here, step C1.1 specifically includes the following steps:
step C1.1.1: reciprocal push picking judgment of target mushrooms
And searching out neighborhood mushrooms around the target mushroom and secondary neighborhood mushrooms according to the mushroom data characteristics obtained from the mushroom distribution map.
Judging the suspicious mushroom as the evaluation index of the neighborhood mushroom, wherein the determination form is as follows:
0＜a 0i ≤r oi
wherein a is oi Represents the center distance between the target mushroom and the ith mushroom; r is oi Represents the sum of the radius of the cap of the target and the ith mushroom; i belongs to (1, n-1), and n is the total number of mushrooms.
And judging the suspicious mushroom as an evaluation index of the mushroom in the next neighborhood, wherein the determination form is as follows:
r oi ＜a 0i ≤d o +r i
wherein r is i Radius of cap of suspect mushroom, d o Representing the push range of the target mushroom, the formula is as follows:
in the formula h o And r o Respectively representing the height of the target mushroom and the radius of the mushroom cap, k is the coefficient of the pushing picking range, and k belongs to (0, 1)]。
And judging whether the target mushroom is surrounded by the neighboring mushrooms by using the relation between the point and the polygon, simplifying the target mushroom and the neighboring mushrooms into mass points, wherein the central coordinate of the mushroom is the position of the mass point. Except the target mushroom, the adjacent mushrooms are connected clockwise two by two to form a closed polygon. Thus abstracting the question of whether the target mushroom is surrounded by the neighborhood mushrooms as a question of the point-to-polygon relationship in graph theory. And judging the relation between the points and the polygon by using an improved cross-product discrimination method. To-be-discriminated point p o With each vertex p of the polygonal type i Make a vector between
m is the total number of the neighboring mushrooms), selecting any one vector from the vectors
And as a base vector, the rest other vectors are called neighborhood vectors, and the neighborhood vectors and the base vector are subjected to cross multiplication and point multiplication operations in sequence, wherein the specific formula is as follows:
where f is the directional coefficient, θ 2,i Is the vector angle with direction.
All neighborhood vectors and base vectors are sequentially subjected to cross multiplication and point multiplication to obtain results, the results are arranged in an ascending order, and the maximum value theta is selected max With a minimum value theta min . If the maximum value theta max Is absoluteValue and minimum value theta min The absolute value of (a) is added, and the value is greater than 180 degrees, which indicates that the point is in the polygon, and when the absolute value is less than 180 degrees, the point is outside the polygon, and when the absolute value is equal to 180 degrees, the point is on the polygon. The concrete form is as follows:
when the point is both on and outside the polygon, the target mushroom is considered not surrounded by its neighbourhood mushrooms. Recording the neighborhood mushroom solution A, wherein the specific expression form is as follows:
A＝360°-(|θ max |+|θ min |)
and calculating an internal common tangent angle between the target mushroom and the next adjacent mushroom by utilizing an internal common tangent theorem. Assuming that the number of the secondary neighborhood mushrooms is n, the calculation formula of the internal common tangent angle between the target mushroom and the secondary neighborhood mushroom calculated by the internal common tangent theorem is as follows:
wherein alpha is oi Is the internal common tangent angle formed by the target mushroom and the next adjacent mushroom, a oi Is the center distance r between the target mushroom and the next adjacent mushroom o ，r i Respectively the radius of the cap of the target mushroom and the radius of the cap of the next adjacent mushroom.
The inner common tangent angle is a complementary angle beta within the range of 0-360 DEG oi Is called a secondary neighborhood mushroom individual solution set. Angle of compensation beta oi The calculation formula is as follows:
β oi ＝360°-α oi ，i∈[1，…，n]
the existence of neighborhood mushrooms and sub-neighborhood mushrooms around the picked target mushroom is mainly divided into three cases:
1) neighborhood mushrooms and sub-neighborhood mushrooms do not exist around the target mushroom;
2) both neighborhoods and sub-neighborhoods are present around the target mushroom;
3) only one of neighborhoods and subneighborhoods exists around the target mushroom.
For the first case, in order to avoid invalid calculations, the picking push direction of the target mushroom for this case is defaulted to 180 °.
For the second case, the neighborhood mushroom solution A and the next neighborhood mushroom individual solution beta should be sequentially combined oi Performing intersection operation, if the intersection appears, the intersection is an empty set
And if so, judging that the target mushroom fails to be picked by reciprocating pushing, and quitting the judgment of the picking algorithm. And if the intersection set is not the empty set after all the intersection set taking operations are finished, reserving the intersection set and using the intersection set for determining the feasible pushing direction.
For the third case, when only neighborhood mushrooms exist around the target mushroom, a neighborhood mushroom solution set obtained in the judgment of the relationship between the target mushroom and the neighborhood mushrooms is used for determining a feasible pushing direction; when only the next neighbourhood mushroom exists around the target mushroom, all the next neighbourhood mushroom individuals are collected oi The intersection of the two adjacent mushroom solutions is the final feasible direction-promoting solution set of the target mushroom after the interference of all the adjacent mushroom solutions, namely the adjacent mushroom solution set B, and the specific expression form is as follows:
when the next neighborhood mushroom solution B is an empty set, the target mushroom can not be pushed and picked in a reciprocating mode, and the target mushroom is considered to be failed in picking.
And selecting a solution set with the largest angle range from the obtained feasible pushing direction solution sets as a solution set of the optimal pushing direction. Solving formula of optimal pushing direction:
wherein theta is down 、θ up The lower and upper bounds of the solution set are respectively.
Recording the pushing direction of the mushrooms in a complete picking sequence and the number of mushrooms which fail in reciprocating pushing picking.
Step C1.1.2: calculating the picking failure rate of the mushroom picking sequence, wherein the determination form is as follows:
wherein n is failure Total number of mushrooms failing to pick up by reciprocating push in the path, n sum The total number of the mature mushrooms.
Step C1.2: constructing a mushroom path length calculation function, and calculating the path length of the picking sequence; the path length calculation function has the following concrete form:
wherein n is the total number of the mature mushrooms, and x and y are respectively the abscissa and the ordinate of the mushrooms.
Step C1.3: establishing a multi-objective optimization model according to the established mushroom reciprocating pushing picking failure rate function and the path length function;
the multi-objective optimization model is provided with two optimization targets, wherein the first optimization target is to minimize the picking failure rate, and the second optimization target is to minimize the picking path length; the optimization target of the multi-target optimization model is as follows:
step C2: after the model construction in the step C1 is completed, an improved NSGA-II algorithm is used for solving the model, and a Pareto non-dominating set is obtained after an appointed algebra is evolved;
step C2.1: chromosome coding of population individuals; encoding each individual in the population by adopting a fixed-length non-repetitive integer encoding mode, wherein each chromosome gene represents mature mushrooms at corresponding positions, and the chromosome length M is 28;
step C2.2 initialise the population and calculate p for each individual in the population failure 、dist sum Function values, generating an initial population with the size of 2N-1 in a random mode, wherein N is 100;
initializing an initial population with a double population size in a random mode before the algorithm starts iteration, and calculating p of each individual in the population failure 、dist sum And (4) an objective function value. The purpose of this is to optimize the initial population of the population size through the following fast non-dominated sorting and elitism strategy to improve the quality of individuals in the initial population and accelerate the convergence speed of the algorithm.
And C2.3, injecting an extreme value of the length of a single target picking path into the initial population, searching an individual picking sequence with the optimal path length by using a particle swarm algorithm, and injecting the individual into the initial population with the scale of 2N-1(199) in the step C2.2. In the initialized population of the multi-objective optimization, the extreme value of each objective is injected to accelerate the convergence speed of the algorithm, because the reduction of the picking failure rate is easier to realize than the optimization of the picking path length in the mushroom picking path optimization problem, for the unbalanced multi-objective optimization problem, only the extreme value of the mushroom picking path length is injected to accelerate the convergence speed of the algorithm.
Step C2.4: selecting a parent population by an elite strategy; for the 2N (200) scale starting population generated in step C2.3, p was calculated for all individuals in the starting population failure 、dist sum Performing rapid non-dominant sorting on the objective function values, and simultaneously performing crowdedness calculation on individuals in each non-dominant layer; selecting superior individuals to form a parent population with the size of N (100) according to an elite strategy;
step C2.5: selecting, crossing and mutating; selecting and determining a parent of the breeding through the championship according to the initial population generated in the step C2.4; taking out 4 individuals from the initial population by adopting a random mode with replacement, and optimizing the 4 individuals according to the non-dominant level and the crowding degree of the individuals1 individual is selected as an individual to be propagated, and another individual to be propagated is likewise selected in this way. In order to prevent the same individual from being selected as an individual to be bred, it is required that the two individuals to be bred should be different individuals. According to a cross (p) c ) Mutation (p) m ) Carrying out genetic operations such as crossing and mutation on the probability to generate a progeny population, wherein the mutation mode of the population adopts a single-point mutation mode; the population crossing mode adopts a two-point crossing mode and self-adaptively adjusts the crossing probability according to the evolution stage, and the specific formula of adjusting the crossing probability by stages is as follows:
wherein T is maximum evolution algebra, R 1 ＝αT，T 2 (1- α) T; beta is the regulating coefficient of the cross probability at the later stage of evolution, and beta belongs to (0, 1)]The setting of the coefficient can ensure that the cross probability is asymptotic to a value other than 0 at the later stage of evolution. In this example, α is 0.382, and β is 0.4.
Step C2.6: combining and de-duplicating the parent and offspring populations to generate 2N (200) chromosome populations, and adopting a repeated individual control strategy to perform de-duplicated individual operation on the combined populations so as to improve the diversity of population individuals. The specific steps of repeating the individual control strategy are as follows:
(1) deleting the repeat individuals in the parent P (t) and the child R (t) after combination;
(2) judging whether the population scale after the duplication elimination is smaller than the population scale N (100) of the population P (t), if so, continuing to perform championship selection, crossing, mutation and population merging, returning to the step (1), otherwise, calculating p for individuals in the population merged after the duplication elimination failure 、dist sum And (4) a target function value, and performing rapid non-dominated sorting and crowding calculation on the de-duplicated combined population according to the target function value.
Step C2.7: selecting offspring populations by adopting an elite strategy of adding a cycle congestion sorting algorithm, combining individuals in the populations after duplication removal, and sequentially adding a non-dominating set F from high to low according to Pareto grades 1 ,F 2 ,…,F m Putting into new parent population P (t +1), and eliminating F by adopting circular crowding sorting algorithm when the size of the new parent population exceeds N (100) m Up to F m Stopping when the sum of the number of the remaining individuals and the number of the individuals stored in the new parent population is equal to N;
here, step C2.7 specifically includes the following steps:
step C2.7.1: two boundary individuals 1 in the non-dominant hierarchy d 、n d Let inf be the congestion degree, and the calculation formula of the congestion degree is as follows:
where n is the number of individuals in the current level, f m (i) An mth objective function value representing an ith chromosome in the current hierarchy,
respectively the maximum and minimum of the mth objective function in the current level;
sorting the individuals in the non-dominated hierarchy according to the crowding degree from high to low, and deleting the individuals with the minimum crowding degree;
step C2.7.2: recalculating the crowding degrees of the remaining individuals in the hierarchy, and deleting the individuals with the minimum crowding degrees again;
step C2.7.3: and iterating in sequence until the specified number of solutions are screened.
Step C2.8: and C2.5-C2.7 are repeated, and if the current genetic algebra reaches the designated target genetic algebra, the current loop is skipped.
Step C2.9: and selecting an optimal solution from the non-dominated solution set according to the weight coefficient and outputting the optimal solution.
In order to realize the lossless picking of mushrooms, the reciprocating pushing lossless picking method is particularly a track planning method for determining the optimal pushing direction and picking sequence suitable for the reciprocating pushing lossless picking of mushrooms aiming at dense mushrooms. In order to improve the optimization efficiency of the algorithm, methods such as population quality improvement operation on the initial population and injection of the initial population into a single-target extremum are adopted, so that the convergence and the diversity distribution of the algorithm are effectively improved, and the algorithm can obtain an approximate Pareto optimal solution set which is more uniform in distribution and wider in coverage range while ensuring convergence to the real Pareto front edge. The method is not only limited to the picking of edible mushrooms such as mushrooms and straw mushrooms, but also is suitable for directional picking and trajectory planning of other cluster fruits.
According to the mushroom reciprocating pushing nondestructive picking mode and the path planning method thereof, firstly, the reciprocating pushing picking mode of separating the mushrooms from the culture medium is utilized; then implementing a method for determining the optimal pushing direction of the nondestructive picking of the mature mushrooms; taking the lossless picking pushing direction and the optimal path into consideration, and optimizing a mature mushroom picking path planning algorithm by using double targets; the embodiment adopts a specific form of reciprocating pushing picking, the embodiment determines the optimal pushing direction for the reciprocating pushing picking, and the reciprocating pushing picking with the optimal pushing direction can greatly improve the success rate of nondestructive mushroom picking. And the mushroom picking path problem is optimized by the method of the embodiment. The embodiment of the invention realizes the optimization of the multi-target problem after the mushroom reciprocating pushing picking is combined with the optimal path, and well avoids the damage to the current mushroom to be picked and the surrounding mushrooms when the mushrooms are picked through the determination of the lossless picking direction and the planning of the picking path, thereby effectively improving the success rate of lossless picking of the mushrooms and improving the picking efficiency.
The above embodiments are merely illustrative of the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and implement the present invention, and not to limit the protection scope of the present invention. All equivalent changes and modifications made according to the spirit of the present invention should be covered within the protection scope of the present invention.
Claims (7)
1. A mushroom reciprocating pushing nondestructive picking mode and a path planning method thereof are characterized by comprising the following steps:
A. designing a reciprocating pushing picking mode for separating mushrooms from a culture medium;
B. a method for determining the optimal pushing direction of the nondestructive picking of mature mushrooms;
C. and (3) optimizing a mature mushroom picking path planning algorithm by considering a double-target without damaging the picking pushing direction and the optimal path.
2. The reciprocating pushing nondestructive mushroom picking mode and the path planning method thereof according to claim 1, wherein the step A specifically comprises the following steps:
step A1: clamping or adsorbing the mushroom by using an end effector;
step A2: and pushing the mushrooms to and fro along the optimal pushing direction of the mushrooms to realize the separation of the mushrooms from the culture medium.
3. The reciprocal nondestructive mushroom picking method according to claim 1, wherein the optimal direction of pushing the mature mushroom in step a2 is determined based on the method for determining the optimal direction of pushing the mature mushroom in step B, and the method comprises:
step B1: acquiring mushroom central coordinates, mushroom cap radius and mushroom height data in a mushroom distribution image, and storing the data as mushroom data characteristics;
step B2: utilizing mushroom data characteristics to search out neighborhood mushrooms and secondary neighborhood mushrooms around the target mushroom; mushrooms which intersect or are tangent to the target mushroom are called neighborhoods, and mushrooms which are separated from the target mushroom but still cause interference to the reciprocating push space of the target mushroom are called secondary neighborhoods;
judging the suspicious mushroom as the evaluation index of the neighborhood mushroom, wherein the determination form is as follows:
0＜a oi ≤r oi
wherein a is oi Representing the center distance between the target mushroom and the ith suspect mushroom; r is oi A mushroom cap radius sum representing the target and the ith suspect mushroom; i is in the same place as [ 1.,. n-1 ]]N is the total number of mushrooms;
judging the suspicious mushroom as the evaluation index of the next neighborhood mushroom, wherein the determination form is as follows:
r oi ＜a oi ≤d o +r i
wherein r is i Radius of cap of suspect mushroom, d o Representing the reciprocating pushing range of the target mushroom, the formula is as follows:
in the formula h o And r o Respectively representing the height of the target mushroom and the radius of the mushroom cap, k is the coefficient of the pushing picking range, and k belongs to (0, 1)]；
Step B3: calculating a neighborhood mushroom solution set and a secondary neighborhood mushroom solution set and determining the optimal pushing direction of the mushrooms; whether the target mushroom is surrounded by the neighborhood mushroom is analogized to the relation between a point and a polygon, and the relation between the point and the polygon is judged by utilizing an improved cross multiplication judgment method so as to determine whether the target mushroom is surrounded by the neighborhood mushroom; assuming that the number of neighborhood mushrooms is m, the target mushroom mass point p o And each neighborhood mushroom particle p i Make a vector between
Wherein i belongs to [1,2,3]M is the total number of the neighborhood mushrooms; selecting any one of the vectors as selected
And as a base vector, the rest other vectors are called neighborhood vectors, and the neighborhood vectors and the base vector are subjected to cross multiplication and point multiplication operations in sequence, wherein the specific formula is as follows:
wherein f isCoefficient of direction, θ 2，i Is a vector included angle with a direction;
all neighborhood vectors and base vectors are sequentially subjected to cross multiplication and point multiplication to obtain results, the results are arranged in an ascending order, and the maximum value theta in the results is selected max With a minimum value theta min (ii) a The specific formula for judging the relationship between the points and the polygon is as follows:
when the points are on and outside the polygon, the target mushroom is considered to be not surrounded by its neighborhood mushrooms; recording the neighborhood mushroom solution A, wherein the specific expression form is as follows:
A＝360°-(|θ max |+|θ min |)
the calculation formula for calculating the internal common tangent angle between the target mushroom and a certain secondary neighborhood mushroom by using the internal common tangent theorem is as follows:
wherein n is the number of the mushroom in the next neighborhood, alpha oi Is the internal common tangent angle formed by the target mushroom and the next adjacent mushroom, a oi Is the center distance r between the target mushroom and the next adjacent mushroom o ，r i Respectively the radius of the cap of the target mushroom and the radius of the cap of the next adjacent mushroom;
the inner common tangent angle is a complementary angle beta within the range of 0-360 DEG oi Called a sub-neighborhood mushroom individual solution set; angle of compensation beta oi The calculation formula is as follows:
β oi ＝360°-α oi ，i∈[1，...，n]
the existence of neighborhood mushrooms and sub-neighborhood mushrooms around the picked target mushroom is mainly divided into three cases:
1) neighborhood mushrooms and secondary neighborhood mushrooms do not exist around the target mushroom;
2) both neighborhoods and sub-neighborhoods are present around the target mushroom;
3) only one of neighborhoods mushroom and secondary neighborhoods mushroom exists around the target mushroom;
for the first case, in order to avoid invalid calculations, the picking push direction of the target mushroom for this case is defaulted to 180 °; in the second case, the neighborhood mushroom solution A and the next neighborhood mushroom individual solution beta should be sequentially combined oi Performing intersection operation, if the intersection appears, the intersection is an empty set
If so, judging that the target mushroom fails to be picked by reciprocating pushing, and quitting the judgment of the picking algorithm; if the intersection is not an empty set after all the intersection taking operations are finished, reserving the intersection and using the intersection for determining a feasible pushing direction; for the third case, when only neighborhood mushrooms exist around the target mushroom, a neighborhood mushroom solution set obtained in the judgment of the relationship between the target mushroom and the neighborhood mushrooms is used for determining a feasible pushing direction; when only the next neighbourhood mushroom exists around the target mushroom, all the next neighbourhood mushroom individuals are collected oi The intersection of the two adjacent mushroom solutions is the final feasible direction-promoting solution set of the target mushroom after the interference of all the adjacent mushroom solutions, namely the adjacent mushroom solution set B, and the specific expression form is as follows:
when the next neighborhood mushroom solution B is an empty set, the target mushroom is not subjected to reciprocating pushing picking and is considered to be failed in picking, and when the next neighborhood mushroom solution B is not an empty set, the target mushroom is subjected to reciprocating pushing picking and is considered to be successfully picked;
selecting a solution set with the largest angle range from the obtained feasible pushing direction solution sets as a solution set of the optimal pushing direction; solving formula of optimal pushing direction:
wherein theta is down 、θ up The lower and upper bounds of the solution set are respectively.
4. The reciprocal non-destructive mushroom picking mode and the path planning method thereof according to claim 1, wherein, especially for the actual situation of mushroom gathering and growing, in order to realize the non-destructive picking of the mature mushrooms, the combination of step B and step C specifically comprises the following steps:
step C1: constructing a multi-objective optimization model of mushroom reciprocating pushing picking paths:
step C2: after the model construction in the step C1 is completed, solving the model by using an improved NSGA-II algorithm to obtain a Pareto non-dominating set;
step C3: and according to the result obtained in the step C2, carrying out sorting based on the weight value on the obtained Pareto non-dominating set.
5. The reciprocating pushing nondestructive mushroom picking mode and the path planning method thereof according to claim 4, wherein the step C1 specifically comprises the following steps:
step C1.1: constructing a mushroom reciprocating pushing picking failure rate function, and calculating the picking failure rate of a picking sequence;
b, searching out the total number of the mushrooms which fail to be picked in a complete picking sequence by utilizing the step B and recording the total number; calculating the picking failure rate of the mushroom picking sequence, wherein the determination form is as follows:
wherein n is failure Total number of mature mushrooms failing to pick by reciprocating push under the picking path, n sum The total number of mature mushrooms is;
step C1.2: constructing a mushroom path length calculation function, and calculating the path length of the picking sequence; the path length calculation function is specifically formed as follows:
wherein n is the total number of the mature mushrooms, and x and y are respectively the abscissa and the ordinate of the mushrooms;
step C1.3: establishing a multi-objective optimization model according to the established mushroom reciprocating pushing picking failure rate function and the path length function; the optimization target of the multi-target optimization model is as follows:
the multi-objective optimization model sets two optimization objectives, the first objective is to minimize picking failure rate and the second objective is to minimize picking path length.
6. The reciprocating pushing nondestructive mushroom picking mode and path planning method according to claim 4, wherein in the step C2, the multi-objective optimization model solving process based on the NSGA-II method specifically comprises the following steps:
step C2.1: carrying out chromosome coding on population individuals;
step C2.2: initializing the population and calculating P of individuals in the population failure 、dist sum Function values;
step C2.3: injecting an extreme value of the length of a single target picking path into the initial population;
step C2.4: selecting a parent population by an elite strategy;
step C2.5: selecting, crossing and mutating;
step C2.6: merging parent and offspring populations and performing duplicate removal operation;
step C2.7: selecting offspring populations by adopting an elite strategy of adding a cycle congestion sorting algorithm;
step C2.8: repeating the steps C2.5-C2.7 to a target genetic algebra, and jumping out of the current loop;
step C2.9: and selecting an optimal solution from the non-dominated solution set according to the weight coefficient and outputting the optimal solution.
7. The mushroom reciprocating pushing nondestructive picking mode and the path planning method thereof as claimed in claim 6, wherein in the step C2.7, the cycle crowding sorting algorithm comprises the following main steps:
step C2.7.1: two boundary individuals 1 in the non-dominant hierarchy d 、n d Set the congestion degree of (2) as inf, sort the individuals in the non-dominated hierarchy from high to low in the congestion degree, and delete the individual with the smallest congestion degree;
step C2.7.2: recalculating the crowding degrees of the remaining individuals in the hierarchy, and deleting the individuals with the minimum crowding degrees again;
step C2.7.3: and iterating in sequence until the specified number of solutions are screened.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210630037.7A CN115034466A (en) | 2022-06-06 | 2022-06-06 | Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210630037.7A CN115034466A (en) | 2022-06-06 | 2022-06-06 | Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115034466A true CN115034466A (en) | 2022-09-09 |
Family
ID=83123869
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210630037.7A Pending CN115034466A (en) | 2022-06-06 | 2022-06-06 | Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115034466A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115486329A (en) * | 2022-10-24 | 2022-12-20 | 江西华香食品有限公司 | Frame is planted to fungus mushroom convenient to gather |
-
2022
- 2022-06-06 CN CN202210630037.7A patent/CN115034466A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115486329A (en) * | 2022-10-24 | 2022-12-20 | 江西华香食品有限公司 | Frame is planted to fungus mushroom convenient to gather |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110909930B (en) | Goods position distribution method of mobile goods shelf storage system for refrigeration house | |
| Bao et al. | Comparison and analysis of the selection mechanism in the artificial bee colony algorithm | |
| CN108919641A (en) | A kind of unmanned aerial vehicle flight path planing method based on improvement cup ascidian algorithm | |
| CN107563653B (en) | Multi-robot full-coverage task allocation method | |
| CN115034466A (en) | Mushroom reciprocating pushing nondestructive picking mode and path planning method thereof | |
| CN104392283A (en) | Artificial fish swarm algorithm based traffic route searching method | |
| KR102585381B1 (en) | The method, system and equipment for vegetation restoration or rehabilitation of simulating natural ecosystem based on machine learnig | |
| CN106777449A (en) | Distribution Network Reconfiguration based on binary particle swarm algorithm | |
| CN111598209A (en) | Serial fusion-based GA & PSO optimization algorithm research | |
| CN107292391A (en) | Flexibility Task method for optimizing scheduling based on DE and L BFGS B hybrid algorithms | |
| CN113093758A (en) | Improved AGV path planning algorithm based on grid map model | |
| CN116540552A (en) | Control parameter optimization method for EMS (electromagnetic mode) magnetic levitation train | |
| CN112348156A (en) | Standard test function processing method based on particle swarm genetic hybrid algorithm | |
| CN108416381A (en) | A kind of multi-density clustering method towards three-dimensional point set | |
| CN114995390A (en) | Mobile robot path planning method based on dynamic adaptive parameter adjustment dayflies algorithm | |
| Xiao-Ting et al. | Flight path planning based on an improved genetic algorithm | |
| CN114240091A (en) | Flexible job shop scheduling method based on self-adaptive layering strategy | |
| CN106651017A (en) | Method for site selection of land consolidation project based on ant colony optimization algorithm | |
| CN106611213A (en) | Hybrid particle swarm algorithm for solving workshop scheduling problem | |
| CN116439077A (en) | Deep reinforcement learning-based mixed picking method for fruiting bodies of straw rotting fungi | |
| CN116341860A (en) | Vehicle dispatching optimization method based on improved NSGA-II algorithm | |
| CN114118600B (en) | Route planning method for urban garbage collection | |
| CN110363298A (en) | Intelligent adjustment of route alignment and gradient method based on evolution algorithm | |
| WO2023070691A1 (en) | Blast furnace burden trajectory model construction method | |
| CN116127836A (en) | Self-adaptive correction weapon target distribution system based on double-gear mechanism multi-target particle swarm optimization algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |