CN113159687B - A method and system for material distribution route planning based on workshop AGV-UAV collaboration - Google Patents

Abstract

The invention discloses a method and a system for planning a material distribution path coordinated by AGV-UAV in a workshop. The method includes: determining the initial parameters of the material distribution path; since both the AGV and the UAV are subject to energy constraints, and they cannot replenish power in time during the driving process, the energy consumption of all processes of the UAV and AGV material distribution is taken as the optimization target, The path optimization model of AGV-UAV collaborative material distribution is constructed, and the corresponding constraints are given; the improved genetic algorithm is used to solve the optimization model of path planning, so as to obtain the optimal path planning scheme. The invention establishes an optimization model, and adopts an improved genetic algorithm to solve it, so as to improve distribution efficiency.

Description

A method and system for material distribution route planning based on workshop AGV-UAV collaboration

technical field

The present invention relates to the field of distribution path planning, in particular to a material distribution path planning method and system for workshop AGV-UAV collaboration.

Background technique

This section merely presents background information related to the present disclosure which does not necessarily constitute prior art.

Material distribution is an important part of the workshop and plays a very important role in the connection of various processes in the workshop. For the intelligent workshop where research is prevalent today, the method of using AGV trolley for material distribution has many advantages compared with the traditional manual material handling method. Using AGV trolley for distribution can save labor, improve work efficiency, and the degree of automation is also high. very high.

With the continuous maturity of drone technology, drones continue to receive attention and have been widely used in logistics. We can see that the delivery of drones has many advantages compared with traditional vehicle transportation. The UAV does not need to consider the impact of harsh terrain during the transportation process, the delivery time has also been significantly reduced, and the delivery efficiency is high.

Therefore, based on the application scenario of the workshop, how to make full use of the three-dimensional space of the workshop, improve the efficiency and automation of material distribution, and how to optimize the path of AGV and UAV for material distribution has become a problem to be solved.

Contents of the invention

In order to solve the above problems, the present invention proposes a material distribution route planning method and system for workshop AGV-UAV collaboration, establishes an optimization model, and uses an improved genetic algorithm to solve it, and improves the distribution efficiency.

In order to achieve the above object, the present invention adopts the following technical solutions:

A method for planning a material distribution path for AGV-UAV collaboration in a workshop, comprising the following steps:

Obtain the initial parameters of the material distribution path using AGV and UAV;

Based on the initial parameters, the energy consumption of all processes of UAV and AGV material distribution is used as the optimization target, and the path optimization model of AGV-UAV collaborative material distribution is constructed;

According to the constraints, the improved genetic algorithm is used to solve the path planning optimization model, and the optimal path planning scheme is obtained.

As a further improvement of the present invention, the initial variables include the travel speed of each AGV and UAV, the processing and distribution procedures of materials, the travel distance of the AGV between each processing equipment and the flight distance of the UAV, and the consumption of AGV and UAV within a unit distance. Energy, the quality of the delivered material, and the 0-1 decision variable of AGV and UAV; among them, the 0-1 decision variable indicates whether a certain delivery process of the material chooses the AGV or the UAV for delivery.

As a further improvement of the present invention, the minimum optimization target of the AGV-UAV collaborative material distribution is constructed by the energy consumed in the unit travel distance of the AGV and UAV.

As a further improvement of the present invention, the constraints are:

The distribution process of each material can only be carried out on one AGV or UAV;

The delivery time of AGV and UAV does not exceed the time limit of the processing procedure;

Each material distribution requirement has a strict sequence;

At a certain moment, an AGV or UAV can only deliver one delivery requirement for one material;

The quality of materials delivered by each AGV and UAV does not exceed its maximum load;

The total energy consumed by each AGV and UAV delivery cannot exceed the maximum energy it is allowed to consume.

As a further improvement of the present invention, according to the constraints, the specific process of using the improved genetic algorithm to solve the path planning optimization model is:

First, a multi-layer coding method based on natural numbers is used for coding and decoding;

Then take the reciprocal of the total energy consumption of the distribution plan represented by each chromosome as the fitness value of this genetic algorithm;

Then use the hill-climbing algorithm to initialize the population;

Then use the selection method combining the tournament selection method and the roulette method to select the initial population;

Finally, the CX crossover method is used for the crossover operation and the mutation operation is performed by randomly exchanging gene bits.

As a further improvement of the present invention, the reciprocal of the total energy consumption of the distribution scheme represented by each chromosome is used as the fitness value of the genetic algorithm, specifically including:

Given a chromosome, the chromosome is divided into three layers, the first layer is the main chromosome, which performs crossover and mutation operations, and the rest are slave chromosomes, which do not perform crossover and mutation operations, but will be recoded after the main chromosome crossover and mutation;

Each gene bit on the first layer represents the number of the selected distribution equipment, which is the selected part of the distribution equipment. The upper layer of numbers represents the order of the distribution process. This part is a known condition and does not participate in the calculation, so it does not belong to Chromosome category, placed here can facilitate the coding of other gene bits. In the number part of this layer, each number represents the number of the material, and the number of occurrences of each number represents the total number of distribution processes of the material. The order in which each number appears indicates the distribution The distribution sequence of the process corresponds to the first layer of the chromosome, that is, the part selected by the distribution equipment. The gene bits are arranged in order from the first distribution process of the first material to the end of the last distribution process of the last material of;

The second layer is the joint chromosome, which is twice the length of the first layer, that is, twice the total distribution process. Each gene bit in the left half corresponds to the distribution distance required by the distribution equipment selected for each process. The right half is that if the device has been selected before, it is necessary to calculate the distance from the last standby point of the device to the starting point of the distribution process;

The third layer of chromosomes is immediately below the second layer, and its length is the same as that of the first layer, indicating the energy consumption of the selected distribution equipment for delivering the material per unit time;

Scan the first layer of chromosomes from left to right, because the order of each distribution process is known, you can first determine the distribution equipment selected for each distribution process; scan the second layer of chromosomes in the same way, and scan the second layer For chromosomes, the distribution distance of each process on the corresponding distribution equipment is obtained from the left half, and the distance from the distribution equipment to the processing equipment at the starting point of the process is obtained from the left half; finally, the third layer of chromosome is scanned to obtain its unit energy consumption data;

The problem is encoded in the form of chromosomes. Each chromosome is a solution. For each chromosome, the total energy consumption of the solution can be obtained. Therefore, the fitness of the chromosome that minimizes the total energy consumption should be the highest, so The reciprocal of the total energy consumption of the distribution plan represented by each chromosome is used as the fitness value of the genetic algorithm.

As a further improvement of the present invention, the mutation operation includes:

Randomly generate two determined positions in the part that needs chromosomes for calculation, and exchange the genes of these two positions to obtain a new chromosome.

As a further improvement of the present invention, the hill-climbing algorithm is used to initialize the population, and the specific process is as follows:

(1) Take an individual in the population to perform mountain climbing operations;

(2) Perform decoding operation on the taken individual and calculate its fitness;

(3) Randomly select a point in the chromosome part of the individual process, and mutate the value of the gene bit at this point to obtain a new chromosome, which is used as the neighborhood of the original chromosome;

(4) Calculate the fitness value of the new chromosome, if it is better than the original chromosome, replace the original chromosome, otherwise keep the original chromosome;

(5) Repeat the process (3) and (4) until the maximum number of iterations is reached.

(6) Perform hill-climbing operations on the remaining individuals in the population according to the above method until all individuals in the population have performed hill-climbing operations.

As a further improvement of the present invention, the selection method combining the tournament selection method and the roulette method is used to select the initial population, and the specific steps are as follows:

(1) The individual with the highest fitness value in the initial population is designated as an excellent individual;

(2) The excellent individuals are directly copied to the next generation, and the remaining individuals use the roulette method to select the initial population;

(3) When the next generation population performs the selection operation, the fitness value of each individual in the population is compared with the excellent individual. If the fitness value of each individual in the population is worse than the fitness value of the excellent individual, the excellent individual will be directly copied to the next generation; if there is an individual with a better fitness value than the excellent individual in the population, the These individuals are kept to the next generation, and the remaining individuals are selected by roulette;

(4) Repeat step (3) until the population iteration ends.

A material distribution path planning system for workshop AGV-UAV collaboration, including:

The obtaining unit is used to obtain the initial parameters of the material distribution path using AGV and UAV;

Modeling unit, for based on described initial parameter, with the energy consumption of all processes of UAV and AGV material distribution as optimization target, construct the path optimization model of AGV-UAV collaborative material distribution;

The solving unit is used to solve the path planning optimization model by using the improved genetic algorithm according to the constraint conditions to obtain the optimal path planning scheme.

Compared with prior art, the beneficial effect of the present invention is:

The present invention cooperates AGV and UAV to carry out the material distribution of the workshop, which greatly improves the delivery efficiency of the workshop, makes full use of the three-dimensional environment of the workshop, and makes the workshop more automatic. In addition, the improved genetic algorithm is used to solve the optimization model, which can be faster Find the optimal solution to improve delivery efficiency.

In the workshop, some terrains are more complicated. For places where the terrain is more complicated and AGVs are inconvenient to reach, materials are distributed by drones. The minimum energy consumption of AGVs and UAVs is used as the optimization model. Under the corresponding constraints , using an improved genetic algorithm to solve the problem, to achieve accurate and rapid distribution of materials.

Description of drawings

The accompanying drawings constituting a part of the present invention are used to provide a further understanding of the present invention, and the schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations to the present invention.

Fig. 1 is a schematic flow chart of a material distribution path planning method for AGV-UAV collaboration in a workshop of the present invention;

Fig. 2 collection is the production scheduling Gantt diagram of the processing procedure of each material of an example involved in the inventive method;

Fig. 3 is the coding schematic diagram in the method of the present invention;

Fig. 4 is a schematic diagram of the population initialization process in the present invention;

Fig. 5 is a schematic diagram of the selection operation process in the present invention;

Fig. 6 is an example diagram of cross operation in the present invention;

Fig. 7 is an example diagram of mutation operation in the present invention;

Fig. 8 is a schematic structural diagram of a material distribution path planning system for workshop AGV-UAV collaboration;

FIG. 9 is a schematic structural diagram of an electronic device.

Detailed ways

The present invention will be further described below in conjunction with accompanying drawings and examples.

It should be noted that the following detailed description is exemplary and intended to provide further explanation of the present invention. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

It should be noted that the terminology used herein is only for describing specific embodiments, and is not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly dictates otherwise, the singular is intended to include the plural, and it should also be understood that when the terms "comprising" and/or "comprising" are used in this specification, they mean There are features, steps, operations, means, components and/or combinations thereof.

Example 1

As shown in Fig. 1, the present invention provides a kind of AGV-UAV collaborative material distribution path planning method in workshop, comprising:

S1: Determine the initial parameters of the material distribution route: including the driving speed of each AGV and UAV, the processing and distribution procedures of materials, the driving distance of the AGV between each processing equipment and the flight distance of the UAV, and the consumption per unit distance of the AGV and UAV energy of.

The initial variables also include: the quality of the materials to be delivered, and the 0-1 decision variables of AGV and UAV; among them, the 0-1 decision variable indicates whether a certain distribution process of materials chooses the AGV or the UAV for distribution.

For example, in this example, there are S materials P in each material base point Base0 of the workshop, and the production schedule of all processing procedures of materials P is known. Now, H AGVs and F UAVs are used to transfer S materials P from materials The base point Base 0 is delivered to each processing equipment i, j that each material P needs to reach. Due to the difference in the maximum load of AGV and UAV, RFID tags are used to collect the quality data of each material, so that UAV and AGV can make certain delivery choices based on the quality data of the material. For each distribution process of material P, different UAV or AGV equipment can be selected for distribution.

Decision variables include:

S2: Taking the energy consumption of all processes of UAV and AGV material distribution as the optimization target, construct a path optimization model for AGV-UAV collaborative material distribution.

The route optimization model of the material distribution is:

The required parameters and symbols of the model are shown in the table below:

Table 1

Objective function:

constraint:

Among them, L is a very large positive number, and the meanings of other symbols are:

in Indicates the sum of distribution operations of all materials.

(2) It means that the distribution process of each material can only be carried out on one AGV or UAV.

(3) represents the time constraint on the selected AGV.

(4) represents the temporal constraints on the selected UAV.

(5) and (6) represent the sequence constraints of each material distribution requirement.

(7)(8) means that at a certain moment, an AGV or UAV can only deliver one delivery demand of one material.

(9) Indicates that the quality of materials delivered by each AGV does not exceed its maximum load.

(10) indicates that the mass of materials delivered by each UAV does not exceed its maximum load.

(11) indicates that the total energy consumed by each AGV distribution cannot exceed the maximum energy it is allowed to consume.

(12) indicates that the total energy consumed by each UAV distribution cannot exceed the maximum energy it is allowed to consume.

(13) Indicates that the number of times each AGV or UAV performs the material distribution process cannot exceed the limit.

(14) indicates that each variable parameter is positive.

As some possible implementations, relevant assumptions are made as follows:

Every AGV and UAV is fully charged before starting delivery.

The specifications of each AGV and UAV are the same, that is, the speed of each AGV is the same, and the speed of each UAV is also the same, and its driving speed is not affected by the quality of materials.

The material volume factor is not considered.

AGV and UAV operate independently without interfering with each other.

AGV and UAV travel at a uniform speed.

The driving process of AGV and UAV is regarded as barrier-free passage.

At the same point in time, a material can only be delivered by one AGV or UAV.

There is a strict sequence for each distribution process of a material, and there is no strict sequence for the distribution processes between different materials.

The priority of each item is the same.

AGV and UAV are not allowed to stop without reason during the delivery process.

All AGVs and UAVs need to stay at the target equipment after completing a material distribution task.

Under the corresponding constraints, the improved genetic algorithm is used to solve the optimal solution of the path planning model. The specific process is as follows:

First, a multi-layer coding method based on natural numbers is used to code the example shown in Fig. 2 .

Table 2 Distribution process required for each material and energy consumption required for UAV and AGV distribution

Table 3 AGV travel distance between each processing equipment (m)

Table 4 Flight distance of UAV between each processing equipment (m)

The speed of the AGV is given as 10m/min, and the flight speed of the UAV is 15m/min. As shown in Figure 3, a chromosome (in a rectangular box) that has been coded for a given example is divided into three layers. The first layer is the master chromosome, which performs crossover and mutation operations, and the rest are slave chromosomes, which do not perform crossover and mutation operations. , but they are recoded following crossover and mutation of the main chromosomes. Each gene bit on the first layer represents the number of the selected distribution equipment, which is the selected part of the distribution equipment. The upper layer of numbers represents the order of the distribution process. This part is a known condition and does not participate in the calculation, so it does not belong to Chromosome category, placed here can facilitate the coding of other gene bits. In the number part of this layer, each number represents the number of the material, and the number of occurrences of each number represents the total number of distribution processes of the material. The order in which each number appears indicates the distribution The delivery order of the process, for example, the first "2" that appears indicates the first delivery process of material P ₂ , and the second "2" that appears indicates the second delivery process O ² of material P _{2 13} . Therefore, corresponding to the first layer of the chromosome, that is, the part selected by the distribution equipment, the gene bits are arranged sequentially from the first distribution process of the first material to the end of the last distribution process of the last material. Because there are three materials in this example, there are seven distribution processes in total, so the chromosome genes of the selected part of the distribution equipment are arranged according to the corresponding distribution processes. For example, the number "4" at the far right of this layer represents the third process of material _P2 The delivery process O ² ₃₂ selects the fourth delivery device, ie UAV2, for delivery. The second layer is the joint chromosome, which is twice the length of the first layer, that is, twice the total distribution process. Each gene bit in the left half corresponds to the distribution distance required by the distribution equipment selected for each process. The right half is that if the equipment has been selected before, it is necessary to calculate the distance from the last stand-by point of the equipment to the starting point of the distribution process, for example, the third gene position "2" in the first layer of chromosome has been selected before If the first distribution process of material _P1 has been selected, then if this distribution equipment is selected again, it is necessary to add the equipment from the end point of the first distribution process of material P1 "machine tool 4" to the first distribution process of material _P3 The distance "13" from the starting point "Machine 2". The third layer of chromosomes is just below the second layer, and its length is the same as that of the first layer, which represents the energy consumption of the selected distribution equipment for delivering the material per unit time. The advantage of using this encoding is that the readability of the chromosome is improved, and the key information of the whole problem is contained in the chromosome, so the decoding process will be very clear.

Decoding: Scan the first layer of chromosomes from left to right, because the order of each distribution process is known, and the distribution equipment selected for each distribution process can be determined first. In the same way, the second layer of chromosomes is scanned sequentially. When scanning the second layer of chromosomes, the distribution distance of each process on the corresponding distribution equipment is obtained from the left half, and the distribution equipment from its last standby point to the distribution equipment is obtained from the left half. The distance from the processing equipment to the starting point of the process. Finally, scan the third layer of chromosomes to obtain the data of its unit energy consumption.

The problem is encoded in the form of chromosomes. Each chromosome is a solution. For each chromosome, the total energy consumption of the solution can be obtained. Therefore, the fitness of the chromosome that minimizes the total energy consumption should be the highest, so The reciprocal of the total energy consumption of the distribution plan represented by each chromosome is used as the fitness value of the genetic algorithm. Right now

Then use the hill-climbing algorithm to initialize the population; the specific process is as follows:

Take an individual in the population for hill climbing operation.

Perform decoding operation on the taken out individuals to calculate their fitness.

Randomly select a point in the chromosome part of the individual process, and mutate the value of the gene bit at this point to obtain a new chromosome, which is used as the neighborhood of the original chromosome.

Calculate the fitness value of the new chromosome, if it is better than the original chromosome, replace the original chromosome, otherwise keep the original chromosome.

Repeat the process until the maximum number of iterations is reached.

The remaining individuals of the population perform hill climbing operations according to the above method until all individuals in the population have performed hill climbing operations.

The specific flow chart is shown in Figure 4.

Then use the selection method combining the tournament selection method and the roulette method to select the initial population; the specific steps are as follows:

The individual with the highest fitness value in the initial population is designated as an excellent individual.

The excellent individuals are directly copied to the next generation, and the remaining individuals use the roulette method to select the initial population.

When the next generation population performs the selection operation, the fitness value of each individual in the population is compared with the excellent individual. If the fitness value of each individual in the population is worse than the fitness value of the excellent individual, the excellent individual will be directly copied to the next generation; if there is an individual with a better fitness value than the excellent individual in the population, the These individuals are kept to the next generation, and the remaining individuals are selected by roulette.

Repeat the steps until the population iteration ends.

Its specific flow chart is shown in Figure 5

Finally, the CX crossover method is used for the crossover operation and the mutation operation is performed by randomly exchanging gene bits.

A Cycle Crossover (CX) method is adopted, which can retain the good genes of the parent and make the offspring feasible. First select two parent chromosomes P ₁ , P ₂ , and then randomly select the same gene bit from the two parent chromosomes. If the genes of the selected gene bits are exactly the same, you need to re-select, and then the selected gene bit Copy directly to the offspring O ₁ and O ₂ according to the original position, put the remaining genes of P ₂ into O ₁ , and put the remaining genes of P ₁ into O ₂ , as shown in Figure 6.

Mutation operation: Randomly generate two certain positions in the part that needs chromosomes for calculation, and exchange the genes of these two positions to obtain a new chromosome, which can ensure its solvability. The example diagram is shown in Figure 7.

As shown in Figure 8, another object of the present invention is to propose a material distribution path planning system for workshop AGV-UAV collaboration, including:

The obtaining unit is used to obtain the initial parameters of the material distribution path using AGV and UAV;

Modeling unit, for based on described initial parameter, with the energy consumption of all processes of UAV and AGV material distribution as optimization target, construct the path optimization model of AGV-UAV collaborative material distribution;

The solving unit is used to solve the path planning optimization model by using the improved genetic algorithm according to the constraint conditions to obtain the optimal path planning scheme.

As shown in FIG. 9, the third object of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored in the memory and operable on the processor, and the processor executes the The steps of realizing the AGV-UAV collaborative material distribution route planning method in the workshop when the computer program is described.

The fourth object of the present invention is to provide a computer-readable storage medium, the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the AGV-UAV collaborative material distribution path planning in the workshop is realized method steps.

Those skilled in the art should understand that embodiments of the present invention may be provided as methods, systems, or computer program products. Accordingly, the present invention can take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) having computer-usable program code embodied therein.

The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It should be understood that each process and/or block in the flowchart and/or block diagram, and a combination of processes and/or blocks in the flowchart and/or block diagram can be realized by computer program instructions. These computer program instructions may be provided to a general purpose computer, special purpose computer, embedded processor, or processor of other programmable data processing equipment to produce a machine such that the instructions executed by the processor of the computer or other programmable data processing equipment produce a An apparatus for realizing the functions specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing apparatus to operate in a specific manner, such that the instructions stored in the computer-readable memory produce an article of manufacture comprising instruction means, the instructions The device realizes the function specified in one or more procedures of the flowchart and/or one or more blocks of the block diagram.

These computer program instructions can also be loaded onto a computer or other programmable data processing device, causing a series of operational steps to be performed on the computer or other programmable device to produce a computer-implemented process, whereby the The instructions provide steps for implementing the functions specified in the flow chart or blocks of the flowchart and/or the block or blocks of the block diagrams.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the above embodiments, those of ordinary skill in the art should understand that: the present invention can still be Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention shall fall within the protection scope of the claims of the present invention.

Claims (8)

1. A method for planning a material distribution route of a workshop AGV-UAV collaboration, characterized in that, comprising the following steps: Obtain the initial parameters of the material distribution path using AGV and UAV; Based on the initial parameters, with the energy consumption of all processes of UAV and AGV material distribution as the optimization target, a path optimization model for AGV-UAV collaborative material distribution is constructed; The route optimization model of the material distribution is: The required parameters and symbols for this model are as follows: Objective function: constraint: Among them, L is a very large positive number, and the meanings of other symbols are: in Indicates the sum of the delivery procedures of all materials; (2) Indicates that the distribution process of each material can only be carried out on one AGV or UAV; (3) Indicates the time constraint on the selected AGV; (4) Indicates the time constraints on the selected UAV; (5) and (6) represent the sequence constraints of each material distribution requirement; (7) and (8) indicate that at a certain moment, an AGV or UAV can only deliver one delivery demand for one material; (9) Indicates that the quality of the material delivered by each AGV does not exceed its maximum load; (10) Indicates that the quality of materials delivered by each UAV does not exceed its maximum load; (11) Indicates that the total energy consumed by each AGV distribution cannot exceed the maximum energy it is allowed to consume; (12) Indicates that the total energy consumed by each UAV delivery cannot exceed the maximum energy it is allowed to consume; (13) Indicates that the number of times each AGV or UAV performs the material distribution process cannot exceed the limit; (14) represent that each variable parameter is positive; According to the constraints, the improved genetic algorithm is used to solve the path planning optimization model, and the optimal path planning scheme is obtained; According to the constraints, the specific process of using the improved genetic algorithm to solve the path planning optimization model is as follows: First, a multi-layer coding method based on natural numbers is used for coding and decoding; Then take the reciprocal of the total energy consumption of the distribution plan represented by each chromosome as the fitness value of this genetic algorithm; Then use the hill-climbing algorithm to initialize the population; Then use the selection method combining the tournament selection method and the roulette method to select the initial population; Finally, the CX crossover method is used for the crossover operation and the mutation operation is performed by randomly exchanging gene bits; The reciprocal of the total energy consumption of the distribution scheme represented by each chromosome is used as the fitness value of the genetic algorithm, specifically including: Given a chromosome, the chromosome is divided into three layers, the first layer is the main chromosome, which performs crossover and mutation operations, and the rest are slave chromosomes, which do not perform crossover and mutation operations, but will be recoded after the main chromosome crossover and mutation; Each gene bit on the first layer represents the selected distribution equipment number, that is, the selected part of the distribution equipment, and the number on the upper layer represents the order of the distribution process, and some of them are known conditions; in the number part of the layer, each number Represents the serial number of the material, the number of occurrences of each number represents the total number of distribution processes of the material, and the order of each number represents the distribution order of the distribution process, thus corresponding to the first layer of the chromosome, which is the part selected by the distribution equipment, the gene bit is according to Arranged sequentially from the first delivery procedure of the first material to the end of the last delivery procedure of the last material; The second layer is the joint chromosome, which is twice the length of the first layer, that is, twice the total distribution process. Each gene bit in the left half corresponds to the distribution distance required by the distribution equipment selected for each process. The right half is if the equipment has been selected before, it is necessary to calculate the distance from the last standby point of the equipment to the starting point of this distribution process; The third layer of chromosomes is immediately below the second layer, and its length is the same as that of the first layer, which represents the energy consumption of the selected distribution equipment for delivering materials per unit time; Scan the first layer of chromosomes from left to right, and scan the second layer of chromosomes in the same way. When scanning the second layer of chromosomes, get the distribution distance of each process on the corresponding distribution equipment from the left half, and from the left half Obtain the distance from the last standby point of the distribution equipment to the processing equipment at the starting point of the process; finally scan the third layer of chromosomes to obtain the data of its unit energy consumption; The problem is encoded in the form of chromosomes, each chromosome is a solution, and for each chromosome, the total energy consumption of the solution is obtained; the chromosome that minimizes the total energy consumption has the highest fitness, so each chromosome represents The reciprocal of the total energy consumption of the distribution plan is used as the fitness value of the genetic algorithm. 2. A kind of workshop AGV-UAV collaborative material delivery route planning method as claimed in claim 1, is characterized in that, The initial variables include the driving speed of each AGV and UAV, the processing and distribution procedures of materials, the driving distance of AGV and the flight distance of UAV between each processing equipment, the energy consumed by AGV and UAV per unit distance, and the quality of delivered materials , and the 0-1 decision variable of AGV and UAV; among them, the 0-1 decision variable indicates whether a certain distribution process of the material chooses AGV or UAV for distribution. 3. A kind of workshop AGV-UAV collaborative material delivery route planning method as claimed in claim 1, is characterized in that, The minimum optimization objective of the AGV-UAV collaborative material distribution is constructed by the energy consumed by the AGV and UAV within the unit travel distance. 4. A kind of workshop AGV-UAV collaborative material delivery route planning method as claimed in claim 1, is characterized in that, The constraints are: The distribution process of each material can only be carried out on one AGV or UAV; The delivery time of AGV and UAV does not exceed the time limit of the processing procedure; Each material distribution requirement has a strict sequence; At a certain moment, an AGV or UAV can only deliver one delivery requirement for one material; The quality of materials delivered by each AGV and UAV does not exceed its maximum load; The total energy consumed by each AGV and UAV delivery cannot exceed the maximum energy it is allowed to consume. 5. A kind of workshop AGV-UAV collaborative material distribution route planning method as claimed in claim 1, is characterized in that, The mutation operations include: In the part that requires chromosomes for calculation, two certain positions are randomly generated, and the genes at these two positions are exchanged to obtain a new chromosome. 6. A kind of workshop AGV-UAV collaborative material distribution route planning method as claimed in claim 1, is characterized in that, The hill-climbing algorithm is used to initialize the population, and the specific process is as follows: 1) Take an individual in the population to perform mountain climbing operations; 2) Decode the extracted individual and calculate its fitness; 3) randomly select a point in the chromosome part of the individual process, and change the value of the gene bit at the point to obtain a new chromosome, which is used as the neighborhood of the original chromosome; 4) Calculate the fitness value of the new chromosome, if it is better than the original chromosome, replace the original chromosome, otherwise keep the original chromosome; 5) Repeat process 3) and 4) until reaching the maximum number of iterations; 6) The remaining individuals in the population perform hill-climbing operations according to the above method until all individuals in the population have performed hill-climbing operations. 7. A kind of workshop AGV-UAV collaborative material distribution path planning method as claimed in claim 1, is characterized in that, The selection method combining the tournament selection method and the roulette method is used to select the initial population. The specific steps are as follows: 1) The individual with the highest fitness value in the initial population is designated as an excellent individual; 2) The excellent individuals are directly copied to the next generation, and the remaining individuals use the roulette method to select the initial population; 3) When the next generation population performs the selection operation, compare the fitness value of each individual in the population with the excellent individual; if the fitness value of each individual in the population is worse than the fitness value of the excellent individual, then the excellent individual Copy directly to the next generation; if there are individuals in the population whose fitness value is higher than the fitness value of the excellent individual, these individuals will be directly retained to the next generation, and the remaining individuals will be selected by roulette; 4) Repeat step 3) until the population iteration ends. 8. A workshop AGV-UAV collaborative material distribution path planning system, based on a workshop AGV-UAV collaborative material distribution path planning method according to claim 1, characterized in that it comprises: The obtaining unit is used to obtain the initial parameters of the material distribution path using AGV and UAV; The modeling unit is used to construct a path optimization model for AGV-UAV collaborative material distribution based on the initial parameters, with the energy consumption of all processes of UAV and AGV material distribution as the optimization target; The solving unit is used to solve the path planning optimization model by using the improved genetic algorithm according to the constraint conditions, and obtain the optimal path planning scheme.