AGV transportation path optimization decision system and method combined with genetic algorithm

Abstract

The present invention discloses an AGV transportation path optimization decision system and method combined with a genetic algorithm, which relates to the field of transportation path optimization, including: drawing the plane coordinate system of the AGV transportation path in a proportional scaling manner; determining the fitness function of the AGV transportation path selection in a distance / time optimal manner; obtaining the parent population and the child population, and screening out the initial optimal path; identifying sudden obstacles in the AGV transportation path, and judging whether the obstacles can be passed; updating the parent population, and re-screening out the optimal AGV transportation path; setting an AGV transportation path display platform, and recording and displaying the AGV transportation situation in real time. The advantages of the present invention are: effectively screening out the optimal AGV transportation path, overcoming the path decision problem of the AGV when sudden obstacles occur in the transportation path to a great extent, and effectively improving the AGV transportation efficiency.

Description

Technical Field

[0001] The present invention relates to the field of transport path optimization, and in particular to an AGV transport path optimization decision system and method combined with a genetic algorithm. Background Art

[0002] With the development of artificial intelligence technology, more and more AGVs are applied to various industries. Optimizing the transportation path planning of AGVs and improving the transportation capacity of AGVs will be an important means to ensure the normal operation of corporate cargo transportation. Genetic algorithm is an optimization algorithm that simulates Darwin's biological evolution process. It is based on the principles of natural selection and genetics. It searches for the optimal solution or approximate optimal solution by simulating the biological evolution process in nature. By applying genetic algorithm to AGV transportation path optimization, it has significant advantages. It can globally search for the optimal solution and adapt to optimization problems of different scales, thereby improving the transportation capacity and efficiency of AGV.

[0003] The existing technology of using genetic algorithms to optimize AGV transportation paths mainly focuses on the allocation of AGV to multiple targets and improving the algorithm's optimization ability. However, this type of technology lacks the ability to deal with sudden obstacles during transportation. As a result, after the AGV has planned the transportation path, it lacks the ability to deal with sudden obstacles and blocks, making it difficult to move forward according to the planned route, causing the AGV to stagnate and delaying the normal transportation of goods. Summary of the invention

[0004] In order to solve the above technical problems, an AGV transport path optimization decision system and method combined with a genetic algorithm is provided. This technical solution solves the problem that the above-mentioned background technology is lack of the ability to deal with sudden obstacles during transportation, resulting in the AGV lacking the ability to deal with sudden obstacles after planning the transport path, making it difficult to move forward according to the predetermined route, causing the AGV to stagnate and delaying the normal transportation of goods.

[0005] In order to achieve the above purpose, the technical solution adopted by the present invention is:

[0006] A method for optimizing AGV transportation path decision-making combined with a genetic algorithm, characterized by comprising:

[0007] According to the actual situation of the AGV transportation path, draw the plane coordinate system of the AGV transportation path in a proportional scaling manner;

[0008] According to the intersection situation in the AGV transportation path, the transfer node is set, and the fitness function of the AGV transportation path selection is determined in the optimal distance / time manner;

[0009] According to the fitness function of AGV transport path selection, the path combination with the minimum value and its adjacent values ​​is selected as the parent population, and crossover and mutation are performed to obtain the child population to screen out the initial optimal path;

[0010] Based on image recognition technology, it can identify sudden obstacles in the AGV transportation path and determine whether it can pass through the obstacles;

[0011] According to the identification of sudden obstacles in the AGV transportation path, the parent population is updated and the optimal AGV transportation path is re-screened;

[0012] Based on the Internet of Things technology, an AGV transportation path display platform is set up to record and display the AGV transportation status in real time.

[0013] Preferably, drawing the plane coordinate system of the AGV transport path in a proportional scaling manner according to the actual situation of the AGV transport path specifically includes:

[0014] According to the actual situation of the AGV transportation path, obtain the road length, width, intersection location information of the AGV transportation path and the average moving speed information of the road AGV;

[0015] According to the AGV's appearance design, obtain the AGV's appearance information and set the narrowest distance of the road for safe passage;

[0016] According to the actual measurement of the AGV transport path, the road information and AGV appearance information of the AGV transport path are scaled by proportional scaling and drawn into a plane coordinate system, and the road information and AGV appearance information of the AGV transport path are generated in the coordinate system.

[0017] Preferably, the transfer node is set according to the intersection situation in the AGV transportation path, and the fitness function for determining the AGV transportation path selection in the distance / time optimal manner specifically includes:

[0018] According to the intersection of the AGV transportation path, mark it in the plane coordinate system and set it as a transfer node, so that the AGV can change the transportation path through the transfer node;

[0019] Obtain the shortest transportation distance of the AGV transportation path according to the optimal distance method;

[0020] Obtain the shortest transportation time of the AGV transportation path based on the time-optimal method;

[0021] Based on big data, obtain the energy consumption coefficient and limit threshold of the shortest transportation distance of the AGV transportation path, as well as the energy consumption coefficient and limit threshold of the shortest transportation time of the AGV transportation path;

[0022] According to the actual demand of AGV transportation, determine the fitness function of AGV transportation path selection;

[0023] The optimal distance expression is:

[0024] ;

[0025] In the formula, is the shortest transportation distance of the AGV transportation path, For the The total transport distance of the AGV transport path combination, For the The number of paths for AGV transport path combinations, For the AGV transport paths, The number of combinations of AGV transport path combinations;

[0026] The time optimal expression is:

[0027] ;

[0028] In the formula, is the shortest transportation time of the AGV transportation path, To pass the The average moving speed of AGVs in the AGV transport path;

[0029] The fitness function of the AGV transport path selection is:

[0030] ;

[0031] In the formula, The fitness function for AGV transport path selection, is the energy consumption coefficient of the shortest transportation distance of the AGV transportation path, is the energy consumption coefficient of the shortest transportation time of the AGV transportation path, is the threshold value of the shortest transportation distance of the AGV transportation path, It is the limiting threshold of the shortest transportation time of the AGV transportation path.

[0032] Preferably, the fitness function selected according to the AGV transport path selects the path combination of the minimum value and its adjacent values ​​as the parent population, and performs crossover and mutation to obtain the child population, and the screening of the initial optimal path specifically includes:

[0033] Select the fitness function according to the AGV transportation path and select The AGV transport path selects the path combination with the minimum fitness value and its adjacent values ​​as the parent population;

[0034] According to the ratio of the fitness value of the AGV transport path selection in the parent population to the total population, the probability of being selected as the child generation is determined, and the The maximum probability value and its adjacent values ​​are taken as the next generation population;

[0035] According to the sub-generation population, crossover and mutation processing is performed on the sub-generation population to obtain A new sub-generation population;

[0036] The parent population combinations and the new sub-generation population Combinations, merged into one of the population, and screened out Each AGV transport path selects the path combination with the minimum fitness value and its adjacent values;

[0037] Repeat the above operation until the optimal AGV transport path combination is iterated out, and define the AGV transport path combination as the initial optimal path.

[0038] Preferably, the method of identifying sudden obstacles in the AGV transport path based on image recognition technology and judging whether the obstacle can be passed specifically includes:

[0039] Integrate image acquisition devices on AGV to collect image information on the transportation path in real time;

[0040] Image recognition technology based on Canny operator edge detection can obtain the outer contour information of sudden obstacles in the AGV transportation path;

[0041] According to the outer contour information of the obstacle and the road surface information of the transportation path, the remaining passable distance of the road occupied by the sudden obstacle is calculated;

[0042] According to the remaining passable distance of the road occupied by the sudden obstacle, determine whether the distance is greater than the narrowest distance of the road that the AGV can safely pass. If so, it means that the AGV can pass safely and continue to move forward according to the original path combination. If not, it means that the AGV is difficult to pass the obstacle safely and needs to re-plan the route.

[0043] Preferably, the updating of the parent population according to the identification of sudden obstacles in the AGV transport path and re-screening the optimal AGV transport path specifically includes:

[0044] According to the identification of sudden obstacles in the AGV transportation path, further judgment is made on the AGV transportation path selection;

[0045] When the AGV can pass safely, the AGV continues to move forward along the original path combination;

[0046] When the AGV has difficulty passing through an obstacle safely, obtain the position information of the AGV, and take this point as the starting point. According to the information of this point, re-obtain the parental population, and re-screen the optimal AGV transportation path according to the initial optimal path determination method.

[0047] Preferably, based on the Internet of Things technology, an AGV transportation path display platform is set up for real-time recording and display of the AGV transportation situation, which specifically includes:

[0048] Based on the Internet of Things technology, an AGV transportation path display platform is set up for building an operation environment for screening the optimal AGV transportation path;

[0049] Based on the AGV transportation path display platform, through human-computer interaction settings, set the starting point and the ending point of the AGV transportation path;

[0050] Based on the AGV transportation path display platform, it is used for real-time recording and display of the AGV transportation situation, and to give early warnings for abnormal events in a timely manner;

[0051] Based on the AGV transportation path display platform, it is used for updating and optimizing the screening of the optimal AGV transportation path algorithm, and for updating new routes.

[0052] Furthermore, this solution proposes an AGV transportation path optimization decision system combined with a genetic algorithm for implementing the AGV transportation path optimization decision method combined with a genetic algorithm as described above, including:

[0053] A coordinate system establishment module, which is used to draw a plane coordinate system of the AGV transportation path according to the actual situation of the AGV transportation path in a way of equal-proportion scaling;

[0054] An initial optimal path module, which is used to set transfer nodes according to the intersection situation in the AGV transportation path, and determine the fitness function for AGV transportation path selection in the optimal way of distance / time; according to the fitness function for AGV transportation path selection, select the path combination of the minimum value and its adjacent values as the parental population, and perform crossover and mutation to obtain the offspring population, and screen out the initial optimal path;

[0055] An optimal path module, which is used to identify sudden obstacles in the AGV transportation path based on image recognition technology, and judge whether it can pass through the obstacles; according to the identification situation of sudden obstacles in the AGV transportation path, update the parental population, and re-screen the optimal AGV transportation path;

[0056] The display platform module is used to set up an AGV transportation path display platform based on the Internet of Things technology, and is used to record and display the AGV transportation status in real time.

[0057] Preferably, the initial optimal path module specifically includes:

[0058] A fitness function unit, wherein the fitness function unit is used to set a transfer node according to the intersection situation in the AGV transportation path, and determine the fitness function of the AGV transportation path selection in a distance / time optimal manner;

[0059] The initial optimal path unit is used to select the path combination of the minimum value and its adjacent values ​​as the parent population according to the fitness function of the AGV transport path selection, and perform crossover and mutation to obtain the child population to screen out the initial optimal path.

[0060] Preferably, the optimal path module specifically includes:

[0061] An obstacle recognition unit, which is used to recognize sudden obstacles in the AGV transportation path based on image recognition technology and determine whether the obstacle can be passed;

[0062] The optimal path unit is used to update the parent population according to the identification of sudden obstacles in the AGV transportation path, and re-screen the optimal AGV transportation path.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] By establishing the relationship between the actual transportation environment and the plane coordinate system, the AGV transportation environment is expressed in the coordinate form of the plane coordinate system, thereby improving the processing capacity of transportation road data. Secondly, through the basic content of the genetic algorithm, the fitness function of the AGV transportation path selection is built, and the parent population is screened out in the distance / time optimal way, and the offspring population is obtained according to crossover and mutation, so as to screen out the initial optimal path through the iteration of the algorithm. Finally, the outer contour information of the sudden obstacle in the AGV transportation path is obtained through the image recognition technology of the Canny operator edge detection. By judging whether the remaining passable distance of the road occupied by the sudden obstacle is greater than the minimum distance of the road that the AGV can safely pass, according to the judgment situation, the AGV is guided to obtain the optimal transportation path, thereby effectively screening out the optimal AGV transportation path, and to a great extent overcoming the path decision problem of the AGV when there are sudden obstacles in the transportation path, effectively improving the AGV transportation efficiency and the robustness of the genetic algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] Figure 1A flow chart of an AGV transport path optimization decision method combined with a genetic algorithm according to the present invention;

[0066] Figure 2 The present invention sets the transfer node according to the intersection situation in the AGV transportation path, and determines the fitness function flow chart of the AGV transportation path selection in the distance / time optimal way;

[0067] Figure 3 Based on the image recognition technology of the present invention, sudden obstacles in the AGV transportation path are identified and whether the obstacle can be passed is determined. DETAILED DESCRIPTION

[0068] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments described below are only examples, and those skilled in the art may think of other obvious variations.

[0069] Reference Figure 1 As shown, a AGV transportation path optimization decision method combined with a genetic algorithm includes:

[0070] According to the actual situation of the AGV transportation path, draw the plane coordinate system of the AGV transportation path in a proportional scaling manner;

[0071] According to the intersection situation in the AGV transportation path, the transfer node is set, and the fitness function of the AGV transportation path selection is determined in the optimal distance / time manner;

[0072] According to the fitness function of AGV transport path selection, the path combination with the minimum value and its adjacent values ​​is selected as the parent population, and crossover and mutation are performed to obtain the child population to screen out the initial optimal path;

[0073] Based on image recognition technology, it can identify sudden obstacles in the AGV transportation path and determine whether it can pass through the obstacles;

[0074] According to the identification of sudden obstacles in the AGV transportation path, the parent population is updated and the optimal AGV transportation path is re-screened;

[0075] Based on the Internet of Things technology, an AGV transportation path display platform is set up to record and display the AGV transportation status in real time.

[0076] It can be understood that this solution, by establishing the relationship between the actual transportation environment and the plane coordinate system, expresses the AGV transportation environment in the form of coordinates of the plane coordinate system, thereby improving the processing capacity of transportation road surface data. Secondly, through the basic content of the genetic algorithm, the fitness function of the AGV transportation path selection is built, and the parent population is screened out in the distance / time optimal way, and the offspring population is obtained according to crossover and mutation, so as to screen out the initial optimal path through the iteration of the algorithm. Finally, the outer contour information of the sudden obstacle in the AGV transportation path is obtained through the image recognition technology of the Canny operator edge detection. By judging whether the remaining passable distance of the road occupied by the sudden obstacle is greater than the minimum distance of the road that the AGV can safely pass, according to the judgment situation, the AGV is guided to obtain the optimal transportation path, thereby effectively screening out the optimal AGV transportation path, and to a great extent overcoming the path decision problem of the AGV when there are sudden obstacles in the transportation path, and effectively improving the AGV transportation efficiency and the robustness of the genetic algorithm.

[0077] Reference Figure 2 As shown, the transfer node is set according to the intersection situation in the AGV transportation path, and the fitness function for determining the AGV transportation path selection in the distance / time optimal manner specifically includes:

[0078] According to the intersection of the AGV transportation path, mark it in the plane coordinate system and set it as a transfer node, so that the AGV can change the transportation path through the transfer node;

[0079] Obtain the shortest transportation distance of the AGV transportation path according to the optimal distance method;

[0080] Obtain the shortest transportation time of the AGV transportation path based on the time-optimal method;

[0081] Based on big data, obtain the energy consumption coefficient and limit threshold of the shortest transportation distance of the AGV transportation path, as well as the energy consumption coefficient and limit threshold of the shortest transportation time of the AGV transportation path;

[0082] According to the actual demand of AGV transportation, determine the fitness function of AGV transportation path selection;

[0083] The optimal distance expression is:

[0084] ;

[0085] In the formula, is the shortest transportation distance of the AGV transportation path, For the The total transport distance of the AGV transport path combination, For the The number of paths for AGV transport path combinations, For the AGV transport paths, The number of combinations of AGV transport path combinations;

[0086] The time optimal expression is:

[0087] ;

[0088] In the formula, is the shortest transportation time of the AGV transportation path, To pass the The average moving speed of AGVs in the AGV transport path;

[0089] The fitness function of the AGV transport path selection is:

[0090] ;

[0091] In the formula, The fitness function for AGV transport path selection, is the energy consumption coefficient of the shortest transportation distance of the AGV transportation path, is the energy consumption coefficient of the shortest transportation time of the AGV transportation path, is the threshold value of the shortest transportation distance of the AGV transportation path, It is the limiting threshold of the shortest transportation time of the AGV transportation path.

[0092] It is understandable that when screening the optimal AGV transportation path, it is necessary to consider the transportation time and transportation distance, as well as the conditions of the transportation road surface and the impact of energy consumption. This solution introduces the energy consumption coefficient and limit threshold of the shortest transportation distance of the AGV transportation path, as well as the energy consumption coefficient and limit threshold of the shortest transportation time of the AGV transportation path while establishing the optimal AGV transportation distance and optimal time expressions, thereby establishing the fitness function of the AGV transportation path selection, comprehensively considering the AGV transportation path selection under the influence of multiple factors, and effectively screening out a more suitable parent population. Among them, the energy consumption coefficient refers to the energy consumption loss ratio of the total AGV transportation distance, which can be confirmed by the following formula:

[0093] ;

[0094] In the formula, is the energy loss ratio of the total AGV transportation distance, that is, the energy consumption coefficient, For the The friction coefficient of the road section, For the overall quality of AGV and transported goods, is the acceleration due to gravity, To pass the The average moving speed of AGVs in the AGV transport path, To pass the AGV transport time for each AGV transport path, is the number of AGV transport paths, is the total kinetic energy of the AGV;

[0095] Among them, the limited threshold refers to the introduction of a balance limit value on the basis of determining the optimal AGV transportation distance and optimal time, which is used to adjust the numerical error when judging which of the two is better. The limited threshold can be obtained based on big data by conducting test experiments and comparing the data after path selection during transportation of AGVs in different sections.

[0096] Reference Figure 3 As shown, the image recognition technology is used to identify sudden obstacles in the AGV transportation path and determine whether the obstacle can be passed, specifically including:

[0097] Integrate image acquisition devices on AGV to collect image information on the transportation path in real time;

[0098] Image recognition technology based on Canny operator edge detection can obtain the outer contour information of sudden obstacles in the AGV transportation path;

[0099] According to the outer contour information of the obstacle and the road surface information of the transportation path, the remaining passable distance of the road occupied by the sudden obstacle is calculated;

[0100] According to the remaining passable distance of the road occupied by the sudden obstacle, determine whether the distance is greater than the narrowest distance of the road that the AGV can safely pass. If so, it means that the AGV can pass safely and continue to move forward according to the original path combination. If not, it means that the AGV is difficult to pass the obstacle safely and needs to re-plan the route.

[0101] It is understandable that the use of genetic algorithms can effectively determine the initial optimal path of the AGV transportation path, but the AGV may be affected by sudden obstacles during the transportation process, resulting in the AGV lacking the ability to deal with sudden obstacles after planning the transportation path, making it difficult to move forward according to the planned route, delaying the normal transportation of goods. This solution uses the image recognition technology of Canny operator edge detection to obtain the outer contour information of sudden obstacles in the AGV transportation path, and judges whether the remaining passable distance of the road occupied by the sudden obstacle is greater than the minimum distance of the road that the AGV can safely pass. According to the judgment, the AGV is guided to obtain the optimal transportation path, thereby effectively screening out the optimal AGV transportation path, thereby overcoming the path decision problem of the AGV when there are sudden obstacles in the transportation path to a great extent, and effectively improving the AGV transportation efficiency and the robustness of the genetic algorithm.

[0102] Furthermore, based on the same inventive concept as the above AGV transportation path optimization decision-making method combined with the genetic algorithm, this solution proposes an AGV transportation path optimization decision-making system combined with the genetic algorithm, including:

[0103] A coordinate system establishment module, which is used to draw a plane coordinate system of the AGV transportation path according to the actual situation of the AGV transportation path in a way of equal proportion scaling;

[0104] An initial optimal path module, which is used to set transfer nodes according to the intersection situation in the AGV transportation path, determine the fitness function for AGV transportation path selection in the optimal way of distance / time; according to the fitness function for AGV transportation path selection, select the path combination of the minimum value and its adjacent values as the parental population, and perform crossover and mutation to obtain the offspring population, and screen out the initial optimal path;

[0105] An optimal path module, which is used to identify sudden obstacles in the AGV transportation path based on image recognition technology and judge whether it can pass through the obstacles; according to the identification situation of sudden obstacles in the AGV transportation path, update the parental population and re-screen out the optimal AGV transportation path;

[0106] A display platform module, which is used to set up an AGV transportation path display platform based on the Internet of Things technology for real-time recording and displaying of AGV transportation conditions;

[0107] The initial optimal path module specifically includes:

[0108] A fitness function unit, which is used to set transfer nodes according to the intersection situation in the AGV transportation path and determine the fitness function for AGV transportation path selection in the optimal way of distance / time;

[0109] An initial optimal path unit, which is used to select the path combination of the minimum value and its adjacent values as the parental population according to the fitness function for AGV transportation path selection, and perform crossover and mutation to obtain the offspring population, and screen out the initial optimal path;

[0110] The optimal path module specifically includes:

[0111] An obstacle recognition unit, which is used to identify sudden obstacles in the AGV transportation path based on image recognition technology and judge whether it can pass through the obstacles;

[0112] The optimal path unit is used to update the parent population according to the identification of sudden obstacles in the AGV transportation path, and re-screen the optimal AGV transportation path.

[0113] In summary, the advantages of the present invention are: by establishing the relationship between the actual transportation environment and the plane coordinate system, the AGV transportation environment is expressed in the coordinate form of the plane coordinate system, thereby improving the processing capacity of the transportation road surface data; secondly, through the basic content of the genetic algorithm, the fitness function of the AGV transportation path selection is built, and the parent population is screened out in the distance / time optimal manner, and the offspring population is obtained according to the crossover and mutation, so that the initial optimal path is screened out through the iteration of the algorithm; finally, the outer contour information of the sudden obstacle in the AGV transportation path is obtained through the image recognition technology of the Canny operator edge detection, and by judging whether the remaining passable distance of the road occupied by the sudden obstacle is greater than the minimum distance of the road that the AGV can safely pass, according to the judgment situation, the AGV is guided to obtain the optimal transportation path, thereby effectively screening out the optimal AGV transportation path, and to a great extent overcoming the path decision problem of the AGV when there are sudden obstacles in the transportation path, and effectively improving the AGV transportation efficiency and the robustness of the genetic algorithm.

[0114] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions only describe the principles of the present invention. The present invention may be subject to various changes and improvements without departing from the spirit and scope of the present invention. These changes and improvements fall within the scope of the present invention. The scope of protection claimed by the present invention is defined by the attached claims and their equivalents.

Claims

1. An AGV transportation path optimization decision method combined with genetic algorithm, characterized in that: include: According to the actual situation of the AGV transportation path, draw the plane coordinate system of the AGV transportation path in a proportional scaling manner; According to the intersection situation in the AGV transportation path, the transfer node is set, and the shortest transportation distance and the shortest transportation time of the AGV transportation are obtained in the optimal distance / time manner. According to the shortest transportation distance and the shortest transportation time of the AGV transportation path, combined with the energy consumption coefficient of the path and time and the limited threshold, the fitness function of the AGV transportation path selection is determined; According to the fitness function of AGV transport path selection, the path combination with the minimum value and its adjacent values ​​is selected as the parent population, and crossover and mutation are performed to obtain the child population to screen out the initial optimal path; Based on image recognition technology, it can identify sudden obstacles in the AGV transportation path and determine whether it can pass through the obstacles; According to the identification of sudden obstacles in the AGV transportation path, the parent population is updated and the optimal AGV transportation path is re-screened; Based on the Internet of Things technology, an AGV transportation path display platform is set up to record and display the AGV transportation status in real time; The method of setting the transfer node according to the intersection situation in the AGV transportation path and determining the shortest transportation distance and shortest transportation time of the AGV transportation according to the distance / time optimal method specifically includes: According to the intersection of the AGV transportation path, mark it in the plane coordinate system and set it as a transfer node, so that the AGV can change the transportation path through the transfer node; Obtain the shortest transportation distance of the AGV transportation path according to the optimal distance method; Obtain the shortest transportation time of the AGV transportation path based on the time-optimal method; The optimal distance expression is: Where, L min is the shortest transportation distance of the AGV transportation path, is the total transport distance of the i-th AGV transport path combination, n i is the number of paths of the i-th AGV transport path combination, L i is the i-th AGV transport path, and m is the number of combinations of AGV transport path combinations; The time optimal expression is: Where, T min is the shortest transportation time of the AGV transportation path, is the average moving speed of the AGV passing through the i-th AGV transport path; The fitness function for determining the AGV transport path selection specifically includes: Based on big data, obtain the energy consumption coefficient and limit threshold of the shortest transportation distance of the AGV transportation path, as well as the energy consumption coefficient and limit threshold of the shortest transportation time of the AGV transportation path; According to the shortest transportation distance and shortest transportation time of the AGV transportation path, combined with the energy consumption coefficient of the path and time and the limited threshold, the fitness function of the AGV transportation path selection is determined; The fitness function of the AGV transport path selection is: Where F is the fitness function of AGV transport path selection, α1 is the energy consumption coefficient of the shortest transport distance of the AGV transport path, α2 is the energy consumption coefficient of the shortest transport time of the AGV transport path, β1 is the limited threshold of the shortest transport distance of the AGV transport path, β2 is the limited threshold of the shortest transport time of the AGV transport path, the energy consumption coefficient refers to the energy consumption loss ratio of the total AGV transport distance, and the limited threshold refers to the introduction of a balance limit value based on the determination of the optimal AGV transport distance and the optimal time, which is used to adjust the numerical error when judging which of the two is better.

2. The AGV transportation path optimization decision method combined with genetic algorithm according to claim 1 is characterized in that: According to the actual situation of the AGV transportation path, the plane coordinate system of the AGV transportation path is drawn in a proportional scaling manner, specifically including: According to the actual situation of the AGV transportation path, obtain the road length, width, intersection location information of the AGV transportation path and the average moving speed information of the road AGV; According to the AGV's appearance design, obtain the AGV's appearance information and set the narrowest distance of the road for safe passage; According to the actual measurement of the AGV transport path, the road information and AGV appearance information of the AGV transport path are scaled by proportional scaling and drawn into a plane coordinate system, and the road information and AGV appearance information of the AGV transport path are generated in the coordinate system.

3. The AGV transportation path optimization decision method combined with genetic algorithm according to claim 2 is characterized in that: The fitness function selected according to the AGV transport path selects the path combination of the minimum value and its adjacent values ​​as the parent population, and performs crossover and mutation to obtain the child population, and screens out the initial optimal path specifically including: According to the AGV transport path selection fitness function, select the path combination with the minimum fitness value of N AGV transport path selection and its adjacent values ​​as the parent population; According to the ratio of the fitness value of the AGV transport path selection in the parent population to the total population, the probability of being selected as the next generation is determined, and the M maximum probability values ​​and their adjacent values ​​are selected as the next generation population; According to the sub-generation population, crossover and mutation processing is performed on the sub-generation population to obtain M new sub-generation populations; Merge the N combinations in the parent population and the M combinations in the new child population into an M+N population, and select the path combination with the minimum fitness value and its adjacent values ​​of N AGV transport path selection in the merged population; Repeat the above operation until the optimal AGV transport path combination is iterated out, and define the AGV transport path combination as the initial optimal path.

4. The AGV transportation path optimization decision method combined with genetic algorithm according to claim 3 is characterized in that: The image recognition technology is used to identify sudden obstacles in the AGV transportation path and determine whether the obstacle can be passed, which specifically includes: Integrate image acquisition devices on AGV to collect image information on the transportation path in real time; Image recognition technology based on Canny operator edge detection can obtain the outer contour information of sudden obstacles in the AGV transportation path; According to the outer contour information of the obstacle and the road surface information of the transportation path, the remaining passable distance of the road occupied by the sudden obstacle is calculated; According to the remaining passable distance of the road occupied by the sudden obstacle, determine whether the distance is greater than the narrowest distance of the road that the AGV can safely pass. If so, it means that the AGV can pass safely and continue to move forward according to the original path combination. If not, it means that the AGV is difficult to pass the obstacle safely and needs to re-plan the route.

5. The AGV transportation path optimization decision method combined with genetic algorithm according to claim 4 is characterized in that: The updating of the parent population according to the identification of sudden obstacles in the AGV transport path and the re-screening of the optimal AGV transport path specifically include: According to the identification of sudden obstacles in the AGV transportation path, further judgment is made on the AGV transportation path selection; When the AGV can pass safely, the AGV continues to move forward along the original path combination; When it is difficult for the AGV to pass through obstacles safely, the location information of the AGV is obtained, and this point is used as the starting point. According to the information of this point, the parent population is re-obtained, and the optimal AGV transportation path is re-screened according to the initial optimal path determination method.

6. The AGV transportation path optimization decision method combined with genetic algorithm according to claim 5 is characterized in that: The AGV transportation path display platform is set up based on the Internet of Things technology to record and display the AGV transportation situation in real time, specifically including: Based on the Internet of Things technology, an AGV transportation path display platform is set up to build a computing environment for screening the optimal AGV transportation path; Based on the AGV transport path display platform, set the starting point and end point of the AGV transport path through human-computer interaction settings; Based on the AGV transportation path display platform, it is used to record and display the AGV transportation status in real time and issue early warnings for abnormal events in a timely manner; Based on the AGV transport path display platform, it is used to update and optimize the screening of AGV transport optimal path algorithms, as well as the update of new routes.

7. An AGV transport path optimization decision system combined with genetic algorithm, characterized in that: The method for optimizing the AGV transport path according to any one of claims 1 to 6 and combining the genetic algorithm comprises: A coordinate system establishment module is used to draw a plane coordinate system of the AGV transport path in a proportional scaling manner according to the actual situation of the AGV transport path; An initial optimal path module, which is used to set transfer nodes according to the intersection conditions in the AGV transport path, and determine the fitness function of the AGV transport path selection in a distance / time optimal manner; according to the fitness function of the AGV transport path selection, select the path combination of the minimum value and its adjacent values ​​as the parent population, and perform crossover and mutation to obtain the child population, and screen out the initial optimal path; The optimal path module is used to identify sudden obstacles in the AGV transportation path based on image recognition technology and determine whether the obstacles can be passed; according to the identification of sudden obstacles in the AGV transportation path, the parent population is updated and the optimal AGV transportation path is re-screened; The display platform module is used to set up an AGV transportation path display platform based on the Internet of Things technology, and is used to record and display the AGV transportation status in real time.

8. The AGV transportation path optimization decision system combined with genetic algorithm according to claim 7 is characterized in that: The initial optimal path module specifically includes: A fitness function unit, wherein the fitness function unit is used to set a transfer node according to the intersection situation in the AGV transportation path, and determine the fitness function of the AGV transportation path selection in a distance / time optimal manner; The initial optimal path unit is used to select the path combination of the minimum value and its adjacent values ​​as the parent population according to the fitness function of the AGV transport path selection, and perform crossover and mutation to obtain the child population to screen out the initial optimal path.

9. The AGV transportation path optimization decision system combined with genetic algorithm according to claim 8, characterized in that: The optimal path module specifically includes: An obstacle recognition unit, which is used to recognize sudden obstacles in the AGV transportation path based on image recognition technology and determine whether the obstacle can be passed; The optimal path unit is used to update the parent population according to the identification of sudden obstacles in the AGV transportation path, and re-screen the optimal AGV transportation path.

Images