Dynamic vehicle path planning method considering workshop empty material distribution turnover vehicle recovery

Abstract

The invention discloses a dynamic vehicle path planning method considering workshop empty material distribution turnover vehicle recovery. The method comprises the following steps: step 1, establishing a target function and a constraint condition of a multi-target material distribution path planning model; 2, an improved NSGA-II algorithm is adopted to solve the multi-target material distribution path planning model, a non-dominated solution set is obtained, an optimal non-dominated solution in the non-dominated solution set is found, and therefore a current material transportation path is obtained; and step 3, judging whether the vehicle completes material distribution or not, and if the vehicle completes material distribution, selecting an optimal empty tool recovery task which does not affect the subsequent distribution task and dynamically inserting the optimal empty tool recovery task into the current material transportation path. According to the method, the efficiency of logistics distribution and the utilization efficiency of resources are improved, complex distribution and recovery tasks can be processed, the complexity of the problem is simplified through the step-by-step optimization strategy of the algorithm, and the problem is easier to manage and optimize.

Description

Technical Field

[0001] The invention relates to the field of material distribution path planning methods, and in particular to a dynamic vehicle path planning method that takes into account the recovery of empty material distribution turnover vehicles in a workshop. Background Art

[0002] In modern manufacturing, material distribution has an extremely important impact on production efficiency and cost control. The recycling of empty material distribution vehicles accounts for a considerable proportion, which is directly related to distribution efficiency and vehicle utilization. With the rapid development of industrial Internet of Things technology, the combination of advanced Internet of Things equipment and production and manufacturing technology has become a new development trend. The new demand model combined with new information technology has also put forward higher requirements for material distribution in the intelligent manufacturing environment. With the acceleration of industrialization and the further growth of industrial production capacity, the use of material distribution vehicles has also increased day by day. Under the multiple pressures of resource utilization and economic benefits, the material distribution form of 1:n demand stations towing a certain number of material distribution vehicles by traction AGV is widely used in actual production, especially for intermediate industrial products such as parts and raw materials, which have large production quantities and high consumption rates, and the resulting material transportation needs are also relatively large.

[0003] At present, the material distribution of traditional manufacturing workshops has the following problems in theoretical research and production practice:

[0004] (1) At present, the research on reverse logistics of material distribution mainly focuses on material recycling and waste disposal. However, in the actual production process of manufacturing workshops, empty material distribution tools are also a common and non-negligible link. These tools need to be effectively recycled after completing material transportation to reduce resource waste and improve overall efficiency. However, existing research ignores this point, which may cause workshops to face problems of inefficiency and resource waste in actual operations. In order to improve overall efficiency and reduce waste, research on the recycling of empty material transportation tools should be strengthened.

[0005] (2) Since the material distribution problem has the characteristics of an NP-hard problem, the solution methods currently focus on heuristic and meta-heuristic algorithms. In the process of solving multi-objective optimization problems, weighting is usually used to integrate many objectives and convert them into a single objective problem for easy solution. However, this approach may lead to subjective and one-sided results, and the conflicts and trade-offs between different objectives are difficult to accurately quantify.

[0006] (3) Traditional material distribution research mainly focuses on solving static problems, that is, once the distribution path is determined, it will no longer be adjusted during the entire distribution process. In actual production, there are often disturbances from various uncertain factors, which may cause the originally planned distribution path to be unable to adapt to the actual situation. The distribution process may need to be adjusted dynamically in real time. At present, research on dynamic distribution mainly focuses on equipment failure and material shortages, and there is little research on the problem of distribution path planning combined with the recovery of empty material distribution turnover vehicles. Summary of the invention

[0007] The present invention provides a dynamic vehicle path planning method that takes into account the recovery of empty material distribution turnover vehicles in the workshop, so as to solve the problems of the material distribution path planning method in the prior art, such as ignoring the empty material distribution turnover vehicles, the subjective and one-sided results of solving the material distribution problem, and the inability to dynamically adjust the planned distribution path.

[0008] In order to achieve the above object, the technical solution adopted by the present invention is:

[0009] The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in the workshop includes the following steps:

[0010] Step 1: Analyze the multi-objective material distribution problem in the workshop and establish the objective function and constraint conditions of the multi-objective material distribution path planning model;

[0011] Step 2: Use the improved NSGA-II algorithm to solve the multi-objective material distribution path planning model established in step 1, obtain a non-dominated solution set, and find the optimal non-dominated solution, thereby obtaining the current material transportation path;

[0012] Step 3: Use the Internet of Things technology to monitor the status of the distribution point in real time to determine whether the vehicle has completed the material delivery. If the vehicle has completed the material delivery, select the optimal empty tooling recovery task that does not affect subsequent delivery tasks and dynamically insert it into the current material transportation path obtained in step 2.

[0013] In the further step 1, the objective function of the multi-objective material distribution path planning model aims to minimize the total cost f1 of the distribution vehicle assignment, the total cost f2 of the path distribution, and the total cost f3 of the penalty of the demand workstation time window.

[0014] In the further step 1, the constraints of the multi-objective material distribution path planning model include: each workstation is served only once and only one vehicle performs the task, the upper limit of the number of turnover material vehicles that each AGV can tow is the set Wmax vehicles, the vehicles arriving at and leaving the workstation are the same, and the starting point and end point of the vehicle are both the distribution center.

[0015] In the further step 2, the fitness of all non-dominated solutions in the non-dominated solution set is calculated, and the non-dominated solution with the most ideal fitness value is selected as the optimal solution for the current material transportation route, that is, the current material transportation route is obtained.

[0016] Furthermore, in step 3, the quadrant optimization strategy is used to select the optimal empty tooling recovery task that does not affect the subsequent delivery task and dynamically insert it into the current material transportation path obtained in step 2.

[0017] Furthermore, the constraints when using the quadrant optimization strategy include: the number of turnover vehicles towed by the trolley after the recovery task is inserted cannot exceed the maximum towable number constraint, and the inserted recovery task must not affect the normal delivery execution of subsequent delivery tasks.

[0018] The present invention proposes a material distribution strategy considering the empty material distribution vehicle in the workshop. Firstly, the material distribution process of the traction automatic guided vehicle (AGV) combined with the material distribution vehicle is analyzed, and the material distribution demand in the flexible workshop and the recycling demand of the empty material distribution vehicle are considered. Combined with the capacity constraint of the specific material distribution container, a multi-objective material distribution path planning model is established with the minimization of the total cost of the distribution vehicle assignment, the total cost of the path distribution and the total cost of the penalty of the demand station time window in the workshop material distribution process as the optimization objectives.

[0019] In order to solve the model, the present invention adopts a heuristic step-by-step optimization algorithm. First, the generation of multi-objective distribution task sequences is realized by using an improved non-dominated sorting genetic algorithm (NSGA-II), and then the dynamic recycling tasks are inserted into the existing distribution sequence by using a quadrant optimization strategy. Compared with the prior art, the present invention has the following advantages:

[0020] 1. Comprehensive consideration is given to material distribution and the recovery of empty material distribution turnover vehicles, which improves the efficiency of logistics distribution and the utilization efficiency of resources.

[0021] 2. Through the improved NSGA-II algorithm and quadrant optimization strategy, an effective multi-objective optimization solution is provided, which can handle complex distribution and recovery tasks.

[0022] 3. The algorithm's step-by-step optimization strategy simplifies the complexity of the problem, making it easier to manage and optimize. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 It is a flowchart of a method according to an embodiment of the present invention.

[0024] Figure 2 It is a layout diagram of workshop workstations in the experimental example of the present invention.

[0025] Figure 3 It is a comparison chart of the minimum value of the regularized fitness function in this practical experimental example.

[0026] Figure 4 It is a comparison diagram of the minimum path cost in this practical experimental example.

[0027] Figure 5 It is the comparison of the minimum penalty cost in this practical experimental example. DETAILED DESCRIPTION

[0028] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0029] like Figure 1 As shown, this embodiment discloses a dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in a workshop, comprising the following steps:

[0030] Step 1: Analyze the multi-objective material distribution problem in the workshop and establish the objective function and constraint conditions of the multi-objective material distribution path planning model.

[0031] In this embodiment, the multi-objective material distribution problem in a workshop is analyzed, and the following assumptions are made:

[0032] (1) There is only one distribution center in the workshop, and the starting and ending points of the traction material turnover vehicle are both the distribution center.

[0033] (2) Each detachable material cart is identical, and the starting, stopping, and collision of the cart are negligible, and the driving speed is constant.

[0034] (3) The material demand of each workstation shall not exceed the maximum loading capacity of a detachable material turnover vehicle. When the turnover vehicle is empty, a corresponding empty material distribution turnover vehicle recovery task is generated.

[0035] (4) Material demand information, distribution center and workstation coordinates are known, and all nodes in the path can be connected to each other.

[0036] (5) The requirements of each workstation cannot be split. Each material distribution vehicle is only responsible for the material distribution requirements of one workstation.

[0037] (6) The recovery tasks of empty material distribution vehicles are collected and uploaded through the logic controller of the workstation, and the material system can receive the generated recovery tasks in a timely and stable manner.

[0038] In this embodiment, the parameters and decision variables involved in the multi-objective material distribution path planning model to be constructed are shown in Table 1:

[0039] Table 1 Parameters and decision variables

[0040]

[0041]

[0042] Based on the above assumptions, the objective function of the multi-objective material distribution path planning model established in this embodiment aims to minimize the total cost f1 of the distribution vehicle assignment, the total cost f2 of the path distribution, and the total cost f3 of the penalty of the required workstation time window, where:

[0043] The total cost of delivery vehicle assignment f1 is the sum of the number of AGV deliveries multiplied by the fixed cost of a single delivery, as shown in formula (1):

[0044]

[0045] The total cost of path delivery f2 is the total distance traveled by the AGV during the delivery process multiplied by the path cost per unit length, as shown in formula (2):

[0046]

[0047] The total penalty cost f3 of the time window of the required workstation is the sum of the penalty costs of each required workstation, as shown in formula (3):

[0048]

[0049] Therefore, the objective function of the multi-objective material distribution path planning model established in this embodiment is shown in formula (4):

[0050] F={minf1∪minf2∪minf3} (4)

[0051] Based on the above assumptions, this embodiment also establishes the constraint conditions, penalty factors and decision variable attributes of the objective function of the multi-objective material distribution path planning model, as shown in formulas (5)-(11):

[0052]

[0053]

[0054] In formulas (5)-(11), formula (5) indicates that each workstation is served only once and only one vehicle performs the task; formula (6) indicates that the upper limit of the number of turnover vehicles that each AGV can pull is W. max Each vehicle starts from the distribution center and responds at most W at a time. max distribution demand; Formula (7) indicates that the vehicles arriving at and leaving the workstations are the same; Formula (8) indicates that the starting point and the end point of the vehicle are both the distribution center; Formula (9) indicates that the material is i Arriving at the workstation after time, the penalty factor is β. Formulas (10) and (11) are the attributes of decision variables.

[0055] That is, in this embodiment, the constraints of the multi-objective material distribution path planning model include: each workstation is served only once and only one vehicle performs the task, the upper limit of the number of turnover material vehicles that each AGV can tow is the set Wmax vehicles, the vehicles arriving at and leaving the workstation are the same, and the starting point and end point of the vehicle are both the distribution center.

[0056] Step 2: Use the improved NSGA-II algorithm to solve the multi-objective material distribution path planning model established in step 1, obtain the non-dominated solution set, and find the optimal non-dominated solution among them, thereby obtaining the current material transportation path.

[0057] In this embodiment, the improved NSGA-II algorithm process is as follows:

[0058] a. Encoding and decoding: The encoding process is an important part of the algorithm solution. The final output of the model is the material delivery order of different AGVs. Because it is necessary to consider the simultaneous delivery of multiple vehicles and the number of service stations for the delivery vehicles, natural number encoding is selected. The chromosome encoding structure is as follows:

[0059] 0,N i1 ,N i2 ,...N io ,0,N j1 ,N j2 ,...N jp ,0,...0

[0060] Among them, N jp —The pth delivery task of the jth vehicle is for workstation N jp Carry out material distribution tasks; 0—distribution center.

[0061] b. Population initialization: A random generation strategy is used to determine the initial population. Due to the constraint on the number of traction turnover vehicles, each chromosome in the initial population must be assigned to a workstation. The purpose of this step is to ensure that each chromosome clearly reflects the required workstations and their respective delivery order, while satisfying the constraints of vehicle allocation. In this way, a diverse starting point that meets the problem constraints can be provided for subsequent iterations of the algorithm. The steps for assigning vehicles to chromosomes in the initial population are as follows:

[0062] b1): Randomly generate a chromosome individual containing all required workstations.

[0063] b2): Considering the maximum number of traction turnover vehicles, the workstations on the chromosome are allocated to the AGV through different probability selections. The probability selection strategy here is: to make the car have a higher probability of being assigned to more demand workstations. That is, when the maximum number of traction turnover vehicles is set to 4, each AGV can pull up to 4 material turnover vehicles to different demand workstations to respond to demand tasks. The number of demand workstations to which the car is assigned is selected through the roulette strategy. The probability of being assigned to 1 workstation is 1 / 10, the probability of 2 workstations is 2 / 10, the probability of 3 workstations is 3 / 10, and the probability of 4 workstations is 4 / 10. After the demand workstations of the first car are allocated, all the remaining workstations are allocated.

[0064] b3): Repeat the above steps until the initial population size is reached.

[0065] c. Crossover strategy: A new uneven crossover strategy is designed to retain the excellent sub-path information of the parent generation and generate differentiated individuals in the population. The specific operations are as follows:

[0066] c1): Randomly select a subpath on the parent individual.

[0067] c2): The selected sub-segments are placed in front, thus generating some differentiated individuals in the population. This helps prevent the algorithm from falling into a local optimal solution and makes it possible to find a better solution in the search space.

[0068] c3): For the daughter chromosome 1, first select the subpath A in the parent chromosome 1 as the component of the daughter chromosome 1. Then, select those codes that are not in the subpath A from the parent chromosome 2, and add these codes to the end of the subpath A according to the original order of the parent chromosome 2. Finally, attach the code 0 to the tail of the daughter chromosome.

[0069] c4): For chromosome 1, in the position after subpath A, considering the number of turnover vehicles, fill the code 0 twice through the roulette workstation allocation strategy to obtain two offspring chromosomes. Calculate the dominance of the two individuals obtained, select the better solution to enter the offspring population, and randomly select individuals to enter the offspring population when no choice can be made in the non-dominated situation. Similarly, obtain offspring chromosome 2.

[0070] d. Mutation strategy: In order to enhance the search ability of individuals, a two-point swap mutation strategy is implemented for chromosomes. A random number is generated and checked to see if the number is lower than the preset mutation probability. If the condition is met, the mutation operation is performed. At the same time, the legitimacy of the chromosome individual after mutation must be guaranteed. If the mutated chromosome is an infeasible solution, the chromosome is mutated again until two valid chromosomes are generated. One of the two mutated chromosomes and the original individual is selected as the offspring individual through the elite retention strategy.

[0071] e. Selection strategy: Combine the hierarchical selection and elite retention strategies to prevent premature convergence of the algorithm and improve the quality of global search. The hierarchical selection method effectively prevents premature convergence of the algorithm by selecting the proportion of fitness values. The elite retention rule ensures that the algorithm maintains efficient optimization ability by directly selecting the best individuals in the current population into the next generation. In the early stage of iteration, the hierarchical selection method is mainly used to promote the diversity of the population and avoid premature convergence. In each non-dominated level, the individuals with excellent performance in the level are selected to enter the next generation. In the later stage of iteration, the elite retention strategy is adopted instead. This not only helps to expand the search space and speed up the search, but also continuously improves the quality of global search during the iteration process. Through the dynamic adjustment of this strategy, the algorithm can effectively balance local and global searches while maintaining the diversity of solutions, thereby increasing the probability of finding the global optimal solution.

[0072] In this embodiment, after all non-dominated solutions are obtained, the fitness of all non-dominated solutions in the non-dominated solution set is calculated, and the non-dominated solution with the most ideal fitness value is selected as the optimal solution for the current material transportation path, that is, the current material transportation path is obtained. The fitness function is shown in formula (12):

[0073] F(x)=n1f1(x)+n2f2(x)+n3f3(x) (12)

[0074] In formula (12), n i is the corresponding objective function weight coefficient, f i (x) is the objective function value corresponding to the current solution.

[0075] Step 3: Use the Internet of Things technology to monitor the status of the distribution point in real time to determine whether the vehicle has completed the material distribution. If the vehicle has completed the material distribution, the quadrant optimization strategy is used to select the optimal empty tooling recovery task t that does not affect the subsequent distribution task and dynamically insert it into the current material transportation path obtained in step 2. The constraints of the quadrant optimization strategy include that the number of traction turnover vehicles of the trolley after inserting the recovery task cannot exceed the maximum traction quantity constraint, and the inserted recovery task must not affect the normal distribution execution of the subsequent distribution task, as shown in formulas (13)-(15):

[0076] w i ≤w max -1 (13)

[0077] T i-1 +T pt ≤min{T i ,LT i} (14)

[0078] T pt =[(di-1,t +d t,i )-d i-1,i ] / v (15)

[0079] Among them, formula (13) indicates that after the recovery task is inserted, the number of turnover vehicles towed by the trolley cannot exceed the maximum towable number constraint; formulas (14) and (15) indicate that the inserted recovery task shall not affect the normal delivery execution of subsequent delivery tasks.

[0080] In this embodiment, the goal of the quadrant optimization strategy is to find an ideal time and place to insert the real-time generated recycling task without affecting the current delivery task of the AGV. This embodiment divides the material distribution area into several quadrants, and each quadrant is evaluated based on its geographical location and the remaining material demand to be delivered. In this way, this embodiment can determine which recycling task is most suitable for inserting into the current vehicle's delivery path after completing the delivery task. The application of this path adjustment strategy helps this embodiment to maximize the efficiency of recycling empty material distribution turnover vehicles while ensuring the delivery task.

[0081] The performance of the method of this embodiment is described below through experiments.

[0082] In order to verify the effect of the method described in the embodiment of the present invention, this experimental example conducted a simulation experiment through an actual digital workshop case of a manufacturing enterprise.

[0083] The experiment set up a control group of the standard NSGA-Ⅱ algorithm combined with the current pick-up and delivery strategy, that is, when the recycling tasks accumulate to a certain number, a small car is specially dispatched from the distribution center to carry out the empty turnover car recycling task. The population size and number of iterations of the standard NSGA-Ⅱ algorithm are set to be the same as those of the improved algorithm strategy. The experimental data proves the good effect of the present invention in improving distribution efficiency, reducing costs, increasing AGV utilization, and adapting to dynamic changes.

[0084] like Figure 2 As shown, the workshop is 165m long and 85m wide, with a total area of ​​14025m 2, the distribution demand and time window in the workshop are issued by the upper-level factory MOM system. It is known that the material distribution center in the workshop is located in the southwest of the workshop. The distribution center is used as the starting point. The AGV cart pulls a certain number of turnover carts to distribute materials to 25 workstations in the workshop. When it drives to the corresponding workstation, the turnover cart storing the required materials will be left next to the corresponding workstation, and the cart pulls other turnover carts to continue to perform other material distribution tasks. When the workstation is loaded with materials, an empty material cart recovery task for the workstation will be generated, and the AGV needs to pull the empty material cart back to the material distribution center. The coordinate information of the distribution center and the workstation is shown in Table 2. Combined with the actual situation of the enterprise, assign values ​​to each distribution parameter. C1 = 10 yuan / time, C2 = 1 yuan / meter, C3 = 100 yuan / minute, v = 40 meters / minute, W = 4 vehicles.

[0085] like Figure 3-Figure 5 As shown in the figure, during the entire iterative process of generating the initial demand distribution path, the improved strategy converged to the local optimal value in about 50 generations, then jumped out of the local optimal solution in the iterative process of 50-100 generations, and then began to converge rapidly in 150 generations, and gradually converged to the optimal in 200-300 generations. The reason why the improved strategy fluctuated greatly in the early stage was that the first 150 generations used hierarchical selection to select offspring individuals, which increased the diversity of the population in order to better achieve global search. As the iteration progressed, the tendency to select offspring individuals became greedy, and the convergence speed accelerated.

[0086] As shown in Table 2, the plane coordinate information of each workstation and distribution center, as well as the latest delivery time, are used as the original conditions for solving. Table 2 is as follows:

[0087] Table 2 Distribution center and workstation information

[0088]

[0089]

[0090] The solution results are shown in Table 3, where 0 represents the material distribution center and * represents the recycling task. Obviously, the improved strategy algorithm has better solution results and better solution quality, and can well solve the workshop material distribution optimization problem considering the recycling of material transportation tooling. This result not only demonstrates the adaptability and flexibility of the step-by-step multi-objective optimization solution method based on the improved NSGA-Ⅱ algorithm for dynamic task processing, but also shows the effectiveness of the improved strategy in cost control and resource allocation, thereby providing decision makers with more choices. Table 3 is as follows:

[0091] Table 3 Summary of solution results

[0092]

[0093]

[0094] The comparison before and after optimization is shown in Table 4. Considering the vehicle driving path cost and the reduction in the number of vehicle dispatches, the number of vehicles dispatched to complete all distribution and recovery tasks has been reduced from 15 to 8, a decrease of 46.7%; the average number of tasks each traction AGV is responsible for has changed from 3.3 to 6.2; the vehicle driving path cost has been reduced from 4309.05 to 3541.86, a decrease of 17.8%. It effectively controls the material distribution cost and distribution time, reduces the investment in traction AGVs, and greatly improves vehicle utilization. The penalty cost for late arrival at the optimized workstation is 59.74, which is 69% less than the penalty cost of 197.73 before optimization. While balancing the total cost, it effectively ensures the timely response to material needs. Table 4 is as follows:

[0095] Table 4 Comparison of results before and after improvement

[0096]

[0097] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. The embodiments described in the present invention are merely descriptions of the preferred embodiments of the present invention, and do not limit the concept and scope of the present invention. The various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction, and such combinations should also be regarded as the contents disclosed in the present disclosure as long as they do not violate the concept of the present invention. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0098] The present invention is not limited to the specific details of the above-mentioned embodiments. Within the technical concept of the present invention and without departing from the design concept of the present invention, various modifications and improvements made to the technical solution of the present invention by technical personnel in this field should fall within the protection scope of the present invention. The technical contents for which protection is sought in the present invention have been fully recorded in the claims.

Claims

1. A dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops, characterized in that: The following steps are involved: Step 1: Analyze the multi-objective material distribution problem in the workshop and establish the objective function and constraint conditions of the multi-objective material distribution path planning model; Step 2: Use the improved NSGA-II algorithm to solve the multi-objective material distribution path planning model established in step 1, obtain a non-dominated solution set, and find the optimal non-dominated solution, thereby obtaining the current material transportation path; Step 3: Use the Internet of Things technology to monitor the status of the distribution point in real time to determine whether the vehicle has completed the material delivery. If the vehicle has completed the material delivery, select the optimal empty tooling recovery task that does not affect subsequent delivery tasks and dynamically insert it into the current material transportation path obtained in step 2.

2. The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops according to claim 1 is characterized in that: In step 1, the objective function of the multi-objective material distribution path planning model is the total cost of the distribution vehicle assignment f 1 Minimum, total cost of route delivery f 2 Minimum, total cost of penalty for demand workstation time window f 3 Minimum is the goal.

3. The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops according to claim 1 is characterized in that: In step 1, the constraints of the multi-objective material distribution path planning model include: each workstation is served only once and only one vehicle performs the task, the upper limit of the number of turnover material vehicles that each AGV can tow is the set Wmax vehicles, the vehicles arriving at and leaving the workstation are the same, and the starting point and end point of the vehicle are both the distribution center.

4. The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops according to claim 1 is characterized in that: In step 2, the fitness of all non-dominated solutions in the non-dominated solution set is calculated, and the non-dominated solution with the best fitness value is selected as the optimal solution for the current material transportation route, that is, the current material transportation route is obtained.

5. The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops according to claim 1 is characterized in that: In step 3, the quadrant optimization strategy is used to select the optimal empty tooling recovery task that does not affect the subsequent delivery task and dynamically insert it into the current material transportation path obtained in step 2.

6. The dynamic vehicle path planning method considering the recovery of empty material distribution turnover vehicles in workshops according to claim 1 is characterized in that: The constraints when using the quadrant optimization strategy include: after inserting the recovery task, the number of turnover vehicles towed by the trolley cannot exceed the maximum towable number constraint, and the inserted recovery task must not affect the normal delivery execution of subsequent delivery tasks.

Images