Intelligent carrying trolley path search optimization method, device, equipment and medium

Abstract

The invention relates to an intelligent carrying trolley path search optimization method and device, equipment and a medium, and the method comprises the steps: taking an initial planning path scheme as an initial solution of a simulated annealing algorithm, and carrying out the disturbance of the initial solution, so as to generate a new planning path scheme; determining a difference value between a target function value corresponding to the new path planning scheme and a target function value of the current path planning scheme, and replacing the current path planning scheme with the new path planning scheme according to the difference value by adopting a Metropolis criterion in a simulated annealing algorithm; and calculating and determining the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function, judging whether the current temperature is lower than a preset temperature threshold, and if so, selecting a path planning scheme with the shortest path from all iteration results as a final path planning scheme. According to the method, the path schemes enabling the trolley to fall into circulation can be accurately and quickly eliminated, and the path scheme for finishing the specified task at the fastest speed is searched.

Description

Technical Field

[0001] The present application relates to the field of production control, and in particular to a method for optimizing the path search of an intelligent transport vehicle, a corresponding device, an electronic device, and a computer-readable storage medium. Background Art

[0002] In the context of the information age, intelligent manufacturing has become an important development trend in the transformation and upgrading of the industry. In the context of the rapid development of the intelligent manufacturing industry, intelligent logistics has received more and more attention, and workshop logistics distribution, as an important part of it, has received much attention. In intelligent manufacturing workshops, facility layout and resource allocation issues are important links in the planning and design of discrete manufacturing systems. In the system layout design and logistics distribution stage of intelligent manufacturing workshops, the path selection and distribution efficiency of AGV carts are important system performance indicators. Most other system facility layout studies in China are committed to optimizing the transportation cost of the logistics distance matrix, and few studies have taken into account the multi-path selection in manufacturing workshops. Multi-path selection includes path plan planning, speed changes, and the selection of the optimal path plan.

[0003] In the factory layout stage, in order to create greater production capacity in a limited workshop area, the AGV track is placed in a ring, and the rings of different sizes are nested with each other. In the multi-ring nested closed loop layout mode, the operation and scheduling of production materials are more flexible, scientific, economical, and more executable. In the manufacturing system layout design and resource allocation stage, the output rate and average production cycle of the product are important system performance indicators. As a production auxiliary facility, the operating efficiency of AGV has a significant impact on the workshop output rate and average production cycle. In the research on AGV path layout planning, most scholars focus on avoiding obstacles, optimal path selection, and avoiding collisions. During the research process, the venue is relatively simple, and there are few studies combined with actual complex workshop venues. For the special path planning problem of multi-task multi-ring nested closed loop workshop, whether the planning is reasonable directly affects the speed of the overall workshop logistics, and plays a key role in controlling the workshop logistics cost and various waiting costs caused by congestion. It is rare to see relevant research that takes this type of path planning problem as part of the optimization goal.

[0004] At present, the paths generated in multi-ring nested closed-loop workshops may fall into multiple loops, which are prone to "0"-shaped loops or "6"-shaped loops, increasing the operating time of the intelligent transport vehicle (AGV vehicle), the waiting time of the machining center and the path congestion time, thereby causing a waste of transportation costs.

[0005] In summary, the path generated by the existing technology in a multi-ring nested closed-loop workshop may fall into multiple loops, and it is easy to fall into a "0"-shaped loop or a "6"-shaped loop, which increases the operating time of the intelligent transport vehicle, the waiting time of the machining center and the path congestion time, thereby causing waste of transportation costs and other problems. This application makes corresponding explorations to solve this problem. Summary of the invention

[0006] The purpose of this application is to solve the above-mentioned problems and to provide a method for optimizing the path search of an intelligent transport vehicle, a corresponding device, an electronic device and a computer-readable storage medium.

[0007] In order to meet the various objectives of this application, this application adopts the following technical solutions:

[0008] An intelligent transport vehicle path search optimization method proposed to meet one of the purposes of this application is applied to a multi-ring nested closed loop workshop, including:

[0009] In response to the intelligent transport vehicle path search optimization instruction, a passable track set, a track set being connected, an unconnected track set, a connected track set, an initial track, and a target track in a multi-ring nested closed loop workshop are obtained, wherein the unconnected track set represents a track that is not selected after the track of the track set being connected is connected;

[0010] The initial planning path plan of the intelligent transport vehicle is generated by adopting a greedy algorithm strategy in a preset path self-generation algorithm according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track;

[0011] Using the initial planning path plan as an initial solution of a simulated annealing algorithm, and perturbing the initial solution to generate a new planning path plan;

[0012] Determine the difference between the objective function value corresponding to the new planned path solution and the objective function value of the current planned path solution, and replace the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in the simulated annealing algorithm;

[0013] The current temperature of the simulated annealing algorithm is determined based on the preset rapid temperature drop function calculation, and it is judged whether the current temperature is lower than the preset temperature threshold. If so, the planned path plan with the shortest path is selected from all iterative results as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

[0014] Optionally, the step of using a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path solution for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track includes:

[0015] Determine the passable track set R, the track set S being connected, and the unconnected track set S in the multi-ring nested closed loop workshop 0 , the connected orbit set S', the initial orbit a0 and the target orbit a n , where the unconnected track set S 0 represents the set of unselected orbits after S is turned on, and the initial orbit a0 is the initial orbit x 23 , the target track a n The target track x 22 ;

[0016] Determine the target track x of the intelligent transport vehicle 22 , from the initial track x in the parking lot 23 Initially, add a0 to the set of tracks S being connected;

[0017] From the initial track x 23 Start, select the next track according to the greedy algorithm, and select an accessible and unvisited track by checking the reachability relationship of the track;

[0018] For each selected track a n , a strong trade-off is made. If one of the tracks x1 and x7 is selected as a1, the other track will enter the unconnected track set S 0 , to determine the initial unconnected track set S 0 1. Repeat this process until the set of tracks being connected S contains all target tracks x i 、x j 、x k 、x 22 , then the path S1 is generated;

[0019] The completed path S1 is stored in the connected track set S', and the unconnected track set S generated during the path generation process is stored in the connected track set S 0 Deposit in the no-call table;

[0020] From the initial unconnected track set S 0 Select the first track in 1 as the new starting point, repeat the above path generation process, generate a new path S2, store the completed path S2 into the connected track set S', and record the new unconnected track set S 02. Continue until all unconnected elements in a set are found to be consistent with the previously recorded initial unconnected track set S 0 1, the planning path plan that meets the current task of the intelligent transport vehicle is generated to determine the initial planning path plan of the intelligent transport vehicle.

[0021] Optionally, the step of using the initial planned path solution as an initial solution of a simulated annealing algorithm and perturbing the initial solution to generate a new planned path solution includes:

[0022] Determine an initial planning path plan for the intelligent transport vehicle, and use the initial planning path plan as an initial solution of the simulated annealing algorithm;

[0023] The initial solution is exchanged, reversed, inserted or partially exchanged using a conversion operator to generate a new planning path solution.

[0024] Optionally, the step of determining a difference between an objective function value corresponding to a new planned path solution and an objective function value of a current planned path solution, and replacing the current planned path solution with the new planned path solution according to the difference using a Metropolis criterion in a simulated annealing algorithm includes:

[0025] The expression of the Metropolis criterion is:

[0026]

[0027] Among them, f(l) represents the objective function of the current planned path plan, f(l′) represents the objective function of the new planned path plan, n is the scale factor of the objective function, T is the current temperature, when f(l′)-f(l)<0, the objective function value of the new planned path plan is lower, and the new planned path plan is directly accepted; when f(l′)-f(l)>0, the probability is used to Accept the new planned path plan.

[0028] Optionally, the step of determining a rapid temperature drop function of a simulated annealing algorithm comprises:

[0029] Determine the initial temperature, number of iterations, and temperature drop coefficient during the annealing process of the simulated annealing algorithm;

[0030] Calculate and determine a first product between the number of iterations and the temperature drop coefficient, and calculate and determine a first sum value between the first product and a value 1;

[0031] Based on a first ratio between the initial temperature and the first sum value, determining a temperature when the number of iterations is k to determine a rapid temperature drop function;

[0032] The steps of determining the initial temperature of the simulated annealing algorithm include:

[0033] Determine the objective function of the current planned path plan, the objective function of the new planned path plan, and the preset acceptance probability;

[0034] Calculating and determining the natural logarithm value of the acceptance probability;

[0035] Calculate and determine a first difference between the objective function of the new planned path solution and the objective function of the current planned path solution;

[0036] A second ratio between the first difference and the natural logarithm of the acceptance probability is calculated and determined, and a negative value of the second ratio is used as an initial temperature of the simulated annealing algorithm.

[0037] Optionally, after the step of generating an initial planning path plan for the intelligent transport vehicle, the following steps are included:

[0038] Calling a preset improved A* algorithm, and optimizing the initial planned path plan based on the improved A* algorithm;

[0039] The optimized initial planning path plan is used as the initial solution of the simulated annealing algorithm.

[0040] Optionally, after determining the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function calculation, judging whether the current temperature is lower than a preset temperature threshold, and if so, selecting a planning path solution with the shortest path from all iteration results as the final planning path solution, the method further comprises:

[0041] Based on the preset speed adaptation algorithm, the speed of the intelligent transport vehicle is adapted to avoid collision with other intelligent transport vehicles;

[0042] Calculate and determine the safe speed and braking acceleration of the intelligent transport vehicle to ensure that it can stop safely before encountering obstacles;

[0043] According to the power acceleration and current speed of the intelligent transport vehicle, the speed adjustment window is determined to dynamically update the feasible speed range;

[0044] For multiple intelligent transport vehicles, predict the displacement of other intelligent transport vehicles and adjust the obstacle avoidance strategy to reduce collisions;

[0045] Based on the forward movement and expansion radius of other intelligent transport vehicles, the distance evaluation function is updated to ensure that obstacles can be accurately avoided in actual path planning.

[0046] An intelligent transport vehicle path search and optimization device provided to meet another purpose of the present application includes:

[0047] A data acquisition module is configured to respond to the intelligent transport vehicle path search optimization instruction, and acquire a passable track set, a track set being connected, an unconnected track set, a connected track set, an initial track, and a target track in a multi-ring nested closed loop workshop, wherein the unconnected track set represents a track set that is not selected after accessing the track in the track set being connected;

[0048] An initial path determination module is configured to use a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path plan for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track;

[0049] A new planning path determination module is configured to use the initial planning path solution as an initial solution of a simulated annealing algorithm and perturb the initial solution to generate a new planning path solution;

[0050] a path updating module, configured to determine a difference between an objective function value corresponding to a new planned path solution and an objective function value of a current planned path solution, and replace the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in a simulated annealing algorithm;

[0051] The search optimization module is configured to calculate and determine the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function, and determine whether the current temperature is lower than a preset temperature threshold. If so, the planned path plan with the shortest path among all iterative results is selected as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

[0052] An electronic device provided to meet another purpose of the present application includes a central processing unit and a memory, wherein the central processing unit is used to call and run a computer program stored in the memory to execute the steps of the intelligent transport vehicle path search optimization method described in the present application.

[0053] A computer-readable storage medium is provided to meet another purpose of the present application, which stores a computer program implemented according to the intelligent transport vehicle path search optimization method in the form of computer-readable instructions. When the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

[0054] Compared with the prior art, the present application aims at the problem that the paths generated by the prior art in the multi-ring nested closed loop workshop may fall into multiple loops, which are easy to fall into a "0"-shaped loop or a "6"-shaped loop, increasing the running time of the intelligent transport vehicle, the waiting time of the machining center and the path congestion time, thereby causing a waste of transportation costs. The present application includes but is not limited to the following beneficial effects:

[0055] First, a new path search method is innovatively proposed. On the basis of generating the initial planning path by the Feasible Path Self-Generation Algorithm (FSGA), the simulated annealing (SA) algorithm is integrated for optimization, so that it can generate all path plans that meet the task requirements, and can accurately and quickly eliminate the path plans that make the car fall into a loop. Combined with the running speed of the intelligent transport car, it can accurately and quickly search for the path plan that completes the specified task the fastest.

[0056] Second, the speed adaptation of the Feasible Path Self Generation Algorithm (FSGA): The Feasible Path Self Generation Algorithm (FSGA) adjusts the speed of the intelligent transport trolley to achieve intelligent obstacle avoidance and dynamically adjust the speed to avoid congestion caused by multiple intelligent transport trolleys running at the same time.

[0057] Third, the path self-generation algorithm is integrated into the improved A* algorithm: searching for the fastest path among all path solutions generated by the Feasible path Self Generation Algorithm (FSGA) is an indispensable key step of the path self-generation algorithm (FSGA), which can accurately and quickly search for the optimal path solution to complete the specified task. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] The above and / or additional aspects and advantages of the present application will become apparent and easily understood from the following description of the embodiments in conjunction with the accompanying drawings, in which:

[0059] Figure 1 This is a schematic diagram of a path generated in an embodiment of the present application in a "0"-shaped loop;

[0060] Figure 2 This is a schematic diagram of a "6"-shaped loop of the path generated in the embodiment of the present application;

[0061] Figure 3 This is a flow chart of the intelligent transport vehicle path search optimization method in the embodiment of the present application;

[0062] Figure 4 A schematic diagram of the facility layout of a multi-ring nested closed loop workshop in an embodiment of the present application;

[0063] Figure 5A schematic diagram of the accessible relationship between various tracks of a multi-ring nested closed loop workshop in an embodiment of the present application;

[0064] Figure 6 A schematic diagram of the congestion phenomenon of the intelligent transport vehicle in the embodiment of the present application;

[0065] Figure 7 A schematic diagram of the deadlock phenomenon of the intelligent transport vehicle in the embodiment of the present application;

[0066] Figure 8 This is a principle block diagram of the intelligent transport vehicle path search and optimization device in the embodiment of the present application;

[0067] Fig. 9 It is a schematic diagram of the structure of the computer device in the embodiment of the present application. DETAILED DESCRIPTION

[0068] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and cannot be interpreted as limiting the present application.

[0069] It will be understood by those skilled in the art that, unless expressly stated, the singular forms "one", "said", and "the" used herein may also include plural forms. It should be further understood that the term "comprising" used in the specification of the present application refers to the presence of the features, integers, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or groups thereof. It should be understood that when we refer to an element as being "connected" or "coupled" to another element, it may be directly connected or coupled to the other element, or there may be an intermediate element. In addition, the "connection" or "coupling" used herein may include wireless connection or wireless coupling. The term "and / or" used herein includes all or any unit and all combinations of one or more associated listed items.

[0070] It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as those generally understood by those skilled in the art to which this application belongs. It should also be understood that terms such as those defined in general dictionaries should be understood to have meanings consistent with those in the context of the prior art, and will not be interpreted with idealized or overly formal meanings unless specifically defined as here.

[0071] It will be understood by those skilled in the art that the "client", "terminal" and "terminal device" used herein include both devices with wireless signal receivers, which are devices with only wireless signal receivers without transmission capabilities, and devices with receiving and transmitting hardware, which are devices with receiving and transmitting hardware capable of two-way communication on a two-way communication link. Such devices may include: cellular or other communication devices such as personal computers, tablet computers, which have single-line displays or multi-line displays or cellular or other communication devices without multi-line displays; PCS (Personal Communications Service, personal communication system), which can combine voice, data processing, fax and / or data communication capabilities; PDA (Personal Digital Assistant, personal digital assistant), which may include a radio frequency receiver, pager, Internet / intranet access, web browser, notepad, calendar and / or GPS (Global Positioning System, global positioning system) receiver; conventional laptop and / or palmtop computers or other devices, which have and / or include a conventional laptop and / or palmtop computer or other device with and / or including a radio frequency receiver. The "client", "terminal" and "terminal device" used herein may be portable, transportable, installed in a vehicle (air, sea and / or land), or suitable for and / or configured to run locally, and / or in a distributed form, at any other location on the earth and / or in space. The "client", "terminal" and "terminal device" used herein may also be a communication terminal, an Internet terminal, a music / video playing terminal, for example, a PDA, a MID (Mobile Internet Device) and / or a mobile phone with a music / video playing function, or a smart TV, a set-top box and other devices.

[0072] The hardware referred to by the names such as "server", "client", and "service node" in this application is essentially an electronic device with the equivalent capabilities of a personal computer. It is a hardware device with the necessary components revealed by the von Neumann principle, such as a central processing unit (including an arithmetic unit and a controller), a memory, an input device, and an output device. The computer program is stored in its memory, and the central processing unit calls the program stored in the external memory into the internal memory for execution, executes the instructions in the program, and interacts with the input and output devices to complete specific functions.

[0073] It should be pointed out that the concept of "server" referred to in this application can also be extended to the case of server clusters. According to the network deployment principle understood by those skilled in the art, the servers should be logically divided. In physical space, these servers can be independent of each other but can be called through interfaces, or integrated into a physical computer or a set of computer clusters. Those skilled in the art should understand this flexibility, and should not use it to restrict the implementation of the network deployment method of this application.

[0074] Unless expressly specified, one or more technical features of the present application can be deployed on a server for implementation and accessed by a client through a remote call to obtain an online service interface provided by the server, or can be directly deployed and run on a client for access.

[0075] The neural network models referenced or may be referenced in this application, unless expressly specified, can be deployed on a remote server and remotely called on the client, or can be deployed and directly called on a client with sufficient device capabilities. In some embodiments, when it runs on the client, its corresponding intelligence can be obtained through transfer learning to reduce the requirements for the client's hardware operating resources and avoid excessive occupation of the client's hardware operating resources.

[0076] Unless explicitly specified, the various data involved in this application can be stored remotely on a server or on a local terminal device, as long as it is suitable for being called by the technical solution of this application.

[0077] Those skilled in the art should be aware that, although the various methods of the present application are described based on the same concept and thus present commonality to each other, unless otherwise specified, these methods can be independently executed. Similarly, for each embodiment disclosed in the present application, they are all proposed based on the same inventive concept, therefore, concepts with the same expression, and concepts that are appropriately changed for convenience despite different expressions, should be understood as equivalent.

[0078] Unless the mutually exclusive relationship between the embodiments to be disclosed in this application is explicitly stated, the relevant technical features involved in each embodiment can be cross-combined to flexibly construct a new embodiment, as long as such combination does not deviate from the creative spirit of this application and can meet the needs of the prior art or solve certain deficiencies in the prior art. Those skilled in the art should be aware of this flexibility.

[0079] See also Figure 1 as well as Figure 2, the Feasible Path Self-Generation Algorithm (FSGA) proposed in this application can generate all paths that meet the task requirements, but these paths are not all efficient algorithms. The generated paths may fall into multiple cycles, increasing the running time of the intelligent transport vehicle (AGV vehicle), the waiting time of the processing center and the path congestion time, thereby causing a waste of transportation costs. It is easy to fall into a "0"-shaped cycle or a "6"-shaped cycle, specifically including:

[0080] (1) Please refer to Figure 1 ,like Figure 1 As shown in the figure, the generated path repeatedly returns to the starting point of the road, forming a "0"-shaped loop. The intelligent transport vehicle (AGV vehicle) selects the starting track in the selection of a certain track, and then repeats the initial planning plan, falling into a loop. After multiple cycles, it jumps out and forms a complete path plan. Although it meets the task requirements and can reach the target track, it is inefficient.

[0081] (2) Please refer to Figure 2 ,like Figure 2 As shown in the figure, the generated path is repeated back to the road, forming a "6"-shaped loop. The intelligent transport vehicle (AGV vehicle) selects a track that has been selected in the track plan when choosing a certain track, and then repeats the initial planning plan, falling into a loop. After multiple cycles, it jumps out and forms a complete path plan, which also meets the task requirements and can reach the target track, but increases the time cost.

[0082] Based on the above exemplary scenarios, please refer to Figure 3 In one embodiment, the intelligent transport vehicle path search optimization method of the present application is applied to a multi-ring nested closed loop workshop, including:

[0083] Step S10, responding to the intelligent transport vehicle path search optimization instruction, obtaining a passable track set, a track set being connected, an unconnected track set, a connected track set, an initial track, and a target track in a multi-ring nested closed loop workshop, wherein the unconnected track set represents a track that is not selected after the track of the track set being connected is connected;

[0084] See also Figure 4 , the facility layout of a multi-ring nested closed loop workshop is as follows Figure 4As shown, the intelligent transport cart path search optimization method of the present application generates all path plans that meet the task requirements in a multi-ring nested closed-loop workshop and then selects the optimal path plan. Considering the actual layout of the production workshop, some channel spaces are narrow and can only accommodate one intelligent transport cart (AGV cart); some spaces are wider and can accommodate two intelligent transport carts (AGV carts) at the same time. The present application increases the complexity of the track during the construction of the workshop model. Some aisles in the workshop support two-way passage of intelligent transport carts (AGV carts), while some only allow one-way passage and prevent accidents caused by collisions when the carts turn. All tracks can only go straight by default and cannot turn around on the track to change the running direction. The path plan goal is to generate a set of tracks that receive assigned tasks, start from the parking lot, pass through the designated processing center, and return to the parking lot.

[0085] The computer terminal device can respond to the intelligent transport vehicle path search optimization instruction to obtain the passable track set R, the track set S being connected, and the unconnected track set S in the multi-ring nested closed loop workshop. 0 , the connected orbit set S', the initial orbit a0 and the target orbit a n , where the unconnected track set S 0 Represents the set of tracks that are not selected after S is turned on.

[0086] Step S20, using a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path plan for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track;

[0087] After obtaining the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track in the multi-ring nested closed loop workshop, the greedy algorithm strategy in the preset path self-generation algorithm is used to generate the initial planning path plan of the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track;

[0088] Further, the step of using a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path plan for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track includes:

[0089] Step S201: Determine the passable track set R, the track set S being connected, and the unconnected track set S in the multi-ring nested closed loop workshop. 0 , the connected orbit set S', the initial orbit a0 and the target orbit an , where the unconnected track set S 0 represents the set of unselected orbits after S is turned on, and the initial orbit a0 is the initial orbit x 23 , the target track a n The target track x 22 ;

[0090] Step S202: Determine the target track x of the intelligent transport vehicle 22 , from the initial track x in the parking lot 23 Initially, add a0 to the set of tracks S being connected;

[0091] From the initial track x 23 Start, select the next track according to the greedy algorithm, and select an accessible and unvisited track by checking the reachability relationship of the track;

[0092] Step S203: for each selected track a n , a strong trade-off is made. If one of the tracks x1 and x7 is selected as a1, the other track will enter the unconnected track set S 0 , to determine the initial unconnected track set S 0 1. Repeat this process until the set of tracks being connected S contains all target tracks x i 、x j 、x k 、x 22 , then the path S1 is generated;

[0093] Step S204: store the completed path S1 into the connected track set S', and store the unconnected track set S generated during the path generation process 0 Deposit in the no-call table;

[0094] Step S205: From the initial unconnected track set S 0 Select the first track in 1 as the new starting point, repeat the above path generation process, generate a new path S2, store the completed path S2 into the connected track set S', and record the new unconnected track set S 0 2. Continue until all unconnected elements in a set are found to be consistent with the previously recorded initial unconnected track set S 0 1, the planning path plan that meets the current task of the intelligent transport vehicle is generated to determine the initial planning path plan of the intelligent transport vehicle.

[0095] Specifically, see Figure 5, the Feasible path Self Generation Algorithm (FSGA) adopts a greedy algorithm strategy, each time starting from the initial track x 23 Start from the unvisited track until all target tracks are expanded; define x to represent the passable track of the workshop intelligent transport vehicle (AGV), R to represent the passable track set of the workshop intelligent transport vehicle (AGV), the connected track set S is used to store the track set being connected, and the unconnected track set S 0 It is used to store the unselected tracks after the track connected to S. The connected track set S' is used to store the connected tracks. a represents a single track element stored in each set, a0 represents the initial track, and a n represents the target track, such as Figure 4 As shown, the car can only leave the parking lot through track 23 and enter the parking lot through track 22, so the initial track, the target track and the final track are determined. The expression of the initial track, the target track and the track set being connected is expressed as follows:.

[0096] x n ∈R,n=1,2,…,23,

[0097] a0=x 23 , a n =x 22 ,

[0098] S={a0,a1……a n-1 , a n},

[0099] exist Figure 4 The dashed arrows in the middle indicate the connectable relationship between the tracks. For example, the track 23 can be connected to track 1 or track 7. Figure 5 As shown, two unidirectional orbits on the same channel are not connected to each other and are defined as conjugate orbits. A conjugate orbit table is established, and a total of 7 pairs of conjugate orbits, (4, 5), (6, 7), (8, 9), (10, 11), (12, 13), (16, 17), and (18, 19), are stored in the conjugate orbit table.

[0100] Further, the car receives the assigned task, assuming that the machining center is at x i 、x j 、x k On the track, the current intelligent transport vehicle (AGV vehicle) target track is x i 、x j 、x k , starting from the parking lot through the initial track x 23Enter the multi-ring nested closed loop workshop and make a strong choice for the next access track. For each selected track a n , a strong trade-off is made. If one of the tracks x1 and x7 is selected as a1, the other track will enter the unconnected track set S 0 , repeat this process until the set of orbits being connected S contains all target orbits x i 、x j 、x k 、x 22 At this time, the path S1 is generated, and the complete path S1 is stored in the connected set S' table, and the new unconnected set S generated during the connection process is 0 The latest row of the unconnected table is stored, and the first set of complete paths is generated. The expression is as follows:

[0101]

[0102]

[0103]

[0104] Furthermore, from the unconnected track set S 0 Select the first track as the new starting point, repeat the above path generation process, generate a new path S2, store the completed path S2 into the connected track set S', and record the new unconnected track set S 0 2. Continue until all unconnected elements in a set are found to be consistent with the previously recorded initial unconnected track set S 0 1, the planned path plan that meets the current task of the intelligent transport vehicle is generated to determine the initial planned path plan of the intelligent transport vehicle;

[0105] More specifically, we then start from the initial unconnected track set S 0 1Select the first element a1 0 As a1 of path S2, repeat the above steps, reselect a new connected track, generate a complete path S2 and store it in the connected set S'. In the process of selecting a new connected track, a new unconnected track S will be generated. 0 2. S 0 2 Store the latest row in the unconnected table until a set of all unconnected elements and S 0 1 is exactly the same, and the path plan that meets the current task is generated to determine the initial planning path plan of the intelligent transport vehicle, that is, when S 0 n =S 0 1, terminate the path generation method.

[0106] In some embodiments, after the step of generating an initial planning path plan for the intelligent transport vehicle, the following steps are included:

[0107] Step S2001, calling a preset improved A* algorithm, and optimizing the initial planned path plan based on the improved A* algorithm;

[0108] Step S2002: Use the optimized initial planning path plan as the initial solution of the simulated annealing algorithm.

[0109] The algorithm flow of the improved A* algorithm specifically includes:

[0110] (1) Initialization: Create two lists: open list and close list, which are used to store nodes to be explored and nodes that have been explored; add the starting node to the open list; set the initial dynamic weight factor and intersection priority. (Assume that the intersection priority is determined by the traffic flow. The smaller the traffic flow, the higher the priority; assume that the weight of the new path is the length of the new path, and the weight of the old path is the length of the old path. The shorter the path length, the smaller the weight). Because the intelligent transport vehicle (AGV vehicle) can usually only move in four directions: up, down, left, and right; Manhattan distance refers to the sum of the horizontal and vertical distances from the current point m to the target point F, that is, |h(m)|=|Xm-XF|+|Ym-YF|. By continuously updating the f value of the intermediate point m and selecting the point with the smallest f value for exploration, the A* algorithm can gradually search for the optimal solution, that is, the shortest path from the starting point to the target point. In this process, all the points searched are process points of the shortest path.

[0111] (2) Initialize the path planning map and environmental information: perform a cyclic search. When the open list is not empty, perform the following steps: select the node c with the smallest f(m) from the open list as the current node, and move c to the close list; if c is the target node, stop searching and output the optimal path result; otherwise, traverse the adjacent nodes m of the current node c: set g(m) = g(c) + d(c, m), and the parent node of m is c; if the adjacent point m is in the open list, when g(m)>g(c) + d(c, m), update g(m) = g(c) + d(c, m), and set the parent node of m to c;

[0112] (3) If m is not in the closelist, calculate the dynamic weight of m: adjust the weight based on factors such as obstacle density, path congestion, and intersection priority.

[0113] (4) If m is not in the open list, add m to the open list, update its parent node to c, and calculate g(m), h(m) and f(m); if m is in the open list, new_weight = distance(new_path), old_weight = distance(old_path)

[0114] (5) Output the optimal path: When the target node appears in the open list, the search ends. The node grid sequence in the output is in the order in which it enters the closed list. This sequence is the optimal path.

[0115] (6) Real-time path update: Update the path planning map and environmental information according to real-time environmental changes; when the environment changes, re-plan the path and re-execute the A* algorithm; update the dynamic weight factor and intersection priority according to the new path information.

[0116] Here, speed adaptation is taken into consideration, and the corresponding distance adaptation is added to timely update the dynamic weight, so as to further ensure that the system is always in a high-quality solution: the path adaptation formula is used to adjust the f value of node m: adjusted_f(m) = f(m) / w, where adjusted_f(m) is the adjusted f value of node m, f(m) is the original f value of node m, and w is the dynamic weight factor of node m.

[0117] The improved A* algorithm process has very detailed considerations for path planning and path updating, especially in terms of path optimization under real-time environmental changes. The algorithm combines the dynamic weight factor of the node, the intersection priority and the real-time path update to achieve more flexible and efficient path planning in a dynamic environment. In addition, the f value of the node is adjusted through the path adaptive formula to further keep the system in a high-quality solution, avoid multiple nested closed loops, and find a faster path. These detailed designs efficiently complete the path planning and real-time adjustment of the intelligent transport vehicle (AGV vehicle).

[0118] Based on the above steps, the optimized initial planning path solution can be determined, and the optimized initial planning path solution is used as the initial solution of the simulated annealing algorithm.

[0119] Step S30, using the initial planned path solution as an initial solution of a simulated annealing algorithm, and perturbing the initial solution to generate a new planned path solution;

[0120] After generating an initial planning path plan of the intelligent transport vehicle, the initial planning path plan is used as an initial solution of a simulated annealing algorithm, and the initial solution is disturbed to generate a new planning path plan;

[0121] Furthermore, the step of using the initial planning path solution as an initial solution of a simulated annealing algorithm and perturbing the initial solution to generate a new planning path solution includes:

[0122] Step S301, determining an initial planning path plan of the intelligent transport vehicle, and using the initial planning path plan as an initial solution of a simulated annealing algorithm;

[0123] Step S302: Use a conversion operator to perform an exchange operation, a reversal operation, an insertion operation or a local exchange on the initial solution to generate a new planning path solution.

[0124] Step S40: determining a difference between an objective function value corresponding to the new planned path solution and an objective function value of the current planned path solution, and replacing the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in the simulated annealing algorithm;

[0125] After perturbing the initial solution to generate a new planned path solution, determining a difference between an objective function value corresponding to the new planned path solution and an objective function value of the current planned path solution, and replacing the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in the simulated annealing algorithm;

[0126] Furthermore, the expression of the Metropolis criterion is:

[0127]

[0128] Among them, f(l) represents the objective function of the current planned path plan, f(l′) represents the objective function of the new planned path plan, n is the scale factor of the objective function, T is the current temperature, when f(l′)-f(l)<0, the objective function value of the new planned path plan is lower, and the new planned path plan is directly accepted; when f(l′)-f(l)>0, the probability is used to Accept the new planned path plan.

[0129] Step S50, determine the current temperature of the simulated annealing algorithm based on the preset rapid temperature drop function, and judge whether the current temperature is lower than the preset temperature threshold. If so, select the planned path plan with the shortest path from all iterative results as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

[0130] After replacing the current planned path plan with the new planned path plan according to the difference value using the Metropolis criterion in the simulated annealing algorithm, the current temperature of the simulated annealing algorithm is determined based on a preset rapid temperature drop function, and it is judged whether the current temperature is lower than a preset temperature threshold. If so, the planned path plan with the shortest path is selected from all iteration results as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

[0131] The steps of determining a rapid temperature drop function for a simulated annealing algorithm include:

[0132] Step S501, determining the initial temperature, number of iterations, and temperature drop coefficient during the annealing process of the simulated annealing algorithm;

[0133] Step S502, calculating and determining a first product between the number of iterations and the temperature drop coefficient, and calculating and determining a first sum value between the first product and a value 1;

[0134] Step S503: Based on a first ratio between the initial temperature and the first sum value, determine the temperature when the number of iterations is k, so as to determine a rapid temperature drop function.

[0135] Specifically, the expression of the rapid temperature drop function is expressed as follows:

[0136]

[0137] Where k is the number of iterations, a is the temperature drop coefficient during annealing, T k is the temperature when the number of iterations is k.

[0138] Further, the step of determining the initial temperature of the simulated annealing algorithm comprises:

[0139] Step S5011, determining the objective function of the current planned path solution, the objective function of the new planned path solution, and the preset acceptance probability;

[0140] Step S5012, calculating and determining the natural logarithm value of the acceptance probability;

[0141] Step S5013: Calculate and determine a first difference between the objective function of the new planned path solution and the objective function of the current planned path solution;

[0142] Step S5014: Calculate and determine a second ratio between the first difference and the natural logarithm of the acceptance probability, and use the negative value of the second ratio as the initial temperature of the simulated annealing algorithm.

[0143] The initial temperature is set to a sufficiently large value to ensure a stronger global search capability. According to the Metropolis criterion, the initial temperature of the simulated annealing algorithm can be expressed as:

[0144]

[0145] Where f(l′) represents the objective function of the new planned path plan, f(l) represents the objective function of the current planned path plan, and P0 is the preset acceptance probability.

[0146] In some embodiments, the calculation formula of the objective function increment is expressed as follows:

[0147] Δf=f(l′)-f(l)

[0148] Where l represents the initial path plan, l′ represents the new planned path plan, f(l) represents the objective function of the current planned path plan, f(l′) represents the objective function of the new planned path plan, and Δf represents the increment of the objective function.

[0149] In order to ensure accurate definition and judge the state space when falling into a loop, this application adopts the construction of appropriate one-dimensional serial number identification and two-dimensional serial number identification, wherein the one-dimensional serial number identification is a continuous positive integer serial number as shown in Table 1, and the two-dimensional identification is a matrix-like axis mode as shown in Table 2;

[0150] Table 1 One-dimensional ordinal coordinate system

[0151] 1 6 11 16 21 2 7 12 17 22 3 8 13 18 23 4 9 14 19 24 5 10 15 20 25

[0152] Table 2 Two-dimensional serial number coordinate system

[0153] (1，1) (1，2) (1，3) (1，4) (1，5) (2，1) (2，2) (2，3) (2，4) (2，5) (3，1) (3，2) (3，3) (3，4) (3，5) (4，1) (4，2) (4，3) (4，4) (4，5) (5，1) (5，2) (5，3) (5，4) (5，5)

[0154] The specific conversion relationship is as follows:

[0155]

[0156]

[0157] N=(j-1)*n+i,

[0158] In this formula, n is the dimension of the coordinate system, N is the serial number in the one-dimensional coordinate system, i and j are the row and column pairs in the two-dimensional coordinate system, mod is the remainder function, and ceil is the integer function.

[0159] The method further comprises: determining the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function, judging whether the current temperature is lower than a preset temperature threshold, and if so, selecting a planning path solution with the shortest path from all iteration results as a final planning path solution.

[0160] Step S1100, performing speed adaptation on the intelligent transport vehicle based on a preset speed adaptation algorithm to avoid collision with other intelligent transport vehicles;

[0161] Step S1200: Calculate and determine the safe speed and braking acceleration of the intelligent transport vehicle to ensure that it can stop safely before encountering an obstacle;

[0162] Step S1300: determining a speed adjustment window according to the power acceleration and current speed of the intelligent transport vehicle to dynamically update a feasible speed range;

[0163] Step S1400: predict the displacement of other intelligent transport vehicles for multiple intelligent transport vehicles, and adjust the obstacle avoidance strategy to reduce collisions;

[0164] Step S1500: Based on the forward movement and expansion radius of other intelligent transport vehicles, the distance evaluation function is updated to ensure that obstacles can be accurately avoided in actual path planning.

[0165] Specifically, if Figure 6 As shown, the Feasible Path Self-Generation Algorithm (FSGA) proposed in this application solves the path planning problem of a multi-ring nested closed-loop workshop. Multiple carts are dynamically scheduled at the same time. There are situations where multiple carts need to go to the same processing center at the same time and need to pass through the same track, causing congestion. Congestion will cause unnecessary car operation costs and time costs, directly affecting the speed of the overall workshop logistics and the overall production efficiency of the workshop; Figure 7 As shown, since the current intelligent transport vehicle (AGV vehicle) and other intelligent transport vehicles (AGV vehicles) have to enter each other's paths, a deadlock phenomenon occurs, which cannot be resolved by the priority method and the traffic rules method.

[0166] In order to solve the above congestion and deadlock problems, a speed adaptive solution for an intelligent transport vehicle (AGV vehicle) is proposed. The speed adaptive algorithm includes:

[0167] (1) The steps for setting the safe speed are as follows: Set the safe speed so that the car can stop before colliding with an obstacle. P(v) is the shortest distance between the car and the obstacle on its trajectory, and V a This is the range of motion of the AGV that does not collide with the nearest obstacle. Let the acceleration during braking be V b , indicating the range:

[0168]

[0169] (2) Considering the dynamic acceleration of the car, the search space is sampled into a dynamic window, and only the speed that can be reached with the current acceleration is retained. Let t be the time interval, V a is the actual speed, then the motion range of the dynamic window is:

[0170]

[0171] (3) Final search space:

[0172] V r =V s ∩V a ∩V d , ③

[0173] Among them, V s It is the maximum speed and minimum speed limit of the robot itself.

[0174] In the multi-task multi-loop nested closed loop of multiple AGVs, it is possible to safely avoid sudden obstacles (AGV itself) in the collaborative operation mode of multiple AGVs without affecting the overall route of each AGV. Considering the operation environment of multiple AGVs, when one of the AGVs is taken as the research object, the other AGVs are equivalent to moving obstacles. Considering that the displacement of the dynamic AGV at the next moment is very likely to cause the research object to fail to avoid obstacles in time and cause conflicts, a forward prediction strategy is proposed to predict the position information of the obstacles at the next moment to reduce the collision conflicts between AGVs. Therefore, among the m AGVs, S ij It represents the distance between the i-th and j-th intelligent transport vehicles (AGVs). When the research object is the intelligent transport vehicle (AGV) No. 1, the distance between the No. 1 intelligent transport vehicle (AGV) and other intelligent transport vehicles (AGVs) is considered, which is expressed as follows:

[0175] min{T12, T13…T1m}, ④

[0176] That is, select the minimum value in the set to determine the research object and its nearest dynamic obstacle.

[0177] At this time, P(v) cannot only consider the safe distance between the research object and the nearest obstacle, because the two intelligent transport vehicles (AGV vehicles) are moving, which is equivalent to a moving obstacle. The safe distance at this moment is the safe distance for the research object at this moment. When the dynamic obstacle moves forward at the next moment, a collision conflict may occur. In order to avoid conflicts, the distance evaluation function is improved:

[0178] P′(v)=P(v i )+P*(v j ), ⑤

[0179] In formula ①, P(v j ) represents the obstacle distance evaluation function of the research object at the current moment. In the speed window, at this moment, all obstacles are static. But in fact, the intelligent transport vehicles (AGV vehicles) are moving and planning their paths towards their respective target points. Their positions and speeds are changing all the time. At this time, it is necessary to add P*(v j ), P*(v j ) represents the forward moving distance of the obstacle. This avoids the situation that although the predicted forward distance of the research object is feasible at the previous moment, the obstacle is also moving forward. Considering the forward moving distance of the obstacle can well predict the appropriate obstacle distance evaluation function at the next moment. In the speed window of the research object, the position of the obstacle at the next moment can be predicted in advance, thereby avoiding unnecessary collision problems. On the other hand, the intelligent transport vehicle (AGV vehicle) cannot be too close to the obstacle during driving, which is prone to collision. At this time, if the actual radius of the obstacle is r, the collision judgment area of ​​the obstacle is expanded, and the range of its radius expansion is set as the coefficient When calculating the distance value of P′(v), we should no longer calculate the distance from the center of the mobile robot to the center of the obstacle, but calculate the distance from the center of the mobile robot to the center of the obstacle, and then subtract the expansion radius of the obstacle. At this time, a more reliable safe speed range can be obtained. The improved distance evaluation function is substituted into formula ①, and the speed window of the distance obstacle changes from Va* to Va′. The improved speed search space is Vr′, which is expressed as follows:

[0180]

[0181] V′ r =V s ∩V′ a ∩V d , ⑦

[0182] From the above steps, it can be seen that after the Feasible Path Self Generation Algorithm (FSGA) generates all path solutions that meet the task requirements, the simulated annealing (SA) algorithm is integrated to determine whether the generated path solution is a cyclic path. If it is determined to be a cyclic path, it is eliminated, and the speed is adapted in the remaining path solutions to form a complete fastest path search algorithm.

[0183] It can be seen from the above embodiments that, compared with the prior art, the present application aims at the fact that the paths generated by the prior art in a multi-ring nested closed loop workshop may fall into multiple loops, which are prone to fall into a "0"-shaped loop or a "6"-shaped loop, increasing the running time of the intelligent transport vehicle, the waiting time of the machining center, and the path congestion time, thereby causing a waste of transportation costs. The present application includes but is not limited to the following beneficial effects:

[0184] First, a new path search method is innovatively proposed. On the basis of generating the initial planning path by the Feasible Path Self-Generation Algorithm (FSGA), the simulated annealing (SA) algorithm is integrated for optimization, so that it can generate all path plans that meet the task requirements, and can accurately and quickly eliminate the path plans that make the car fall into a loop. Combined with the running speed of the intelligent transport car, it can accurately and quickly search for the path plan that completes the specified task the fastest.

[0185] Second, the speed adaptation of the Feasible Path Self Generation Algorithm (FSGA): The Feasible Path Self Generation Algorithm (FSGA) adjusts the speed of the intelligent transport trolley to achieve intelligent obstacle avoidance and dynamically adjust the speed to avoid congestion caused by multiple intelligent transport trolleys running at the same time.

[0186] Third, the path self-generation algorithm is integrated into the improved A* algorithm: searching for the fastest path among all path solutions generated by the Feasible path Self Generation Algorithm (FSGA) is an indispensable key step of the path self-generation algorithm (FSGA), which can accurately and quickly search for the optimal path solution to complete the specified task.

[0187] See also Figure 8, a path search and optimization device for an intelligent transport vehicle provided to meet one of the purposes of the present application, includes a data acquisition module 1100, an initial path determination module 1200, a new planned path determination module 1300, a path update module 1400 and a search optimization module 1500. Among them, the data acquisition module 1100 is configured to respond to the path search and optimization instruction of the intelligent transport vehicle, and obtain the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track in the multi-ring nested closed loop workshop, and the unconnected track set represents the track set that is not selected after connecting to the track set being connected; the initial path determination module 1200 is configured to use the greedy algorithm strategy in the preset path self-generation algorithm to generate the initial planned path plan of the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track; the new planned path determination module 1300 is configured to convert the initial planned path The path scheme is used as the initial solution of the simulated annealing algorithm, and the initial solution is disturbed to generate a new planned path scheme; the path updating module 1400 is configured to determine the difference between the objective function value corresponding to the new planned path scheme and the objective function value of the current planned path scheme, and the Metropolis criterion in the simulated annealing algorithm is used to replace the current planned path scheme with the new planned path scheme according to the difference; the search optimization module 1500 is configured to determine the current temperature of the simulated annealing algorithm based on a preset fast temperature drop function calculation, and determine whether the current temperature is lower than the preset temperature threshold. If so, the planned path scheme with the shortest path is selected from all iterative results as the final planned path scheme to complete the search optimization of the intelligent transport vehicle path.

[0188] Based on any embodiment of this application, please refer to Fig. 9 Another embodiment of the present application further provides an electronic device, which can be implemented by a computer device, such as Fig. 9As shown, a schematic diagram of the internal structure of a computer device. The computer device includes a processor, a computer-readable storage medium, a memory, and a network interface connected via a system bus. Among them, the computer-readable storage medium of the computer device stores an operating system, a database, and computer-readable instructions. The database may store a control information sequence. When the computer-readable instructions are executed by the processor, the processor can implement a method for searching and optimizing the path of an intelligent transport trolley. The processor of the computer device is used to provide computing and control capabilities to support the operation of the entire computer device. The memory of the computer device may store computer-readable instructions. When the computer-readable instructions are executed by the processor, the processor can execute the method for searching and optimizing the path of an intelligent transport trolley of the present application. The network interface of the computer device is used to connect and communicate with a terminal. Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0189] In this embodiment, the processor is used to execute Figure 8 The memory stores the program code and various data required to execute the above modules or submodules. The network interface is used to transmit data between user terminals or servers. The memory in this embodiment stores the program code and data required to execute all modules / submodules in the intelligent transport vehicle path search and optimization device of this application, and the server can call the program code and data of the server to execute the functions of all submodules.

[0190] The present application also provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the intelligent transport vehicle path search optimization method described in any embodiment of the present application.

[0191] The present application also provides a computer program product, including a computer program / instruction, which, when executed by one or more processors, implements the steps of the intelligent transport vehicle path search optimization method described in any embodiment of the present application.

[0192] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments of the present application can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, the aforementioned storage medium can be a computer-readable storage medium such as a disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM).

[0193] The above description is only a partial implementation method of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.

[0194] In summary, this application innovatively proposes a new path search method. On the basis of generating the initial planning path by the Feasible Path Self Generation Algorithm (FSGA), the simulated annealing (SA) algorithm is integrated for optimization, so that it can generate all path plans that meet the task requirements, and can accurately and quickly eliminate the path plans that cause the trolley to fall into a loop. Combined with the running speed of the intelligent transport trolley, it can accurately and quickly search for the path plan that completes the specified task the fastest.

Claims

1. An intelligent transport vehicle path search optimization method, applied to a multi-ring nested closed loop workshop, characterized in that: include: In response to the intelligent transport vehicle path search optimization instruction, a passable track set, a track set being connected, an unconnected track set, a connected track set, an initial track, and a target track in a multi-ring nested closed loop workshop are obtained, wherein the unconnected track set represents a track that is not selected after the track of the track set being connected is connected; The initial planning path plan of the intelligent transport vehicle is generated by adopting a greedy algorithm strategy in a preset path self-generation algorithm according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track; Using the initial planning path plan as an initial solution of a simulated annealing algorithm, and perturbing the initial solution to generate a new planning path plan; Determine the difference between the objective function value corresponding to the new planned path solution and the objective function value of the current planned path solution, and replace the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in the simulated annealing algorithm; The current temperature of the simulated annealing algorithm is determined based on the preset rapid temperature drop function calculation, and it is judged whether the current temperature is lower than the preset temperature threshold. If so, the planned path plan with the shortest path is selected from all iterative results as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

2. The intelligent transport vehicle path search and optimization method according to claim 1 is characterized in that: The steps of using a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path plan for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track include: Determine the passable track set R, the track set S being connected, and the unconnected track set S in the multi-ring nested closed loop workshop 0 , the connected orbit set S', the initial orbit a0 and the target orbit a n , where the unconnected track set S 0 represents the set of unselected orbits after S is turned on, and the initial orbit a0 is the initial orbit x 23 , the target track a n The target track x 22 ; Determine the target track x of the intelligent transport vehicle 22 , from the initial track x in the parking lot 23 Initially, add a0 to the set of tracks S being connected; From the initial track x 23 Start, select the next track according to the greedy algorithm, and select an accessible and unvisited track by checking the reachability relationship of the track; For each selected track a n , a strong trade-off is made. If one of the tracks x1 and x7 is selected as a1, the other track will enter the unconnected track set S 0 , to determine the initial unconnected track set S 0 1. Repeat this process until the set of tracks being connected S contains all target tracks x i 、x j 、x k 、x 22 , then the path S1 is generated; The completed path S1 is stored in the connected track set S', and the unconnected track set S generated during the path generation process is stored in the connected track set S 0 Deposit in the no-call table; From the initial unconnected track set S 0 Select the first track in 1 as the new starting point, repeat the above path generation process, generate a new path S2, store the completed path S2 into the connected track set S', and record the new unconnected track set S 0 2. Continue until all unconnected elements in a set are found to be consistent with the previously recorded initial unconnected track set S 0 1, the planning path plan that meets the current task of the intelligent transport vehicle is generated to determine the initial planning path plan of the intelligent transport vehicle.

3. The intelligent transport vehicle path search optimization method according to claim 1 is characterized in that: The step of using the initial planning path solution as an initial solution of a simulated annealing algorithm and perturbing the initial solution to generate a new planning path solution comprises: Determine an initial planning path plan for the intelligent transport vehicle, and use the initial planning path plan as an initial solution of the simulated annealing algorithm; The initial solution is exchanged, reversed, inserted or partially exchanged using a conversion operator to generate a new planning path solution.

4. The intelligent transport vehicle path search optimization method according to claim 1 is characterized in that: The step of determining a difference between an objective function value corresponding to a new planned path solution and an objective function value of a current planned path solution, and replacing the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in a simulated annealing algorithm comprises: The expression of the Metropolis criterion is: Among them, f(l) represents the objective function of the current planned path plan, f(l′) represents the objective function of the new planned path plan, n is the scale factor of the objective function, T is the current temperature, when f(l′)-f(l)<0, the objective function value of the new planned path plan is lower, and the new planned path plan is directly accepted; when f(l′)-f(l)>0, the probability is used to Accept the new planned path plan.

5. The intelligent transport vehicle path search and optimization method according to claim 1, characterized in that: The steps of determining a rapid temperature drop function for a simulated annealing algorithm include: Determine the initial temperature, number of iterations, and temperature drop coefficient during the annealing process of the simulated annealing algorithm; Calculate and determine a first product between the number of iterations and the temperature drop coefficient, and calculate and determine a first sum value between the first product and a value 1; Based on a first ratio between the initial temperature and the first sum value, determining a temperature when the number of iterations is k to determine a rapid temperature drop function; The steps of determining the initial temperature of the simulated annealing algorithm include: Determine the objective function of the current planned path plan, the objective function of the new planned path plan, and the preset acceptance probability; Calculating and determining the natural logarithm value of the acceptance probability; Calculate and determine a first difference between the objective function of the new planned path solution and the objective function of the current planned path solution; A second ratio between the first difference and the natural logarithm of the acceptance probability is calculated and determined, and a negative value of the second ratio is used as an initial temperature of the simulated annealing algorithm.

6. The intelligent transport vehicle path search and optimization method according to claim 1, characterized in that: After the steps of generating the initial planning path plan of the intelligent transport vehicle include: Calling a preset improved A* algorithm, and optimizing the initial planned path plan based on the improved A* algorithm; The optimized initial planning path plan is used as the initial solution of the simulated annealing algorithm.

7. The intelligent transport vehicle path search and optimization method according to any one of claims 1 to 6, characterized in that: The method further comprises: determining the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function, judging whether the current temperature is lower than a preset temperature threshold, and if so, selecting a planning path solution with the shortest path from all iteration results as a final planning path solution. Based on the preset speed adaptation algorithm, the speed of the intelligent transport vehicle is adapted to avoid collision with other intelligent transport vehicles; Calculate and determine the safe speed and braking acceleration of the intelligent transport vehicle to ensure that it can stop safely before encountering obstacles; According to the power acceleration and current speed of the intelligent transport vehicle, the speed adjustment window is determined to dynamically update the feasible speed range; For multiple intelligent transport vehicles, predict the displacement of other intelligent transport vehicles and adjust the obstacle avoidance strategy to reduce collisions; Based on the forward movement and expansion radius of other intelligent transport vehicles, the distance evaluation function is updated to ensure that obstacles can be accurately avoided in actual path planning.

8. An intelligent transport vehicle path search and optimization device, characterized in that: include: A data acquisition module is configured to respond to the intelligent transport vehicle path search optimization instruction, and acquire a passable track set, a track set being connected, an unconnected track set, a connected track set, an initial track, and a target track in a multi-ring nested closed loop workshop, wherein the unconnected track set represents a track set that is not selected after accessing the track in the track set being connected; An initial path determination module is configured to use a greedy algorithm strategy in a preset path self-generation algorithm to generate an initial planning path plan for the intelligent transport vehicle according to the passable track set, the track set being connected, the unconnected track set, the connected track set, the initial track and the target track; A new planning path determination module is configured to use the initial planning path solution as an initial solution of a simulated annealing algorithm and perturb the initial solution to generate a new planning path solution; a path updating module, configured to determine a difference between an objective function value corresponding to a new planned path solution and an objective function value of a current planned path solution, and replace the current planned path solution with the new planned path solution according to the difference using the Metropolis criterion in a simulated annealing algorithm; The search optimization module is configured to calculate and determine the current temperature of the simulated annealing algorithm based on a preset rapid temperature drop function, and determine whether the current temperature is lower than a preset temperature threshold. If so, the planned path plan with the shortest path among all iterative results is selected as the final planned path plan to complete the search optimization of the intelligent transport vehicle path.

9. An electronic device, comprising a central processing unit and a memory, characterized in that: The central processing unit is used to call and run the computer program stored in the memory to execute the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: It stores a computer program implemented according to the method described in any one of claims 1 to 7 in the form of computer-readable instructions, and when the computer program is called and executed by a computer, the steps included in the corresponding method are executed.

Images