Unmanned forklift path planning method, system, equipment and medium

Abstract

The invention discloses an unmanned forklift path planning method, system and device and a medium. The method comprises the steps that a grid map used for unmanned forklift path planning is established; obstacle evaluation operation is carried out on obstacles on the path of the unmanned forklift, and the obstacle density is calculated; based on the obstacle density, the motion step length of the unmanned forklift is dynamically adjusted; traversing a motion step length and an angle in the grid map, calculating a next possible node, and then updating node information; and if the path is found after the traversal operation, backtracking the final path. Map environment evaluation indexes are adopted, the grid map obstacles are detected, the complexity and the obstacle density of the map are quantified, and step length adjustment of an algorithm through the environment indexes is facilitated; the method improves the flexibility of the algorithm, designs step length adjustment functions in different obstacle density intervals, achieves the rapid expansion of the algorithm in a low-density region, precisely plans the path in a high-density region, and reduces the collision risk of the planned path.

Description

Technical Field

[0001] The present application relates to the field of path planning technology, and in particular to a method, system, device and medium for unmanned forklift path planning. Background Art

[0002] In the intelligent logistics system, unmanned forklifts, as an automated equipment, can effectively cope with the current challenges of severe aging and labor shortage, while improving efficiency and reducing error rates in warehousing and transportation. The path planning problem of unmanned forklifts is an important and complex challenge.

[0003] Although the hybrid A* algorithm has certain applications in path planning, there are still some significant problems and shortcomings in actual use. First, the algorithm's movement step size is fixed, which makes it lack adaptability and flexibility when dealing with different environments. In a complex dynamic environment, the fixed step size may not be able to effectively cope with changes in obstacles and adjustments to the path, resulting in unsatisfactory path planning results. In addition, the hybrid A* algorithm also has deficiencies in the accuracy and efficiency of path planning. The fixed step size will limit the precision of the path, which may cause the planned path to be inaccurate, thereby affecting the driving efficiency of the unmanned forklift and the optimality of the path. Summary of the invention

[0004] The present application provides a path planning method for an unmanned forklift, which is used to solve the technical problem of low efficiency and poor accuracy of the existing path planning for unmanned forklifts based on the A* algorithm.

[0005] In a first aspect, the present application provides a method for unmanned forklift path planning, characterized in that the method comprises the following steps:

[0006] Step S1: establishing a grid map for unmanned forklift path planning;

[0007] Step S2: performing an obstacle evaluation operation on the obstacles on the path of the unmanned forklift and calculating the obstacle density;

[0008] Step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density;

[0009] Step S4: traverse the movement step length and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

[0010] In one implementation of the present application, in step S2, the obstacle evaluation operation is specifically:

[0011] Initialize input parameters; wherein the input parameters include: coordinates of the position to be detected, detection radius and obstacle list;

[0012] Initialize the obstacle counter to zero;

[0013] Traversing each obstacle position in the obstacle list, calculating the distance to the position, and increasing the count of the obstacle counter according to the calculated distance;

[0014] Calculate obstacle density.

[0015] In one implementation of the present application, the count of the obstacle counter is increased according to the calculation of the distance, specifically: the distance is compared with the detection radius, and if the distance is smaller than the detection radius, the count of the obstacle counter is increased by one.

[0016] In one implementation of the present application, after step S1, the method further includes:

[0017] Initialize the variables related to the grid map, and add the starting point represented by the unmanned forklift to the Open list;

[0018] Enter the main loop until a path is found or the Open list is empty; in each loop, select the node with the smallest cost from the Open list and remove it from the Open list;

[0019] Check if the node is already in the Close list, if so, update its cost value; otherwise, add it to the Close list;

[0020] Check whether the current node can be connected to the target point End. If so, the path is found, set foundPath to 1, and record the last node lastNode.

[0021] In one implementation of the present application, the step S4 also includes: checking whether the node is empty or already in the Close list, if so, repeating the operation of traversing the movement step and angle in the grid map to calculate the next possible node; otherwise, checking whether it is already in the Open list, if so, updating the node information; if not, adding the node to the Open list.

[0022] In one implementation of the present application, the final path traced back includes the x-coordinate, y-coordinate, and direction θ of the path.

[0023] In one implementation of the present application, the process of dynamically adjusting the motion step length is specifically as follows:

[0024] Introduce two domain value parameters, namely T1 and T2, and T2>T1;

[0025] When the current node is in a low-density obstacle area: If ρ < T1, it means that there are fewer obstacles in the current area. To speed up the search, the movement step size is increased, and the movement step size is inversely proportional to the square of the obstacle density, as shown in the following formula:

[0026] d pos = d pos × 2(1 + (T1 - ρ) 2 × 10)

[0027] In the formula, d pos represents the movement step size. The operation of multiplying by 2 is used to initially amplify the step size, and the subsequent inverse square term further refines the adjustment to ensure that the increase in the step size is proportional to the sparsity of the obstacles;

[0028] When the current node is in a medium-density obstacle area, if T1 ≤ ρ < T2, it means that the obstacle density in the current area is at a medium level, and the movement step size d is adjusted linearly pos , so as to ensure the search efficiency and accuracy, as shown in the following formula:

[0029]

[0030] In the formula, the step size is first halved, and then linearly adjusted according to the obstacle density, so that the step size change can have a smooth transition and adapt to the medium-density environment;

[0031] When the current node is in a high-density obstacle area, if ρ ≥ T2, it means that the obstacles in the current area are dense, and d is reduced pos , and the multiple by which it is reduced is proportional to the cube of the obstacle density. The formula is as follows:

[0032]

[0033] In a second aspect, the present application also provides an unmanned forklift path planning system, and the system includes:

[0034] A grid map building module for building a grid map for unmanned forklift path planning;

[0035] An obstacle evaluation module for performing an obstacle evaluation operation on the obstacles on the unmanned forklift path and calculating the obstacle density;

[0036] A dynamic adjustment module for dynamically adjusting the movement step size of the unmanned forklift based on the obstacle density;

[0037] A path calculation module for traversing the movement step size and angle in the grid map, calculating the next possible node, and then updating the node information; if a path is found after the traversal operation, the final path is traced back.

[0038] In a third aspect, the present application also provides an unmanned forklift path planning device, the device comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can complete: step S1: establishing a grid map for unmanned forklift path planning; step S2: performing an obstacle evaluation operation on obstacles on the path of the unmanned forklift and calculating the obstacle density; step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density; step S4: traversing the movement step length and angle in the grid map, calculating the next possible node, and then updating the node information; if a path is found after the traversal operation, backtracking to the final path.

[0039] In a fourth aspect, the present application also provides a non-volatile computer storage medium for unmanned forklift path planning, storing computer executable instructions, which are executed by a processor to implement: Step S1: Establish a grid map for unmanned forklift path planning; Step S2: Perform an obstacle evaluation operation on obstacles on the path of the unmanned forklift, and calculate the obstacle density; Step S3: Based on the obstacle density, dynamically adjust the movement step of the unmanned forklift; Step S4: Traverse the movement step and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

[0040] The present application provides an unmanned forklift path planning method, system, device and medium, which have the following features:

[0041] Beneficial effects:

[0042] (1) The adaptability of the hybrid A* algorithm to the environment is improved. By adopting the map environment evaluation index, the obstacles on the grid map are detected, the complexity of the map and the density of obstacles are quantified, which makes it easier for the algorithm to adjust the step size through the environmental index.

[0043] (2) The flexibility of the algorithm is improved. By designing a step-size adjustment function within different obstacle density ranges, the algorithm can be quickly expanded in low-density areas and accurately plan paths in high-density areas, reducing the collision risk of the planned path. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0045] Figure 1 A flow chart of a method for unmanned forklift path planning provided in an embodiment of the present application;

[0046] Figure 2 A flowchart of the map environment evaluation index algorithm provided in the embodiment of the present application;

[0047] Figure 3 The unmanned forklift work map provided in the embodiment of the present application;

[0048] Figure 4 A diagram showing the change of heading angle with path points of the improved hybrid A* algorithm provided in an embodiment of the present application;

[0049] Figure 5 A path diagram of the traditional hybrid A* algorithm before and after the improvement provided in the embodiment of the present application;

[0050] Figure 6 A diagram showing the composition of an unmanned forklift path planning system provided in an embodiment of the present application;

[0051] Figure 7 A schematic diagram of an unmanned forklift path planning device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0052] In order to make the purpose, technical solution and advantages of the present application clearer, the technical solution of the present application will be clearly and completely described below in combination with the specific embodiments of the present application and the corresponding drawings. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present application.

[0053] The embodiments of the present application provide a method, system, device and medium for unmanned forklift path planning. The technical solutions proposed in the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0054] Example 1

[0055] Figure 1 A flow chart of a method for planning a path for an unmanned forklift provided in an embodiment of the present application. Figure 1 As shown, the method mainly includes the following steps:

[0056] Step S1: establishing a grid map for unmanned forklift path planning;

[0057] Step S2: performing an obstacle evaluation operation on the obstacles on the path of the unmanned forklift and calculating the obstacle density;

[0058] Step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density;

[0059] Step S4: traverse the movement step length and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

[0060] In the embodiment of the present application, the map environment evaluation index can provide more detailed and accurate environmental information for the path planning algorithm by quantifying the complexity and obstacle density of the map. This helps the algorithm to find the best path more effectively in a complex environment, thereby improving the accuracy and effectiveness of path planning. The map environment is evaluated by designing an obstacle density detection function to calculate the obstacle density around a given location. It determines the obstacle density of the location by checking the number of obstacles within a specified radius. The function traverses the locations of all obstacles, calculates the distance of each obstacle from the specified location, and counts the number of obstacles within the specified radius. Ultimately, the obstacle density is defined as the proportion of obstacles that occupy the detection range. The map environment evaluation index algorithm flow is as follows: Figure 2 shown.

[0061] The specific obstacle evaluation process is as follows:

[0062] Step 1: Initialize input parameters Pos, R s , and ObstList, respectively represent the position coordinates to be detected, the detection radius and the obstacle list.

[0063] Step 2: Initialize the obstacle counter count to 0.

[0064] Step 3: Traverse each obstacle position in the obstacle list ObstList and calculate its distance d to the position Pos i =||ObstList i -Pos||, if d i <R s , then increase the obstacle counter count = count + 1.

[0065] Step 4: Calculate obstacle density P.

[0066] In the embodiment of the present application, the traditional hybrid A* algorithm process needs to perform d pos and Angle_step to traverse different combinations. Among them, the movement step length d pos Refers to the change in distance moved each time a new node is explored, and Angle_step refers to the change in angle each time a new node is explored during path planning. These two determine the size and accuracy of each step in the algorithm's path search.

[0067] For the traditional hybrid A* algorithm, its movement step size is generally a constant, that is, the exploration step size is the same each time a new node is explored. However, in different environments, a fixed movement step size may not be able to effectively adapt to complex scene changes. Especially in open areas, using a constant movement step size will lead to an increase in the number of expanded nodes of the algorithm, limiting the search speed of the algorithm and the efficiency of path planning.

[0068] Aiming at the problem that the hybrid A* algorithm has the same movement step size in various situations and lacks adaptability to the environment. An adaptive movement step size is used. That is, if the obstacles around the currently explored node are sparse, its movement step size is increased, that is, the search range each time is expanded, so that the algorithm searches fewer nodes in the open environment and the search is accelerated. If the obstacles around the currently explored node are dense, the movement step size is appropriately reduced to make the search more accurate.

[0069] First, we calculate the obstacle density ρ around the current node by the number of obstacles within a certain radius R. According to different obstacle densities, the movement step size d is dynamically adjusted pos to adapt to the complexity of the environment. The specific method is as follows.

[0070] To adapt to maps with different obstacle densities and improve the accuracy and efficiency of path planning, two threshold parameters T1 and T2 are introduced here, and T2 > T1

[0071] When the current node is in a low-density obstacle area: If ρ < T1, it means that there are fewer obstacles in the current area. To accelerate the search speed, we increase d pos , making it inversely proportional to the square of the obstacle density. The specific formula is:

[0072] d pos = d pos × 2(1 + (T1 - ρ) 2 × 10)

[0073] Here, the operation of multiplying by 2 is used to initially enlarge the step size, and the subsequent inverse square term further refines the adjustment to ensure that the increase amplitude of the step size is proportional to the sparsity degree of the obstacles.

[0074] When the current node is in a medium-density obstacle area: If T1 ≤ ρ < T2, it means that the obstacle density in the current area is at a medium level. In this case, we adjust d according to a linear relationship pos , which not only ensures the search efficiency but also does not lose accuracy. The specific formula is:

[0075]

[0076] Here, the step size is first halved and then linearly adjusted according to the obstacle density, so that the change of the step size can be smoothly transitioned to adapt to the medium-density environment.

[0077] When the current node is in a high-density obstacle area: If ρ ≥ T2, it means that the obstacles in the current area are dense. In order to avoid path planning errors or collision risks, we significantly reduce d pos , so that its reduction multiple is proportional to the cube of the obstacle density. The specific formula is:

[0078]

[0079] The improved hybrid A* algorithm steps are given below

[0080] Step 1: Initialize PathTab, Open, Close, lastNode, and foundPath variables to store path information and control algorithm flow. Add the starting point to the Open list.

[0081] Step 2: Enter the main loop until a path is found or the Open list is empty. In each loop, select the node with the lowest cost from the Open list and remove it from the Open list.

[0082] Step 3: Check if the node is already in the Close list. If so, update its cost value; otherwise, add it to the Close list.

[0083] Step 4: Check whether the current node can be connected to the target point End. If so, the path is found, set foundPath to 1, and record the last node lastNode.

[0084] Step 5: According to the set detection radius R, check the obstacle density ρ around the current node.

[0085] Step 6: Dynamically adjust the motion step length d according to the obstacle density ρ obtained in step 5 pos .

[0086] Step 7: For each motion control parameter: motion step length d pos Traverse with the traversal angle Angle_step and calculate the next possible node tnode.

[0087] Step 8: Check whether the node is empty or already in the Close list. If so, return to step 7; otherwise, check whether it is already in the Open list. If so, update the node information; if not, add the node to the Open list.

[0088] Step 9: If the path is found, backtrack to the final path and set the x-coordinate, y-coordinate, and direction of the path to θ.

[0089] A specific example of the present application is as follows: The experimental environment is: Intel(R) Core(TM) i5-9300H CPU@2.40GHz, memory 16GB, and the compilation tool is MATLAB R2022a. Test different starting points and end points in a simulated open warehouse environment, set the vehicle parameters and various parameters of the hybrid A* algorithm, and compare the improved hybrid A* algorithm with the traditional hybrid A* algorithm in different environments by changing different starting points to observe the improvement effect of the hybrid A* algorithm.

[0090] Figure 3 This is the unmanned forklift work map established in this application. The map environment is a rectangular area with a length of 50 meters and a width of 30 meters. The forklift work is simplified to the forklift moving from the starting point to the pallet position. The blue area is regarded as an obstacle in the forklift working environment. The simplified single-steering wheel forklift AGV is a rectangular vehicle, and the center points of its two follower wheels are used to represent the current direction and position of the forklift and as the reference point for calculating the vehicle movement. The simulation initialization parameters are shown in Table 1.

[0091] Table 1 Simulation initialization parameters

[0092]

[0093] The heading angle of the improved hybrid A* algorithm changes with the path points as follows Figure 4 As shown in the figure, the heading angle is discontinuous once because the planned path has a reversing situation. In addition, the heading angle of the improved algorithm changes continuously and relatively smoothly without large fluctuations. Therefore, it is proved that the path planned by the improved hybrid A* algorithm is feasible for the actual single-steering wheel forklift motion trajectory planning.

[0094] Figure 5 The traditional hybrid A* path planning map before and after improvement. Before the improvement, the number of expanded nodes was 510, and after the improvement, the number of expanded nodes was 394. It can be seen that the number of nodes of the improved hybrid A* algorithm is reduced, the program running time is shortened, and the algorithm running efficiency is improved. In order to verify the universality of the optimization effect of the improved hybrid A* algorithm, multiple starting points are now changed in the map to put the vehicle in different obstacle environments, and the improvement effect in various situations is compared. The number of expanded nodes before and after the improvement is shown in Table 2.

[0095] Table 2 Number of expanded nodes before and after improvement

[0096]

[0097] From the experimental data, we can see that the improved and optimized hybrid A* algorithm has fewer explored nodes than the traditional hybrid A* algorithm. Compared with the results of the traditional hybrid A* algorithm, the total number of traversed nodes of the improved and optimized algorithm is reduced by an average of 173, which is an improvement of 33.68%. Therefore, the improved hybrid A* algorithm improves the efficiency of the traditional hybrid A* algorithm.

[0098] Example 2

[0099] The above is an unmanned forklift path planning method provided by an embodiment of the present application. Based on the same inventive concept, an unmanned forklift path planning system is also provided by an embodiment of the present application. Figure 6 A diagram of the composition of an unmanned forklift path planning system provided in an embodiment of the present application, such as Figure 6 As shown, the system mainly includes:

[0100] A grid map building module 601 is used to build a grid map for unmanned forklift path planning;

[0101] The obstacle evaluation module 602 is used to perform an obstacle evaluation operation on the obstacles on the path of the unmanned forklift and calculate the obstacle density;

[0102] A dynamic adjustment module 603, used to dynamically adjust the movement step length of the unmanned forklift based on the obstacle density;

[0103] The path calculation module 604 is used to traverse the movement steps and angles in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, the final path is backtracked.

[0104] Example 3

[0105] The above is an unmanned forklift path planning system provided by the embodiment of the present application. Based on the same inventive concept, the embodiment of the present application also provides an unmanned forklift path planning device. Figure 7 A schematic diagram of an unmanned forklift path planning device provided in an embodiment of the present application, such as Figure 7As shown, the device mainly includes: at least one processor 701; and, a memory 702 that is communicatively connected to the at least one processor; wherein the memory 702 stores instructions that can be executed by the at least one processor 701, and the instructions are executed by the at least one processor 701, so that the at least one processor 701 can complete the aforementioned: step S1: establishing a grid map for unmanned forklift path planning; step S2: performing an obstacle evaluation operation on obstacles on the path of the unmanned forklift, and calculating the obstacle density; step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density; step S4: traversing the movement step length and angle in the grid map, calculating the next possible node, and then updating the node information; if a path is found after the traversal operation, backtracking to the final path.

[0106] Example 4

[0107] In addition, an embodiment of the present application also provides a non-volatile computer storage medium for unmanned forklift path planning, storing computer executable instructions, which are executed by a processor to implement: Step S1: Establish a grid map for unmanned forklift path planning; Step S2: Perform an obstacle evaluation operation on obstacles on the path of the unmanned forklift, and calculate the obstacle density; Step S3: Based on the obstacle density, dynamically adjust the movement step of the unmanned forklift; Step S4: Traverse the movement step and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

[0108] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0109] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1A function specified in one or more boxes.

[0110] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0111] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0112] Each embodiment in this application is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the device embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0113] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0114] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A method for unmanned forklift path planning, characterized in that: The method includes the following steps: Step S1: Establish a grid map for the path planning of the driverless forklift; Step S2: Perform an obstacle evaluation operation on the obstacles on the path of the driverless forklift and calculate the obstacle density; Step S3: Dynamically adjust the movement step length of the driverless forklift based on the obstacle density; Step S4: Traverse the movement step length and angle in the grid map, calculate the next possible node, and then update the node information; if the path is found after the traversal operation, backtrack the final path.

2. The unmanned forklift path planning method according to claim 1, characterized in that: In the step S2, the obstacle evaluation operation is specifically: Initialize the input parameters; among them, the input parameters include: the coordinates of the position to be detected, the detection radius, and the obstacle list; Set the initialized obstacle counter to zero; Traverse each obstacle position in the obstacle list, calculate the distance from its position, and increase the count of the obstacle counter according to the calculation of the distance; Calculate the obstacle density.

3. The unmanned forklift path planning method according to claim 2, characterized in that: And increase the count of the obstacle counter according to the calculation of the distance, specifically: compare the distance with the detection radius, if the distance is less than the detection radius, then increase the count of the obstacle counter by one.

4. The unmanned forklift path planning method according to claim 1, characterized in that: After the step S1, the method further includes: Initialize the variables related to the grid map, and add the starting point represented by the driverless forklift to the Open list; Enter the main loop until the path is found or the Open list is empty; among them, in each loop, select the node with the minimum cost from the Open list and remove it from the Open list; Check whether this node is already in the Close list, if so, update its cost value; otherwise, add it to the Close list; Check whether the current node can be connected to the target point End, if so, the path is found, set foundPath to 1, and record the last node lastNode.

5. The unmanned forklift path planning method according to claim 1, characterized in that: The step S4 further includes: check whether this node is empty or already in the Close list, if so, repeat the operation of traversing the movement step length and angle in the grid map to calculate the next possible node; otherwise, check whether it is already in the Open list, if so, update the node information; if not, add the node to the Open list.

6. The unmanned forklift path planning method according to claim 1, characterized in that: Backtracking the final path includes the x coordinate, y coordinate, and orientation θ of the path.

7. The unmanned forklift path planning method according to claim 1, characterized in that: The process of dynamically adjusting the movement step length is specifically: Introduce two threshold parameters, namely T1 and T2, and T2>T1; When the current node is in a low-density obstacle area: if ρ<T1, it means that there are fewer obstacles in the current area. In order to speed up the search speed, increase the movement step length, and make the movement step length inversely proportional to the square of the obstacle density, as shown in the following formula: d pos =d pos ×2(1+(T1-ρ) 2 ×10) Where, d pos Represents the motion step length. The multiplication by 2 is used to initially amplify the step length, and the subsequent inverse square term further refines the adjustment to ensure that the increase in step length is proportional to the sparseness of the obstacle. When the current node is in a medium-density obstacle area, if T1 ≤ ρ < T2, it means that the obstacle density in the current area is at a medium level, and the movement step size d is adjusted according to a linear relationship pos , so as to ensure the search efficiency and accuracy, as shown in the following formula: In the formula, first halve the step length, and then perform a linear adjustment according to the obstacle density, so that the step length change can have a smooth transition and adapt to the medium-density environment; When the current node is in a high-density obstacle area, if ρ ≥ T2, it means that the obstacles in the current area are dense, and the value of d is reduced. pos , so that its reduction multiple is proportional to the cube of the obstacle density, the formula is as follows:

8. An unmanned forklift path planning system, characterized in that: The system includes: A grid map establishment module for establishing a grid map for the path planning of the driverless forklift; An obstacle evaluation module, used to perform obstacle evaluation operations on obstacles on the path of the unmanned forklift and calculate obstacle density; A dynamic adjustment module, used to dynamically adjust the movement step length of the unmanned forklift based on the obstacle density; The path calculation module is used to traverse the movement steps and angles in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, the final path is backtracked.

9. An unmanned forklift path planning device, characterized in that: The device comprises: at least one processor; and, a memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to complete: Step S1: establishing a grid map for unmanned forklift path planning; Step S2: performing an obstacle evaluation operation on the obstacles on the path of the unmanned forklift and calculating the obstacle density; Step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density; Step S4: traverse the movement step length and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

10. A non-volatile computer storage medium for unmanned forklift path planning, storing computer executable instructions, characterized in that: The computer executable instructions are executed by a processor to implement: Step S1: establishing a grid map for unmanned forklift path planning; Step S2: performing an obstacle evaluation operation on the obstacles on the path of the unmanned forklift and calculating the obstacle density; Step S3: dynamically adjusting the movement step length of the unmanned forklift based on the obstacle density; Step S4: traverse the movement step length and angle in the grid map, calculate the next possible node, and then update the node information; if a path is found after the traversal operation, backtrack to the final path.

Images