Mobile robot control multi-thread scheduling method, device and equipment and storage medium

Abstract

The invention provides a mobile robot control multi-thread scheduling method and device, equipment and a storage medium, and belongs to the technical field of automatic guidance, and the method specifically comprises the steps: generating a shortest path based on a path starting point, a path end point, map information and a path constraint condition; forming a time slice according to the total planning time and the time window length; according to the time slice and the shortest path, each time window corresponding to the transportation equipment is predicted, and the time window comprises position information of the transportation equipment; performing collision prediction on the plurality of transportation devices in each time window by adopting an independent thread to obtain collision points; dynamically adding the collision point as a collision constraint condition, and generating an update path according to the shortest path and the collision constraint condition; and when the predicted updated path does not have the collision point, outputting the updated path for scheduling the plurality of transportation devices. Through the processing scheme provided by the invention, the number of times of total comparison and the calculation amount are reduced, and higher efficiency and stronger real-time performance are achieved in a complex environment.

Description

Technical Field

[0001] The present invention relates to the field of automatic guidance, and particularly to a multi-threaded scheduling method, device, equipment and storage medium for mobile robot control. Background Art

[0002] In a multi-AGV (Automated Guided Vehicle) system, in order to ensure the safe operation of each vehicle on the planned path, it is usually necessary to perform full-scale collision detection for each time segment. These traditional methods have the following disadvantages: 1. Low efficiency: It is necessary to compare the movement trajectories of all AGVs one by one within the entire time series to determine whether there is a collision risk. When the number of AGVs reaches hundreds or even thousands, it will lead to significant performance bottlenecks, making the full-scale collision detection method impractical in actual applications; 2. High computational complexity: The complexity of full-scale comparison is O(N 2 *T), where N is the number of AGVs and T is the number of time segments. As the number of AGVs and the number of time segments increase, the amount of calculation will increase rapidly. In actual applications, this may lead to excessive consumption of computing resources; 3. Lack of real-time performance: In actual scenarios, AGVs need to quickly respond to emergencies in a dynamic environment, and traditional full-scale detection methods are difficult to meet the requirements of high real-time performance.

[0003] Therefore, traditional full-scale detection methods are difficult to operate effectively in large-scale or dynamic environments. Summary of the Invention

[0004] Therefore, in order to overcome the above-mentioned disadvantages of the prior art, the present invention provides a multi-threaded scheduling method, device, computer equipment and storage medium for mobile robot control, which reduces the number of full-scale comparisons and the amount of calculation, and makes full use of the computing power of multi-core processors, having higher efficiency and stronger real-time performance in complex environments.

[0005] To achieve the above object, the present invention provides a multi-threaded scheduling method for mobile robot control, which is used for collision-free scheduling of multiple transportation devices, including: generating the shortest path based on the path start point, path end point, map information and path constraint conditions; forming time segments according to the total planning time and the time window length; predicting each time window corresponding to the transportation device according to the time segment and the shortest path, and the time window includes the position information of the transportation device; using an independent thread to perform collision prediction on multiple transportation devices within each time window to obtain collision points; dynamically adding the collision points as collision constraint conditions, and generating an updated path according to the shortest path and the collision constraint conditions; when it is predicted that there are no collision points in the updated path, output the updated path for scheduling multiple transportation devices.

[0006] In one embodiment, the generating the shortest path based on the path start point, path end point, map information and path constraint conditions includes: using a path planning algorithm to generate all candidate paths from the path start point to the path end point based on the map information and the path constraint conditions; optimizing the candidate paths to obtain the shortest path.

[0007] In one embodiment, the forming time segments according to the total planning time and the time window length includes: determining the number of time segments according to the total planning time and the time window length; generating time segments according to the number of time segments and generating a time segment set.

[0008] In one embodiment, the using an independent thread to perform collision prediction on multiple transportation devices within each time window includes: obtaining the predicted positions of each transportation device according to the time window to generate a predicted position set for each time segment; determining collision points based on the predicted position set, the known dynamic obstacle position set and the safety distance; determining the corresponding time segment according to the collision points.

[0009] In one embodiment, the dynamically adding the collision points as collision constraint conditions includes: calculating the real-time priority when the transportation devices conflict using a dynamic priority strategy; adding the real-time priority, the collision points and the corresponding time segments as collision constraint conditions.

[0010] In one embodiment, when it is predicted that there are collision points in the updated path, an adjusted path is regenerated according to the collision points and the updated path, and when it is predicted that there are no collision points in the adjusted path, the adjusted path corresponding to multiple transportation devices is output.

[0011] A mobile robot control multi-threaded scheduling device, the device comprising: a shortest path generation module for generating a shortest path based on a path start point, a path end point, map information, and path constraint conditions; a time segment determination module for forming time segments according to a total planning time and a time window length; a time window prediction module for predicting, according to the time segments and the shortest path, each time window corresponding to the transportation device, the time window including the position information of the transportation device; a collision prediction module for performing collision prediction on a plurality of the transportation devices within each of the time windows by using an independent thread to obtain collision points; a path update module for dynamically adding the collision points as collision constraint conditions, and generating an updated path according to the shortest path and the collision constraint conditions; an output module for outputting the updated path for scheduling a plurality of the transportation devices when it is predicted that there are no collision points in the updated path.

[0012] A computer device, comprising a memory and a processor, the memory storing a computer program, wherein the processor, when executing the computer program, implements the steps of the above method.

[0013] A computer-readable storage medium, having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the steps of the above method.

[0014] Compared with the prior art, the advantages of the present invention are as follows: Combining time window grouping and multi-threaded parallel computing reduces the number of full-scale comparisons and the amount of computation, and makes full use of the computing power of a multi-core processor, having higher efficiency and stronger real-time performance in a complex environment; and when collision points are predicted, collision constraint conditions are dynamically generated to adjust the path in real time, so as to ensure that the transportation devices do not collide after scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained according to these drawings.

[0016] Figure 1 is a flowchart of a mobile robot control multi-threaded scheduling method in an embodiment of the present invention; Figure 2 is a structural block diagram of a mobile robot control multi-threaded scheduling device in an embodiment of the present invention; Figure 3 is an internal structure diagram of a computer device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0017] The embodiments of the present application will be described in detail below with reference to the accompanying drawings.

[0018] The following uses specific specific examples to illustrate the implementation manners of the present application. Those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation manners. Various details in this specification can also be modified or changed based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that, without conflict, the following embodiments and the features in the embodiments can be combined with each other. All other embodiments obtained by those of ordinary skill in the art based on the embodiments in the present application without making creative efforts belong to the scope of protection of the present application.

[0019] It should be noted that the following describes various aspects of embodiments within the protection scope of the present invention. It should be obvious that the aspects described herein can be embodied in a wide variety of forms, and any specific structure and / or function described herein is only illustrative. Based on the present application, those skilled in the art should understand that one aspect described herein can be implemented independently of any other aspect, and two or more of these aspects can be combined in various ways. For example, any number and aspects described herein can be used to implement the device and / or practice the method. In addition, this device and / or this method can be implemented using other structures and / or functions in addition to one or more of the aspects described herein.

[0020] It should also be noted that the drawings provided in the following embodiments only schematically illustrate the basic concept of the present application. The drawings only show the components related to the present application, rather than being drawn according to the number, shape, and size of the components in actual implementation. The type, quantity, and ratio of each component in actual implementation can be an arbitrary change, and the component layout type may also be more complex.

[0021] In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, those skilled in the art will understand that the described aspects can be practiced without these specific details.

[0022] The embodiments of the present application provide a multi-threaded scheduling method for mobile robot control, which is used for collision-free scheduling of multiple transportation devices and can be applied to a server or a terminal. The terminal can be, but is not limited to, various personal computers, laptop computers, smart phones, tablet computers, and portable intelligent devices. The server can be implemented by an independent server or a server cluster composed of multiple servers. The transportation device can be an AGV cart or a mobile robot, etc. As Figure 1As shown in the figure, taking the application on the server as an example, the multi-threaded scheduling method for mobile robot control schedules multiple AGV vehicles simultaneously, including the following steps: Step 101, generate the shortest path based on the path start point, path end point, map information, and path constraint conditions.

[0023] The server generates the shortest path based on the path start point, path end point, map information, and path constraint conditions. The map information M can include the set of static obstacles obstacles. The server can also consider the maximum speed v of the AGV vehicle max and the maximum allowable turning angle θ of the AGV vehicle max . The shortest path P includes the transportation routes of all AGV vehicles, expressed as , including a series of nodes or coordinate points. The calculation formula of the shortest path P is , where d(p i , p i+1 ) is the distance between point p i and p i+1 .

[0024] The constraint condition is .

[0025] The server can first initialize the path start point P start and the path end point P end , and initialize the map information M, the maximum speed u max and the maximum turning angle θ max . In some embodiments, the server can also initialize the set of dynamic obstacle positions O(t), the safety distance d safe and the dynamic area limit function restricted(t k ), etc. Then, the server uses the path planning algorithm to generate the path P from the start point to the end point considering the constraint conditions. The server optimizes the generated path P to ensure the shortest path. In one embodiment, the server uses a local optimization method to further shorten the path length. Both the path planning algorithm and the local optimization method can adopt common algorithms.

[0026] Step 102, form time segments according to the total planning time and the time window length.

[0027] The server forms time segments according to the total planning time and the time window length. The time segments divide the total planning time T into several consecutive time periods with a length of Δt. The start time of each time segment can be expressed as t k = k *Δt, where k is the index of the time segment, and k can be a natural number starting from 0. The time window length is Δt. The time segment set T can be expressed as , including the start times of all time segments from t0 to t N of the time segments.

[0028] Step 103: According to the time segments and the shortest path, predict each time window corresponding to the transportation device, where each time window contains the location information of the transportation device.

[0029] The server predicts each time window corresponding to the transportation device according to the time segments and the shortest path, where each time window contains the location information of the transportation device. The time window is the time constraint for the AGV to reach a certain node within a specific time period. By setting time windows for each node, the arrival time of the AGV can be restricted, thereby reducing the possibility of collisions; if the vehicle arrives at the node earlier than the earliest start time, it needs to wait. The server decomposes the shortest path into a series of linear segments, and the start and end points of each linear segment are p i-1 and p i respectively. The server obtains the planned speed v i of each linear segment. The server calculates the next location p i-1 (t k-1 ) and speed v i based on the current location p i (t k ). The server calculates the earliest arrival time and the latest arrival time of each linear segment according to the speed and path of the AGV to form a time window. The server outputs the predicted location set of each time window t k , denoted as . By decomposing the path movement of the AGV into time segments and predicting the location of the AGV in each time segment according to path planning and time window to form a time window, the server can provide basic data for dynamic detection and processing.

[0030] Step 104: Use independent threads to perform collision prediction on multiple transportation devices within each time window to obtain collision points.

[0031] The server uses independent threads to perform collision prediction on multiple AGV vehicles within each time window to obtain collision points. The server can use multiple independent threads to simultaneously and independently predict the collision points within different time windows, and output all collision points and the corresponding time segments to form a collision point set C = {(p i (t k ), t k )}. The judgment formula for collision detection is . When this judgment formula is not satisfied, it is determined that there is a collision risk d safe within this time window, and the collision point (p i (t k ), t k is recorded.). The server divides time into discrete segments and realizes the dynamic grouping of time windows through formulation. It calculates the collision risk only within the grouping, avoiding full-scale detection. And the whole process can be combined with multi-threaded parallel computing to improve the speed and efficiency of collision detection.

[0032] Step 105: Dynamically add the collision point as a collision constraint condition, and generate an updated path according to the shortest path and the collision constraint condition.

[0033] The server dynamically adds the collision point as a collision constraint condition. The server can generate a collision constraint condition that prohibits the AGV vehicle from reaching this position at time segment t for each collision point (p i (t k ),t k ) ∈ C: k The server can introduce a dynamic constraint adjustment mechanism in collision detection. For the detected conflict points, add constraint conditions in real time to prohibit specific vehicles from entering specific areas during specific time periods. And the server can iteratively eliminate the collision risk by dynamically adjusting the path and speed until there are no conflicts in the global path.

[0034] The server generates an updated path according to the shortest path and the collision constraint condition. At this time , where d(p i ,p i+1 ) is the distance between point p i and p i+1 i+1 .

[0035] The constraint condition is .

[0036] The set of dynamic obstacle positions O(t) is the set of positions o k (t j ) of the dynamic obstacle in each time segment t k , expressed as . The dynamic area restriction function restricted(t k ) is the dynamic area restriction within time segment t k . The safety distance d safe is the minimum safety distance that needs to be maintained between the AGV vehicle and the obstacle.

[0037] Step 106: When there are no collision points in the predicted updated path, output the updated path for scheduling multiple transportation devices.

[0038] The server can re - perform collision prediction on the updated path. When it is predicted that there are no collision points on the updated path, the server outputs the updated path for scheduling multiple transportation devices. When the server predicts that there are still collision points on the updated path, the server will dynamically add the new collision points as collision constraint conditions and obtain a new updated path again until the updated path meets the collision - free condition.

[0039] The above - mentioned method combines time - window grouping and multi - thread parallel computing to reduce the number of full - scale comparisons and the amount of computation, and makes full use of the computing power of multi - core processors, having higher efficiency and stronger real - time performance in complex environments; and when collision points are predicted, collision constraint conditions are dynamically generated and the path is adjusted in real time, so as to ensure that there are no collisions among transportation devices after scheduling.

[0040] In one embodiment, generating the shortest path based on the path start point, path end point, map information, and path constraint conditions includes: Using a path - planning algorithm, generating all candidate paths from the path start point to the path end point based on the map information and path constraint conditions; Optimizing the candidate paths to obtain the shortest path.

[0041] In one embodiment, forming time segments according to the total planning time and the time - window length includes: determining the number of time segments according to the total planning time and the time - window length; generating time segments according to the number of time segments and generating a set of time segments.

[0042] The server can determine the number of time segments N according to the total planning time T and the time - window length Δt. The number of time segments can be obtained by N = T / Δt, and N can be rounded up. The server generates a set of time segments T according to the number of time segments N, expressed as , including the start times of all time segments from t0 to t N The total planning time T is 60 seconds, and the time - window length Δt is 10 seconds. Then, the number of time segments N is calculated: N = T / Δt = 6, and then the set of time segments T is generated: .

[0043] In one embodiment, using independent threads to perform collision prediction on multiple transportation devices in each time window includes: obtaining the predicted positions of each transportation device according to the time window, generating a set of predicted positions in each time segment; determining collision points based on the set of predicted positions, the known set of dynamic obstacle positions, and the safety distance; and determining the corresponding time segments according to the collision points.

[0044] The server can obtain the predicted positions of each transportation device according to the time window, generate the set of predicted positions P(t) for each time segment, obtain the set of dynamic obstacles O(t), and perform initialization. The server traverses the time window t using multiple independent threads k , for each time window t k calculate the position p of the AGV i (t k ) and the position o of the dynamic obstacle j (t k ), and calculate the distance || p i (t k ) - o j (t k )||. When the distance is less than the safety distance, it is recorded as a collision point (p i (t k ), t k ). The server stores the corresponding collision point and time segment

[0045] In one embodiment, the collision point is dynamically added as a collision constraint condition, including: calculating the real-time priority when a conflict occurs in the transportation device using a dynamic priority policy; adding the real-time priority, the collision point, and the corresponding time segment as collision constraint conditions

[0046] The server can calculate the real-time priority when an AGV conflicts according to the dynamic priority policy. The real-time priority can be calculated based on at least one of the following factors: waiting time (the time the AGV has waited), travel distance (the distance the AGV has traveled), task urgency (determined by the task priority setting), and path length (the remaining path length from the current position to the target position). In one embodiment, the server can calculate the real-time priority Priority(i) by simultaneously using the waiting time WaitTime(i), travel distance Distance(i), and task urgency Urgency(i) , where α, β, and γ are weight coefficients used to balance the influence of different factors

[0047] In one embodiment, the server can generate a collision constraint condition where the low-priority AGV waits at the conflict point until the high-priority AGV passes, and this collision constraint condition also includes the collision point and the corresponding time segment. In one embodiment, the server can generate a collision constraint condition where the low-priority AGV re-plans its path to avoid the high-priority AGV, and this collision constraint condition also includes the collision point and the corresponding time segment

[0048] In one embodiment, when there is a collision point in the predicted updated path, an adjusted path is regenerated according to the collision point and the updated path When there is no collision point in the predicted adjustment path, output the adjustment paths corresponding to multiple transportation devices.

[0049] In one embodiment, as Figure 2 shown, a multi-threaded scheduling device for controlling a mobile robot is provided. The device includes a shortest path generation module 201, a time segment determination module 202, a time window prediction module 203, a collision prediction module 204, a path update module 205, and an output module 206.

[0050] The shortest path generation module 201 is configured to generate a shortest path based on a path start point, a path end point, map information, and path constraint conditions.

[0051] The time segment determination module 202 is configured to form time segments according to a total planning time and a time window length.

[0052] The time window prediction module 203 is configured to predict each time window corresponding to a transportation device according to the time segments and the shortest path, and the time window includes the position information of the transportation device.

[0053] The collision prediction module 204 is configured to perform collision prediction on multiple transportation devices within each time window by using an independent thread to obtain collision points.

[0054] The path update module 205 is configured to dynamically add the collision points as collision constraint conditions, and generate an updated path according to the shortest path and the collision constraint conditions.

[0055] The output module 206 is configured to output an updated path for scheduling multiple transportation devices when there is no collision point in the predicted updated path.

[0056] In one embodiment, the shortest path generation module 201 includes: A path generation unit configured to generate all candidate paths from a path start point to a path end point based on map information and path constraint conditions by using a path planning algorithm.

[0057] A shortest path optimization unit configured to optimize the candidate paths to obtain the shortest path.

[0058] In one embodiment, the time segment determination module 202 includes: A quantity determination unit configured to determine the quantity of time segments according to the total planning time and the time window length.

[0059] A segment generation unit configured to generate time segments according to the quantity of time segments and generate a time segment set.

[0060] In one embodiment, the collision prediction module 204 includes: A predicted position set unit, configured to obtain the predicted positions of each transportation device according to a time window, and generate a predicted position set for each time segment.

[0061] A collision point determination unit, configured to determine a collision point based on the predicted position set, the known dynamic obstacle position set, and a safety distance.

[0062] A corresponding unit, configured to determine a corresponding time segment according to the collision point.

[0063] In one embodiment, the path update module 205 includes: A priority calculation unit, configured to calculate the real-time priority when a conflict occurs between transportation devices by using a dynamic priority policy.

[0064] A collision constraint condition generation unit, configured to add the real-time priority, the collision point, and the corresponding time segment as collision constraint conditions.

[0065] For the specific limitations of the multi-threaded scheduling device for mobile robot control, reference may be made to the limitations of the multi-threaded scheduling method for mobile robot control in the foregoing text, which will not be elaborated herein. Each module in the above multi-threaded scheduling device for mobile robot control can be implemented in whole or in part by software, hardware, and their combination. The above-mentioned modules can be embedded in the processor of the computer device in hardware form or be independent of it, or can be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above-mentioned modules.

[0066] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as Figure 3 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as a path start point, a path end point, map information, a maximum speed, and a maximum turning angle. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a multi-threaded scheduling method for mobile robot control.

[0067] In one embodiment, a computer device is provided, including a memory and a processor. The memory stores a computer program. When the processor executes the computer program, the following steps are implemented: generating a shortest path based on a path start point, a path end point, map information, and path constraint conditions; forming time segments according to a total planning time and a time window length; predicting, according to the time segments and the shortest path, each time window corresponding to a transportation device, where the time window includes location information of the transportation device; using an independent thread to perform collision prediction on multiple transportation devices within each time window to obtain collision points; dynamically adding the collision points as collision constraint conditions, and generating an updated path according to the shortest path and the collision constraint conditions; when it is predicted that there are no collision points in the updated path, outputting the updated path for scheduling multiple transportation devices.

[0068] In one embodiment, when the processor executes the computer program, generating a shortest path based on a path start point, a path end point, map information, and path constraint conditions includes: using a path planning algorithm to generate all candidate paths from the path start point to the path end point based on the map information and the path constraint conditions; optimizing the candidate paths to obtain the shortest path.

[0069] In one embodiment, when the processor executes the computer program, forming time segments according to a total planning time and a time window length includes: determining the number of time segments according to the total planning time and the time window length; generating time segments according to the number of time segments, and generating a time segment set.

[0070] In one embodiment, when the processor executes the computer program, using an independent thread to perform collision prediction on multiple transportation devices within each time window includes: obtaining the predicted positions of each transportation device according to the time window, and generating a predicted position set for each time segment; determining collision points based on the predicted position set, a known set of dynamic obstacle positions, and a safety distance; determining the corresponding time segment according to the collision points.

[0071] In one embodiment, when the processor executes the computer program, dynamically adding the collision points as collision constraint conditions includes: using a dynamic priority strategy to calculate the real-time priority when a conflict occurs between transportation devices; adding the real-time priority, the collision points, and the corresponding time segments as collision constraint conditions.

[0072] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the following steps are implemented: generating a shortest path based on a path start point, a path end point, map information, and path constraint conditions; forming time segments according to a total planning time and a time window length; predicting, according to the time segments and the shortest path, each time window corresponding to a transportation device, where the time window includes location information of the transportation device; using an independent thread to perform a collision prediction on multiple transportation devices within each time window to obtain collision points; dynamically adding the collision points as collision constraint conditions, and generating an updated path according to the shortest path and the collision constraint conditions; when it is predicted that there are no collision points in the updated path, outputting the updated path for scheduling multiple transportation devices.

[0073] In one embodiment, generating a shortest path based on a path start point, a path end point, map information, and path constraint conditions, which is implemented when the computer program is executed by a processor, includes: using a path planning algorithm to generate all candidate paths from the path start point to the path end point based on the map information and the path constraint conditions; optimizing the candidate paths to obtain the shortest path.

[0074] In one embodiment, forming time segments according to a total planning time and a time window length, which is implemented when the computer program is executed by a processor, includes: determining the number of time segments according to the total planning time and the time window length; generating time segments according to the number of time segments, and generating a time segment set.

[0075] In one embodiment, using an independent thread to perform a collision prediction on multiple transportation devices within each time window, which is implemented when the computer program is executed by a processor, includes: obtaining the predicted positions of each transportation device according to the time window, and generating a predicted position set for each time segment; determining collision points based on the predicted position set, a known dynamic obstacle position set, and a safety distance; determining the corresponding time segment according to the collision points.

[0076] In one embodiment, dynamically adding the collision points as collision constraint conditions, which is implemented when the computer program is executed by a processor, includes: calculating a real-time priority when a conflict occurs between transportation devices using a dynamic priority strategy; adding the real-time priority, the collision points, and the corresponding time segments as collision constraint conditions.

[0077] As described above, the foregoing is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any changes or substitutions that can be easily thought of by those skilled in the art within the technical scope disclosed in the present application should be covered by the protection scope of the present application.

Claims

1. A multi-threaded scheduling method for mobile robot control, which is used for collision-free scheduling of multiple transportation devices, characterized in that, Including: Generate the shortest path based on the path start point, path end point, map information, and path constraint conditions; Form time segments according to the total planned time and the time window length; Predict each time window corresponding to the transportation device according to the time segment and the shortest path, where the time window contains the position information of the transportation device; Use an independent thread to perform collision prediction on multiple transportation devices within each time window to obtain collision points; Dynamically add the collision points as collision constraint conditions, and generate an updated path according to the shortest path and the collision constraint conditions; When it is predicted that there are no collision points in the updated path, output the updated path for scheduling multiple transportation devices.

2. The mobile robot control multi-thread scheduling method according to claim 1, wherein The generating the shortest path based on the path start point, path end point, map information, and path constraint conditions includes: Adopt a path planning algorithm to generate all candidate paths from the path start point to the path end point based on the map information and the path constraint conditions; Optimize the candidate paths to obtain the shortest path.

3. The multi-threaded scheduling method for mobile robot control according to claim 1, wherein The forming time segments according to the total planned time and the time window length includes: Determine the number of time segments according to the total planned time and the time window length; Generate time segments according to the number of time segments, and generate a time segment set.

4. The mobile robot control multi-thread scheduling method according to claim 1, characterized in that, The using an independent thread to perform collision prediction on multiple transportation devices within each time window includes: Obtain the predicted positions of each transportation device according to the time window, and generate a predicted position set for each time segment; Determine collision points based on the predicted position set, the known dynamic obstacle position set, and the safety distance; Determine the corresponding time segment according to the collision points.

5. The mobile robot control multi-threaded scheduling method according to claim 4, wherein The dynamically adding the collision points as collision constraint conditions includes: Use a dynamic priority strategy to calculate the real-time priority when the transportation devices conflict; Add the real-time priority, the collision points, and the corresponding time segments as collision constraint conditions.

6. The mobile robot control multi-thread scheduling method according to claim 1, wherein When it is predicted that there are collision points in the updated path, regenerate an adjusted path according to the collision points and the updated path, When it is predicted that there are no collision points in the adjusted path, output the adjusted path corresponding to multiple transportation devices.

7. A multi-threaded scheduling device for mobile robot control, characterized in that, The device includes: A shortest path generation module for generating the shortest path based on the path start point, path end point, map information, and path constraint conditions; A time segment determination module for forming time segments according to the total planned time and the time window length; A time window prediction module for predicting each time window corresponding to the transportation device according to the time segment and the shortest path, where the time window contains the position information of the transportation device; A collision prediction module for using an independent thread to perform collision prediction on multiple transportation devices within each time window to obtain collision points; A path update module for dynamically adding the collision points as collision constraint conditions, and generating an updated path according to the shortest path and the collision constraint conditions; An output module for outputting the updated path for scheduling multiple transportation devices when it is predicted that there are no collision points in the updated path.

8. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images