Traffic control method and system based on path conflict-free clustering

Abstract

The invention relates to a traffic control method and system based on path conflict-free clustering, and the method comprises the steps: a scheduling system carries out the grouping of all robots based on a traffic control period and the first information of all robots needing traffic control calculation in a current map, and obtains one or more robot groups; the scheduling system allocates an independent calculation unit to each robot group based on all the robot groups, so that each calculation unit obtains dynamic operation path information of each robot in the robot group to which the calculation unit belongs in the current traffic control period; and the scheduling system generates and sends a traffic control instruction of each robot to each robot based on the dynamic operation path information of the robots in each robot group returned by all the calculation units. According to the scheme, the defects of long time consumption and high cost of serial calculation in the prior art are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of robot scheduling, and in particular to a traffic control method and system based on path conflict-free clustering. Background Art

[0002] With the widespread use of robots in various fields, the number of robots in a single workshop is also growing rapidly. In photovoltaic and other fields, a single plant (a single map in the scheduling system) has deployed more than 200 robots. There are currently two main modes for implementing robot scheduling and traffic control. One is the centralized scheduling mode, which makes traffic control decisions based on global information. Its advantage is that it can optimize globally and ensure the best overall effect. However, with the expansion of the scale of robots, the computational complexity of the centralized traffic control algorithm increases exponentially, and it is necessary to continuously improve the CPU single-core computing performance to adapt to more robots, but this is not only costly, but also has an upper limit bottleneck. The other is a distributed mode, which allows each robot to make decisions independently and coordinate through communication. This method has higher robustness and flexibility than centralized scheduling, but it is difficult to guarantee global optimality and has higher design requirements. In addition, the frequent information interaction between a large number of robots greatly affects the effect in an industrial environment with unstable network. Therefore, in order to better deal with the problem of large-scale robot cluster scheduling, it is necessary to find a new solution.

[0003] Most of the existing robot scheduling system traffic management algorithms use traditional centralized scheduling algorithms. As the scale of robots expands, the computational complexity of centralized traffic management algorithms increases exponentially, and it is necessary to continuously improve the CPU single-core computing performance to accommodate more robots. However, this is not only costly, but also has an upper limit bottleneck. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the above-mentioned shortcomings and deficiencies of the prior art, the present invention provides a traffic control method and system based on path conflict-free clustering, which solves the problem of long time and high cost of serial calculation in the prior art through parallel traffic control calculation.

[0006] (II) Technical solution

[0007] In order to achieve the above object, the main technical solutions adopted by the present invention include:

[0008] In a first aspect, an embodiment of the present invention provides a traffic control method based on path conflict-free clustering, comprising:

[0009] The dispatching system groups all robots based on the traffic control cycle and first information of all robots that need to perform traffic control calculation in the current map to obtain more than one robot group;

[0010] The scheduling system allocates an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle;

[0011] The dispatching system generates a traffic control instruction to send to each robot based on the dynamic operation path information of the robots in each robot group returned by all the computing units.

[0012] Optionally, the first information of the robot includes: current position information of the robot, target position information of the robot, path planning information of the robot, and self parameter information of the robot;

[0013] Before the dispatching system groups all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map, the method further includes:

[0014] The dispatching system obtains first information of all robots in the map.

[0015] Optionally, the dispatching system groups all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map, including:

[0016] The scheduling system uses a path conflict algorithm to cluster all robots in the map to obtain more than one robot group.

[0017] Optionally, the scheduling system uses a path conflict algorithm to perform clustering processing on all robots in the map, including:

[0018] Step S21: Initialize the centroid based on the constraints.

[0019] Step S211: Determine the number of centroids k, k=min(rc / gc,mk);

[0020] Among them, rc is the total number of robots that need to perform traffic control calculations in the map, gc is the number of robots in each group preset in the dispatching system, and mk is the maximum number of groups preset in the dispatching system;

[0021] Step S212: randomly selecting k robots from all robots, and constructing cluster centers, i.e., centroids, based on the coordinates of the selected robots;

[0022] Step S22: Calculate the distance between the position coordinates (x, y) of each robot in the map and the position coordinates (zx, zy) of each center of mass, and assign the robot to the group with the closest center of mass;

[0023] The distance calculation formula is: d = (x-zx)*(x-zx)+(y-zy)*(y-zy)

[0024] Robot x is the X-axis coordinate value of the robot in the map, zx is the X-axis coordinate value of the center of mass in the map, y is the Y-axis coordinate value of the robot in the map, and zy is the Y-axis coordinate value of the center of mass in the map;

[0025] Step S23: Update the centroid, that is, according to the k groups obtained in the previous step, calculate the average distance of all robots in each group and use it as the new centroid;

[0026] S22 and S23 are repeated until the centroid does not change or the maximum number of iterations preset by the scheduling system is reached.

[0027] Optionally, the constraint conditions include:

[0028] The safe distance between any two robots is: traffic control period*robot speed+redundant distance; the redundant distance is a pre-given number; the robot speed is the maximum speed of the two robots to be calculated.

[0029] Optionally, the scheduling system allocates an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains dynamic running path information of each robot in the robot group to which it belongs during the current traffic control cycle, including:

[0030] When each computing unit is a thread, the main thread of the scheduling system sends the first information of the robot in the robot group corresponding to the sub-thread in the current traffic control cycle to each sub-thread, and enables the sub-thread to obtain the dynamic running path information of each robot in the robot group to which it belongs in the current traffic control cycle;

[0031] or,

[0032] Each computing unit is a distributed subsystem in the scheduling system. The main node of the scheduling system sends the first information of the robots in the robot group corresponding to the subsystem during the current traffic control cycle to each distributed subsystem, and enables the subsystem to obtain the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle.

[0033] In a second aspect, an embodiment of the present invention further provides a traffic control system based on path conflict-free clustering, comprising:

[0034] A grouping unit is used to group all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map to obtain more than one group of robots.

[0035] An allocation unit is used to allocate an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains dynamic operation path information of each robot in the robot group to which it belongs in the current traffic control cycle;

[0036] The traffic control instruction generating unit is used to generate a traffic control instruction to be sent to each robot based on the dynamic operation path information of the robots in each robot group returned by all the computing units.

[0037] Optionally, the first information of the robot includes: current position information of the robot, target position information of the robot, path planning information of the robot, and self parameter information of the robot;

[0038] The system further comprises:

[0039] The acquisition unit is used to acquire the first information of all robots in the map.

[0040] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, comprising: a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of a traffic control method based on path conflict-free clustering as described in any one of the first aspects are implemented.

[0041] (III) Beneficial effects

[0042] The beneficial effects of the present invention are:

[0043] The scheduling system of the present invention first groups the robots that need to perform traffic control calculations, and then allocates an independent computing unit to each robot group, so that each computing unit calculates the dynamic operation path information of the robots in each group. It can convert the serial calculation in the prior art into parallel calculation, and at the same time solves the defects of the prior art that the serial calculation is time-consuming and the hardware cost of the scheduling system is high.

[0044] The dispatching system of the present invention can support traffic control calculations for 1,000 robots on a single map. At the same time, without purchasing expensive CPUs, it can support a relatively large robot cluster by horizontally expanding the server. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 A flow chart of a traffic control method based on path conflict-free clustering provided by an embodiment of the present invention;

[0046] Figure 2 A flow chart of a traffic control method based on path conflict-free clustering provided by another embodiment of the present invention;

[0047] Figure 3A structural diagram of a traffic control system based on path conflict-free clustering provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0048] In order to better explain the present invention and facilitate understanding, the present invention is described in detail below through specific implementation modes in conjunction with the accompanying drawings.

[0049] The relevant terms in the embodiments of the present invention are explained as follows.

[0050] Map: refers to the topological map of the robot scheduling field, which is used for long-distance navigation and coarse-grained path planning. The map contains the location information of points, lines, walls, obstacles, etc.

[0051] Points in the map: Contains two-dimensional coordinate information, whether parking is possible, etc.

[0052] Lines in the map: They are the connecting lines between points in the map, and contain information such as the direction, speed, and width of the robot's movement.

[0053] Path: refers to a series of connected points and lines that the robot passes through from the starting point to the destination.

[0054] Planned path: It is a path calculated by the scheduling system based on the robot's starting point and destination.

[0055] Before starting the traffic control calculation, the scheduling system needs to pre-configure two configuration items, one is the number of robots in each group (gc), and the other is the maximum number of groups (mk).

[0056] In order to better understand the above technical solution, exemplary embodiments of the present invention will be described in more detail below with reference to the accompanying drawings. Although exemplary embodiments of the present invention are shown in the accompanying drawings, it should be understood that the present invention can be implemented in various forms and should not be limited by the embodiments described herein. On the contrary, these embodiments are provided to enable a clearer and more thorough understanding of the present invention and to fully convey the scope of the present invention to those skilled in the art.

[0057] Embodiment 1

[0058] The embodiment of the present invention provides a traffic control method based on path conflict-free clustering, the execution subject of which may be a dispatching system in a device. The method of this embodiment may include the following steps: Figure 2 shown.

[0059] 101. The dispatching system groups all robots based on the traffic control cycle and first information of all robots that need to perform traffic control calculation in the current map to obtain more than one robot group.

[0060] The first information of the robot in this embodiment may include: the current position information of the robot, the target position information of the robot, the path planning information of the robot, the robot's own parameter information, etc. The first information of this embodiment can be configured according to actual needs.

[0061] In this embodiment, the first information of all robots may be pre-acquired by the scheduling system, that is, the scheduling system may plan a path for each robot and obtain path planning information.

[0062] 102. The dispatching system allocates an independent computing unit to each robot group based on all robot groups, so that each computing unit can obtain the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle.

[0063] For example, the scheduling system may use a path conflict algorithm to cluster all robots in the map to obtain more than one robot group. Optionally, the clustering algorithm used in this embodiment is a K-means algorithm.

[0064] 103. The dispatching system generates a traffic control instruction to send to each robot based on the dynamic operation path information of the robots in each robot group returned by all computing units.

[0065] In practical applications, when each computing unit is a thread, the main thread of the scheduling system sends the first information of the robot in the robot group corresponding to the sub-thread in the current traffic control cycle to each sub-thread, and enables the sub-thread to obtain the dynamic running path information of each robot in the robot group to which it belongs in the current traffic control cycle;

[0066] In addition, in other embodiments, each computing unit is a distributed subsystem in the scheduling system, and the main node of the scheduling system sends the first information of the robots in the robot group corresponding to the subsystem during the current traffic control cycle to each distributed subsystem, and enables the subsystem to obtain the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle.

[0067] The dispatching system of this embodiment first groups the robots that need to perform traffic control calculations, and then allocates an independent computing unit to each robot group, so that each computing unit calculates the dynamic operation path information of the robots in each group. This can convert the serial calculation in the prior art into parallel calculation, and at the same time solves the defects of the prior art that the serial calculation is time-consuming and requires high hardware costs for the dispatching system.

[0068] In a possible implementation, the scheduling system in step 102 of this embodiment uses a path conflict algorithm to perform clustering processing on all robots in the map, which may specifically include:

[0069] Step S21: Initialize the centroid based on the constraints.

[0070] For example, the safe distance between any two robots is: traffic control period*robot speed+redundant distance; the redundant distance is a predetermined number; and the robot speed is the maximum speed of the two robots to be calculated.

[0071] Step S211: Determine the number of centroids k, k=min(rc / gc,mk);

[0072] Among them, rc is the total number of robots that need to perform traffic control calculations in the map, gc is the number of robots in each group preset in the dispatching system, and mk is the maximum number of groups preset in the dispatching system;

[0073] Step S212: randomly selecting k robots from all robots, and constructing cluster centers, i.e., centroids, based on the coordinates of the selected robots;

[0074] Step S22: Calculate the distance between the position coordinates (x, y) of each robot in the map and the position coordinates (zx, zy) of each center of mass, and assign the robot to the group with the closest center of mass;

[0075] The distance calculation formula is: d = (x-zx)*(x-zx)+(y-zy)*(y-zy)

[0076] Robot x is the X-axis coordinate value of the robot in the map, zx is the X-axis coordinate value of the center of mass in the map, y is the Y-axis coordinate value of the robot in the map, and zy is the Y-axis coordinate value of the center of mass in the map;

[0077] Step S23: Update the centroid, that is, according to the k groups obtained in the previous step, calculate the average distance of all robots in each group and use it as the new centroid;

[0078] S22 and S23 are repeated until the centroid does not change or the maximum number of iterations preset by the scheduling system is reached.

[0079] The dispatching system of this embodiment can support traffic control calculations for 1,000 robots on a single map. At the same time, without purchasing expensive CPUs, it can support a relatively small robot cluster by horizontally expanding the server.

[0080] Embodiment 2

[0081] In the solution of this embodiment, the core goal of traffic control is to ensure that there is no collision between robots during movement in the map area, and to calculate their next feasible movement route based on the current position information of the robots and the planned path.

[0082] The traffic control method based on path non-conflict clustering of this embodiment may include the following steps: Figure 1 shown.

[0083] Step S1: The scheduling system collects the first information of all robots in the map; the first information includes: current location information and path planning information, etc.

[0084] The first information must include: the coordinate information (x0, y0) of each robot's current location in the map, and the coordinate information (x1, y1) of each robot's target location.

[0085] Step S2: The scheduling system applies a path conflict algorithm to cluster the robots in the map to form several robot groups.

[0086] In this embodiment, when the dispatching system performs traffic control calculations, the dispatching system will perform traffic control calculations regularly according to a certain mechanism, such as a certain frequency (i.e., traffic control cycle). The above-mentioned current location information and path planning information are necessary data for traffic control calculations, and are not necessarily limited to these two types of information. Other information can be added according to different scenarios.

[0087] For example, the above step S2 may include the following sub-steps:

[0088] Step S21: Initialize the centroid based on the constraints, divided into two small steps:

[0089] Step S211: Determine the number of centroids (k), the formula for calculating the number of centroids is: k=min(rc / gc,mk);

[0090] Among them, rc is the total number of robots that need traffic control calculation in the map, gc is the number of robots in each group preset by the dispatch system, and mk is the maximum number of groups preset by the dispatch system. This value is mainly constrained by computing resources and can be appropriately increased as computing resources increase. Therefore, the number of centroids is equal to the smaller value of rc / gc and mk.

[0091] Step S212: Determine the centroid. Randomly select k (the calculation result of S211) robots from all robots, and construct the cluster center (centroid) based on the coordinates of the selected robots.

[0092] Step S22: Assigning data points. Calculate the distance between each robot position coordinate (x, y) and each center of mass position coordinate (zx, zy) in the map, and assign it to the group with the closest center of mass.

[0093] The distance calculation formula is: d = (x-zx)*(x-zx)+(y-zy)*(y-zy).

[0094] In the above formula, robot x is the x-axis coordinate value of the robot in the map, zx is the x-axis coordinate value of the center of mass in the map, y is the y-axis coordinate value of the robot in the map, and zy is the y-axis coordinate value of the center of mass in the map.

[0095] Step S23: Update the centroid. According to the k groups obtained in the previous step, calculate the average distance of all robots in each group and use it as the new centroid.

[0096] Repeat S22 and S23 until the centroid no longer changes or the maximum number of iterations preset by the system is reached.

[0097] The constraint condition (i.e., basic assumption) in this step is that if any two robots are far apart (i.e., far beyond the safe distance), even if there is a potential conflict in their planned paths (a collision may occur at a certain point), no actual collision will occur in the short term (the current traffic control cycle).

[0098] Therefore, it is only necessary to calculate the new traffic control result in advance (that is, according to the route planned, the robot can go to a certain position next without colliding with other vehicles) within a safe distance before the robot approaches the possible collision point to prevent the occurrence of collision.

[0099] Safety distance = traffic control cycle * maximum speed of two robots + redundant distance.

[0100] Step S3: The dispatching system allocates an independent computing unit to each group, performs parallel traffic control calculations, and obtains the control results of the robots in each group;

[0101] The computing unit in this embodiment has at least two implementation modes, one is thread mode and the other is distributed mode. Regardless of thread mode or distributed mode, the computing units in the scheduling system are all implemented in parallel and independently.

[0102] The computing unit of this embodiment can be deployed in a distributed cluster mode. The cluster computing nodes encapsulate the computing results as input parameters in parallel, call the computing unit through RPC (Remote Procedure Call), and return the results to the cluster computing node after the computing unit completes the calculation.

[0103] Step S4: The dispatching system summarizes the calculation results of all groups and returns the final traffic control instructions to each robot in the dispatching system.

[0104] The dispatching system of this embodiment can support traffic control calculations for 1,000 robots in a single map. In addition, the device of this embodiment can support an ever-increasing robot cluster by horizontally expanding the server without purchasing expensive CPUs.

[0105] Embodiment 3

[0106] In addition, an embodiment of the present invention further provides a traffic control system based on path conflict-free clustering, comprising:

[0107] A grouping unit is used to group all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map to obtain more than one group of robots.

[0108] An allocation unit is used to allocate an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains dynamic operation path information of each robot in the robot group to which it belongs in the current traffic control cycle;

[0109] The traffic control instruction generating unit is used to generate a traffic control instruction to be sent to each robot based on the dynamic operation path information of the robots in each robot group returned by all the computing units.

[0110] In this embodiment, the first information of the robot includes: current position information of the robot, target position information of the robot, path planning information of the robot, and parameter information of the robot itself;

[0111] In one possible implementation, Figure 3 As shown, the above system also includes:

[0112] The acquisition unit is used to acquire the first information of all robots in the map.

[0113] In the system of this embodiment, the grouping unit first groups the robots that need to perform traffic control calculations, and then the allocation unit allocates an independent calculation unit to each robot group, so that each calculation unit calculates the dynamic operation path information of the robots in each group, which can realize the conversion of serial calculations in the prior art into parallel calculations, and at the same time solves the defects of the prior art that serial calculations are time-consuming and require high hardware costs for the scheduling system.

[0114] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium, comprising: a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of a traffic control method based on path conflict-free clustering as described in any of the above embodiments are implemented.

[0115] It will be appreciated by those skilled in the art that embodiments of the present invention may be provided as methods, systems or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0116] The present invention is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems) and computer program products according to the embodiments of the present invention. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions.

[0117] It should be noted that in the claims, any reference numerals placed between brackets shall not be construed as limiting the claims. The word "comprising" does not exclude the presence of components or steps not listed in the claims. The word "a" or "an" preceding a component does not exclude the presence of a plurality of such components. The invention may be implemented by means of hardware comprising several different components and by means of a suitably programmed computer. In the claims enumerating several means, several of these means may be embodied by the same hardware. The use of the words first, second, third, etc., is for convenience of expression only and does not indicate any order. These words may be understood as part of the component name.

[0118] In addition, it should be noted that, in the description of this specification, the description of the terms "one embodiment", "some embodiments", "embodiment", "example", "specific example" or "some examples" etc. means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art may combine and combine the different embodiments or examples described in this specification and the features of the different embodiments or examples, unless they are contradictory.

[0119] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments after knowing the basic creative concept. Therefore, the claims should be interpreted as including the preferred embodiments and all changes and modifications falling within the scope of the present invention.

[0120] Obviously, those skilled in the art can make various modifications and variations to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention should also include these modifications and variations.

Claims

1. A traffic control method based on path conflict-free clustering, characterized in that: include: The dispatching system groups all robots based on the traffic control cycle and first information of all robots that need to perform traffic control calculation in the current map to obtain more than one robot group; The scheduling system allocates an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle; The dispatching system generates a traffic control instruction to send to each robot based on the dynamic operation path information of the robots in each robot group returned by all the computing units.

2. The method according to claim 1, characterized in that The first information of the robot includes: current position information of the robot, target position information of the robot, path planning information of the robot, and parameter information of the robot itself; Before the dispatching system groups all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map, the method further includes: The dispatching system obtains first information of all robots in the map.

3. The method according to claim 1, characterized in that: The dispatch system groups all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculations in the current map, including: The scheduling system uses a path conflict algorithm to cluster all robots in the map to obtain more than one robot group.

4. The method according to claim 3, characterized in that The scheduling system uses a path conflict algorithm to cluster all robots in the map, including: Step S21: Initialize the centroid based on the constraints. Step S211: Determine the number of centroids k, k=min(rc / gc,mk); Among them, rc is the total number of robots that need to perform traffic control calculations in the map, gc is the number of robots in each group preset in the dispatching system, and mk is the maximum number of groups preset in the dispatching system; Step S212: randomly selecting k robots from all robots, and constructing cluster centers, i.e., centroids, based on the coordinates of the selected robots; Step S22: Calculate the distance between the position coordinates (x, y) of each robot in the map and the position coordinates (zx, zy) of each center of mass, and assign the robot to the group with the closest center of mass; The distance calculation formula is: d = (x-zx)*(x-zx)+(y-zy)*(y-zy) Robot x is the X-axis coordinate value of the robot in the map, zx is the X-axis coordinate value of the center of mass in the map, y is the Y-axis coordinate value of the robot in the map, and zy is the Y-axis coordinate value of the center of mass in the map; Step S23: Update the centroid, that is, according to the k groups obtained in the previous step, calculate the average distance of all robots in each group and use it as the new centroid; S22 and S23 are repeated until the centroid does not change or the maximum number of iterations preset by the scheduling system is reached.

5. The method according to claim 4, characterized in that The constraints include: The safe distance between any two robots is: traffic control period*robot speed+redundant distance; the redundant distance is a pre-given number; the robot speed is the maximum speed of the two robots to be calculated.

6. The method according to any one of claims 1 to 5, characterized in that: The scheduling system allocates an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle, including: When each computing unit is a thread, the main thread of the scheduling system sends the first information of the robot in the robot group corresponding to the sub-thread in the current traffic control cycle to each sub-thread, and enables the sub-thread to obtain the dynamic running path information of each robot in the robot group to which it belongs in the current traffic control cycle; or, Each computing unit is a distributed subsystem in the scheduling system. The main node of the scheduling system sends the first information of the robots in the robot group corresponding to the subsystem during the current traffic control cycle to each distributed subsystem, and enables the subsystem to obtain the dynamic operation path information of each robot in the robot group to which it belongs during the current traffic control cycle.

7. A traffic control system based on path conflict-free clustering, characterized in that: include: A grouping unit is used to group all robots based on the traffic control cycle and the first information of all robots that need to perform traffic control calculation in the current map to obtain more than one group of robots. An allocation unit is used to allocate an independent computing unit to each robot group based on all robot groups, so that each computing unit obtains dynamic operation path information of each robot in the robot group to which it belongs in the current traffic control cycle; The traffic control instruction generating unit is used to generate a traffic control instruction to be sent to each robot based on the dynamic operation path information of the robots in each robot group returned by all the computing units.

8. The system according to claim 7, characterized in that The first information of the robot includes: current position information of the robot, target position information of the robot, path planning information of the robot, and parameter information of the robot itself; The system further comprises: The acquisition unit is used to acquire the first information of all robots in the map.

9. A computer-readable storage medium comprising: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of a traffic control method based on path conflict-free clustering as described in any one of claims 1 to 6 are implemented.

Images