Collaborative planning method for moving path of robot and related device

Abstract

The invention discloses a collaborative planning method for a robot moving path and a related device, and relates to the technical field of data processing, and the method comprises the steps: carrying out the real-time mapping based on real-time environment information, and obtaining a target scene map; selecting a plurality of corresponding target robots in the robot sequence based on the real-time task information; performing task allocation on each target robot based on the real-time task information to obtain corresponding task information; based on the target scene map and the task information, performing path planning by using a distributed calculation model to obtain an initial moving path corresponding to each target robot; performing movement conflict analysis on the initial movement path corresponding to each target robot to obtain movement conflict information; and the initial moving path is adjusted and optimized based on the moving conflict information in combination with the real-time task information, and each target robot executes an operation task based on the corresponding optimized moving path. According to the invention, the moving efficiency of the robot is improved, and the moving coordination among multiple robots is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular, to a method and related device for collaborative planning of a robot's moving path. Background Art

[0002] With the maturity of robot technology, more and more enterprises use robots to perform corresponding task operations. The moving path planning of robots affects the efficiency of their task operations. Currently, the collaborative work of multiple robots is usually adopted. In this regard, how to solve the collaborative planning of the moving paths of multiple robots has become the key to the collaborative work of multiple robots. Currently, for the collaborative planning of the moving paths of robots, most enterprises usually manually plan the moving paths of each robot. However, this method is difficult to ensure the reliability of the moving path planning and is prone to confusion in the moving path planning. At the same time, currently, after the moving path is planned, it is directly sent to the robot for moving operations without considering the possible conflicts that may occur during the robot's movement, resulting in a large obstacle to the robot's movement and affecting its work efficiency. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and related device for collaborative planning of a robot's moving path, realizing collaborative movement between multiple robots and making the collaborative planning of the robot's moving path achieve a more ideal effect.

[0004] To solve the above technical problems, the present invention provides a method for collaborative planning of a robot's moving path, the method comprising:

[0005] Performing real-time mapping based on real-time environment information to obtain a target scene map;

[0006] Selecting a corresponding number of target robots from a robot sequence based on real-time task information;

[0007] Performing task allocation on each target robot based on the real-time task information to obtain the task information corresponding to each target robot;

[0008] Performing path planning using a distributed computing model based on the target scene map and task information to obtain the initial moving paths corresponding to each target robot;

[0009] Performing moving conflict analysis on the initial moving paths corresponding to each target robot to obtain moving conflict information;

[0010] Adjusting and optimizing the initial moving paths based on the moving conflict information in combination with the real-time task information to obtain the optimized moving paths corresponding to each target robot, and each target robot performs task operations based on the corresponding optimized moving path.

[0011] Optionally, the real-time mapping based on the real-time environment information to obtain the target scene map includes:

[0012] Performing formatting processing on the real-time environment information to obtain formatted real-time environment information;

[0013] Performing rasterization and binarization processing on the formatted real-time environment information to obtain an obstacle area and a non-obstacle area;

[0014] Performing real-time mapping based on the obstacle area and the non-obstacle interval to obtain the target scene map.

[0015] Optionally, the selecting of corresponding several target robots from the robot sequence based on the real-time task information includes:

[0016] Determining the required movement speed and movement load of the robot based on the real-time task information;

[0017] Matching the required movement speed and movement load with the working parameters of each robot to obtain a matching result;

[0018] Selecting corresponding several target robots from the robot sequence based on the matching result.

[0019] Optionally, the task assignment to each target robot based on the real-time task information to obtain the task information corresponding to each target robot includes:

[0020] Calculating the target cost value required for each task to be assigned to each target robot based on the real-time task information and the load-bearing capacity of each target robot;

[0021] Determining a task assignment scheme based on the target cost value using the minimum cost criterion, and performing task assignment to each target robot based on the task assignment scheme to obtain the task information corresponding to each target robot.

[0022] Optionally, the path planning using a distributed computing model based on the target scene map and the task information to obtain the initial movement paths corresponding to each target robot includes:

[0023] Obtaining obstacle position information based on the target scene map;

[0024] Generating several first movement paths corresponding to each target robot based on the starting point, the end point of the movement path, and the obstacle position information of each target robot in combination with the target scene map;

[0025] Setting constraint conditions and a loss function, and generating a cost function based on the constraint conditions and the loss function;

[0026] Based on the distributed computing model, use the cost function to calculate the movement costs of several first movement paths corresponding to each target robot, obtain the target movement costs of each first movement path, and use the first movement path with the minimum target movement cost as the initial movement path corresponding to each target robot.

[0027] Optionally, the movement conflict analysis of the initial movement paths corresponding to each target robot to obtain movement conflict information includes:

[0028] Judge the path overlap of the initial movement paths corresponding to each target robot. If there is an overlapping path segment between the initial movement paths of the target robots, analyze the movement directions of the target robots in the overlapping path segment. If the movement directions of the target robots in the overlapping path segment are the same, there is a same-direction movement conflict between the initial movement paths of the target robots;

[0029] If the movement directions of the target robots in the overlapping path segment are opposite, there is an opposite-direction movement conflict between the initial movement paths of the target robots;

[0030] If there is no overlapping path segment between the initial movement paths of the target robots, judge whether there is an intersection point between the initial movement paths of each target robot. If there is an intersection point, there is an intersection conflict between the initial movement paths of the target robots.

[0031] Optionally, the adjustment and optimization of the initial movement paths based on the movement conflict information combined with the real-time task information to obtain the optimized movement paths corresponding to each target robot includes:

[0032] Determine the task priority information based on the real-time task information;

[0033] Based on the task priority information, compare the task priorities of the target robots for the initial movement paths with intersection conflicts. If the task priorities of the target robots are different, the target robot with a higher task priority passes first;

[0034] If the task priorities of the target robots are the same, intercept the path segment based on the intersection point, re-plan the path segment based on the improved A-star algorithm to obtain a new path segment, and adjust and optimize the initial movement paths with intersection conflicts based on the new path segment to obtain the corresponding optimized movement paths;

[0035] Intercept the overlapping path segment for the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts, re-plan the overlapping path segment based on the path weight matrix using the constraint tree to obtain a new path segment, and adjust and optimize the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts based on the new path segment to obtain the corresponding optimized movement paths.

[0036] In addition, the present invention also provides a collaborative planning device for a robot moving path, and the device includes:

[0037] A real-time mapping module: configured to perform real-time mapping based on real-time environment information to obtain a target scene map;

[0038] A robot selection module: configured to select a corresponding number of target robots from a robot sequence based on real-time task information;

[0039] A task allocation module: configured to allocate tasks to each target robot based on the real-time task information to obtain task information corresponding to each target robot;

[0040] An initial path planning module: configured to perform path planning using a distributed computing model based on the target scene map and task information to obtain an initial moving path corresponding to each target robot;

[0041] A moving conflict analysis module: configured to perform moving conflict analysis on the initial moving paths corresponding to each target robot to obtain moving conflict information;

[0042] A path adjustment and optimization module: configured to adjust and optimize the initial moving path based on the moving conflict information in combination with the real-time task information to obtain an optimized moving path corresponding to each target robot, and each target robot executes an operation task based on the corresponding optimized moving path.

[0043] In addition, the present invention also provides an electronic device, and the electronic device includes a processor and a memory. The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the above-mentioned collaborative planning method for a robot moving path.

[0044] In addition, the present invention also provides a computer-readable storage medium, and the computer-readable storage medium stores computer instructions. When the computer instructions run on an electronic device, the electronic device is caused to execute the above-mentioned collaborative planning method for a robot moving path.

[0045] In the embodiments of the present invention, a task allocation scheme is determined based on the target cost value obtained from real-time task information and carrying capacity by using the minimum cost criterion, and task allocation is performed on each target robot based on the task allocation scheme to ensure that each target robot can be assigned an appropriate task and avoid overloading of tasks. Path planning is performed by using a distributed computing model based on the target scene map and task information, which can improve the accuracy and efficiency of path planning. Mobile conflict analysis is performed on the initial movement paths corresponding to each target robot, and the initial movement paths are adjusted and optimized based on the mobile conflict information combined with real-time task information to obtain the optimized movement paths corresponding to each target robot. Considering the conflicts that occur during the movement of the target robot, its initial movement path is adjusted accordingly, which can effectively avoid path conflicts, improve the movement efficiency of the robot, realize cooperative movement among multiple robots, and make the collaborative planning of the robot movement path reach a more ideal effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0047] Figure 1 is a flowchart of a method for collaborative planning of robot movement paths in an embodiment of the present invention;

[0048] Figure 2 is a flowchart of a method for collaborative planning of robot movement paths in another embodiment of the present invention;

[0049] Figure 3 is a schematic structural diagram of a device for collaborative planning of robot movement paths in an embodiment of the present invention;

[0050] Figure 4 is a schematic structural diagram of an electronic device in an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0051] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, rather than all embodiments. All other embodiments obtained by those of ordinary skill in the art without creative efforts based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0052] Embodiment 1

[0053] Please refer to Figure 1, Figure 1 It is a schematic flowchart of a collaborative path planning method for a robot in an embodiment of the present invention. The method includes:

[0054] S11: Perform real-time mapping based on real-time environmental information to obtain a target scene map;

[0055] In a specific implementation process of the present invention, the performing real-time mapping based on real-time environmental information to obtain a target scene map includes: performing formatting processing on the real-time environmental information to obtain formatted real-time environmental information; performing rasterization and binarization processing on the formatted real-time environmental information to obtain an obstacle area and a non-obstacle area; performing real-time mapping based on the obstacle area and the non-obstacle area to obtain a target scene map.

[0056] Specifically, obtain real-time environmental information. The real-time environmental information includes obstacle information, road conditions and lengths in the scene, and the obstacle information includes point cloud data of obstacles, etc. Perform formatting processing on the real-time environmental information, that is, perform format standardization processing on the real-time environmental information for subsequent data analysis to obtain formatted real-time environmental information. Perform rasterization and binarization processing on the formatted real-time environmental information, binarize the point cloud data in the formatted real-time environmental information to enhance features, divide the environmental space using grids of the same size in combination with the formatted real-time environmental information, and represent the environment with a grid array. Black grids represent obstacles and white grids represent non-obstacles. For mixed grid points, assign them to the corresponding area according to the proportion occupied by obstacles and non-obstacles to obtain an obstacle area and a non-obstacle area. Perform real-time mapping based on the obstacle area and the non-obstacle area, fuse the obstacle area and the non-obstacle area, and combine with the road conditions in the formatted real-time environmental information to construct a scene map, realizing real-time mapping of a large-scale scene and obtaining a target scene map.

[0057] S12: Select a corresponding number of target robots from the robot sequence based on real-time task information;

[0058] In a specific implementation process of the present invention, the selecting a corresponding number of target robots from the robot sequence based on real-time task information includes: determining the required moving speed and required moving load of the robot based on the real-time task information; matching the required moving speed and required moving load with the working parameters of each robot to obtain a matching result; selecting a corresponding number of target robots from the robot sequence based on the matching result.

[0059] Specifically, obtain real-time task information, which includes the time, load, task location, and the number of required robots for task execution, etc. Based on the real-time task information, determine the required moving speed and load of the robots, that is, determine the moving speed and load required for the robots to execute tasks. Obtain the working parameters of each robot in the robot sequence, where the working parameters include the moving speed, load capacity, etc. of each robot, and match the required moving speed and load with the working parameters of each robot to obtain a matching result. Based on the matching result, select several corresponding target robots from the robot sequence, and select the robots that meet the required moving speed and load, and then select several target robots with better performance and the required quantity from them.

[0060] S13: Based on the real-time task information, perform task allocation for each target robot to obtain the task information corresponding to each target robot;

[0061] In the specific implementation process of the present invention, the performing task allocation for each target robot based on the real-time task information to obtain the task information corresponding to each target robot includes: calculating the target cost value required for each task to be allocated to each target robot based on the real-time task information and the load capacity of each target robot; determining the task allocation plan using the minimum cost criterion based on the target cost value, and performing task allocation for each target robot based on the task allocation plan to obtain the task information corresponding to each target robot.

[0062] Specifically, obtain the load capacity of each target robot, that is, obtain the load-bearing size of each target robot and the corresponding mode for different task load-bearings. Based on the real-time task information and the load capacity, calculate the target cost value required for each task to be allocated to each target robot, calculate the power consumption and the wear and tear caused to the target robot for each task allocation based on the real-time task information and the load capacity of each robot, and calculate the target cost value required for each target robot based on the required power consumption and the caused wear and tear. Determine the task allocation plan using the minimum cost criterion based on the target cost value, that is, follow the minimum cost criterion, allocate the task with the minimum target cost value required for the target robot to the corresponding target robot, and perform task allocation for each target robot based on the task allocation plan. Mark each target robot according to the task allocation plan, and each target robot obtains the corresponding task information according to the task mark, such as the items required for the task, etc., that is, obtain the task information corresponding to each target robot.

[0063] S14: Based on the target scene map and the task information, use a distributed computing model to perform path planning to obtain the initial moving paths corresponding to each target robot;

[0064] In the specific implementation process of the present invention, path planning is performed using a distributed computing model based on the target scenario map and task information to obtain the initial movement paths corresponding to each target robot, including: obtaining obstacle position information based on the target scenario map; generating several first movement paths corresponding to each target robot by combining the starting points, movement path endpoints, and obstacle position information of each target robot with the target scenario map; setting constraint conditions and a loss function, and generating a cost function based on the constraint conditions and the loss function; calculating the movement cost of several first movement paths corresponding to each target robot using the cost function based on the distributed computing model, obtaining the target movement cost of each first movement path, and taking the first movement path with the minimum target movement cost as the initial movement path corresponding to each target robot.

[0065] Specifically, obstacle position information is obtained based on the target scenario map. Several first movement paths corresponding to each target robot are generated by combining the starting points, movement path endpoints, and obstacle position information of each target robot with the target scenario map. Several passing points are generated according to the starting points, movement path endpoints, and obstacle information of each target robot, and several first movement paths corresponding to each target robot are generated in the target scenario map according to the connection lines of the several passing points. Constraint conditions and a loss function are set. The constraint conditions can be set as constraints on completion time, path length, and path smoothness. The loss function can adopt the mean square error function, which is used to characterize the error of cost calculation, and a cost function is generated based on the constraint conditions and the loss function. The movement cost of several first movement paths corresponding to each target robot is calculated using the cost function based on the distributed computing model. The distributed computing model is a deep reinforcement learning neural network structure, which includes a convolutional neural network and a residual neural network. Initialize the number of iteration rounds, maximum number of steps, attenuation factor, exploration rate, batch gradient descent sample number, and gradient descent step interval, etc. Set a cost calculation channel in the neural network structure according to the cost function, and set an inflection point cost calculation channel for calculating the loss brought by the inflection points of each first movement path. Input each first movement path into the distributed computing model for movement cost calculation, obtain the target movement cost of each first movement path, and take the first movement path with the minimum target movement cost as the initial movement path corresponding to each target robot.

[0066] S15: Perform a movement conflict analysis on the initial movement paths corresponding to each target robot to obtain movement conflict information;

[0067] In the specific implementation process of the present invention, performing a moving conflict analysis on the initial moving paths corresponding to each target robot to obtain moving conflict information includes: judging whether there are overlapping path segments in the initial moving paths corresponding to each target robot. If there are overlapping path segments between the initial moving paths of the target robots, then analyze the moving directions of the target robots in the overlapping path segments. If the moving directions of the target robots in the overlapping path segments are the same, then there is a same-direction moving conflict between the initial moving paths of the target robots; if the moving directions of the target robots in the overlapping path segments are opposite, then there is an opposite-direction moving conflict between the initial moving paths of the target robots; if there are no overlapping path segments between the initial moving paths of the target robots, then judge whether there are intersection points between the initial moving paths of the target robots. If there are intersection points, then there is an intersection conflict between the initial moving paths of the target robots.

[0068] Specifically, when judging whether there are overlapping path segments in the initial moving paths corresponding to each target robot, considering that directly using the original initial moving paths will increase the data processing time and consume too much computing resources. Therefore, according to the preset compression granularity, the trajectory points of the initial moving paths corresponding to each target robot are compressed to obtain the compressed initial moving paths corresponding to each target robot. Matching overlapping line segments according to the different compressed initial moving paths, that is, judging whether there are overlapping path segments, can avoid occupying too much computing resources while ensuring the matching accuracy of the overlapping path segments. If there are overlapping path segments between the initial moving paths of the target robots, then analyze the moving directions of the target robots in the overlapping path segments. If the moving directions of the target robots in the overlapping path segments are the same, then there is a same-direction moving conflict between the initial moving paths of the target robots, and the target robots will conflict when moving in the same direction in the overlapping path segments. If the moving directions of the target robots in the overlapping path segments are opposite, then there is an opposite-direction moving conflict between the initial moving paths of the target robots, and the target robots will collide when moving in opposite directions in the overlapping path segments. If there are no overlapping path segments between the initial moving paths of the target robots, then judge whether there are intersection points between the initial moving paths of the target robots. If there are intersection points, calculate the time for the corresponding target robot to move from the starting point to the intersection point. If the times are the same, then there is an intersection conflict between the initial moving paths of the target robots. Thus, different conflict types existing between the initial moving paths of the target robots can be analyzed, so that corresponding path adjustments can be made according to the corresponding conflict types subsequently to avoid conflicts among the robots.

[0069] S16: Based on the moving conflict information and in combination with the real-time task information, adjust and optimize the initial moving paths to obtain the optimized moving paths corresponding to each target robot, and each target robot executes the operation task based on the corresponding optimized moving path.

[0070] In the specific implementation process of the present invention, adjusting and optimizing the initial movement path based on the mobile conflict information and the real-time task information to obtain the optimized movement path corresponding to each target robot includes: determining task priority information based on the real-time task information; comparing the task priorities of the target robots for the initial movement paths with intersection conflicts based on the task priority information. If the task priorities of the target robots are different, the target robot with a higher task priority passes first; if the task priorities of the target robots are the same, intercept the path segment based on the intersection point, and re-plan the path segment based on the improved A-star algorithm to obtain a new path segment. Adjust and optimize the initial movement path with intersection conflicts based on the new path segment to obtain the corresponding optimized movement path; intercept the overlapping path segments for the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts, re-plan the overlapping path segments based on the path weight matrix using the constraint tree to obtain a new path segment, and adjust and optimize the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts based on the new path segment to obtain the corresponding optimized movement paths.

[0071] Specifically, determine the task priority information based on the real-time task information, that is, determine the priorities of the tasks assigned to the target robot. Compare the task priorities of the target robots for the initial movement paths with intersection conflicts based on the task priority information. If the task priorities of the target robots are different, the target robot with a higher task priority passes first. If the task priorities of the target robots are the same, intercept path segments based on the intersection point. Take the intersection point as the center and intercept path segments in the initial movement path according to a preset intercept length. Then, re-plan the path segments based on the improved A-star algorithm. Use the two endpoints of the intercepted path segments as the start and end points, select several path points between the two endpoints according to the obstacle information and the target scene map, and select the target points of the path points based on the direction change penalty and the local area complexity penalty to make the planned path smoother and the algorithm more efficient. After selecting the required several target points, connect the start point, the end point, and the several target points to form an initial path segment. Perform two-way smoothing processing on the initial path segment according to the improved Floyd algorithm to ensure the safety and reliability of the planned path and obtain a new path segment. Adjust and optimize the initial movement path with intersection conflicts based on the new path segment, that is, replace the intercepted path segment with intersection conflicts with the new path segment to obtain the corresponding optimized movement path. Intercept the overlapping path segments for the initial movement paths with same-direction movement conflicts and head-on movement conflicts. Re-plan the overlapping path segments based on the path weight matrix using the constraint tree, and obtain the occupancy of the path nodes within the preset range of the overlapping path segments, that is, analyze the movement paths of the other target robots within the preset range. Use the path nodes of the movement paths of the regional target robots within the preset range as obstacle points. Take the two endpoints of the overlapping path segment as the start and end points respectively, select several path points between the start and end points, and generate several paths that meet the constraint conditions according to the constraint tree. The constraint conditions include occupancy position constraints, vertex conflict constraints, and edge conflict constraints. Construct a path weight matrix with time weight and path length weight, calculate the weights of each path according to the path weight matrix, and select the two non-conflicting paths with the smallest weights as the required path segments, that is, obtain a new path segment. Then, adjust and optimize the initial movement paths with same-direction movement conflicts and head-on movement conflicts based on the new path segment, and replace the overlapping path segment with the new path segment to obtain the corresponding optimized movement path.

[0072] In an embodiment of the present invention, a task allocation scheme is determined based on the target cost value obtained from real-time task information and the bearing capacity, and task allocation is performed on each target robot based on the task allocation scheme to ensure that each target robot can be assigned an appropriate task and avoid overloading of tasks. Path planning is performed using a distributed computing model based on the target scene map and task information, which can improve the accuracy and efficiency of path planning. A moving conflict analysis is performed on the initial moving path corresponding to each target robot, and the initial moving path is adjusted and optimized based on the moving conflict information combined with the real-time task information to obtain the optimized moving path corresponding to each target robot. Considering the conflicts that occur during the movement of the target robot, its initial moving path is adjusted accordingly, which can effectively avoid path conflicts, improve the movement efficiency of the robot, achieve cooperative movement between multiple robots, and make the collaborative planning of the robot moving path reach a more ideal effect.

[0073] Embodiment 2

[0074] Please refer to Figure 2 , Figure 2 which is a schematic flowchart of a method for collaborative planning of robot moving paths in another embodiment of the present invention. The method includes:

[0075] S201: Perform real-time mapping based on real-time environmental information to obtain a target scene map;

[0076] S202: Select a corresponding number of target robots from the robot sequence based on real-time task information;

[0077] S203: Perform task allocation on each target robot based on the real-time task information to obtain the task information corresponding to each target robot;

[0078] S204: Perform path planning using a distributed computing model based on the target scene map and task information to obtain the initial moving path corresponding to each target robot;

[0079] S205: Perform a moving conflict analysis on the initial moving path corresponding to each target robot to obtain moving conflict information;

[0080] S206: Determine task priority information based on the real-time task information;

[0081] S207: Compare the task priorities of the target robots for the initial moving paths with intersection conflicts based on the task priority information. If the task priorities of the target robots are different, the target robot with a higher task priority passes first;

[0082] S208: If the task priorities of the target robots are the same, intercept the path segments based on the intersection points, re-plan the path segments based on the improved A-star algorithm to obtain new path segments, and adjust and optimize the initial movement paths with intersection conflicts based on the new path segments to obtain the corresponding optimized movement paths;

[0083] S209: Intercept the overlapping path segments of the initial movement paths with same-direction movement conflicts and head-on movement conflicts, re-plan the overlapping path segments based on the path weight matrix using the constraint tree to obtain new path segments, and adjust and optimize the initial movement paths with same-direction movement conflicts and head-on movement conflicts based on the new path segments to obtain the corresponding optimized movement paths. Each target robot executes the operation tasks based on the corresponding optimized movement paths.

[0084] In the embodiments of the present invention, task allocation is performed on each target robot based on real-time task information to ensure that each target robot can be assigned appropriate tasks and avoid overloading of tasks. Path planning is performed using the distributed computing model based on the target scenario map and task information, which can improve the accuracy and efficiency of path planning. Movement conflict analysis is performed on the initial movement paths corresponding to each target robot, and the initial movement paths are adjusted and optimized based on the movement conflict information in combination with the real-time task information to obtain the optimized movement paths corresponding to each target robot. Considering the conflicts that occur during the movement of the target robots, the initial movement paths are adjusted accordingly, which can effectively avoid path conflicts, improve the movement efficiency of the robots, achieve cooperative movement between multiple robots, and make the collaborative planning of the robot movement paths reach a more ideal effect.

[0085] Embodiment Three

[0086] Please refer to Figure 3 , Figure 3 which is a schematic structural composition diagram of the collaborative planning device for the robot movement path in the embodiments of the present invention. The device includes:

[0087] Real-time mapping module 31: used to perform real-time mapping based on real-time environment information to obtain the target scenario map;

[0088] Robot selection module 32: used to select corresponding several target robots from the robot sequence based on real-time task information;

[0089] Task allocation module 33: used to perform task allocation on each target robot based on the real-time task information to obtain the task information corresponding to each target robot;

[0090] Initial path planning module 34: used to perform path planning using the distributed computing model based on the target scenario map and task information to obtain the initial movement paths corresponding to each target robot;

[0091] Moving conflict analysis module 35: configured to perform moving conflict analysis on the initial moving paths corresponding to the target robots, and obtain moving conflict information;

[0092] Path adjustment and optimization module 36: configured to adjust and optimize the initial moving paths based on the moving conflict information in combination with the real-time task information, obtain the optimized moving paths corresponding to the target robots, and the target robots execute operation tasks based on the corresponding optimized moving paths.

[0093] In the specific implementation process of the present invention, the specific implementation manners of the device items may refer to the implementation manners of the above method items, which will not be elaborated herein.

[0094] In the embodiment of the present invention, a task allocation scheme is determined by using the minimum cost criterion based on the target cost value obtained from the real-time task information and the carrying capacity, and the target robots are task-allocated based on the task allocation scheme to ensure that the target robots can be allocated appropriate tasks and avoid overloading of task loads. Path planning is performed by using a distributed computing model based on the target scene map and the task information, which can improve the accuracy and efficiency of path planning. Moving conflict analysis is performed on the initial moving paths corresponding to the target robots, and the initial moving paths are adjusted and optimized based on the moving conflict information in combination with the real-time task information to obtain the optimized moving paths corresponding to the target robots. Considering the conflicts that occur during the movement of the target robots, the initial moving paths are adjusted accordingly, which can effectively avoid path conflicts, improve the moving efficiency of the robots, realize the cooperative movement between multiple robots, and make the collaborative planning of the robot moving paths reach a more ideal effect.

[0095] A computer-readable storage medium provided by an embodiment of the present invention, on which a computer program is stored, and when the program is executed by a processor, it implements the collaborative planning method for the robot movement path in any one of the above embodiments. Among them, the computer-readable storage medium includes, but is not limited to, any type of disk (including floppy disks, hard disks, optical disks, CD-ROMs, and magneto-optical disks), ROM (Read-Only Memory), RAM (Random Access Memory), EPROM (Erasable Programmable Read-Only Memory), EEPROM (Electrically Erasable Programmable Read-Only Memory), flash memory, magnetic cards, or optical cards. That is, the storage device includes any medium that can store or transmit information in a readable form by a device (such as a computer, a mobile phone), and can be a read-only memory, a magnetic disk, an optical disk, etc.

[0096] Embodiment 4

[0097] Please refer to Figure 4 , Figure 4 It is a schematic diagram of the structural composition of the electronic device in the embodiment of the present invention.

[0098] The embodiment of the present invention also provides an electronic device, as Figure 4 shown, the electronic device includes a memory 41, a processor 43, and a computer program 42 stored in the memory 41 and executable on the processor 43. Those skilled in the art can understand that Figure 3The illustrated electronic device does not constitute a limitation on all devices, and may include more or fewer components than shown, or combine certain components. The memory 41 can be used to store the computer program 42 and each functional module. The processor 43 runs the computer program 42 stored in the memory 41, thereby executing various functional applications and data processing of the device. The memory can be an internal memory or an external memory, or include both an internal memory and an external memory. The internal memory can include a read-only memory (ROM), a programmable ROM (PROM), an electrically programmable ROM (EPROM), an electrically erasable programmable ROM (EEPROM), a flash memory, or a random access memory. The external memory can include a hard disk, a floppy disk, a ZIP disk, a USB flash drive, a magnetic tape, etc. The processor 43 can be a central processing unit (CPU), or can also be other general-purpose processors, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor can be a microprocessor, a single-chip microcomputer, or the processor 43 can also be any conventional processor, etc. The processors and memories disclosed in the present invention include, but are not limited to, these types of processors and memories. The processors and memories disclosed in the present invention are only examples and not limitations.

[0099] As an embodiment, the electronic device includes: one or more processors 43, a memory 41, one or more computer programs 42, wherein the one or more computer programs 42 are stored in the memory 41 and are configured to be executed by the one or more processors 43, and the one or more computer programs 42 are configured to execute the collaborative planning method for the robot movement path in any one of the above embodiments. For the specific implementation process, please refer to the above embodiments and will not be elaborated here.

[0100] In the embodiment of the present invention, a task allocation scheme is determined based on the target cost value obtained from real-time task information and bearing capacity by using the minimum cost criterion, and tasks are allocated to each target robot based on the task allocation scheme to ensure that each target robot can be assigned appropriate tasks and avoid overloading of tasks. Path planning is performed by using a distributed computing model based on the target scene map and task information, which can improve the accuracy and efficiency of path planning. Mobile conflict analysis is performed on the initial movement paths corresponding to each target robot, and the initial movement paths are adjusted and optimized based on the mobile conflict information combined with real-time task information to obtain the optimized movement paths corresponding to each target robot. Considering the conflicts that occur during the movement of the target robot, the initial movement path is adjusted accordingly, which can effectively avoid path conflicts, improve the movement efficiency of the robot, realize cooperative movement among multiple robots, and make the collaborative planning of the robot movement paths achieve a more ideal effect.

[0101] In addition, the above has introduced in detail a method and related device for collaborative planning of a robot movement path provided by an embodiment of the present invention. Specific examples should have been used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A collaborative planning method for a robot's moving path, characterized in that, The method includes: Performing real-time mapping based on real-time environment information to obtain a target scene map; Selecting a corresponding number of target robots from the robot sequence based on real-time task information; Performing task allocation for each target robot based on the real-time task information to obtain the task information corresponding to each target robot; Performing path planning using a distributed computing model based on the target scene map and task information to obtain the initial movement paths corresponding to each target robot; Performing movement conflict analysis on the initial movement paths corresponding to each target robot to obtain movement conflict information; Adjusting and optimizing the initial movement paths based on the movement conflict information in combination with the real-time task information to obtain the optimized movement paths corresponding to each target robot, and each target robot executes the operation task based on the corresponding optimized movement path.

2. The collaborative planning method for the robot movement path according to claim 1, wherein, The performing real-time mapping based on real-time environment information to obtain a target scene map includes: Performing formatting processing on the real-time environment information to obtain formatted real-time environment information; Performing rasterization and binarization processing on the formatted real-time environment information to obtain an obstacle area and a non-obstacle area; Performing real-time mapping based on the obstacle area and non-obstacle interval to obtain a target scene map.

3. The collaborative planning method for the robot moving path according to claim 1, wherein The selecting a corresponding number of target robots from the robot sequence based on real-time task information includes: Determining the required movement speed and movement load of the robot based on the real-time task information; Matching the required movement speed and movement load with the working parameters of each robot to obtain a matching result; Selecting a corresponding number of target robots from the robot sequence based on the matching result.

4. The collaborative planning method for the robot movement path according to claim 1, wherein The performing task allocation for each target robot based on the real-time task information to obtain the task information corresponding to each target robot includes: Calculating the target cost value required for allocating each task to each target robot based on the real-time task information and the load-bearing capacity of each target robot; Determining a task allocation scheme using the minimum cost criterion based on the target cost value, and performing task allocation for each target robot based on the task allocation scheme to obtain the task information corresponding to each target robot.

5. The collaborative planning method for the robot moving path according to claim 1, wherein The performing path planning using a distributed computing model based on the target scene map and task information to obtain the initial movement paths corresponding to each target robot includes: Obtaining obstacle position information based on the target scene map; Generating a number of first movement paths corresponding to each target robot based on the starting point, the end point of the movement path, and the obstacle position information of each target robot in combination with the target scene map; Setting constraint conditions and a loss function, and generating a cost function based on the constraint conditions and the loss function; Performing movement cost calculation on the number of first movement paths corresponding to each target robot using the cost function based on the distributed computing model to obtain the target movement cost of each first movement path, and taking the first movement path with the minimum target movement cost as the initial movement path corresponding to each target robot.

6. The collaborative planning method for the robot moving path according to claim 1, characterized in that The performing movement conflict analysis on the initial movement paths corresponding to each target robot to obtain movement conflict information includes: Perform path overlap judgment on the initial movement paths corresponding to each target robot. If there are overlapping path segments among the initial movement paths of the target robots, analyze the movement directions of the target robots in the overlapping path segments. If the movement directions of the target robots in the overlapping path segments are the same, there is a same-direction movement conflict among the initial movement paths of the target robots; If the movement directions of the target robots in the overlapping path segments are opposite, there is an opposite-direction movement conflict among the initial movement paths of the target robots; If there are no overlapping path segments among the initial movement paths of the target robots, determine whether there are intersection points among the initial movement paths of the target robots. If there are intersection points, there is an intersection conflict among the initial movement paths of the target robots.

7. The collaborative planning method for the robot movement path according to claim 1, characterized in that Adjusting and optimizing the initial movement paths based on the movement conflict information in combination with the real-time task information to obtain the optimized movement paths corresponding to each target robot includes: Determine the task priority information based on the real-time task information; Based on the task priority information, compare the task priorities of the target robots for the initial movement paths with intersection conflicts. If the task priorities of the target robots are different, the target robot with a higher task priority passes first; If the task priorities of the target robots are the same, intercept the path segment based on the intersection point, and re-plan the path segment based on the improved A-star algorithm to obtain a new path segment. Adjust and optimize the initial movement paths with intersection conflicts based on the new path segment to obtain the corresponding optimized movement paths; Intercept the overlapping path segments for the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts, re-plan the overlapping path segments based on the path weight matrix using the constraint tree to obtain new path segments, and adjust and optimize the initial movement paths with same-direction movement conflicts and opposite-direction movement conflicts based on the new path segments to obtain the corresponding optimized movement paths.

8. A collaborative planning device for a robot's movement path, characterized in that, The device includes: Real-time mapping module: used to perform real-time mapping based on real-time environment information to obtain the target scene map; Robot selection module: used to select corresponding several target robots from the robot sequence based on the real-time task information; Task assignment module: used to assign tasks to each target robot based on the real-time task information to obtain the task information corresponding to each target robot; Initial path planning module: used to perform path planning based on the target scene map and task information using a distributed computing model to obtain the initial movement paths corresponding to each target robot; Movement conflict analysis module: used to analyze the movement conflicts of the initial movement paths corresponding to each target robot to obtain movement conflict information; Path adjustment and optimization module: used to adjust and optimize the initial movement paths based on the movement conflict information in combination with the real-time task information to obtain the optimized movement paths corresponding to each target robot, and each target robot executes the operation task based on the corresponding optimized movement path.

9. An electronic device, the electronic device comprising a processor and a memory, characterized in that, The memory is used to store instructions, and the processor is used to call the instructions in the memory so that the electronic device executes the collaborative path planning method for the robot movement path as described in any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that, when run on an electronic device, cause the electronic device to execute the collaborative planning method for the robot movement path as described in any one of claims 1 to 7.

Images