A robot cluster collaborative task planning method, device and storage medium

Abstract

The present invention provides a robot cluster collaborative task planning method, device and storage medium, which relate to the robot technology neighborhood. The method comprises: obtaining a robot cluster that performs a target recognition task and an environmental map where the robot cluster is located; converting the environmental map into a grid map, and determining the starting point grid and the destination grid of the robot cluster; obtaining target information of a target to be recognized by the robot cluster, and the robot performs random walks, and detects the surrounding environmental information in real time during the random walk; performing target recognition according to the environmental information, and broadcasting the path information and recognition information of the robot in the robot cluster; determining the next grid to be walked according to the path information and recognition information of all robots in the robot cluster, and moving toward the destination grid along the optimal path after completing the search for the target to be recognized; the present invention can improve the recognition efficiency of the robot cluster by improving the collaborative efficiency of the existing robot cluster.

Description

[0001] Technology Neighborhood

[0002] The present invention relates to but is not limited to the field of robotics technology, and in particular to a robot cluster collaborative task planning method, device and storage medium. Background Art

[0003] When a robot identifies a target in an unknown location, it needs to constantly deal with environmental uncertainties, such as interference from obstacles in the environment. Since a single robot has only limited perception and computing capabilities, the individual robot can only establish a local communication network within its own capabilities, and the efficiency of searching and identifying targets is very low.

[0004] In the prior art, there is also a method of using robot clusters to collaboratively perform tasks. However, when the robot clusters continuously search and identify in a specified area, there is still a problem of repeated identification, which affects the identification efficiency.

[0005] Therefore, it is necessary to improve the collaborative efficiency of existing robot clusters and to improve the recognition efficiency of robot clusters. Summary of the invention

[0006] The following is a summary of the subject matter described in detail herein. This summary is not intended to limit the scope of the claims.

[0007] The embodiments of the present invention provide a robot cluster collaborative task planning method, device and storage medium, which can find the optimal navigation path in real time and adaptively.

[0008] In a first aspect, an embodiment of the present invention provides a robot cluster collaborative task planning method, comprising:

[0009] Step S100, obtaining an environment map where a robot cluster performing a target recognition task is located; wherein the robot cluster includes a plurality of robots, and each robot in the robot cluster is communicatively connected with each other;

[0010] Step S200, converting the environment map into a grid map, and determining the starting point grid and the destination grid of the robot cluster;

[0011] Step S300, obtaining target information of the target to be identified by the robot cluster, each robot in the robot cluster performs random walk, and detects the surrounding environmental information in real time during the random walk; wherein the target information includes the number of targets and image information of each target; the environmental information includes image information, distance information and angle information;

[0012] Step S400: The robots in the robot cluster perform target recognition according to the environmental information, and broadcast the path information and recognition information of the robot in the robot cluster; wherein the recognition information is the image information and position information of the target recognized by the robot; and the path information is the grid passed by the robot;

[0013] Step S500: The robots in the robot cluster determine the next grid to go according to the path information and identification information of all the robots in the robot cluster, and after completing the search for the target to be identified, the robots in the robot cluster move toward the destination grid along the optimal path.

[0014] In some embodiments, the robots in the robot cluster determine the grid to be taken next according to the path information and identification information of all robots in the robot cluster, including:

[0015] Step S510, forming a target recognition list with target information of the target to be recognized;

[0016] Step S520, matching the image information of the target recognized by the robot cluster with the image information of the target to be recognized in the target recognition list, and marking the target to be recognized that has been successfully matched;

[0017] Step S530, determining whether there are unmarked targets to be identified in the target identification list, and if there are unmarked targets to be identified in the target identification list, obtaining path information and identification information of all robots in the robot cluster;

[0018] Step S540, determining grids that the robot cluster has not passed through according to the path information of all robots in the robot cluster, and recording them as blank grids;

[0019] Step S550: The robots in the robot cluster determine the grid they are currently in, and select blank grids from eight neighboring grids adjacent to the grid they are currently in.

[0020] Step S560, determining whether there is an obstacle in the neighborhood direction of the blank grid, if yes, executing step S570; if no, executing step S580;

[0021] Step S570: the robot determines the relative position information of the obstacle according to the detected environmental information, determines the avoidance grid of the robot according to the relative position information of the obstacle, and executes step S550 after the robot enters the avoidance grid;

[0022] Step S580: determine the grid that the robot will move to next from the blank grids.

[0023] In some embodiments, the robot determines relative position information of an obstacle according to detected environmental information, and determines an avoidance grid of the robot according to the relative position information of the obstacle, including:

[0024] Step S571: the robot obtains detected environmental information;

[0025] Step S572: identifying obstacles according to the image information in the environmental information, and obtaining distance information and angle information from the robot to the obstacles;

[0026] Step S573: After an interval of one time unit, the robot acquires the detected environmental information again, and determines the moving direction of the obstacle according to the environmental information acquired twice;

[0027] Step S574, determining whether the distance from the robot to the obstacle is greater than the safety distance, if not, executing step S575; if yes, executing step S576;

[0028] Step S575, determining the blank grids through which the connecting line from the robot to the obstacle passes, removing the blank grids and selecting a blank grid with the largest deviation angle from the remaining blank grids, and after the robot enters the blank grid, executing step S574; wherein the deviation angle is the angle between the connecting line from the robot to the blank grid and the moving direction of the obstacle;

[0029] Step S576: Select a blank grid farthest from the obstacle from the blank grids, and use the blank grid as an avoidance grid for the robot.

[0030] In some embodiments, determining the grid that the robot will walk to next from the blank grid includes:

[0031] Step S581, taking the robot as the starting point and the detection distance of the robot as the end point, determining the total number of grids from the starting point to the end point in 8 neighborhood directions respectively;

[0032] Step S582, calculating the ratio of the blank grids of the robot in the eight neighborhood directions to the total number of grids in the corresponding neighborhood directions, and obtaining eight ratio values;

[0033] Step S583, determining whether there is a ratio value greater than the set ratio threshold value among the 8 ratio values, and if there is a ratio value greater than the set ratio threshold value, executing step S584; otherwise, executing step S588;

[0034] Step S584, determining the highest ratio value, if there are multiple highest ratio values, randomly selecting a neighborhood direction corresponding to one of the ratio values ​​as the next forward direction; otherwise, selecting the neighborhood direction with the highest ratio value as the next forward direction;

[0035] Step S585, determining the pheromone in the neighborhood direction corresponding to each of the highest ratio values; wherein the pheromone is positively correlated with the total number of times the robot and the obstacle passed by the grid;

[0036] Step S586, determining the smallest pheromone, if the smallest pheromone is 1, selecting the neighborhood direction with the smallest pheromone, and taking the blank grid passed by the neighborhood direction as the grid for the robot to walk next;

[0037] Step S587, if there are multiple minimum pheromones, two robots are selected from the robot cluster so that the angles formed by the robot and the connecting lines of the two robots are the largest, the grid between the two robots is determined, and the blank grids passed by the robot to the grid between the two robots are used as the grids that the robot will walk to next;

[0038] Step S588, calculating the path of the robot from the current grid through each blank grid to the destination grid, and determining the longest path of the robot from the current grid to the destination grid;

[0039] Step S589: determine the blank grid that the longest path passes through, and use the blank grid as the grid that the robot will walk to next.

[0040] In a second aspect, an embodiment of the present invention further provides an electronic device, comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the robot cluster collaborative task planning method as described in the first aspect is implemented.

[0041] In a third aspect, an embodiment of the present invention further provides a computer-readable storage medium storing computer-executable instructions, wherein the computer-executable instructions are used to execute the robot cluster collaborative task planning method as described in the first aspect.

[0042] The embodiment of the present invention includes: obtaining an environmental map where a robot cluster that performs a target recognition task is located; wherein the robot cluster includes multiple robots, and each robot in the robot cluster is connected to each other by communication; converting the environmental map into a grid map, determining the starting point grid and the destination grid of the robot cluster; obtaining target information of a target to be recognized by the robot cluster, each robot in the robot cluster performs a random walk, and detects the surrounding environmental information in real time during the random walk; wherein the target information includes the number of targets and image information of each target; the environmental information includes image information, distance information and angle information; the robots in the robot cluster perform target recognition according to the environmental information, and broadcast the path information and recognition information of the robot in the robot cluster; wherein the recognition information is the image information and position information of the target recognized by the robot; the path information is the grid passed by the robot; the robots in the robot cluster determine the grid to be taken next according to the path information and recognition information of all robots in the robot cluster, and after completing the search for the target to be recognized, the robots in the robot cluster move toward the destination grid along the optimal path.

[0043] Other features and advantages of the present invention will be described in the following description, and partly become apparent from the description, or understood by practicing the present invention. The purpose and other advantages of the present invention can be realized and obtained by the structures particularly pointed out in the description, claims and drawings. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The accompanying drawings are used to provide a further understanding of the technical solution of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the technical solution of the present invention and do not constitute a limitation on the technical solution of the present invention.

[0045] Figure 1 is a flowchart of a robot cluster collaborative task planning method in an embodiment of the present invention;

[0046] Figure 2 It is a structural diagram of an electronic device provided by another embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0048] It should be noted that although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than in the flowchart. The terms "first", "second", etc. in the specification, claims or the above drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0049] The embodiments of the present invention are further described below in conjunction with the accompanying drawings.

[0050] like Figure 1 As shown, Figure 1 1 is a flowchart of a robot cluster collaborative task planning method provided by an embodiment of the present invention, in which the method includes but is not limited to the following steps:

[0051] Step S100, obtaining an environment map where a robot cluster performing a target recognition task is located; wherein the robot cluster includes a plurality of robots, and each robot in the robot cluster is communicatively connected with each other;

[0052] It should be noted that the grid in the grid map is the smallest square that allows a single robot to rotate once; the grid map contains targets and obstacles; the robot's driving speed per unit time is 1 grid; there can only be one robot in each grid at the same time, otherwise it is considered a conflict; the robot can avoid conflicts through communication before moving forward.

[0053] Step S200, converting the environment map into a grid map, and determining the starting point grid and the destination grid of the robot cluster; wherein the starting point grid is the grid where the starting point of the robot cluster is located, and the destination grid is the grid where the end point of the robot cluster is located;

[0054] Step S300, obtaining target information of the target to be identified by the robot cluster, each robot in the robot cluster performs random walk, and detects the surrounding environmental information in real time during the random walk; wherein the target information includes the number of targets and image information of each target; the environmental information includes image information, distance information and angle information;

[0055] It should be noted that, in some embodiments, each robot in the robot cluster is equipped with an image sensor, a distance detector and an angle sensor.

[0056] Step S400: The robots in the robot cluster perform target recognition according to the environmental information, and broadcast the path information and recognition information of the robot in the robot cluster; wherein the recognition information is the image information and position information of the target recognized by the robot; and the path information is the grid passed by the robot;

[0057] Step S500: The robots in the robot cluster determine the next grid to go according to the path information and identification information of all the robots in the robot cluster, and after completing the search for the target to be identified, the robots in the robot cluster move toward the destination grid along the optimal path.

[0058] That is to say, it is determined whether the robot cluster has completed the search for the target to be identified. If not, the robots in the robot cluster determine the next grid to go to based on the path information and identification information of all robots in the robot cluster; if yes, the robots in the robot cluster move toward the destination grid along the optimal path.

[0059] In the embodiment provided by the present invention, since the robots in the robot cluster are communicated with each other, they can share path information and identification information in real time, and use this as a basis to determine the next grid to take, thereby avoiding repeated searching and identification through the grids; the present invention can improve the recognition efficiency of the robot cluster by improving the collaborative efficiency of the existing robot cluster.

[0060] In addition, in one embodiment, Figure 1 In step S500 of the illustrated embodiment, the robots in the robot cluster determine the grid to be walked next according to the path information and identification information of all robots in the robot cluster, including:

[0061] Step S510, forming a target recognition list with target information of the target to be recognized;

[0062] Step S520, matching the image information of the target recognized by the robot cluster with the image information of the target to be recognized in the target recognition list, and marking the target to be recognized that has been successfully matched;

[0063] In one embodiment, under the initial condition, all the targets to be identified in the target identification list are marked as 0, and the successfully matched targets to be identified are marked as 1;

[0064] Step S530, determining whether there are unmarked targets to be identified in the target identification list, and if there are unmarked targets to be identified in the target identification list, obtaining path information and identification information of all robots in the robot cluster;

[0065] Step S540, determining grids that the robot cluster has not passed through according to the path information of all robots in the robot cluster, and recording them as blank grids;

[0066] It can be understood that the grids that the robot cluster passes through in the grid map can be determined through the path information of all robots in the robot cluster, and the remaining grids in the grid map are blank grids;

[0067] Step S550: The robots in the robot cluster determine the grid they are currently in, and select blank grids from eight neighboring grids adjacent to the grid they are currently in.

[0068] Step S560, determining whether there is an obstacle in the neighborhood direction of the blank grid, if yes, executing step S570; if no, executing step S580;

[0069] It should be noted that the obstacles are determined based on the image information in the environmental information, and through the image recognition algorithm, objects other than the target to be identified and the robots in the robot cluster are regarded as obstacles; the obstacles can be walls or other objects, and other objects may be stationary or moving.

[0070] Step S570: the robot determines the relative position information of the obstacle according to the detected environmental information, determines the avoidance grid of the robot according to the relative position information of the obstacle, and executes step S550 after the robot enters the avoidance grid;

[0071] Step S580: determine the grid that the robot will move to next from the blank grids.

[0072] In addition, in one embodiment, in step S570, the robot determines the relative position information of the obstacle according to the detected environmental information, and determines the avoidance grid of the robot according to the relative position information of the obstacle, including:

[0073] Step S571: the robot obtains detected environmental information;

[0074] Step S572: identifying obstacles according to the image information in the environmental information, and obtaining distance information and angle information from the robot to the obstacles;

[0075] Step S573: After an interval of one time unit, the robot acquires the detected environmental information again, and determines the moving direction of the obstacle according to the environmental information acquired twice;

[0076] Step S574, determining whether the distance from the robot to the obstacle is greater than the safety distance, if not, executing step S575; if yes, executing step S576;

[0077] Step S575, determining the blank grids through which the connecting line from the robot to the obstacle passes, removing the blank grids and selecting a blank grid with the largest deviation angle from the remaining blank grids, and after the robot enters the blank grid, executing step S574; wherein the deviation angle is the angle between the connecting line from the robot to the blank grid and the moving direction of the obstacle;

[0078] Step S576: Select a blank grid farthest from the obstacle from the blank grids, and use the blank grid as an avoidance grid for the robot.

[0079] The image information sensed by the image sensor is used to judge the distance of the surrounding moving or stationary obstacles. If the distance is less than the safe distance, the robot moves in the opposite direction to maintain a certain distance from the obstacle and avoid it.

[0080] In addition, in one embodiment, in step S580, determining the grid that the robot will move to next from the blank grid includes:

[0081] Step S581, taking the robot as the starting point and the detection distance of the robot as the end point, determining the total number of grids from the starting point to the end point in 8 neighborhood directions respectively;

[0082] Step S582, calculating the ratio of the blank grids of the robot in the eight neighborhood directions to the total number of grids in the corresponding neighborhood directions, and obtaining eight ratio values;

[0083] It should be noted that the detection distance is the maximum distance that the robot can reach when detecting distance information; the eight neighborhood directions of the robot are front, back, left, right, left front, right, front, left back, and right back;

[0084] Step S583, determining whether there is a ratio value greater than the set ratio threshold value among the 8 ratio values, and if there is a ratio value greater than the set ratio threshold value, executing step S584; otherwise, executing step S588;

[0085] Step S584, determining the highest ratio value. If there are multiple highest ratio values, randomly selecting a neighborhood direction corresponding to one of the ratio values ​​as the next forward direction; otherwise, selecting the neighborhood direction with the highest ratio value as the next forward direction; in some embodiments, the ratio threshold is set to 0.6;

[0086] Step S585, determining the pheromone in the neighborhood direction corresponding to each of the highest ratio values; wherein the pheromone is positively correlated with the total number of times the robot and the obstacle passed by the grid;

[0087] Step S586, determining the smallest pheromone, if the smallest pheromone is 1, selecting the neighborhood direction with the smallest pheromone, and taking the blank grid passed by the neighborhood direction as the grid for the robot to walk next;

[0088] Step S587, if there are multiple minimum pheromones, two robots are selected from the robot cluster so that the angles formed by the robot and the connecting lines of the two robots are the largest, the grid between the two robots is determined, and the blank grids passed by the robot to the grid between the two robots are used as the grids that the robot will walk to next;

[0089] Step S588, calculating the path of the robot from the current grid through each blank grid to the destination grid, and determining the longest path of the robot from the current grid to the destination grid;

[0090] Step S589: determine the blank grid that the longest path passes through, and use the blank grid as the grid that the robot will walk to next.

[0091] In the embodiment provided by the present invention, by calculating the ratio value, pheromone, and angle value, it is ensured that the robot searches as wide a range as possible when performing target recognition, thereby improving the recognition integrity of the target to be recognized.

[0092] In addition, refer to Figure 2 An embodiment of the present invention further provides an electronic device 10, which includes: a memory 11, a processor 12, and a computer program stored in the memory 11 and executable on the processor 12.

[0093] The processor 12 and the memory 11 may be connected via a bus or other means.

[0094] The non-transient software program and instructions required to implement the robot cluster collaborative task planning method of the above embodiment are stored in the memory 11, and when executed by the processor 12, the robot cluster collaborative task planning method of the above embodiment is executed.

[0095] In addition, an embodiment of the present invention also provides a computer-readable storage medium, which stores computer-executable instructions, and the computer-executable instructions are executed by a processor or controller, for example, by a processor in the above-mentioned electronic device embodiment, so that the above-mentioned processor can execute the robot cluster collaborative task planning method in the above-mentioned embodiment.

[0096] It will be appreciated by those skilled in the art that all or some of the steps and systems in the disclosed method above may be implemented as software, firmware, hardware and appropriate combinations thereof. Some physical components or all physical components may be implemented as software executed by a processor, such as a central processing unit, a digital signal processor or a microprocessor, or may be implemented as hardware, or may be implemented as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on a computer-readable medium, and the computer-readable medium may include a computer storage medium (or a non-transitory medium) and a communication medium (or a temporary medium). As known to those skilled in the art, the term computer storage medium includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storing information (such as computer-readable instructions, data structures, program modules or other data). Computer storage media include, but are not limited to, RAM, ROM, EEPROM, flash memory or other memory technologies, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, disk storage or other magnetic storage devices, or any other medium that may be used to store desired information and may be accessed by a computer. Furthermore, it is well known to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave or other transport mechanism, and may include any information delivery media.

[0097] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the above-mentioned implementation mode. Technical personnel familiar with the field can also make various equivalent deformations or substitutions without violating the spirit of the present invention. These equivalent deformations or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A robot cluster collaborative task planning method, characterized in that: include: Step S100, obtaining an environment map where a robot cluster performing a target recognition task is located; wherein the robot cluster includes a plurality of robots, and each robot in the robot cluster is communicatively connected with each other; Step S200, converting the environment map into a grid map, and determining the starting point grid and the destination grid of the robot cluster; Step S300, obtaining target information of the target to be identified by the robot cluster, each robot in the robot cluster performs random walk, and detects the surrounding environmental information in real time during the random walk; wherein the target information includes the number of targets and image information of each target; the environmental information includes image information, distance information and angle information; Step S400: The robots in the robot cluster perform target recognition according to the environmental information, and broadcast the path information and recognition information of the robot in the robot cluster; wherein the recognition information is the image information and position information of the target recognized by the robot; and the path information is the grid passed by the robot; Step S500: The robots in the robot cluster determine the next grid to go according to the path information and identification information of all the robots in the robot cluster, and after completing the search for the target to be identified, the robots in the robot cluster move toward the destination grid along the optimal path; The robots in the robot cluster determine the grid to be walked next according to the path information and identification information of all robots in the robot cluster, including: Step S510, forming a target recognition list with target information of the target to be recognized; Step S520, matching the image information of the target recognized by the robot cluster with the image information of the target to be recognized in the target recognition list, and marking the target to be recognized that has been successfully matched; Step S530, determining whether there are unmarked targets to be identified in the target identification list, and if there are unmarked targets to be identified in the target identification list, obtaining path information and identification information of all robots in the robot cluster; Step S540, determining grids that the robot cluster has not passed through according to the path information of all robots in the robot cluster, and recording them as blank grids; Step S550: The robots in the robot cluster determine the grid they are currently in, and select blank grids from eight neighboring grids adjacent to the grid they are currently in. Step S560, determining whether there is an obstacle in the neighborhood direction of the blank grid, if yes, executing step S570; if no, executing step S580; Step S570: the robot determines the relative position information of the obstacle according to the detected environmental information, determines the avoidance grid of the robot according to the relative position information of the obstacle, and executes step S550 after the robot enters the avoidance grid; Step S580: determine the grid that the robot will move to next from the blank grids.

2. The robot cluster collaborative task planning method according to claim 1, characterized in that: The robot determines relative position information of an obstacle according to detected environmental information, and determines an avoidance grid of the robot according to the relative position information of the obstacle, including: Step S571: the robot obtains detected environmental information; Step S572: identifying obstacles according to the image information in the environmental information, and obtaining distance information and angle information from the robot to the obstacles; Step S573: After an interval of one time unit, the robot acquires the detected environmental information again, and determines the moving direction of the obstacle according to the environmental information acquired twice; Step S574, determining whether the distance from the robot to the obstacle is greater than the safety distance, if not, executing step S575; if yes, executing step S576; Step S575, determining the blank grids through which the connecting line from the robot to the obstacle passes, removing the blank grids and selecting a blank grid with the largest deviation angle from the remaining blank grids, and after the robot enters the blank grid, executing step S574; wherein the deviation angle is the angle between the connecting line from the robot to the blank grid and the moving direction of the obstacle; Step S576: Select a blank grid farthest from the obstacle from the blank grids, and use the blank grid as an avoidance grid for the robot.

3. The robot cluster collaborative task planning method according to claim 1, characterized in that: The step of determining the grid to be walked next by the robot from the blank grids comprises: Step S581, taking the robot as the starting point and the detection distance of the robot as the end point, determining the total number of grids from the starting point to the end point in 8 neighborhood directions respectively; Step S582, calculating the ratio of the blank grids of the robot in the eight neighborhood directions to the total number of grids in the corresponding neighborhood directions, and obtaining eight ratio values; Step S583, determining whether there is a ratio value greater than the set ratio threshold value among the 8 ratio values, and if there is a ratio value greater than the set ratio threshold value, executing step S584; otherwise, executing step S588; Step S584, determining the highest ratio value, if there are multiple highest ratio values, randomly selecting a neighborhood direction corresponding to one of the ratio values ​​as the next forward direction; otherwise, selecting the neighborhood direction with the highest ratio value as the next forward direction; Step S585, determining the pheromone in the neighborhood direction corresponding to each of the highest ratio values; wherein the pheromone is positively correlated with the total number of times the robot and the obstacle passed by the grid; Step S586, determining the smallest pheromone, if the smallest pheromone is 1, selecting the neighborhood direction with the smallest pheromone, and taking the blank grid passed by the neighborhood direction as the grid for the robot to walk next; Step S587, if there are multiple minimum pheromones, two robots are selected from the robot cluster so that the angles formed by the robot and the connecting lines of the two robots are the largest, the grid between the two robots is determined, and the blank grids passed by the robot to the grid between the two robots are used as the grids that the robot will walk to next; Step S588, calculating the path of the robot from the current grid through each blank grid to the destination grid, and determining the longest path of the robot from the current grid to the destination grid; Step S589: determine the blank grid that the longest path passes through, and use the blank grid as the grid that the robot will walk to next.

4. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the robot cluster collaborative task planning method as described in any one of claims 1 to 3 when executing the computer program.

5. A computer-readable storage medium storing computer-executable instructions, characterized in that: The computer executable instructions are used to execute the robot cluster collaborative task planning method as described in any one of claims 1 to 3.

Images