Robot control method and system based on space-time unit, equipment and medium

Abstract

The invention relates to the technical field of robot control, in particular to a space-time unit-based robot control method and system, equipment and a medium. According to the method, a task to be executed by a robot is subjected to unified modeling through three dimensions based on time and space dimensions and task elements, and the three factors are comprehensively considered for task planning, so that the task execution efficiency is improved. A space-time unit is allocated to a to-be-executed sub-task of the robot, and the space-time unit comprises time and space attributes and task elements in execution of the sub-task. The three dimensions are mapped into the space-time unit, optimization and path planning are carried out on the space-time unit, when overlapping exists, it can be considered that a certain space-time unit in a plurality of target actions is completed at the same time, and therefore it is guaranteed that the finally planned task is optimal in the three dimensions.

Description

Technical Field

[0001] The present invention relates to the technical field of robot control. Specifically, it relates to a robot control method, system, device, and medium based on spatio-temporal units. Background Art

[0002] Currently, with the rapid development of new technologies, the application of robots has become increasingly widespread. The extensive application of robots in various industries not only improves work efficiency but also liberates a large number of workers from tedious and mechanical repetitive labor. However, the current robot task planning is relatively single. Usually, the task sequence is set based on time attributes, referring to certain criteria, such as the shortest path factor, the least time-consuming, the least cost, etc. For complex tasks, they are often decomposed into N (N is greater than or equal to 1) subtasks, and the task planning is to plan the execution sequence of the subtasks in the set of decomposed subtasks.

[0003] The execution of a task has certain time and space attributes. The time attribute corresponds to the start time and duration of the task, as well as the sequential dependencies with other tasks. The space attribute corresponds to the position in space and the running trajectory during the task execution. Usually, the tasks to be executed by a robot may need to be decomposed into N (N is greater than or equal to 1) subtasks according to the usage scenario. There are time or space intersections between various tasks (such as parallelism, serialism, etc. in the time dimension, and overlapping in the space dimension during task execution), and in addition, the task elements (external elements on which the task execution depends and the resources occupied by the robot itself) are not the same either. Therefore, single-dimensional task planning based on time or space cannot enable the robot to complete tasks more efficiently. Summary of the Invention

[0004] The purpose of the present invention is to provide a robot control method, system, device, and medium based on spatio-temporal units to solve the above problems in the prior art.

[0005] The present invention is achieved through the following technical solutions:

[0006] In a first aspect, a robot control method based on spatio-temporal units includes:

[0007] Obtain the current task instruction, and decompose the current task instruction into several target actions, and the several target actions together complete the current task instruction;

[0008] Respectively obtain the task trajectory and task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system;

[0009] Establish a spatio-temporal unit group of the target action within a three-dimensional coordinate system. The spatio-temporal unit group includes the two-dimensional space where the robot moves and the task execution time.

[0010] Different spatio-temporal unit groups are sequentially arranged at different heights on the vertical axis of the three-dimensional coordinate axis. Several spatio-temporal unit groups are divided into several spatio-temporal units, and the task trajectories of the target action are respectively mapped into the corresponding spatio-temporal unit groups.

[0011] Mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate. After modifying the task execution times of the target spatio-temporal units in the same group to be consistent, output the control instructions acting on the robot.

[0012] Preferably, the decomposition of the current task instruction into several target actions includes:

[0013] Judge whether the current target action is greater than 1. If it is not greater than 1, do not decompose and end the task.

[0014] If it is greater than 1, perform task decomposition.

[0015] Preferably, the division of several spatio-temporal unit groups into several spatio-temporal units includes:

[0016] Obtain the maximum activity range of the robot. The maximum activity range includes the farthest first distance that can be reached forward centered on itself and the farthest second distance that can be reached to the left or right.

[0017] Generate the length and width of the spatio-temporal unit with the first distance and the second distance, and generate the height of the spatio-temporal unit with the task execution time. The spatio-temporal unit is formed by the length, width and height.

[0018] Preferably, the modification of the task execution times of the target spatio-temporal units to be consistent includes:

[0019] Respectively obtain the target actions to be corrected where the target spatio-temporal units are located, and judge whether there is a sequence relationship among several target actions to be corrected. The sequence relationship includes that if the previous target action to be corrected is not completed, the subsequent target action to be corrected cannot be carried out.

[0020] If there is no sequence relationship, evaluate the target action to be corrected.

[0021] If there is a sequence relationship, divide and select the target actions to be corrected, and evaluate the target actions to be corrected after division and selection.

[0022] Analyze the evaluation results of the target actions to be corrected and output the optimal task execution time.

[0023] Preferably, if there is a sequential relationship, the division and selection of the target action to be corrected include:

[0024] Dividing the target actions to be corrected with a sequential relationship into a group to be confirmed, and dividing the target actions to be corrected without a sequential relationship into a confirmation group for storage;

[0025] Among the target actions to be corrected in the group to be confirmed, the target actions to be corrected that perform tasks first are saved to the confirmation group, and the target actions to be corrected that perform tasks later are deleted;

[0026] Output the target actions to be corrected saved in the confirmation group.

[0027] Preferably, the evaluation of the target action to be corrected includes:

[0028] Judging the number of the current target actions to be corrected. If it is not greater than 1, modify the task execution time of all the corrected target actions to the task execution time of the current target action to be corrected;

[0029] If it is greater than 1, obtain the number of marked target spatio-temporal units in the spatio-temporal unit group of each target action to be corrected;

[0030] Obtain the task execution time of the spatio-temporal unit group with the smallest number of target spatio-temporal units as the task execution time of the target actions to be corrected in the current group.

[0031] Preferably, it further includes:

[0032] If the number of spatio-temporal unit groups with the smallest number of target spatio-temporal units is greater than 1, obtain the positions of the vertical axes in the three-dimensional coordinate system where several spatio-temporal unit groups are located;

[0033] Obtain the task execution time of the spatio-temporal unit group closest to the origin of the three-dimensional coordinate system as the task execution time of the target actions to be corrected in the current group.

[0034] In a second aspect, the present invention further provides a robot control method based on spatio-temporal units, including:

[0035] A task decomposition module, configured to obtain the current task instruction, decompose the current task instruction into several target actions, and several of the target actions combine to complete the current task instruction;

[0036] The task mapping module is configured to respectively obtain the task trajectory and task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system; establish a spatio-temporal unit group of the target action within the three-dimensional coordinate system, where the spatio-temporal unit group includes the two-dimensional space in which the robot moves and the task execution time; different spatio-temporal unit groups are sequentially arranged at different heights on the vertical axis of the three-dimensional coordinate axes, divide several spatio-temporal unit groups into several spatio-temporal units, and map the task trajectory of the target action to the corresponding spatio-temporal unit group respectively;

[0037] The task optimization module is configured to mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, modify the task execution times of the target spatio-temporal units in the same group to be the same, and then output a control instruction acting on the robot;

[0038] The main control module is connected to the task decomposition module, the task mapping module, and the task optimization module, and is used to execute the above-mentioned robot control method based on spatio-temporal units.

[0039] In a third aspect, the present invention further provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above-mentioned robot control method based on spatio-temporal units is implemented.

[0040] In a fourth aspect, the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned robot control method based on spatio-temporal units is implemented.

[0041] The technical solution of the present invention has at least the following advantages and beneficial effects:

[0042] The method provided by the present invention mainly includes respectively obtaining the task trajectory and task execution time for completing the current target action, establishing a three-dimensional coordinate system, mapping the task execution time to the vertical axis of the three-dimensional coordinate system, and mapping the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system; marking the space-time units passed by the task trajectory, obtaining several groups of marked target space-time units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, modifying the task execution times of the target space-time units in the same group to be the same, and then outputting a control instruction for the robot. This method models the task to be executed by the robot based on time, space dimensions, and task elements, unifies the modeling through three dimensions, and comprehensively considers these three factors for task planning, thereby improving the efficiency of task execution. Assigning space-time units to the subtasks to be executed by the robot, where the space-time units include the time, space attributes, and task elements during the execution of the subtasks. By mapping the three dimensions into the space-time units, optimizing and path planning are performed on the space-time units. When there is an overlap, it is possible to consider simultaneously completing a certain space-time unit among several target actions, so as to ensure that the finally planned task is optimal in these three dimensions. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following will briefly introduce the drawings required for the embodiments. It should be understood that the following drawings only show some embodiments of the present invention, and therefore should not be regarded as limiting the scope. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0044] Figure 1 Schematic diagram of multiple space-time unit groups of the present invention on the coordinate axes;

[0045] Figure 2 Trajectory schematic diagram of a single space-time unit group of the present invention;

[0046] Figure 3 Plane trajectory schematic diagram of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, 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 some, but not all, of the embodiments of the present invention. The components of the embodiments of the present invention described and illustrated herein can generally be arranged and designed in a variety of different configurations.

[0048] The division of modules in this application is a logical division. In actual implementation, there may be other division methods. For example, multiple modules can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the connection, coupling, or communication in this application can be a direct connection, coupling, or communication between associated objects, or an indirect connection, coupling, or communication through other devices. Moreover, the connection, coupling, or communication between objects can be electrical or other similar forms, which are not limited in this application. The independently described modules or sub-modules can be physically separated or not: they can be implemented in software or in hardware, and some modules or sub-modules can be implemented in software and the functions of these modules or sub-modules can be called by a processor, while other modules or sub-modules are implemented in hardware, for example, through a hardware circuit. In addition, some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this application.

[0049] Please refer to Figures 1-3 , the present invention provides a robot control method based on spatio-temporal units, including:

[0050] S101: Obtain the current task instruction, decompose the current task instruction into a number of target actions, and the number of said target actions combine to complete the current task instruction;

[0051] In this embodiment, the task instruction refers to the control instruction received by the robot, which is a control signal that enables the robot to perform corresponding actions and achieve a certain purpose. This control signal can be a command sent to the robot receiver through wireless communication.

[0052] For example, if the task instruction received by the robot at this time is to clean the room, the control system of the robot calls all the control programs for cleaning the room and each action required to complete this task that are written in advance. This action is the target action required by the present invention. Then, in cleaning the room, it can be decomposed into two target actions: sweeping the floor and mopping the floor. The robot then takes sweeping the floor and mopping the floor as the goals to complete the currently received task instruction.

[0053] S102: Respectively obtain the task trajectory and task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system;

[0054] S103: Establish a spatio-temporal unit group for the target action within the three-dimensional coordinate system, and the spatio-temporal unit group includes the two-dimensional space where the robot moves and the task execution time;

[0055] Similarly, for the two target actions of sweeping and mopping the floor obtained from cleaning, there is a chronological order between these two target actions. Therefore, the spatio-temporal unit groups for sweeping and mopping are presented in the form of different coordinates on the vertical axis of the three-dimensional coordinate system. Since a broom is required for the sweeping task and a mop is required for the mopping task, different paths are further planned to complete these two target actions.

[0056] Map the trajectories formed by completing the two target actions into a two-dimensional plane graph, and cover the two-dimensional plane graph on the established three-dimensional coordinate system. Each trajectory point forms a coordinate point composed of the horizontal axis coordinate and the vertical axis coordinate of the three-dimensional coordinate system.

[0057] That is, establish a Cartesian coordinate system, where the X-axis corresponds to the X direction of the map, the Y-axis corresponds to the Y direction of the map, and the Z-axis represents the time of task execution. The unit in the spatio-temporal coordinate is called a spatio-temporal unit. The spatio-temporal unit contains the time and space attributes and task elements during the execution of the subtask. To simplify the description of the subsequent solution, the values on the Z-axis, that is, the time axis, are uniformly displayed using unit time in the solution, and the specific execution time is recorded in the description information of the spatio-temporal unit.

[0058] That is, the task execution time is the height of the spatio-temporal action unit, and the activity range of the robot is the length and width of the spatio-temporal unit, forming a three-dimensional cube structure in the three-dimensional coordinate system.

[0059] S104: Different said spatio-temporal unit groups are sequentially set at different heights on the vertical axis of the three-dimensional coordinate axis. Several spatio-temporal unit groups are divided into several spatio-temporal units, and the task trajectories of the target actions are respectively mapped into the corresponding spatio-temporal unit groups.

[0060] To better compare the spatio-temporal unit groups of each target action, the entire spatio-temporal unit group is divided into several spatio-temporal units, which is equivalent to defining a range for subsequent comparison. This range can be the maximum activity range of the robot when it stays still in place.

[0061] S105: Mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate. After modifying the task execution times of the target spatio-temporal units in the same group to be the same, output a control instruction acting on the robot.

[0062] In a three-dimensional coordinate system, different groups of space-time units can present a very intuitive comparison. When comparing in the vertical axis direction, it is possible to quickly obtain the target space-time units of different space-time unit groups with the same abscissa and ordinate. For these selected target space-time units, if there are actions that need to be executed, for example, picking up a broom, then their task execution times can be adjusted to be unified. That is, it can be considered to complete the tasks required by these two target space-time units at the same time. Of course, whether to complete them simultaneously must be set according to specific circumstances. This solution only proposes a feasible method. In this way, the working efficiency of the robot is improved to a certain extent, and it is quickly analyzed which space-time units overlap in the vertical axis direction, and it is judged whether to complete the corresponding actions at the same time, etc.

[0063] The method provided by the present invention mainly includes respectively obtaining the task trajectory and task execution time for completing the current target action, establishing a three-dimensional coordinate system, mapping the task execution time to the vertical axis of the three-dimensional coordinate system, and mapping the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system; marking the space-time units passed by the task trajectory, obtaining several groups of marked target space-time units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, and after modifying the task execution times of the target space-time units in the same group to be the same, outputting a control instruction acting on the robot. This method models the tasks to be executed by the robot based on time, space dimensions, and task elements, unifies the modeling through three dimensions, and comprehensively considers these three factors for task planning, thereby improving the efficiency of task execution. Allocating space-time units to the subtasks to be executed by the robot, and the space-time units include the time, space attributes, and task elements during the execution of the subtasks. By mapping the three dimensions into the space-time units, optimizing and path planning for the space-time units, when there is overlap, it can be considered to complete a certain space-time unit among several target actions at the same time, so as to ensure that the finally planned task reaches the optimal in these three dimensions.

[0064] An exemplary implementation manner of the present invention decomposes the current task instruction into several target actions, including:

[0065] Judging whether the current target action is greater than 1. If it is not greater than 1, no decomposition is performed and the task ends; if it is greater than 1, task decomposition is performed.

[0066] Among them, it is first necessary to judge whether the currently decomposed target action is greater than 1. If it is not greater than 1, there is no object for comparison, and there is no meaning in subsequent analysis. Therefore, it is necessary to have the meaning of decomposition and subsequent analysis when the target action is greater than 1.

[0067] Regarding the division of space-time units, this solution proposes a specific embodiment of dividing several groups of space-time units into several space-time units, including:

[0068] Obtain the maximum activity range of the robot. The maximum activity range includes the farthest first distance that can be reached forward with itself as the center and the farthest second distance that can be reached to the left or right. Generate the length and width of the spatio-temporal unit based on the first distance and the second distance, and generate the height of the spatio-temporal unit based on the task execution time. Form the spatio-temporal unit through the length, width and height.

[0069] It can be understood that there is a starting point for the task execution time. After the time to be executed, an end point is obtained. There is a threshold range between the starting point and the end point. When this threshold range is reflected in the three-dimensional coordinate axis, it is a straight line, and thus the height of the spatio-temporal unit can be formed.

[0070] In this embodiment, based on the maximum activity range of the robot, the length and width of the spatio-temporal unit are formed, which can better reflect the real situation of the robot during the execution of actions.

[0071] In this embodiment, to modify the task execution times of the target spatio-temporal units on the same vertical line to be the same, it is necessary to consider which target spatio-temporal unit's task execution time is used as the benchmark for modification. This embodiment gives an example. Modifying the task execution times of the target spatio-temporal units to be the same includes:

[0072] Respectively obtain the to-be-corrected target actions where the target spatio-temporal units are located, and judge whether there is a sequence relationship among several to-be-corrected target actions. The sequence relationship includes that if the previous to-be-corrected target action is not completed, the subsequent to-be-corrected target action cannot be carried out; if there is no sequence relationship, then evaluate the to-be-corrected target actions; if there is a sequence relationship, then divide and select the to-be-corrected target actions. After division and selection, evaluate the to-be-corrected target actions; analyze the evaluation results of the to-be-corrected target actions and output the optimal task execution time.

[0073] In the above method, it is necessary to consider some to-be-corrected target actions with a necessary sequence before and after. For example, when performing floor sweeping and floor mopping, in the robot control program, floor mopping needs to be carried out after floor sweeping. In the spatio-temporal unit groups of floor sweeping and floor mopping respectively, the spatio-temporal units of picking up the mop and picking up the broom have an overlap in the vertical direction. If the task execution time is uniformly modified to the subsequent to-be-corrected target action, the previous to-be-corrected target action cannot be carried out. That is, the task execution time can only be uniformly modified to the task execution time of the target spatio-temporal unit in the previous to-be-corrected target action.

[0074] In addition, if there is a sequence relationship, then dividing and selecting the to-be-corrected target actions includes:

[0075] Divide the target actions to be corrected with a before-and-after relationship into a group to be confirmed, and divide the target actions to be corrected without a before-and-after relationship into a confirmation group for storage; among the target actions to be corrected in the group to be confirmed, save the target actions to be corrected that perform tasks first to the confirmation group, and delete the target actions to be corrected that perform tasks later; output the target actions to be corrected saved in the confirmation group.

[0076] Therefore, in this embodiment, the target actions to be corrected with a before-and-after relationship are separately grouped. In this group, only the first executed target action to be corrected is retained, and the subsequent target actions to be corrected have no meaning for reference modification. Finally, the target actions to be corrected that have no before-and-after relationship are obtained, such as sweeping the floor, tidying up the desktop, and putting away items.

[0077] An exemplary implementation of the present invention for evaluating the target actions to be corrected includes:

[0078] Judge the number of the current target actions to be corrected. If it is not greater than 1, modify the task execution time of all the corrected target actions to the task execution time of the current target action to be corrected.

[0079] Among them, if there is only 1 remaining target action to be corrected, no evaluation is required, and directly modify the other target spatio-temporal units according to the task execution time of the remaining target action to be corrected.

[0080] If it is greater than 1, obtain the number of marked target spatio-temporal units in the spatio-temporal unit group of each target action to be corrected.

[0081] Obtain the task execution time of the spatio-temporal unit group with the smallest number of target spatio-temporal units as the task execution time of the target action to be corrected in the current group.

[0082] The spatio-temporal unit group with the smallest number of target spatio-temporal units represents that the task corresponding to this time unit group has less overlap with other tasks. Selecting to complete the actions corresponding to the target spatio-temporal units in other spatio-temporal unit groups at this time can reduce the processing burden of the current robot and reduce the possibility of errors.

[0083] In addition, it also includes:

[0084] If the number of spatio-temporal unit groups with the smallest number of target spatio-temporal units is greater than 1, obtain the positions of the vertical axes of several spatio-temporal unit groups in the three-dimensional coordinate system; obtain the task execution time of the spatio-temporal unit group closest to the origin of the three-dimensional coordinate system as the task execution time of the target action to be corrected in the current group.

[0085] When there are multiple initial spatio-temporal unit groups, the earliest one is selected, which can leave more room for unexpected situations in subsequent actions, such as failures and insufficient power.

[0086] In a second aspect, the present invention also provides a robot control method based on spatio-temporal units, including:

[0087] A task decomposition module, configured to obtain a current task instruction and decompose the current task instruction into several target actions, and the combination of the several target actions completes the current task instruction;

[0088] A task mapping module, configured to respectively obtain a task trajectory and a task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal axis and the vertical axis of the three-dimensional coordinate system; establish a spatio-temporal unit group of the target action within the three-dimensional coordinate system, where the spatio-temporal unit group includes the two-dimensional space in which the robot moves and the task execution time; different spatio-temporal unit groups are sequentially arranged at different heights on the vertical axis of the three-dimensional coordinate axis, divide the several spatio-temporal unit groups into several spatio-temporal units, and respectively map the task trajectory of the target action into the corresponding spatio-temporal unit group;

[0089] A task optimization module, configured to mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, and after modifying the task execution times of the target spatio-temporal units in the same group to be consistent, output a control instruction acting on the robot;

[0090] A main control module, connected to the task decomposition module, the task mapping module, and the task optimization module, for executing the above-mentioned robot control method based on spatio-temporal units.

[0091] In addition, in each embodiment of the present invention, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above integrated units can be implemented in the form of hardware or in the form of software functional units.

[0092] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. The computer software product is stored in a storage medium and includes several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs that can store program codes.

[0093] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A robot control method based on spatio-temporal units, characterized in that Including: Obtain the current task instruction, decompose the current task instruction into several target actions, and complete the current task instruction through the combination of several said target actions; Respectively obtain the task trajectory and task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal axis and vertical axis of the three-dimensional coordinate system; Establish a spatio-temporal unit group for the target action within the three-dimensional coordinate system, and the spatio-temporal unit group includes the two-dimensional space where the robot moves and the task execution time; The different said spatio-temporal unit groups are sequentially set at different heights on the vertical axis of the three-dimensional coordinate axis, divide several spatio-temporal unit groups into several spatio-temporal units, and respectively map the task trajectory of the target action into the corresponding spatio-temporal unit group; Mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, and after modifying the task execution times of the target spatio-temporal units in the same group to be the same, output the control instruction acting on the robot.

2. The robot control method based on spatio-temporal units according to claim 1, wherein, The decomposition of the current task instruction into several target actions includes; Judge whether the current target action is greater than 1. If it is not greater than 1, no decomposition is performed and the task ends; If it is greater than 1, then perform task decomposition.

3. The robot control method based on spatio-temporal units according to claim 2, characterized in that, The division of several spatio-temporal unit groups into several spatio-temporal units includes: Obtain the maximum activity range of the robot, and the maximum activity range includes the farthest first distance that can be reached forward centered on itself and the farthest second distance that can be reached to the left or right; Generate the length and width of the spatio-temporal unit with the first distance and the second distance, and generate the height of the spatio-temporal unit with the task execution time, and form the spatio-temporal unit through the length, width and height.

4. The robot control method based on spatio-temporal units according to claim 3, characterized in that, The modification of the task execution times of the target spatio-temporal units to be the same includes: Respectively obtain the target actions to be corrected where the target spatio-temporal units are located, and judge whether there is a sequence relationship among several target actions to be corrected, and the sequence relationship includes that if the previous target action to be corrected is not completed, the subsequent target action to be corrected cannot be carried out; If there is no sequence relationship, then perform the evaluation of the target action to be corrected; If there is a sequence relationship, then divide and select the target actions to be corrected, and perform the evaluation of the target action to be corrected after division and selection; Analyze the evaluation results of the target actions to be corrected and output the optimal task execution time.

5. The robot control method based on spatio-temporal units according to claim 4, wherein, The division and selection of the target actions to be corrected when there is a sequence relationship includes: Divide the target actions to be corrected with a sequence relationship into a group to be confirmed, and divide the target actions to be corrected without a sequence relationship into a confirmed group for storage; Among the target actions to be corrected in the group to be confirmed, save the target action to be corrected that performs the task first to the confirmed group, and delete the target action to be corrected that performs the subsequent task; Output the target actions to be corrected saved in the confirmed group.

6. The robot control method based on spatio-temporal units according to claim 5, wherein The evaluation of the target action to be corrected includes: Judge the number of the current target actions to be corrected. If it is not greater than 1, then modify the task execution times of all the corrected target actions to the task execution time of the current target action to be corrected; If it is greater than 1, obtain the number of marked target spatio-temporal units in the spatio-temporal unit group of each target action to be corrected; Obtain the task execution time of the spatio-temporal unit group with the smallest number of target spatio-temporal units as the task execution time of the target action to be corrected in the current group.

7. The robot control method based on spatio-temporal units according to claim 6, characterized in that, It further includes: If the number of spatio-temporal unit groups with the smallest number of target spatio-temporal units is greater than 1, obtain the position of the vertical axis in the three-dimensional coordinate system where several spatio-temporal unit groups are located; Obtain the task execution time of the spatio-temporal unit group closest to the origin of the three-dimensional coordinate system as the task execution time of the target action to be corrected in the current group.

8. A robot control method based on spatio-temporal units, characterized in that, It includes: A task decomposition module, configured to obtain the current task instruction, decompose the current task instruction into several target actions, and several of the target actions complete the current task instruction; A task mapping module, configured to respectively obtain the task trajectory and task execution time for completing the current target action, establish a three-dimensional coordinate system, map the task execution time to the vertical axis of the three-dimensional coordinate system, and map the task trajectory to the horizontal and vertical axes of the three-dimensional coordinate system; establish a spatio-temporal unit group of the target action within the three-dimensional coordinate system, where the spatio-temporal unit group includes the two-dimensional space in which the robot moves and the task execution time; different spatio-temporal unit groups are sequentially arranged at different heights on the vertical axis of the three-dimensional coordinate axis, divide several spatio-temporal unit groups into several spatio-temporal units, and respectively map the task trajectory of the target action to the corresponding spatio-temporal unit group; A task optimization module, configured to mark the spatio-temporal units passed by the task trajectory, obtain several groups of marked target spatio-temporal units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, and after modifying the task execution times of the target spatio-temporal units in the same group to be the same, output a control instruction acting on the robot; A main control module, connected to the task decomposition module, task mapping module, and task optimization module, for executing the spatio-temporal unit-based robot control method according to any one of claims 1-7.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the spatio-temporal unit-based robot control method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, it implements the spatio-temporal unit-based robot control method according to any one of claims 1-7.

Images