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

Abstract

The present invention relates to the field of robot control technology, and in particular, to a robot control method and system, device, and medium based on space-time units. The method models the tasks to be performed by the robot based on the time, space dimensions, and task elements in a unified manner through three dimensions, and comprehensively considers these three factors to plan the tasks, thereby improving the efficiency of task execution. Space-time units are allocated to the subtasks to be performed by the robot, and the space-time units contain the time and space attributes and task elements in the execution of the subtasks. By mapping the three dimensions into space-time units, the space-time units are optimized and path planning is performed. When there is overlap, it is possible to consider completing a space-time unit among several target actions at the same time, thereby ensuring that the task finally planned is optimized in these three dimensions.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a robot control method, system, device, and medium based on space-time units. Background Art

[0002] With the rapid development of new technologies, robotics are becoming increasingly widespread. Their widespread application across various industries is improving productivity while freeing a significant number of workers from tedious, repetitive tasks. However, current robotic task planning is relatively simple, typically setting task sequences based on time attributes and referencing specific criteria such as the shortest path, minimum time, and minimum cost. Complex tasks are often broken down into N (N greater than or equal to 1) subtasks. Task planning involves planning the execution sequence of these subtasks within this set of decomposed subtasks.

[0003] The execution of a task has certain temporal and spatial attributes. The temporal attribute corresponds to the task's start time and duration, as well as its dependencies on other tasks. The spatial attribute corresponds to the task's position in space during execution and its trajectory. Typically, a robot's task may need to be split into N (N greater than or equal to 1) subtasks, depending on the usage scenario. These tasks may overlap in time or space (such as parallel or serial execution in the temporal dimension, and overlap in the spatial dimension). Furthermore, task elements (external elements on which task execution depends, as well as the resources occupied by the robot itself) are not the same. Therefore, solely planning tasks based on time or space will not enable robots to complete tasks more efficiently. Summary of the Invention

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

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

[0006] In the first aspect, a robot control method based on a spatiotemporal unit includes:

[0007] Obtaining a current task instruction, decomposing the current task instruction into a plurality of target actions, and combining the plurality of target actions to complete the current task instruction;

[0008] Obtaining the task trajectory and task execution time for completing the current target action respectively, and establishing a three-dimensional coordinate system, wherein the task execution time is mapped to the vertical axis of the three-dimensional coordinate system, and the task trajectory is mapped to the horizontal and vertical axes of the three-dimensional coordinate system;

[0009] Establishing a spatiotemporal unit group of the target action in a three-dimensional coordinate system, wherein the spatiotemporal unit group includes the two-dimensional space in which the robot moves and the task execution time;

[0010] Different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis in the three-dimensional coordinate axis, a plurality of spatiotemporal unit groups are divided into a plurality of spatiotemporal units, and the task trajectory of the target action is mapped to the corresponding spatiotemporal unit group respectively;

[0011] The space-time units that the task trajectory passes through are marked, and several groups of marked target space-time units with different vertical coordinates under the same horizontal and vertical coordinates are obtained. After the task execution time of the target space-time units in the same group is modified to be consistent, the control instructions acting on the robot are output.

[0012] Preferably, the decomposing the current task instruction into a plurality of target actions includes:

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

[0014] If it is greater than 1, the task is decomposed.

[0015] Preferably, dividing the plurality of space-time unit groups into a plurality of space-time units comprises:

[0016] Obtaining a maximum range of movement of the robot, the maximum range including a first maximum distance that the robot can reach forward and a second maximum distance that the robot can reach leftward or rightward, with the robot as the center;

[0017] The length and width of the space-time unit are generated by the first distance and the second distance, and the height of the space-time unit is generated by the task execution time, and the space-time unit is formed by the length, width and height.

[0018] Preferably, modifying the task execution time of the target spatiotemporal unit to be consistent includes:

[0019] Obtaining the target actions to be corrected in the target spatiotemporal unit respectively, and determining whether there is a sequence relationship between the target actions to be corrected, wherein 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 performed;

[0020] If there is no sequential relationship, the target action to be corrected is evaluated;

[0021] If there is a sequential relationship, the target action to be corrected is divided and selected, and after the division and selection, the target action to be corrected is evaluated;

[0022] The evaluation results of the target action to be corrected are analyzed and the optimal task execution time is output.

[0023] Preferably, if there is a sequential relationship, dividing and selecting the target action to be corrected includes:

[0024] The target actions to be corrected that have a before-after relationship are divided into a pending confirmation group, and the target actions to be corrected that do not have a before-after relationship are divided into a confirmation group for storage;

[0025] Among the target actions to be modified in the pending confirmation group, the target actions to be modified that were executed earlier are saved to the confirmation group, and the target actions to be modified that were executed later are deleted;

[0026] Output the target action to be modified saved in the confirmation group.

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

[0028] Determine 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, the number of marked target spatiotemporal units in each spatiotemporal unit group of the target action to be corrected is obtained;

[0030] The task execution time of the spatiotemporal unit group with the smallest number of target spatiotemporal units is obtained as the task execution time of the target action to be corrected in the current group.

[0031] Preferably, it also includes:

[0032] If the number of the space-time unit group with the smallest number of target space-time units is greater than 1, the positions of the vertical axes of the three-dimensional coordinate systems of the space-time unit groups are obtained;

[0033] The task execution time of the spatiotemporal unit group closest to the origin of the three-dimensional coordinate system is obtained as the task execution time of the target action to be corrected in the current group.

[0034] In a second aspect, the present invention further provides a robot control method based on space-time units, comprising:

[0035] A task decomposition module is configured to obtain a current task instruction, decompose the current task instruction into a plurality of target actions, and combine the plurality of target actions 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 spatiotemporal unit group for the target action in the three-dimensional coordinate system, the spatiotemporal unit group including the two-dimensional space in which the robot is active and the task execution time; different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis of the three-dimensional coordinate axis, divide the multiple spatiotemporal unit groups into multiple spatiotemporal units, and respectively map the task trajectory of the target action to the corresponding spatiotemporal unit group;

[0037] The task optimization module is configured to mark the space-time units that the task trajectory passes through, obtain several groups of marked target space-time units with different vertical coordinates under the same horizontal and vertical coordinates, modify the task execution time of the target space-time units in the same group to be consistent, and output control instructions for 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 time-space units.

[0039] In a third aspect, 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 the processor implements the above-mentioned robot control method based on space-time units when executing the computer program.

[0040] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the robot control method based on spatiotemporal units as described above.

[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 primarily involves obtaining a task trajectory and task execution time for completing a 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 spatiotemporal units that the task trajectory passes through, obtaining several groups of marked target spatiotemporal units with different vertical coordinates located at the same horizontal and vertical coordinates; modifying the task execution times of target spatiotemporal units in the same group to be consistent, and then outputting control instructions for the robot. This method uniformly models the robot's tasks based on time, space, and task elements, comprehensively considering these three factors to plan tasks, thereby improving task execution efficiency. Spatiotemporal units are assigned to the robot's subtasks, each of which contains the time and space attributes and task elements of the subtask execution. By mapping the three dimensions to the spatiotemporal units, optimization and path planning are performed on the spatiotemporal units. When there is overlap, the spatiotemporal units of several target actions can be considered for simultaneous completion, thereby ensuring that the final planned task achieves the optimal performance across the 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 briefly introduces the drawings required for use in the embodiments. It should be understood that the following drawings only illustrate certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other relevant drawings can be obtained based on these drawings without paying any creative work.

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

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

[0046] Figure 3 Schematic diagram of the plane trajectory of the present invention. DETAILED DESCRIPTION

[0047] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Generally, the components of the embodiments of the present invention described and shown in the drawings herein can be arranged and designed in various different configurations.

[0048] The division of modules that appears in this application is a logical division. There may be other division methods when implementing in actual applications. For example, multiple modules can be combined into 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 related objects, or an indirect connection, coupling or communication through other devices. In addition, 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 may be physically separated or not: they may be implemented by software or hardware, and some modules or sub-modules may be implemented by software, and the processor may call the software to implement the functions of these modules or sub-modules, and other modules or sub-modules may be implemented by hardware, for example, by hardware circuits. In addition, some or all of the modules can be selected according to actual needs to achieve the purpose of the present application solution.

[0049] Please refer to Figure 1-Figure 3 The present invention provides a robot control method based on space-time units, comprising:

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

[0051] In this embodiment, the task instruction refers to the control instruction received by the robot, which enables the robot to perform corresponding actions and achieve a certain purpose. The control signal can be a command sent to the receiving end of the robot via wireless communication.

[0052] For example, if the robot receives a task instruction for cleaning, the robot's control system will invoke all pre-programmed control programs for cleaning and each action required to complete the task. This action is the target action required by the present invention. Cleaning can be broken down into two target actions: sweeping and mopping. The robot will complete the currently received task instruction with sweeping and mopping as the targets.

[0053] S102: Obtaining the task trajectory and task execution time for completing the current target action respectively, and establishing a three-dimensional coordinate system, wherein the task execution time is mapped to the vertical axis of the three-dimensional coordinate system, and the task trajectory is mapped to the horizontal and vertical axes of the three-dimensional coordinate system;

[0054] S103: Establishing a spatiotemporal unit group of the target action in the three-dimensional coordinate system, wherein the spatiotemporal unit group includes the two-dimensional space in which the robot moves and the task execution time;

[0055] Similarly, for the two target actions of sweeping and mopping, there is a time sequence between the two target actions. Therefore, the space-time unit group of sweeping and the space-time unit group of mopping are presented in the form of different coordinates on the vertical axis of the three-dimensional coordinate system. The sweeping task requires a broom, and the mopping task requires a mop. Therefore, different paths are further planned to complete these two target actions.

[0056] The trajectory formed by completing the two target actions is mapped into a two-dimensional plane graph, and the two-dimensional plane graph is overlaid 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] Specifically, a Cartesian coordinate system is established, with the X-axis representing the X direction of the map, the Y-axis representing the Y direction of the map, and the Z-axis representing the time of task execution. The units in the space-time coordinate system are called space-time units. Space-time units contain the temporal and spatial attributes of subtask execution and task elements. This simplifies the description of subsequent solutions. The values ​​on the Z-axis (the time axis) are uniformly expressed in units of time for solution presentation, and the specific execution time is recorded in the description of the space-time unit.

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

[0059] S104: different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis of the three-dimensional coordinate axis, a plurality of spatiotemporal unit groups are divided into a plurality of spatiotemporal units, and the task trajectory of the target action is mapped to the corresponding spatiotemporal unit group respectively;

[0060] In order to better compare the space-time unit group of each target action, the entire space-time unit group is divided into several space-time units, which is equivalent to defining a range for subsequent comparisons. This range can be the maximum activity range of the robot when it is stationary.

[0061] S105: Mark the space-time units that the task trajectory passes through, obtain several groups of marked target space-time units with different vertical axis coordinates under the same horizontal axis coordinate and vertical axis coordinate, modify the task execution time of the target space-time units in the same group to be consistent, and output the control instructions acting on the robot.

[0062] Different groups of space-time units can be compared very intuitively in a three-dimensional coordinate system. When comparing in the vertical axis, the target space-time units of different space-time unit groups with consistent horizontal and vertical coordinates can be quickly obtained. If these selected target space-time units happen to have actions to perform, such as picking up a broom, their task execution times can be adjusted to be consistent. In other words, the tasks to be completed by these two target space-time units can be considered to be completed at the same time. Of course, whether they must be completed at the same time can be set according to the specific situation. This solution only proposes one feasible method. This improves the robot's work efficiency to a certain extent, and quickly analyzes the space-time units that overlap in the vertical axis and determines whether the corresponding actions can be completed at the same time.

[0063] The method provided by the present invention primarily involves obtaining a task trajectory and task execution time for completing a 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 spatiotemporal units that the task trajectory passes through, obtaining several groups of marked target spatiotemporal units with different vertical coordinates located at the same horizontal and vertical coordinates; modifying the task execution times of target spatiotemporal units in the same group to be consistent, and then outputting control instructions for the robot. This method uniformly models the robot's tasks based on time, space, and task elements, comprehensively considering these three factors to plan tasks, thereby improving task execution efficiency. Spatiotemporal units are assigned to the robot's subtasks, each of which contains the time and space attributes and task elements of the subtask execution. By mapping the three dimensions to the spatiotemporal units, optimization and path planning are performed on the spatiotemporal units. When there is overlap, the spatiotemporal units of several target actions can be considered for simultaneous completion, thereby ensuring that the final planned task achieves the optimal performance across the three dimensions.

[0064] In an exemplary embodiment of the present invention, decomposing the current task instruction into a plurality of target actions includes:

[0065] Determine whether the current target action is greater than 1. If it is not greater than 1, do not decompose and end the task; if it is greater than 1, decompose the task.

[0066] Among them, it is first necessary to determine whether the target action currently being decomposed 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 only meaningful to decompose and conduct subsequent analysis when the target action is greater than 1.

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

[0068] Obtain the robot's maximum range of activity, where the maximum range includes a first maximum distance the robot can reach forward and a second maximum distance the robot can reach to the left or right. Generate the length and width of a space-time unit using the first and second distances, and generate the height of the space-time unit using the task execution time. The space-time unit is formed by the length, width, and height.

[0069] It can be understood that the task execution time has a starting point, and after the time required for execution, it gets an end point. There is a threshold range between the starting point and the end point. The threshold range is reflected in the three-dimensional coordinate axis as a straight line, which can form the height of the space-time unit.

[0070] In this embodiment, the length and width of the space-time unit are formed based on the maximum range of the robot's activity, which can better reflect the actual situation of the robot in performing the action.

[0071] In this embodiment, to modify the task execution times of target spatiotemporal units on the same vertical line to be consistent, it is necessary to consider which target spatiotemporal unit's task execution time is used as a reference for modification. This embodiment provides an example, and modifying the task execution times of target spatiotemporal units to be consistent includes:

[0072] The target actions to be corrected in the target spatiotemporal unit are obtained respectively, and it is determined whether there is a sequence relationship among several target actions to be corrected, wherein 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 performed; if there is no sequence relationship, the target actions to be corrected are evaluated; if there is a sequence relationship, the target actions to be corrected are divided and selected, and after the division and selection, the target actions to be corrected are evaluated; the evaluation results of the target actions to be corrected are analyzed, and the optimal task execution time is output.

[0073] In the above method, it is necessary to consider some necessary target actions to be corrected that have a sequence before and after. For example, sweeping the floor and mopping the floor. In the robot control program, mopping the floor needs to be done after sweeping the floor. In the space-time unit groups of sweeping the floor and mopping the floor, respectively, the space-time units of holding the mop and holding the broom overlap in the vertical direction. If the task execution time is uniformly modified to the subsequent target action to be corrected, the previous target action to be corrected cannot be performed. That is, the task execution time can only be uniformly modified to the task execution time of the target space-time unit in the previous target action to be corrected.

[0074] In addition, if there is a sequence relationship, the target action to be corrected is divided and selected including:

[0075] The target actions to be corrected that have a before-and-after relationship are divided into a pending confirmation group, and the target actions to be corrected that do not have a before-and-after relationship are divided into a confirmation group for storage; among the target actions to be corrected in the pending confirmation group, the target actions to be corrected that are executed first are saved in the confirmation group, and the target actions to be corrected that are executed later are deleted; and the target actions to be corrected saved in the confirmation group are output.

[0076] Therefore, in this embodiment, the target actions to be corrected that have a sequence relationship are divided into separate groups. In this group, only the first target action to be corrected is retained, and there is no meaning of reference modification for the subsequent target actions to be corrected. Finally, the target actions to be corrected that have no sequence relationship are obtained, such as sweeping the floor, tidying up the desk, and putting items back in place.

[0077] In an exemplary embodiment of the present invention, evaluating the target action to be corrected includes:

[0078] Determine 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 one target action to be corrected, no evaluation is required, and the other target spatiotemporal units are directly modified according to the task execution time of the retained target action to be corrected.

[0080] If it is greater than 1, the number of marked target spatiotemporal units in each spatiotemporal unit group of the target action to be corrected is obtained;

[0081] The task execution time of the spatiotemporal unit group with the smallest number of target spatiotemporal units is obtained as the task execution time of the target action to be corrected in the current group.

[0082] The space-time unit group with the smallest number of target space-time units means that the task corresponding to this space-time unit group has a small overlap with other tasks. Choosing this time to complete the actions corresponding to the target space-time units in other space-time unit groups can reduce the processing burden of the current robot and reduce the possibility of errors.

[0083] Additionally, it includes:

[0084] If the number of the space-time unit group with the smallest number of target space-time units is greater than 1, then obtain the positions of the vertical axes of the several space-time unit groups in the three-dimensional coordinate system; obtain the task execution time of the space-time 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 space-time unit groups with the smallest number, selecting the most initial space-time unit group can leave more room for unpredictability for subsequent actions, such as failures, insufficient power, etc.

[0086] In a second aspect, the present invention further provides a robot control method based on space-time units, comprising:

[0087] A task decomposition module is configured to obtain a current task instruction, decompose the current task instruction into a plurality of target actions, and combine the plurality of target actions to complete the current task instruction;

[0088] 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 spatiotemporal unit group for the target action in the three-dimensional coordinate system, the spatiotemporal unit group including the two-dimensional space in which the robot is active and the task execution time; different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis of the three-dimensional coordinate axis, divide the multiple spatiotemporal unit groups into multiple spatiotemporal units, and respectively map the task trajectory of the target action to the corresponding spatiotemporal unit group;

[0089] The task optimization module is configured to mark the space-time units that the task trajectory passes through, obtain several groups of marked target space-time units with different vertical coordinates under the same horizontal and vertical coordinates, modify the task execution time of the target space-time units in the same group to be consistent, and output control instructions for the robot;

[0090] 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 time-space units.

[0091] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0092] If the integrated unit is implemented as 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 a number of instructions for causing a computer device (which can be a personal computer, server, or network device, etc.) to perform all or part of the steps of the various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc., various media that can store program code.

[0093] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention shall be included within the scope of protection of the present invention.

Claims

1. A robot control method based on space-time units, characterized in that: include: Obtaining a current task instruction, decomposing the current task instruction into a plurality of target actions, and combining the plurality of target actions to complete the current task instruction; Obtaining the task trajectory and task execution time for completing the current target action respectively, and establishing a three-dimensional coordinate system, wherein the task execution time is mapped to the vertical axis of the three-dimensional coordinate system, and the task trajectory is mapped to the horizontal and vertical axes of the three-dimensional coordinate system; Establishing a spatiotemporal unit group of the target action in a three-dimensional coordinate system, wherein the spatiotemporal unit group includes the two-dimensional space in which the robot moves and the task execution time; Different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis in the three-dimensional coordinate axis, a plurality of spatiotemporal unit groups are divided into a plurality of spatiotemporal units, and the task trajectory of the target action is mapped to the corresponding spatiotemporal unit group respectively; Mark the space-time units that the task trajectory passes through, obtain several groups of marked target space-time units with different vertical coordinates under the same horizontal and vertical coordinates, modify the task execution time of the target space-time units in the same group to be consistent, and output the control instructions acting on the robot; Modifying the task execution time of the target spatiotemporal unit to be consistent includes: Obtaining the target actions to be corrected in the target spatiotemporal unit respectively, and determining whether there is a sequence relationship between the target actions to be corrected, wherein 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 performed; If there is no sequential relationship, the target action to be corrected is evaluated; If there is a sequential relationship, the target action to be corrected is divided and selected, and after the division and selection, the target action to be corrected is evaluated; Analyze the evaluation results of the target action to be corrected and output the optimal task execution time; If there is a sequence relationship, dividing and selecting the target action to be corrected includes: The target actions to be corrected that have a before-after relationship are divided into a pending confirmation group, and the target actions to be corrected that do not have a before-after relationship are divided into a confirmation group for storage; Among the target actions to be modified in the pending confirmation group, the target actions to be modified that were executed earlier are saved to the confirmation group, and the target actions to be modified that were executed later are deleted; Output the target action to be corrected saved in the confirmation group; The evaluation of the target action to be corrected includes: Determine 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. If it is greater than 1, the number of marked target spatiotemporal units in each spatiotemporal unit group of the target action to be corrected is obtained; Obtain the task execution time of the spatiotemporal unit group with the smallest number of target spatiotemporal units as the task execution time of the target action to be corrected in the current group; Also includes: If the number of the space-time unit group with the smallest number of target space-time units is greater than 1, the positions of the vertical axes of the three-dimensional coordinate systems of the space-time unit groups are obtained; The task execution time of the spatiotemporal unit group closest to the origin of the three-dimensional coordinate system is obtained as the task execution time of the target action to be corrected in the current group.

2. The robot control method based on space-time unit according to claim 1, characterized in that: Decomposing the current task instruction into a plurality of target actions includes: Determine whether the current target action is greater than 1. If not, do not decompose and end the task. If it is greater than 1, the task is decomposed.

3. The robot control method based on space-time unit according to claim 2, characterized in that: The step of dividing the plurality of space-time unit groups into a plurality of space-time units comprises: Obtaining a maximum range of motion of the robot, the maximum range of motion including a first maximum distance that the robot can reach forward and a second maximum distance that the robot can reach leftward or rightward, with the robot as the center; The length and width of the space-time unit are generated by the first distance and the second distance, and the height of the space-time unit is generated by the task execution time, and the space-time unit is formed by the length, width and height.

4. A robot control system based on space-time units, characterized in that: include: The task decomposition module is configured to obtain a current task instruction, decompose the current task instruction into a plurality of target actions, and combine the plurality of target actions to complete the current task instruction; 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 spatiotemporal unit group for the target action in the three-dimensional coordinate system, the spatiotemporal unit group including the two-dimensional space in which the robot is active and the task execution time; different spatiotemporal unit groups are sequentially arranged at different heights of the vertical axis of the three-dimensional coordinate axis, divide the multiple spatiotemporal unit groups into multiple spatiotemporal units, and respectively map the task trajectory of the target action to the corresponding spatiotemporal unit group; The task optimization module is configured to mark the space-time units that the task trajectory passes through, obtain several groups of marked target space-time units with different vertical coordinates under the same horizontal and vertical coordinates, modify the task execution time of the target space-time units in the same group to be consistent, and output control instructions for the robot; A 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 robot control method based on the space-time unit according to any one of claims 1 to 3.

5. 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 control method based on space-time units according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the robot control method based on the space-time unit according to any one of claims 1 to 3 is implemented.

Images