Robot and task priority planning method thereof, computer readable storage medium

Abstract

The application discloses a task priority planning method of a robot, and the method comprises the following steps: acquiring first importance degree information of each task in a plurality of tasks to be executed by the robot, and acquiring second importance degree information corresponding to a plurality of task demand information respectively; the first importance degree information represents the importance degree of the corresponding task in the plurality of tasks, and the second importance degree information represents the importance degree of the corresponding task demand information in the plurality of task demand information; determining a priority parameter of each task according to the first importance degree information and the second importance degree information; and determining the execution sequence of the plurality of tasks according to the priority parameter of each task. The application further discloses a robot and a computer readable storage medium. The application aims to realize that the multi-task execution process of the robot can be fitted to the user demand, guarantee the satisfaction of the user demand, and improve the user experience.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more particularly to a task prioritization planning method for robots, robots, and computer-readable storage media. Background Technology

[0002] With the development of economy and technology, robots are being used more and more widely in daily life, especially service robots, which can provide users with a variety of intelligent services to meet their diverse life service needs.

[0003] However, currently, when robots perform multiple tasks, they can generally only execute multiple tasks in a pre-set fixed priority order, ignoring the user's actual needs for task execution time, frequency, and other aspects of the task execution process. As a result, when robots execute multiple tasks according to fixed priority, they cannot meet the user's actual needs, thus affecting the user experience. Summary of the Invention

[0004] The main objective of this invention is to provide a task priority planning method for a robot, a robot, and a computer-readable storage medium, aiming to enable the robot's multi-task execution process to be aligned with user needs, ensuring that user needs are met and improving user experience.

[0005] To achieve the above objectives, the present invention provides a task priority planning method for a robot, the task priority planning method for a robot comprising the following steps:

[0006] Obtain first importance information for each of the multiple tasks to be executed by the robot, and obtain second importance information corresponding to the multiple task requirement information respectively; the first importance information represents the importance of the corresponding task in the multiple tasks, and the second importance information represents the importance of the corresponding task requirement information in the multiple task requirement information;

[0007] The priority parameter for each task is determined based on the first importance information and the second importance information;

[0008] The execution order of the plurality of tasks is determined based on the priority parameter of each task.

[0009] Optionally, the first importance information includes task importance information corresponding to each of the multiple task requirement information, wherein the task importance information represents the importance of the task among the multiple tasks when the corresponding task requirement information is used as the evaluation criterion, and the step of determining the priority parameter of each task based on the first importance information and the second importance information includes:

[0010] Based on the second importance information, determine the weight value of the task importance information corresponding to each of the task requirement information;

[0011] The priority parameter of each task is calculated based on the multiple task importance information corresponding to each task and the weight value of each task importance information.

[0012] Optionally, the step of obtaining the second importance information corresponding to the multiple task requirement information includes:

[0013] Obtain the first importance relationship corresponding to the multiple task requirement information; the first importance relationship represents the relative importance between any two of the task requirement information.

[0014] The second importance information corresponding to each task requirement information is determined based on the first importance relationship.

[0015] Optionally, the first importance relationship includes multiple first relationship values, where each first relationship value represents the importance of one task requirement information relative to another task requirement information. The step of determining the second importance information corresponding to each task requirement information based on the first importance relationship is as follows:

[0016] Determine a first feature value corresponding to each of the task requirement information, wherein the first feature value is the sum of multiple first relationship values ​​corresponding to the task requirement information;

[0017] The sum of all first relation values ​​in the first importance relation is determined as the second feature value;

[0018] The second importance information corresponding to each task requirement information is determined based on the first feature value and the second feature value;

[0019] And / or, the first importance relationship is a fuzzy matrix.

[0020] Optionally, the first importance information includes task importance information corresponding to multiple task requirement information, wherein the task importance information represents the importance of the task among the multiple tasks when the corresponding task requirement information is used as the evaluation criterion, and the step of obtaining the first importance information of each task among the multiple tasks to be executed by the robot includes:

[0021] Obtain the second importance relationship corresponding to each of the task requirement information; the second importance relationship represents the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation benchmark;

[0022] Based on multiple second importance relationships, determine multiple task importance information corresponding to each task.

[0023] Optionally, the second importance relationship includes multiple second relationship values, whereby the second relationship value characterizes the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation criterion. The step of determining multiple task importance information corresponding to each task based on multiple second importance relationships is as follows:

[0024] In each of the second importance relations, a third feature value is determined for each task, and the sum of all second relation values ​​is determined as a fourth feature value; the third feature value is the sum of multiple second relation values ​​corresponding to each task.

[0025] Based on the third feature value and the fourth feature value, determine the importance information of multiple tasks corresponding to each task;

[0026] And / or, the second importance relationship is a fuzzy matrix.

[0027] Optionally, one of the plurality of tasks is a help request operation. Before the step of determining a third feature value corresponding to each task in each of the second importance relationships, and determining the sum of all second relationship values ​​as a fourth feature value; and before the step of the third feature value being the sum of the plurality of second relationship values ​​corresponding to each task, the method further includes:

[0028] Obtain the types of people in the space where the robot is located;

[0029] If the personnel type is the target type, then adjust the second relationship value corresponding to the help request operation in each second importance relationship so that the second relationship value corresponding to the help request operation in each second importance relationship is greater than the second relationship value corresponding to other tasks in the plurality of tasks.

[0030] Optionally, the step of obtaining the second importance relationship corresponding to each of the task requirement information includes:

[0031] Based on the task requirement information, the current scene feature parameters of the scene in which the robot is located are detected, and the target state parameters of different tasks corresponding to each task requirement information are obtained; the target state parameters represent the feature parameters of the target state that the robot needs to achieve when performing the corresponding task.

[0032] Determine the deviation value between the target state parameter and the scene feature parameter corresponding to each task;

[0033] The second importance relationship is determined based on the deviation value of different tasks corresponding to each of the task requirement information.

[0034] Optionally, the step of obtaining the target state parameters of different tasks corresponding to each task requirement information includes:

[0035] The robot acquires historical state data corresponding to each task requirement information during the execution of each task; the historical state data is detected within a preset time period prior to the current moment.

[0036] Based on the historical state data, the target state parameters for each of the different tasks corresponding to each task requirement information are determined.

[0037] Optionally, the step of determining the execution order of the plurality of tasks based on the priority parameter of each task may, simultaneously or after, include:

[0038] Receive the instruction to change the execution order, and determine the target execution order corresponding to the instruction to change the execution order;

[0039] Update the first importance relationship or the second importance relationship according to the execution order of the objectives;

[0040] Return to the steps of obtaining the first importance information of each of the multiple tasks to be executed by the robot, and obtaining the second importance information corresponding to the requirements of the multiple tasks respectively.

[0041] Optionally, one of the plurality of tasks is defined as a first task, and another of the plurality of tasks is defined as a second task. After the step of determining the execution order of the plurality of tasks according to the priority parameter of each task, the method further includes:

[0042] During the execution of the first task by the robot, the robot receives the execution instruction for the second task, and obtains a first priority parameter, a second priority parameter, and the current completion status of the first task; the first priority parameter is the priority parameter corresponding to the first task, and the second priority parameter is the priority parameter corresponding to the second task.

[0043] The identification result is determined based on the first priority parameter, the second priority parameter, and the completion rate. The identification result includes whether the first task is interrupted.

[0044] The execution order is adjusted based on the identification results.

[0045] Optionally, the step of determining the recognition result based on the first priority parameter, the second priority parameter, and the completion rate includes:

[0046] Determine the parameter difference between the first priority parameter and the second priority parameter;

[0047] The target parameters are calculated based on the parameter differences and their corresponding first weights, and the completion degree and its corresponding second weights.

[0048] If the target parameter is greater than the set threshold, then the recognition result is determined to be that the first task will not be interrupted;

[0049] If the target parameter is less than or equal to the set threshold, then the identification result is determined to interrupt the first task.

[0050] In addition, to achieve the above objectives, this application also proposes a robot, the robot comprising: a memory, a processor, and a task priority planning program for the robot stored in the memory and executable on the processor, wherein when the task priority planning program for the robot is executed by the processor, it implements the steps of the task priority planning method for the robot as described in any of the preceding claims.

[0051] In addition, to achieve the above objectives, this application also proposes a computer-readable storage medium storing a task priority planning program for a robot, which, when executed by a processor, implements the steps of the task priority planning method for a robot as described in any of the preceding claims.

[0052] This invention proposes a task priority planning method for robots. This method determines the priority parameter of each task by combining the importance of each task among multiple tasks to be performed by the robot, as well as the importance of different task requirements information among the multiple task requirements information. Based on the determined priority parameters, the execution order of multiple tasks is determined. In this process, the priority of each task among multiple tasks is no longer a pre-set fixed parameter, but is determined by combining the importance of each task and the importance of different task requirements information. The combination of these two importance information can accurately represent the user's actual needs for task execution, thereby ensuring that the robot's multi-task execution process can closely match the user's actual needs, ensuring the satisfaction of user needs, and improving user experience. Attached Figure Description

[0053] Figure 1 This is a schematic diagram of the hardware structure involved in the operation of an embodiment of the robot of the present invention;

[0054] Figure 2 This is a flowchart illustrating an embodiment of the robot task priority planning method of the present invention;

[0055] Figure 3This is a flowchart illustrating another embodiment of the task priority planning method for the robot of the present invention;

[0056] Figure 4 This is a flowchart illustrating another embodiment of the task priority planning method for the robot of the present invention.

[0057] Figure 5 This is a flowchart illustrating another embodiment of the task priority planning method for the robot of the present invention.

[0058] Figure 6 This is a flowchart illustrating another embodiment of the task priority planning method for the robot of the present invention.

[0059] Figure 7 This is a schematic diagram of the multi-task priority planning process involved in a practical application example of the task priority planning method for the robot of the present invention.

[0060] The realization of the objective, functional features and advantages of the present invention will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0061] It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.

[0062] The main solution of this invention is to combine first importance information and second importance information to determine the priority parameter of each task among the multiple tasks that the robot needs to perform, and to determine the execution order of the multiple tasks based on the determined priority parameters. The second importance information represents the importance of the corresponding task requirement information among the multiple task requirement information, and the first importance information represents the importance of the corresponding task among the multiple tasks.

[0063] In existing technologies, robots typically execute multiple tasks in a pre-set, fixed priority order, ignoring the user's actual needs regarding task execution time, frequency, and other aspects. This results in the robot failing to meet the user's actual needs when executing multiple tasks according to a fixed priority, thus impacting the user experience.

[0064] The present invention provides the above-mentioned solution, which aims to enable the robot's multi-task execution process to be aligned with user needs, ensure the satisfaction of user needs, and improve user experience.

[0065] This invention proposes a robot, which can be any intelligent machine capable of semi-autonomous or autonomous task execution. Specifically, the robot can be a cleaning robot, a cooking robot, a service robot, etc. In this embodiment, the robot is specifically applied to an indoor setting (such as a home). In other embodiments, the robot can also be applied to outdoor environments.

[0066] Reference Figure 1 In addition to conventional automated operating devices, robots can also include at least two of the following functional modules: air supply module 1, cleaning module 2, prompting module 3 (such as an alarm clock), delivery module 4 (such as serving tea or water), assistance module 5 (such as an alarm module or emergency communication module), and charging module 6. Based on these various modules, the robot can perform multiple functions to execute different tasks according to user needs.

[0067] Specifically, refer to Figure 1 The robot may also include a control device. The aforementioned air supply module 1, cleaning module 2, prompting module 3, delivery module 4, and assistance module 5 can all be connected to this control device. The control device can acquire the operating parameters of each functional module among the air supply module 1, cleaning module 2, prompting module 3, delivery module 4, assistance module 5, and charging module 6, and can also control one or more modules among the air supply module 1, cleaning module 2, prompting module 3, delivery module 4, assistance module 5, and charging module 6 to operate sequentially according to actual needs.

[0068] In this embodiment of the invention, reference is made to Figure 1 The control device includes: a processor 1001 (e.g., CPU), a memory 1002, a timer 1003, etc. The memory 1002 can be a high-speed RAM or a stable memory (non-volatile memory), such as a disk storage device. Optionally, the memory 1002 can also be a storage device independent of the aforementioned processor 1001.

[0069] Those skilled in the art will understand that Figure 1 The device structure shown does not constitute a limitation on the device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0070] like Figure 1 As shown, the memory 1002, which is a computer-readable storage medium, may include a task prioritization planning program for the robot. Figure 1 In the device shown, the processor 1001 can be used to call the robot's task priority planning program stored in the memory 1002 and execute the relevant steps of the robot's task priority planning method in the following embodiments.

[0071] This invention also provides a task priority planning method for a robot, which is applied to the control of the aforementioned robot.

[0072] Reference Figure 2 This application proposes an embodiment of a task priority planning method for a robot. In this embodiment, the task priority planning method for the robot includes:

[0073] Step S10: Obtain first importance information for each of the multiple tasks to be executed by the robot, and obtain second importance information corresponding to the multiple task requirement information respectively; the first importance information represents the importance of the corresponding task in the multiple tasks, and the second importance information represents the importance of the corresponding task requirement information in the multiple task requirement information.

[0074] Specifically, the robot can receive preset instructions or determine multiple tasks to be performed at preset time points. After the tasks to be performed by the robot are determined, step S10 can be executed here.

[0075] In this embodiment, tasks are divided based on the functions the robot can perform, with different functions corresponding to different tasks. These functions can be pre-set system default functions or new functions formed by combining default functions based on user needs. In other embodiments, tasks can also be divided based on the user's actual needs.

[0076] Specifically, in this embodiment, the robot possesses the following functions: following air supply, cleaning, serving tea and water, alarm clock wake-up, returning to charging dock, and alarm / assist function. Based on this, all the tasks the robot can perform correspond to following air supply, cleaning, serving tea and water, alarm clock wake-up, returning to charging dock, and alarm / assist function.

[0077] The multiple tasks to be executed here can be determined by obtaining task instructions input by the user based on their needs. The user can select multiple functions that the robot needs to perform by inputting instructions, and the multiple tasks to be executed by the robot can be determined based on instruction analysis. For example, if the user selects the following air supply function, serving tea and water, and alarm clock wake-up function, then the multiple tasks to be executed can be determined as following air supply, serving tea and water, and alarm clock wake-up. In addition, in other embodiments, the multiple tasks to be executed can also be obtained by analyzing the robot's historical operation data; or, the identity information of the people in the space where the robot is located can be identified, and multiple corresponding tasks to be executed can be obtained based on this identity information; even moreover, the robot can learn the behavior of the users in its space and determine the multiple tasks to be executed based on behavior analysis.

[0078] Each task has its corresponding first importance information, which may include one piece of information or multiple sub-information. The first importance information can be set by the user, determined based on scene feature parameters of the robot's current environment, determined by preset rules, and the number and / or type of multiple tasks to be executed. It can also be obtained by analyzing large amounts of task execution data using a machine learning model. For example, each task can correspond to a preset value, and the first importance information can be determined by pairwise comparisons of multiple preset values ​​corresponding to multiple tasks to be executed.

[0079] Task requirement information specifically refers to the characteristic information that characterizes the task's own operational needs or the user's desired task execution state during execution. In this embodiment, task requirement information specifically includes the following items:

[0080] 1) Task execution level P: The urgency of the task execution. The more urgent the task, the higher the level.

[0081] 2) Task execution time T1: During which time of day will this task be executed?

[0082] 3) Execution duration T2: The time consumed from the start to the end of the task's execution.

[0083] 4) Task execution frequency N: The number of times the task is executed within a specified time period.

[0084] 5) Required resources E: Energy consumption (mainly electrical energy) required to execute this task.

[0085] In addition, in other embodiments, the task requirement information may include any two or more of the items mentioned above, and may even include other requirement information besides the various task requirement information listed above, such as the task execution object. Multiple task requirement information items may be pre-set default attribute information or information selected by the user.

[0086] The task requirements information for different tasks may be the same or different. In this embodiment, the task execution characteristics of each task are characterized using the same multiple task requirement information. In other embodiments, the task execution characteristics of each task can be characterized using different task requirement information.

[0087] Each task requirement has a corresponding second importance information. The second importance information can be set by the user, determined based on scene feature parameters of the robot's current scene, determined based on preset rules and the number and / or type of currently determined task requirements, or obtained by analyzing a large amount of task execution data through machine learning models.

[0088] Step S20: Determine the priority parameter of each task based on the first importance information and the second importance information;

[0089] Priority parameters are specifically feature parameters that characterize task priority.

[0090] The priority parameter for each task can be determined by the task's first importance information and the corresponding second importance information.

[0091] Different levels of primary importance and different levels of secondary importance can correspond to different priority parameters. Specifically, a correspondence between primary importance information, secondary importance information, and priority parameters can be established in advance. This correspondence can take the form of a calculation relationship, a mapping relationship, or an algorithm model, etc.

[0092] Based on this, the first importance information and the second importance information can be numerical values ​​that characterize the importance of the corresponding parameters. Then, by substituting the first importance information and the second importance information corresponding to each task into the pre-set calculation formula of the priority parameter, the result can be used as the priority parameter of the task.

[0093] In addition, if there is a mapping relationship between the first importance information, the second importance information and the priority parameter, the mapping relationship can be queried through the current first importance information and the second importance information of each task, and the matched value can be used as the priority parameter of the corresponding task.

[0094] Step S30: Determine the execution order of the plurality of tasks according to the priority parameter of each task;

[0095] Specifically, each task corresponds to a priority parameter, and multiple tasks can have multiple corresponding priority parameters.

[0096] The priority parameters are sorted sequentially, and the result is used as the execution order of the tasks. A higher priority parameter indicates an earlier task will be executed, while a lower priority parameter indicates a later task will be executed.

[0097] Furthermore, the robot can be controlled to perform the multiple tasks according to the execution order.

[0098] Specifically, the robot executes each of the multiple tasks in the order determined above.

[0099] In practical applications, if the multiple tasks to be executed include following air supply, cleaning and sweeping, and serving tea and water, and the priority parameter of cleaning and sweeping is greater than that of serving tea and water, and the priority parameter of serving tea and water is greater than that of following air supply, then the execution order of the multiple tasks to be executed can be determined as follows: cleaning and sweeping, serving tea and water, and following air supply. The robot will first execute the cleaning and sweeping task, then execute the serving tea and water task after completing the cleaning and sweeping task, and finally execute the following air supply task after completing the following air supply task.

[0100] This invention proposes a task priority planning method for robots. This method determines the priority parameter of each task by combining the importance of each task within the multiple tasks the robot needs to perform, as well as the importance of different task requirements within the overall task requirements. Based on the determined priority parameters, the execution order of the multiple tasks is determined. In this process, the priority of each task is no longer a pre-set fixed parameter, but is determined by combining the importance of each task and the importance of different task requirements. The combination of these two importance information accurately represents the user's actual needs for task execution, thereby ensuring that the robot's multi-task execution process aligns with the user's actual needs, guaranteeing user satisfaction, and improving user experience.

[0101] Furthermore, based on the above embodiments, another embodiment of the task priority planning method for the robot of this application is proposed. In this embodiment, the first importance information includes task importance information corresponding to multiple task requirement information, and the task importance information represents the importance of the task among the multiple tasks when the corresponding task requirement information is used as the evaluation criterion. That is, the number of task importance information corresponding to each task is the same as the number of task requirement information corresponding to that task. The same task may have different task importance information when different task requirement information is used as the evaluation criterion.

[0102] Specifically, in this embodiment, the number and type of task requirement information corresponding to each task are the same. For example, P, T1, T2, N, and E mentioned in the above embodiment can each be considered as multiple task requirement information corresponding to each task. Based on this, the multiple task importance information corresponding to each task includes first task importance information L1 based on P, second task importance information L2 based on T1, third task importance information L3 based on T2, fourth task importance information L4 based on N, and fifth task importance information L5 based on E.

[0103] Based on this, refer to Figure 3 Step S20 includes:

[0104] Step S21: Determine the weight value of the task importance information corresponding to each task requirement information based on the second importance information;

[0105] Specifically, the second most important information in a task requirement corresponds to a weight value. Based on this, each task corresponds to multiple task requirement information pieces, and each task has a weight value equal to the number of task requirement information pieces.

[0106] In this embodiment, the second importance information is a numerical value representing the importance of the corresponding task requirement information among all task requirement information. Based on this, the second importance information can be directly used as the corresponding weight value; alternatively, the normalized results of all second importance information can be used as the corresponding weight values. In other embodiments, if the second importance information is information that cannot be calculated other than numerical values ​​(such as text), the second importance information can be parsed according to pre-defined rules to obtain the corresponding representation value, which can be directly used as the corresponding weight value; alternatively, the normalized results of all representation values ​​can be used as the corresponding weight values. The sum of the multiple weight values ​​corresponding to each task is 1.

[0107] Step S22: Calculate the priority parameter of each task based on the multiple task importance information corresponding to each task and the weight value of each task importance information.

[0108] In this embodiment, the task importance information is a numerical value representing the importance of a task with its corresponding task requirement information as the evaluation benchmark among all tasks. The result of weighted averaging of multiple task importance information according to the weight value corresponding to each task importance information can be used as the priority parameter.

[0109] Based on the aforementioned task requirement information P, T1, T2, N, and E, the second importance information corresponding to each task requirement information is m1, m2, m3, m4, and m5, respectively. The first importance information for each task includes L1, L2, L3, L4, and L5, as mentioned above. Therefore, the priority parameter X for each task is X = L1. m1+ L 2 m2+ L 3 m3+ L 4 m4+ L5 m5. In other embodiments, when there is more or fewer task requirements or tasks than described herein, priority parameters may be calculated in a manner analogous to that mentioned herein.

[0110] In this embodiment, multiple task importance information obtained using different task requirement information as a benchmark are used to evaluate the importance of a certain task among all tasks. Based on this, the importance of each task requirement information is combined as the weight corresponding to each task importance information, thereby calculating the priority parameter for each corresponding task. Based on this, the obtained priority parameter can accurately reflect the impact of different task requirement information on task importance, thus ensuring the accuracy of the determined priority parameter. This ensures that the robot controlled by the obtained priority parameter performs multi-task processes more closely with the actual needs of users, ensuring the satisfaction of user needs and improving user experience.

[0111] Furthermore, based on any of the above embodiments, another embodiment of the task priority planning method for the robot of this application is proposed. In this embodiment, referring to... Figure 4 The process of obtaining the second importance information corresponding to the multiple task requirement information in step S10 is as follows:

[0112] Step S11: Obtain the first importance relationship corresponding to the multiple task requirement information; the first importance relationship represents the relative importance between any two task requirement information pieces.

[0113] The first importance relationship can be a mapping table or a relational expression. Specifically, the first importance relationship can be determined by comparing the importance of any two task requirement pieces from multiple task requirement information.

[0114] The first importance relationship can be determined based on user-defined parameters, or it can be determined by training a machine learning model with a large amount of task execution data, inputting multiple task requirement information based on the trained algorithm model, and using the output of the algorithm model as the first importance relationship.

[0115] Step S12: Determine the second importance information corresponding to each task requirement information according to the first importance relationship.

[0116] Based on the first importance relationship, the relative importance of each task requirement information to every other task requirement information can be determined. Based on this, the representation value of the importance of each task requirement information in all task requirement information can be determined, and the determined representation value can be used as the second importance information corresponding to that task requirement information.

[0117] In this embodiment, the second importance information is determined based on the first importance relationship between pairs of information representing the relative importance of all task requirement information. This ensures that the determined second importance can accurately represent the importance of each task requirement information among multiple task requirement information, thereby further improving the accuracy of robot multi-task planning and ensuring that the robot can accurately meet user needs according to the planned multi-task execution process.

[0118] Specifically, in this embodiment, the first importance relationship includes multiple first relationship values, and in this embodiment, each first relationship value is less than 1. The first relationship value characterizes the importance of one task requirement information relative to another task requirement information. Comparing the importance of any two task requirement information yields two first relationship values. Specifically, the two task requirement information to be compared are defined as the first task requirement information and the second task requirement information, respectively. Comparing the importance of the first task requirement information and the second task requirement information yields a first relationship value for the importance of the first task requirement information relative to the second task requirement information, and another first relationship value for the importance of the second task requirement information relative to the first task requirement information. Based on this, step S12 includes:

[0119] Step S121: Determine a first feature value corresponding to each of the task requirement information, wherein the first feature value is the sum of multiple first relationship values ​​corresponding to the task requirement information;

[0120] Each task requirement has a corresponding first feature value. Specifically, the total number of task requirement pieces of information is the same as the number of first relation values ​​corresponding to each task requirement piece of information. The multiple first relation values ​​corresponding to each task requirement piece of information are the set of first relation values ​​corresponding to that task requirement piece of information relative to the first relation values ​​corresponding to each other task requirement piece of information.

[0121] The first eigenvalue specifically represents the importance of the task requirement information relative to all other task requirement information.

[0122] Step S122: Determine the sum of all first relation values ​​in the first importance relation as the second feature value;

[0123] Specifically, multiple task requirement information corresponds to multiple first feature values, and the sum of all first feature values ​​corresponding to all task requirement information is the second feature value here.

[0124] Step S123: Determine the second importance information corresponding to each task requirement information based on the first feature value and the second feature value.

[0125] In this embodiment, the ratio of the first feature value to the second feature value corresponding to each task requirement information is used as the second importance information corresponding to that task requirement information. In other embodiments, the difference between the first feature value and the second feature value corresponding to each task requirement information is used as the second importance information corresponding to that task requirement information.

[0126] Specifically, in this embodiment, the first importance relationship is a fuzzy matrix. Specifically, to improve the convenience of determining the second importance information and ensure the efficiency of acquiring the second importance information, the first importance relationship can be a fuzzy consistent matrix. In addition, in other embodiments, the first importance relationship can also be other types of fuzzy matrices.

[0127] The definition of the fuzzy matrix is ​​as follows:

[0128] Let matrix If the following conditions are met:

[0129] ( );

[0130] Then matrix F is called a fuzzy matrix.

[0131] If, based on the fuzzy matrix, the following conditions are met... have:

[0132]

[0133] The fuzzy matrix F is then called the fuzzy consistent matrix.

[0134] Therefore, when When, i and j are considered equally important; when At that time, j was considered more important than i; when At that time, it was considered that i was more important than j.

[0135] For the five task requirements P, T1, T2, N, and E above, perform pairwise comparisons to determine the relative importance of each requirement. For example, the importance of task execution level P relative to task execution time T1 is 1, the importance of the resources required for execution E relative to task execution frequency N is 0.55, ..., thus obtaining 25 combinations. The fuzzy consistent matrix F constructed from the obtained relative importance results can be used as the first importance relationship, as shown in the following example:

[0136]

[0137] Based on this, the values ​​in each row of matrix F represent all the first relation values ​​corresponding to a task requirement information. Therefore, the sum of all values ​​in each row is the first feature value corresponding to the task requirement information in that row. For example, if i represents the row, j represents the column, and fij is the first relation value in row i and column j, then the first feature value of task requirement information P = f11 + f12 + f13 + f14 + f15 = 0.5 + 1 + 1 + 1 + 1 = 4.5. The first feature values ​​of other task requirement information can be determined analogously to the method used to determine the first feature value of P. Similarly, when changes in the quantity or importance of task requirement information lead to changes in the first importance relation, the method used to determine the first feature value of P can also be used. The sum of all values ​​in matrix F can be used as the second feature value.

[0138] In this embodiment, the second importance information is determined using a first feature value and a second feature value. This ensures that the determined second importance information accurately reflects the proportion of importance of each task requirement information among all task requirements information, thereby guaranteeing the accuracy of multi-task planning. Furthermore, using a fuzzy matrix to determine the second importance information ensures that the determination process simulates the user's actual task planning process, thus ensuring that the execution order of multiple tasks determined based on the determined second importance information more closely matches the user's actual needs.

[0139] Furthermore, based on any of the above embodiments, another embodiment of the task priority planning method for the robot of this application is proposed. In this embodiment, referring to... Figure 5 The first importance information includes task importance information corresponding to multiple task requirement information. The task importance information represents the importance of the task among the multiple tasks when the corresponding task requirement information is used as the evaluation benchmark. The process of obtaining the first importance information of each task among the multiple tasks to be executed by the robot in step S10 is as follows:

[0140] Step S13: Obtain the second importance relationship corresponding to each task requirement information; the second importance relationship represents the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation benchmark.

[0141] Each task requirement corresponds to a second degree of importance.

[0142] The second importance relationship can be a mapping table or a relational expression. Specifically, the second importance relationship can be determined by comparing the importance of any two tasks from multiple tasks.

[0143] The second importance relationship can be determined based on user-defined parameters; alternatively, it can be determined by training a machine learning model with a large amount of task execution data, inputting the trained algorithm model into multiple tasks, and using the output of the algorithm model as the second importance relationship; in addition, the second importance relationship can also be determined based on the degree of matching between the target state parameters corresponding to the task requirement information and the actual running scenario.

[0144] Step S14: Determine multiple task importance information corresponding to each task based on multiple second importance relationships.

[0145] Based on the second importance relationship, the relative importance of each task to every other task can be determined when different task requirement information is used as the standard evaluation. Based on this, a representation value of the task's importance among all tasks under the evaluation of each task requirement information can be determined. This determined representation value can be used as the task importance information corresponding to a specific task under the evaluation of that task requirement information. By classifying multiple task importance information based on tasks, multiple task importance information corresponding to each task can be determined.

[0146] In this embodiment, the first importance information is determined based on the second importance relationship between the relative importance of each pair of tasks under the evaluation of a certain task requirement information. This ensures that the determined first importance information can accurately represent the importance of each task in multiple tasks when different requirement information is used as the evaluation benchmark, thereby further improving the accuracy of robot multi-task planning and ensuring that the robot can accurately meet user needs according to the planned multi-task execution process.

[0147] The second importance relationship includes multiple second relationship values. Each second relationship value represents the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation criterion. In this embodiment, each first relationship value is less than 1. When any task requirement information is used as the evaluation criterion, comparing the importance of any two tasks yields two second relationship values. Specifically, the two tasks to be compared are defined as the first task and the second task, respectively. Comparing the importance of the first task and the second task yields a second relationship value representing the importance of the first task relative to the second task, and another second relationship value representing the importance of the second task relative to the first task. Based on this, step S14 includes:

[0148] Step S141: In each of the second importance relations, determine the third feature value corresponding to each task, and determine the sum of all second relation values ​​as the fourth feature value; the third feature value is the sum of multiple second relation values ​​corresponding to each task.

[0149] Each second importance relation corresponds to a set of eigenvalues ​​consisting of multiple third eigenvalues. The number of third eigenvalues ​​in each set of eigenvalues ​​corresponding to each second importance relation is the same as the total number of tasks. The amount of task requirement information is the same as the number of eigenvalue sets.

[0150] The third eigenvalue represents the importance of a task relative to all other tasks when the corresponding task requirement information is used as the evaluation benchmark. The eigenvalue set represents the importance of each task relative to all other tasks when the corresponding task requirement information is used as the evaluation benchmark.

[0151] The sum of all third eigenvalues ​​corresponding to each second importance relation is the fourth eigenvalue. Each second importance relation corresponds to one fourth eigenvalue. The number of task requirement information items is the same as the number of second importance relations, and the number of second importance relations is the same as the number of fourth eigenvalues.

[0152] Step S142: Determine the importance information of multiple tasks corresponding to each task based on the third feature value and the fourth feature value;

[0153] Based on the third and fourth eigenvalues ​​corresponding to each second importance relation, the importance of different tasks relative to all tasks can be determined when the corresponding task requirement information is used as the evaluation benchmark. If there are n tasks, then the importance values ​​determined by the third and fourth eigenvalues ​​corresponding to a single second importance relation will be n. By classifying these multiple importance values ​​based on tasks among all the multiple importance values ​​corresponding to all second importance relations, multiple importance values ​​corresponding to each task can be obtained when different task requirement information is used as the evaluation benchmark. These can serve as multiple task importance information for each task.

[0154] Specifically, in this embodiment, the second importance relationship is a fuzzy matrix. Specifically, to improve the convenience of determining the first importance information and ensure the efficiency of acquiring the first importance information, the second importance relationship can be a fuzzy consistent matrix. In addition, in other embodiments, the second importance relationship can also be other types of fuzzy matrices. The relevant definition of fuzzy matrices can be found in the above embodiments. The process of obtaining the matrix and determining the third and fourth eigenvalues ​​can also be analogous to the relevant processes of the matrix, first eigenvalue, and second eigenvalue described above.

[0155] In this embodiment, the first importance information is determined by combining the third and fourth eigenvalues ​​corresponding to each second importance relationship. This ensures that the determined first importance information accurately reflects the proportion of each task requirement information to the importance of a particular task among all tasks, thereby guaranteeing the accuracy of multi-task planning. Furthermore, using a fuzzy matrix to determine the first importance information ensures that the determination process simulates the user's actual task planning process, thus ensuring that the execution order of multiple tasks determined based on the determined first importance information more closely matches the user's actual needs.

[0156] Furthermore, one of the multiple tasks is a help-seeking operation. Before determining a third feature value corresponding to each task in each of the second importance relationships, and determining the sum of all second relationship values ​​as a fourth feature value, the method further includes: obtaining the personnel type within the robot's space; if the personnel type is a target type, adjusting the second relationship value corresponding to the help-seeking operation in each of the second importance relationships so that the second relationship value corresponding to the help-seeking operation in each of the second importance relationships is greater than the second relationship values ​​corresponding to other tasks in the multiple tasks. Specifically, the personnel type can be determined by obtaining user input instructions or automatically identified by a human detection module set on the robot. The target type is specifically a personnel type whose probability of using the help-seeking operation is greater than a set threshold. In this embodiment, the target type specifically includes the elderly and / or children.

[0157] Therefore, when the robot detects that there are elderly people and children in the space, increasing the relative importance of the help-seeking task compared to other tasks helps ensure that the robot can quickly respond to and handle the emergency needs of vulnerable groups, improve user safety, solve real family problems, and increase the utilization rate of home service robots.

[0158] Specifically, in this embodiment, the step of obtaining the second importance relationship corresponding to each task requirement information includes:

[0159] Step S131: Detect the current scene feature parameters of the scene where the robot is located based on the task requirement information, and obtain the target state parameters of different tasks corresponding to each task requirement information; the target state parameters represent the feature parameters of the target state that the robot needs to achieve when performing the corresponding task.

[0160] Specifically, different task requirements correspond to different scene feature parameters for detection. Based on this, the detection type of scene feature parameters for each task requirement can be determined, and the robot can be controlled to detect the scene feature parameters in its current space based on the detection type.

[0161] For example, the scene feature parameter corresponding to T1 above is the current time detected by the clock on the robot; the scene feature parameter corresponding to N above is the number of tasks that the robot has completed within a preset time period; the scene feature parameter corresponding to E above is the type of energy that the robot can currently use, and so on.

[0162] Different task requirements correspond to different types of target state parameters. For example, the target state parameter corresponding to T1 above is the target time period for task execution; the target state parameter corresponding to N above is the number of times the task will be executed within a preset time period; and the target state parameter corresponding to E above is electrical energy. Different tasks correspond to different values ​​of the target state parameters.

[0163] The target state parameters can be set by the user through input commands, or they can be obtained by analyzing the user's preference data for using the robot to perform tasks.

[0164] Specifically, in this embodiment, to simplify user operation and improve the robot's intelligence, the step of obtaining the target state parameters for different tasks corresponding to each task requirement information includes: obtaining historical state data corresponding to each task requirement information during the robot's execution of each task; detecting the historical state data within a preset time period before the current moment; and determining the target state parameters for different tasks corresponding to each task requirement information based on the historical state data. The length of the preset time period can be set according to actual needs. Specifically, within the preset time period, data can be collected during the robot's task execution based on the task requirement information to obtain the historical state data. Statistical analysis of the historical state data can then yield the target state parameters for different tasks under different task requirement information. Specifically, the average or most frequently occurring value of the historical data corresponding to each task requirement information can be used as the target state parameter. For example, a home service robot has the following functions: ① following and blowing air ② cleaning and sweeping ③ serving tea and water ④ alarm clock wake-up ⑤ returning to charging dock ⑥ alarm and assistance, etc. For each function, historical data corresponding to each of the above task requirement information P, T1, T2, N, and E can be statistically analyzed based on the usage of the robot in the past week.

[0165] Step S132: Determine the deviation value between the target state parameter and the scene feature parameter corresponding to each task;

[0166] If the target state parameters match the scene feature parameters, it indicates that the task is of high importance in the current state; if the target state parameters do not match the scene feature parameters, it indicates that the task is of low importance in the current state. The larger the deviation value, the lower the importance of the corresponding task.

[0167] Step S133: Determine the second importance relationship based on the deviation value of different tasks corresponding to each of the task requirement information.

[0168] The deviation values ​​are categorized based on task requirement information, and then further categorized based on the task to obtain the deviation values ​​of different task requirement information in different tasks. Based on this, pairwise comparisons of the deviation values ​​of different tasks corresponding to each task requirement information can determine the relative importance between any two tasks under each task requirement information. Further numerical representation can then yield the second degree of importance relationship.

[0169] In this embodiment, a second importance relationship is generated based on the deviation between the actual scene and the target state corresponding to each task requirement information. This ensures that the determined second importance relationship more accurately reflects the task execution requirements of the robot in the current scene, thereby ensuring that the execution order determined based on the second importance relationship is more accurate and better meets the actual needs of the user in the current space, thus improving the user experience.

[0170] Furthermore, based on any of the above embodiments, after step S30, the method further includes: receiving a change instruction for the execution order, determining the target execution order corresponding to the change instruction; updating the first importance relationship or the second importance relationship according to the target execution order; and returning to the execution step S10. Specifically, user feedback is recorded when the home service robot executes multiple tasks sequentially. That is, if there are currently tasks 1, 2, 3, etc., after task priority planning is performed in the manner mentioned in the above embodiments, the home service robot normally executes tasks in the order corresponding to the priority. If the user does not provide feedback to change the task order during the task execution, the current priority parameters are maintained, and multiple tasks are executed sequentially in the current order. If the user changes the task order during the task execution, the modified task order is analyzed according to the actual state parameters of the task requirement information, the actual state parameters corresponding to the task requirement information of the modified task order are compared, the values ​​in the fuzzy consistency matrix are changed, and the priority parameters are recalculated in the manner described above. Based on the order corresponding to the re-obtained priority parameters, the robot is controlled to execute tasks. Based on this, if the task execution sequence planned by the robot fails to meet the user's actual needs, the user can correct it by inputting a sequence change command. The correction process is also the process of the robot optimizing its own planning rules, thereby ensuring that the robot's task execution process is more in line with the user's actual needs.

[0171] Furthermore, based on any of the above embodiments, another embodiment of the task priority planning method for the robot of this application is proposed. In this embodiment, referring to... Figure 6Define one of the plurality of tasks as the first task, define the other of the plurality of tasks as the second task, and after step S30, further include:

[0172] Step S50: During the process of the robot performing the first task, the robot receives the execution instruction of the second task and obtains the first priority parameter, the second priority parameter, and the current completion status of the first task; the first priority parameter is the priority parameter corresponding to the first task, and the second priority parameter is the priority parameter corresponding to the second task.

[0173] The first priority parameter and the second priority parameter here are task priority parameters determined based on the aforementioned steps S10 to S30 and their related detailed processes.

[0174] The degree of completion can be determined by obtaining the status parameters input by the user, or by detecting the status of the task execution object, the status of the task execution scenario, or the actual operation of the robot during the task execution process.

[0175] Step S60: Determine the recognition result based on the first priority parameter, the second priority parameter, and the completion rate. The recognition result includes whether the first task is interrupted.

[0176] Different first-priority parameters, completion rates, and second-priority parameters correspond to different recognition results. A pre-established correspondence between the first-priority parameters, completion rates, and second-priority parameters can be established. This correspondence can be a direct mapping between these four parameters, or an indirect correspondence between feature parameters and recognition results determined based on the first-priority parameters, completion rates, and second-priority parameters. Based on this correspondence, it can be determined whether the currently executing first task needs to be interrupted using the first-priority parameters, completion rates, and second-priority parameters.

[0177] Step S70: Adjust the execution order according to the recognition result.

[0178] Different recognition results correspond to different adjustments to the execution order. Specifically, if the recognition result is to interrupt the first task, then the second task will be the first task to be executed, and the first task will be the next task to be executed after the second task; if the recognition result is to not interrupt the first task, then the first task will be the first task to be executed, and the second task will be the next task to be executed after the first task is completed.

[0179] After the execution order is adjusted, the robot can be controlled to perform multiple tasks according to the adjusted execution order.

[0180] In this embodiment, when a user needs to temporarily insert a task, the first priority parameter, completion rate, and second priority parameter are combined to determine whether to interrupt the currently executing task. This ensures that the task execution selection process is more in line with the user's own task planning, and that the task execution is more in line with the user's actual needs and the current task execution status, thus satisfying both task execution efficiency and user needs.

[0181] Furthermore, in this embodiment, step S60 includes: determining the parameter difference between the first priority parameter and the second priority parameter; calculating the target parameter based on the parameter difference and its corresponding first weight, the completion degree and its corresponding second weight; determining that the identification result is not to interrupt the first task when the target parameter is greater than a set threshold; and determining that the identification result is to interrupt the first task when the target parameter is less than or equal to the set threshold.

[0182] The first and second weights can be system default parameters or user-defined parameters. The first weight specifically represents the weight for prioritizing the execution of temporary tasks, while the second weight specifically represents the weight for prioritizing the completion of the current task.

[0183] Specifically, the progress of the current task is estimated to obtain the completion degree c( If task S is currently executing and has not yet finished, and the user temporarily assigns task T, then the difference in priority parameters between task T and S is calculated. .Will Normalizing with c, we get:

[0184] , ;

[0185] Weights a and b are set to weigh prioritizing temporary tasks versus prioritizing completion rates, and the task interruption index m is calculated:

[0186] ;

[0187] If m is greater than a certain set threshold, then temporary task T is scheduled after task S. After task S is completed, temporary task T will be executed. If m is less than or equal to a certain set threshold, then temporary task T is inserted before task S. Temporary task T is executed first. After task T is completed, task S will be executed again.

[0188] Here, the target parameter represents whether to interrupt the first task, thereby ensuring that it accurately reflects the user's priority selection needs for the current task and temporary task in the current state, and ensuring that the selection and execution of tasks can be accurately matched with the user's actual needs, thus further improving the user experience.

[0189] Furthermore, this invention also proposes a computer-readable storage medium storing a robot task priority planning program. When the robot task priority planning program is executed by a processor, it implements the relevant steps of any of the above embodiments of the robot task priority planning method.

[0190] Furthermore, to facilitate understanding of the robot task priority planning method involved in the above embodiments, combined with Figure 7 The following is a practical application example of the solution involved in the above embodiments:

[0191] 1. The functions of a certain home service robot are: ① following and blowing air ② cleaning and sweeping ③ serving tea and water ④ waking up with an alarm clock ⑤ returning to the charging dock ⑥ alarm and request assistance. Based on the task characteristics (i.e. the above multiple task requirements information), the characteristic data of the above tasks are statistically analyzed based on the usage data of the past week.

[0192] 2. The user sets the relative importance of the features (i.e., the multiple task requirement information mentioned above). Simultaneously, the home service robot assesses the user's home environment, using facial recognition to determine if there are elderly people or children in the home (i.e., whether the people in the space are the target type). If so, the importance of the alarm and assistance function (⑥) relative to other functions is increased. The fuzzy consistency matrix (i.e., the first importance relationship mentioned above) corresponding to the task features (i.e., the multiple task requirement information mentioned above) is calculated step by step. To simplify the calculation, three features P, T1, and T2 are used here for explanation.

[0193]

[0194] Calculating the sum of the elements in each row of the matrix (i.e., the first eigenvalue mentioned above), we can obtain...

[0195]

[0196] Normalizing it, we get W = (0.378, 0.389, 0.233), where 0.378 is the second importance information corresponding to P, 0.389 is the second importance information corresponding to T1, and 0.233 is the second importance information corresponding to T2.

[0197] 3. Taking three tasks as an example, assuming the user assigns the tasks "follow-up ventilation", "cleaning", and "serving tea and water", determine the fuzzy consistency matrix (second importance relationship) of these three tasks under the five task features.

[0198] Under task execution level P, we obtain matrix A1 (the second importance relationship corresponding to P):

[0199]

[0200] (Explanation: The value of 0.8 in the second row and first column of the matrix indicates that, under the execution level P, the execution level of cleaning and sweeping is compared with that of following air supply, and cleaning and sweeping is considered more important than following air supply, with a relative importance of 0.8.)

[0201] Following the calculation process in step 2, the weights are calculated as follows: Here, 0.311 represents the task importance information corresponding to air supply when P is the evaluation benchmark; 0.378 represents the task importance information corresponding to cleaning when P is the evaluation benchmark; and 0.311 represents the task importance information corresponding to serving tea and water when P is the evaluation benchmark.

[0202] Given task execution time T1, assume the service robot's statistics on user usage over a week are as follows:

[0203] 1) Follow-up air supply 14:00~16:00, T1 corresponding to the target state parameters of the follow-up air supply;

[0204] 2) Cleaning and sweeping 20:00~21:00, T1 corresponds to the target status parameters of cleaning and sweeping;

[0205] 3) Target state parameters for serving tea and water during 8:00~8:30, 12:00~12:30, and 18:00~18:30, corresponding to T1;

[0206] If the current actual time is 11:30 (i.e., the scene feature parameter corresponding to T1), then by comparing this time with the statistically obtained time, matrix A2 (the second importance relationship corresponding to T1) is obtained:

[0207]

[0208] (Explanation: The 1 in the third row and first column of the matrix indicates that, under the characteristic of task execution time T1, 11:30 is closer to the usual time for serving tea and water, which is 12:00~12:30. Therefore, serving tea and water is considered more important than following the delivery of air at this time, and its relative importance is 1.)

[0209] Following the calculation process in step 2, the weights are calculated as follows: Here, 0.289 represents the task importance information corresponding to air supply when T1 is the evaluation benchmark; 0.222 represents the task importance information corresponding to cleaning when T1 is the evaluation benchmark; and 0.489 represents the task importance information corresponding to serving tea and water when T1 is the evaluation benchmark.

[0210] Similarly, we can obtain matrix A3 (the second importance relationship corresponding to T2):

[0211]

[0212] Following the calculation process in step 2, the weights are calculated as follows: Here, 0.333 represents the task importance information corresponding to air supply when T2 is used as the evaluation benchmark; 0.222 represents the task importance information corresponding to cleaning when T2 is used as the evaluation benchmark; and 0.445 represents the task importance information corresponding to serving tea and water when T2 is used as the evaluation benchmark.

[0213] 4. The weight coefficients of the three tasks relative to the three features are obtained by weighting with W.

[0214] Priority parameters for air supply

[0215] Cleaning priority parameters

[0216] Priority parameters for serving tea and water

[0217] Based on the sizes of x1, x2, and x3, it is easy to obtain the task execution order as {"Serving tea and water": 0.411, "Following the air supply": 0.311, "Cleaning and sweeping": 0.285}.

[0218] If the actual time is 22:00, then matrix A2 will change.

[0219]

[0220] Following the calculation process in step 2, the weights are calculated as follows:

[0221] Recalculate the weighted average

[0222] Priority parameters for air supply

[0223] Cleaning priority parameters

[0224] Priority parameters for serving tea and water

[0225] Based on the sizes of x1, x2, and x3, it is easy to obtain the task execution order as {"Cleaning and sweeping": 0.402, "Following air supply": 0.311, "Serving tea and water": 0.290}.

[0226] As can be seen from the example above, the same task can lead to different planning results under different circumstances. The results also show that, given the difference in execution time, the priority task obtained by the robot through planning is more in line with the user's past habits, which is more in line with human thinking.

[0227] 5. If the robot is currently performing "cleaning" and the user assigns a temporary task "serving tea and water," calculate the task interruption index and adjust the task order accordingly. For example, assuming weights a=0.4, b=0.6, and a threshold of 0.55, if the home service robot is performing "cleaning" and is 95% complete, but the user assigns a temporary task "serving tea and water," calculate the difference in weights between the two tasks.

[0228]

[0229] Normalized to a completion rate of 0.95, we get:

[0230] ,

[0231] Calculate the interruption index

[0232]

[0233] In this case, prioritize "cleaning and sweeping" until it ends, and then proceed with "serving tea and water".

[0234] If the "cleaning" process is 50% complete at this point, then m = 0.547 < 0.55.

[0235] In this case, the temporary task "serving tea and water" will be executed first, and then the task "cleaning and sweeping" will be executed.

[0236] (This also aligns with human nature. If a temporary task is not urgent and the task at hand is almost finished, people will generally finish the task at hand first before doing the temporary task.)

[0237] 6. If the user does not provide feedback after the home service robot has finished performing its tasks, it means that the execution was correct and met the user's expectations. If the user requests a change in the task order, such as changing task 4 to {"following air supply", "cleaning and sweeping", "serving tea and water"}, then the task characteristics (i.e., the data corresponding to the task requirements information) of the task "cleaning and sweeping" and "serving tea and water" are compared. The fuzzy consistency matrix mentioned above is then modified accordingly so that the weights calculated are more consistent with the order of "cleaning and sweeping" first and "serving tea and water" last.

[0238] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or system that includes that element.

[0239] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0240] Through the above description of the embodiments, those skilled in the art can clearly understand that the methods of the above embodiments can be implemented by means of software plus necessary general-purpose hardware platforms. Of course, they can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) as described above, and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, robot, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0241] The above are merely preferred embodiments of the present invention and do not limit the patent scope of the present invention. Any equivalent structural or procedural transformations made based on the content of the present invention's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of the present invention.

Claims

1. A task priority planning method for a robot, characterized in that, The robot's task priority planning method includes the following steps: The robot obtains first importance information for each of the multiple tasks to be executed by the robot, and obtains second importance information corresponding to the multiple task requirement information respectively. The first importance information includes task importance information corresponding to the multiple task requirement information respectively. The task importance information represents the importance of the task in the multiple tasks when the corresponding task requirement information is used as the evaluation benchmark. The second importance information represents the importance of the corresponding task requirement information in the multiple task requirement information. The priority parameter for each task is determined based on the first importance information and the second importance information; The execution order of the plurality of tasks is determined based on the priority parameter of each task; The step of obtaining the first importance information of each of the multiple tasks to be performed by the robot includes: Obtain the second importance relationship corresponding to each of the task requirement information; the second importance relationship represents the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation benchmark; Based on multiple second importance relationships, determine multiple task importance information corresponding to each task.

2. The robot task priority planning method as described in claim 1, characterized in that, The step of determining the priority parameter of each task based on the first importance information and the second importance information includes: Based on the second importance information, determine the weight value of the task importance information corresponding to each of the task requirement information; The priority parameter of each task is calculated based on the multiple task importance information corresponding to each task and the weight value of each task importance information.

3. The robot task priority planning method as described in claim 1, characterized in that, The step of obtaining the second importance information corresponding to the multiple task requirement information includes: Obtain the first importance relationship corresponding to the multiple task requirement information; the first importance relationship represents the relative importance between any two of the task requirement information. The second importance information corresponding to each task requirement information is determined based on the first importance relationship.

4. The robot task priority planning method as described in claim 3, characterized in that, The first importance relationship includes multiple first relationship values, each representing the importance of one task requirement piece of information relative to another. The step of determining the second importance information corresponding to each task requirement piece of information based on the first importance relationship is as follows: Determine a first feature value corresponding to each of the task requirement information, wherein the first feature value is the sum of multiple first relationship values ​​corresponding to the task requirement information; The sum of all first relation values ​​in the first importance relation is determined as the second feature value; The second importance information corresponding to each task requirement information is determined based on the first feature value and the second feature value; And / or, the first importance relationship is a fuzzy matrix.

5. The robot task priority planning method as described in claim 1, characterized in that, The second importance relationship includes multiple second relationship values, which represent the relative importance between any two tasks when the corresponding task requirement information is used as the evaluation benchmark. The step of determining multiple task importance information corresponding to each task based on multiple second importance relationships is as follows: In each of the second importance relations, a third feature value is determined for each task, and the sum of all second relation values ​​is determined as a fourth feature value; The third feature value is the sum of multiple second relationship values ​​corresponding to each task; Based on the third feature value and the fourth feature value, determine the importance information of multiple tasks corresponding to each task; And / or, the second importance relationship is a fuzzy matrix.

6. The robot task priority planning method as described in claim 5, characterized in that, One of the multiple tasks is a help request operation. In each of the second importance relationships, a third feature value is determined for each of the tasks, and the sum of all the second relationship values ​​is determined as a fourth feature value. Before the step of stating that the third feature value is the sum of multiple second relation values ​​corresponding to each task, the method further includes: Obtain the types of people in the space where the robot is located; If the personnel type is the target type, then adjust the second relationship value corresponding to the help request operation in each second importance relationship so that the second relationship value corresponding to the help request operation in each second importance relationship is greater than the second relationship value corresponding to other tasks in the plurality of tasks.

7. The robot task priority planning method as described in claim 1, characterized in that, The step of obtaining the second importance relationship corresponding to each of the task requirement information includes: Based on the task requirement information, detect the current scene feature parameters of the scene in which the robot is located, and obtain the target state parameters of different tasks corresponding to each task requirement information; the target state parameters represent the feature parameters of the target state that the robot needs to achieve when performing the corresponding task. Determine the deviation value between the target state parameter and the scene feature parameter corresponding to each task; The second importance relationship is determined based on the deviation value of different tasks corresponding to each of the task requirement information.

8. The robot task priority planning method as described in claim 7, characterized in that, The step of obtaining the target state parameters of different tasks corresponding to each task requirement information includes: The robot acquires historical state data corresponding to each task requirement information during the execution of each task; the historical state data is detected within a preset time period prior to the current moment. Based on the historical state data, the target state parameters for each of the different tasks corresponding to each task requirement information are determined.

9. The task priority planning method for robots as described in claim 1, characterized in that, The step of determining the execution order of the plurality of tasks based on the priority parameter of each task, taken concurrently with or after the step of determining the execution order of the plurality of tasks, further includes: Receive the instruction to change the execution order, and determine the target execution order corresponding to the instruction to change the execution order; Update the first importance relationship or the second importance relationship according to the execution order of the objectives; Return to the steps of obtaining the first importance information of each of the multiple tasks to be executed by the robot, and obtaining the second importance information corresponding to the requirements of the multiple tasks respectively.

10. The task priority planning method for a robot as described in any one of claims 1 to 9, characterized in that, Define one of the plurality of tasks as a first task, define another of the plurality of tasks as a second task, and after the step of determining the execution order of the plurality of tasks according to the priority parameter of each of the tasks, the method further includes: During the execution of the first task by the robot, the robot receives the execution instruction for the second task, and obtains a first priority parameter, a second priority parameter, and the current completion status of the first task; the first priority parameter is the priority parameter corresponding to the first task, and the second priority parameter is the priority parameter corresponding to the second task. The identification result is determined based on the first priority parameter, the second priority parameter, and the completion rate, and the identification result includes whether the first task is interrupted. The execution order is adjusted based on the identification results.

11. The task priority planning method for robots as described in claim 10, characterized in that, The step of determining the recognition result based on the first priority parameter, the second priority parameter, and the completion rate includes: Determine the parameter difference between the first priority parameter and the second priority parameter; The target parameters are calculated based on the parameter differences and their corresponding first weights, and the completion degree and its corresponding second weights. If the target parameter is greater than the set threshold, then the recognition result is determined to be that the first task will not be interrupted; If the target parameter is less than or equal to the set threshold, then the identification result is determined to interrupt the first task.

12. A robot, characterized in that, The robot includes: a memory, a processor, and a task priority planning program for the robot stored in the memory and executable on the processor. When the task priority planning program for the robot is executed by the processor, it implements the steps of the task priority planning method for the robot as described in any one of claims 1 to 11.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a task priority planning program for a robot, which, when executed by a processor, implements the steps of the task priority planning method for a robot as described in any one of claims 1 to 11.

Images