Robot decision-making method, robot decision-making system, and robot

Abstract

The application discloses a robot decision method, a robot decision system, an electronic device, a computer readable storage medium and a robot. The method first determines an event type of the robot, and then generates a corresponding processing strategy according to the event type and event information, so that the event processing of the robot can be automatically performed instead of manually, the processing efficiency of the robot event is improved, and the labor cost is reduced. When the event type is a first type, auxiliary data of the robot is acquired, and a processing strategy corresponding to the event information is generated based on the auxiliary data and a processing plan corresponding to the event information in a plan database, so that the processing strategy is generated in combination with the auxiliary data of the robot, the processing strategy can be applied to various event processing of the robot, and the participation of the human is further reduced.

Description

Technical Field

[0001] This application relates to the field of robotics technology, and in particular to a robot decision-making method, a robot decision-making system, an electronic device, a computer-readable storage medium, and a robot. Background Technology

[0002] With the rapid development of industry and technology in my country, industrial robots are being used more and more in various industries, greatly improving productivity. However, robots are complex in function and operate under harsh conditions, requiring environmental and parameter configuration as well as handling of abnormal events during use.

[0003] In existing technologies, environmental and parameter configurations are manually performed by professionals. Furthermore, when abnormalities occur during robot use, professionals must go to the site to manually perform corresponding corrections and processing based on the robot's abnormal information. This process is inefficient and labor-intensive. Summary of the Invention

[0004] To address the issues of low efficiency and high labor costs in robot event handling, this application provides a robot decision-making method, a robot decision-making system, an electronic device, a computer-readable storage medium, and a robot.

[0005] According to one aspect of the embodiments of this application, a robot decision-making method is disclosed, the robot decision-making method comprising:

[0006] Obtain event information from the robot;

[0007] Based on the event information and event classification rules, the event type of the robot is determined;

[0008] If the event type is the first type, obtain the robot's auxiliary data, and based on the auxiliary data and the corresponding processing plan in the contingency plan database, generate a processing strategy corresponding to the event information.

[0009] In one exemplary embodiment, after determining the event type of the robot, the method further includes:

[0010] If the event type is the second type, the corresponding processing plan in the contingency plan database shall be used as the processing strategy for the event information.

[0011] In one exemplary embodiment, after determining the event type of the robot, the method further includes:

[0012] If the event type is the third type, a feedback message is generated that indicates the event information cannot be processed.

[0013] In one exemplary embodiment, after generating feedback information representing the inability to process the event information, the method further includes:

[0014] Monitor whether the event information is being processed effectively;

[0015] If the monitored event information is effectively processed, obtain a processing solution for the event information;

[0016] Based on the processing scheme, a processing plan for the event information is generated;

[0017] The generated processing plan is added to the plan database.

[0018] In one exemplary embodiment, if the event information is abnormal information, after generating a processing plan for the event information based on the processing scheme, the method further includes:

[0019] The reliability coefficient of the generated processing plan is set to a preset initial value, and the reliability coefficient affects whether the processing plan can be adopted.

[0020] When the monitoring shows that the corresponding abnormal information is effectively handled using the processing scheme, the reliability coefficient of the generated processing plan is increased by a first value.

[0021] In one exemplary embodiment, after setting the reliability coefficient of the generated processing plan to a preset initial value, the method further includes:

[0022] When it is detected that the corresponding abnormal information is not processed using the processing scheme or is not effectively processed, the reliability coefficient of the generated processing plan will be lowered by a second value.

[0023] When the reliability coefficient of the generated processing plan drops below a first threshold, the generated processing plan is discarded. The first threshold is less than the preset initial value.

[0024] In one exemplary embodiment, determining the event type of the robot based on the event information and event classification rules includes:

[0025] For abnormal information in the contingency plan database that contains a processing contingency plan with a reliability coefficient exceeding the first threshold, the event type of the robot is classified into a first type or a second type.

[0026] For abnormal information in the contingency plan database where there is no corresponding processing plan or the reliability coefficient of the corresponding processing plan is below the first threshold, the event type of the robot is classified into the third type.

[0027] In one exemplary embodiment, if the event information is abnormal information, after generating a processing strategy corresponding to the event information, the method further includes:

[0028] Add the corresponding handling plan to the abnormal information to the monitoring list;

[0029] When it is detected that the corresponding abnormal information is effectively handled by the corresponding handling plan, the reliability coefficient of the corresponding handling plan is increased by a first value.

[0030] When it is detected that the processing plan corresponding to the abnormal information does not effectively handle the corresponding abnormal information, the reliability coefficient of the processing plan corresponding to the abnormal information is lowered by a second value.

[0031] When the reliability coefficient of the processing plan corresponding to the abnormal information drops below the first threshold, the processing plan corresponding to the abnormal information is discarded.

[0032] In one exemplary embodiment, the event information and request auxiliary data are obtained through a first communication channel; the auxiliary data is received and the processing strategy is sent through a second communication channel; and a processing solution for unprocessable event information and the result of processing using the processing strategy are obtained through a third communication channel.

[0033] In one exemplary embodiment, the event information includes priority information, and determining the event type of the robot based on the event information and event classification rules includes:

[0034] Obtain the priority information from the event information;

[0035] Based on the event information and event classification rules, the event type of the robot is determined in order from high priority to low priority.

[0036] According to one aspect of the embodiments of this application, a robot decision-making system is disclosed, the robot decision-making system comprising:

[0037] The information acquisition module is used to acquire event information of the robot;

[0038] An event classification module is used to determine the event type of the robot based on the event information and event classification rules;

[0039] The decision generation module is used to acquire auxiliary data of the robot when the event type is the first type, and generate a processing strategy corresponding to the event information based on the auxiliary data and the processing plan corresponding to the event information in the contingency plan database.

[0040] According to one aspect of the embodiments of this application, an electronic device is disclosed, including one or more processors and a memory, the memory being used to store one or more programs, which, when executed by the one or more processors, cause the processors to implement the aforementioned robot decision-making method.

[0041] According to one aspect of the embodiments of this application, a computer-readable storage medium is disclosed, the computer-readable storage medium storing computer-readable instructions, which, when executed by a computer's processor, cause the computer to perform the aforementioned robot decision-making method.

[0042] According to one aspect of the embodiments of this application, a robot is disclosed, comprising:

[0043] Robot body;

[0044] A data acquisition device for acquiring at least some auxiliary data of the robot body;

[0045] An electronic device, as described above, is communicatively connected to the data acquisition device to obtain the auxiliary data.

[0046] The technical solutions provided by the embodiments of this application have at least the following beneficial effects:

[0047] The technical solution provided in this application first determines the event type of the robot, and then generates a corresponding processing strategy based on the event type and event information. This can automatically handle robot events, replacing manual labor, improving the efficiency of robot event handling, and reducing labor costs. Furthermore, when the event type is the first type, by acquiring auxiliary data from the robot and further generating a processing strategy corresponding to the event information based on the auxiliary data and the corresponding processing plan in the contingency plan database, the solution combines the robot's auxiliary data to generate a processing strategy, which is applicable to various event handling scenarios of the robot and further reduces human intervention.

[0048] It should be understood that the above general description and the following detailed description are merely exemplary and do not limit this application. Attached Figure Description

[0049] The accompanying drawings, which are incorporated in and form part of this specification, illustrate embodiments consistent with this application and, together with the specification, serve to explain the principles of this application.

[0050] Figure 1 This is a flowchart illustrating a robot decision-making method in the first exemplary embodiment.

[0051] Figure 2 This is a flowchart illustrating a robot decision-making method in a second exemplary embodiment.

[0052] Figure 3 This is a flowchart illustrating a robot decision-making method in a third exemplary embodiment.

[0053] Figure 4 This is a flowchart illustrating a robot decision-making method in the fourth exemplary embodiment.

[0054] Figure 5 This is a flowchart illustrating a robot decision-making method in the fifth exemplary embodiment.

[0055] Figure 6 This is a partial flowchart illustrating a robot decision-making method as shown in an exemplary embodiment.

[0056] Figure 7 This is a partial flowchart illustrating a robot decision-making method as shown in another exemplary embodiment.

[0057] Figure 8 This is a block diagram illustrating an electronic device according to an exemplary embodiment.

[0058] Figure 9 This is a block diagram illustrating a robot according to an exemplary embodiment.

[0059] Figure 10 This is a computer system architecture block diagram illustrating an electronic device for implementing embodiments of the present application, according to an exemplary embodiment.

[0060] The annotations in the attached figures are explained as follows:

[0061] 100. Electronic equipment; 110. Information acquisition module; 120. Event classification module; 130. Decision generation module; 140. Contingency plan database; 150. Monitoring module; 160. Automatic learning module; 200. Robot; 210. Robot body; 220. Data acquisition device; 230. Electronic equipment; 300. Computer system; 301. CPU; 302. ROM; 303. Storage section; 304. RAM; 305. Bus; 306. I / O interface; 307. Input section; 308. Output section; 309. Communication section; 310. Driver; 311. Removable media. Detailed Implementation

[0062] Exemplary embodiments will now be described more fully with reference to the accompanying drawings. However, these exemplary embodiments can be implemented in many forms and should not be construed as limited to the examples set forth herein; rather, these embodiments are provided to make this application more comprehensive and complete, and to fully convey the concept of the exemplary embodiments to those skilled in the art.

[0063] Furthermore, the described features, structures, or characteristics can be combined in any suitable manner in one or more embodiments. Numerous specific details are provided in the following description to give a thorough understanding of embodiments of this application. However, those skilled in the art will recognize that the technical solutions of this application can be practiced without one or more of the specific details, or other methods, components, apparatuses, steps, etc., can be employed. In other instances, well-known methods, apparatuses, implementations, or operations are not shown or described in detail to avoid obscuring various aspects of this application.

[0064] The block diagrams shown in the accompanying drawings are merely functional entities and do not necessarily correspond to physically independent entities. That is, these functional entities can be implemented in software, in one or more hardware modules or integrated circuits, or in different network and / or processor devices and / or microcontroller devices.

[0065] The flowcharts shown in the accompanying drawings are merely illustrative and do not necessarily include all content and operations / steps, nor do they necessarily have to be performed in the described order. For example, some operations / steps can be broken down, while others can be combined or partially combined; therefore, the actual execution order may change depending on the specific circumstances.

[0066] Robots, especially industrial robots, operate under demanding conditions. Both the initial setup and subsequent use require specific working environments and operating conditions. Furthermore, users may encounter abnormal events during actual use. When configuration adjustments or abnormal events occur, such as when the robot reaches singularities or exceeds its limits, manual intervention by professionals is necessary. These interventions require specialized training and expertise, hindering the widespread adoption of robots and resulting in low efficiency and high labor costs.

[0067] To improve the efficiency of robot event handling and reduce labor costs, this application provides a robot decision-making method, a robot decision-making system, an electronic device, a computer-readable storage medium, and a robot. The following detailed description, using specific embodiments and accompanying drawings, illustrates the robot decision-making method, robot decision-making system, electronic device, computer-readable storage medium, and robot of this application.

[0068] See Figure 1 , Figure 1 This is a flowchart illustrating a robot decision-making method according to a first exemplary embodiment. The execution entity of this method can be an electronic device such as a robot controller, or it can be an additional electronic device independent of the robot controller. The robot decision-making method mainly includes the following steps S101 to S103.

[0069] Step S101: Obtain the robot's event information.

[0070] The event information can be abnormal information, in which case the robot decision-making method is used to handle the robot's abnormality. For example, the event information could be abnormal robot operating mode information, such as the robot operating at high speed when it should be operating in slow mode, or vice versa. In this case, the robot decision-making method would formulate a corresponding handling strategy for the abnormal operating mode event, such as generating a strategy on how to adjust the operating mode.

[0071] Event information can also be information other than anomaly information, such as environmental configuration information. In this case, the robot's decision-making method is used to configure the robot's environment. For example, if the event information is a load identification query, the robot's decision-making method will use a corresponding processing strategy for the load identification query, such as generating a decision result that requires load identification or a decision result that does not require load identification, and returning the corresponding load data.

[0072] In one embodiment of this application, the event information includes priority information. Before performing subsequent steps such as event classification and generating a processing strategy, the priority information in the event information is first obtained. Then, in order from high priority to low priority, subsequent steps S102, S103, etc., are performed on the obtained event information to generate a processing strategy.

[0073] High-priority events can be those involving the robot's basic functions, while low-priority events can be those triggered by a high-priority event. Processing high-priority events first can quickly enable the robot's basic functions to work normally, and may also cause low-priority events to disappear, saving processing resources.

[0074] In one embodiment of this application, the event information includes an event code, an information category, the event that generated the information, a priority, the module that generated the event information, and reserved additional parameters.

[0075] Exception codes can be mapped to specific information about an event. For example, based on the exception code, one can further query the module information that generated the event information, the category of the event information, and the event that generated the event information.

[0076] The robot contains many modules, such as an alarm module and a language processing module. The event information includes information about the module that generated the event, which can directly pinpoint the root cause of the event and assist in generating a processing decision. Of course, the event code can also be used to further query the module information that generated the event. Therefore, in some embodiments, the event information may not include the module that generated the event.

[0077] Information categories, such as notifications, warnings, errors, etc.

[0078] The event that generates this information, such as a power-on event or a power-off event.

[0079] Additional parameters are reserved in the event information format, which can be configured later as needed.

[0080] Step S102: Based on the event information and event classification rules, determine the event type of the robot. If the event type is the first type, proceed to step S103a; if the event type is the second type, proceed to step S103b; if the event type is the third type, proceed to step S103c.

[0081] Before running the robot decision-making method, event classification rules are pre-configured, which are the mapping relationships between various event information and event types. After obtaining the event information, the robot's event type can be further determined. For example, the mapping relationships between various event codes and event types are listed. After obtaining the event information, the robot's event type can be determined by querying the mapping relationship between the event code and the event type.

[0082] Different processing strategies are applied to different event types. In one embodiment of this application, the event types include a first type, a second type, and a third type. The first and second types are events for which corresponding processing plans exist in the contingency plan database. The first type of event requires additional auxiliary data and is an event for which a processing strategy needs to be flexibly generated based on the auxiliary data. The second type of event does not require further auxiliary data and can be processed directly based on the corresponding processing plan in the contingency plan database. The third type of event is an event for which no corresponding processing plan exists in the contingency plan database.

[0083] In one embodiment of this application, the event types also include a first type, a second type, and a third type. The first type and the second type are events for which there is a corresponding processing plan in the plan database. In addition, the reliability of the processing plan corresponding to the event is further required. If the reliability coefficient does not reach a preset threshold, the event is still classified into the third type. That is, the third type of event is an event for which there is no corresponding processing plan in the plan database, or an event for which there is a corresponding processing plan in the plan database but the reliability coefficient of the corresponding processing plan does not reach a preset threshold.

[0084] In one embodiment of this application, in step S102, the system first checks whether there is a corresponding processing plan in the plan database. If there is no plan, the event type is directly classified as the third type. If there is a plan, the system further determines whether the event is the second type. If not, the event type is classified as the first type.

[0085] Step S103a: Obtain the robot's auxiliary data, and based on the auxiliary data and the corresponding event information processing plan in the contingency plan database, generate a processing strategy corresponding to the event information.

[0086] Auxiliary data can be data about the robot's surrounding environment, such as whether there are obstacles; auxiliary data can also be real-time motion data of the robot, such as robot coordinate data; auxiliary data can also be relevant data of the robot's end effector, such as image data of the robot gripper, or quality data of the welding torch.

[0087] In step S103a, generating a processing strategy corresponding to the event information based on the auxiliary data and the processing plan corresponding to the event information in the contingency plan database means that, based on the processing plan corresponding to the event information, the processing strategy corresponding to the event information is further obtained by combining the obtained auxiliary data.

[0088] Step S103b: Use the processing plan corresponding to the event information in the plan database as the event information processing strategy.

[0089] In step S103b, no additional processing is required on the processing plan; the processing plan corresponding to the event information in the plan database is directly used as the processing strategy.

[0090] Step S103c: Generate feedback information representing the event information that cannot be processed.

[0091] It should be noted that a mapping relationship between event information and handling plans is pre-configured before running the robot's decision-making method. After obtaining the event information, the handling plan can be further determined. For example, a mapping relationship between event codes and handling plans is pre-configured. After obtaining the event information, the corresponding handling plan can be determined by querying the mapping relationship between the event code and the handling plan.

[0092] A specific embodiment

[0093] The event pertains to a change in operating mode; that is, the event information pertains to changes in operating mode. See [link / reference]. Figure 2 As shown, the robot decision-making method includes the following steps S201 to S204.

[0094] Step S201: Obtain robot operation mode adjustment information.

[0095] Operating modes include, but are not limited to, slow mode and fast / slow mode.

[0096] Step S202: Query the contingency plan database to see if there is a corresponding processing contingency plan for the operation mode adjustment information. If the query result is yes, proceed to step S203.

[0097] Step S203: Determine whether the running mode adjustment event is of the second type. If the result is yes, proceed to step S204.

[0098] Step S204: The processing plan corresponding to the operation mode adjustment information in the contingency plan database is used as the processing strategy for the operation mode adjustment information. This further controls the robot to adjust to the target operation mode.

[0099] A specific embodiment

[0100] The event is a load identification query; that is, the event information is load identification query information. See [link / reference]. Figure 3 As shown, the robot decision-making method includes the following steps S301 to S306.

[0101] Step S301: Obtain the robot's load identification query information.

[0102] Step S302: Query the contingency plan database to see if there is a processing contingency plan corresponding to the load identification query information. If the query result is yes, proceed to step S303.

[0103] Step S303: Determine whether the load identification query event is of the second type. If the determination result is no, that is, the load identification query event is of the first type, proceed to step S304.

[0104] Step S304: Request the image data of the payload.

[0105] Step S305: Based on the obtained image data, query the contingency plan database to see if there is load data corresponding to the image data. If it exists, proceed to step S306a; otherwise, proceed to step S306b.

[0106] Step S306a generates a decision result that does not require load identification and returns the corresponding load data.

[0107] Step S306b generates a decision result that requires load identification.

[0108] It should be noted that querying the contingency plan database based on the obtained image data to determine whether the corresponding load data exists is the processing contingency plan in the contingency plan database corresponding to the load identification query information. The decision result generated based on the query result regarding whether load identification is required or not, and the return of the corresponding load data under the decision result that load identification is not required, constitutes the processing contingency plan based on the auxiliary data and the contingency plan database corresponding to the load identification query information, thereby generating the processing strategy corresponding to the load identification query information.

[0109] It should be noted that in other embodiments, step S304 may also be other auxiliary data for requesting load, such as the quality data of the requested load. Correspondingly, in step S305, the load data corresponding to the quality data is queried in the plan database based on the obtained quality data.

[0110] Specifically, the type of auxiliary data requested can be part of the processing plan. For example, the processing plan corresponding to the load identification query information includes a first part plan and a second part plan. In step S304, based on the first part plan, it is determined what specific auxiliary data needs to be requested, and then that auxiliary data is requested. In step S305, based on the auxiliary data and the second part plan corresponding to the load identification query event information in the plan database, a processing strategy corresponding to the load identification query event information is generated. The first part plan and the second part plan can be stored in different databases.

[0111] A specific embodiment

[0112] The event is related to an abnormal robot arm position; that is, the event information is about an abnormal robot arm position. See [link / reference]. Figure 4 As shown, the robot decision-making method includes the following steps S401 to S405.

[0113] Step S401: Obtain abnormal position information of the robot arm.

[0114] Step S402: Query the contingency plan database to see if there is a corresponding contingency plan for handling abnormal information of the robot arm position. If the query result is yes, proceed to step S403.

[0115] Step S403: Determine whether the abnormal robot arm position event is of the second type. If the determination result is no, that is, the abnormal robot arm position event is of the first type, proceed to step S404.

[0116] Step S404: Request images of the robot's surrounding environment and robot coordinate data.

[0117] Step S405: Based on the robot's surrounding environment images, robot coordinate data, and robot arm movement plans corresponding to abnormal robot arm positions in the plan database, generate a processing strategy corresponding to the abnormal robot arm positions.

[0118] For example, the robot arm movement plan corresponding to abnormal robot arm position information in the contingency plan database can be to control the robot arm to adjust its position. The specific adjustment method needs to be determined based on the surrounding environment image to determine whether there are obstacles, and then further determined based on the robot coordinate data to determine the adjustment direction, adjustment offset, etc., which is to generate a processing strategy corresponding to abnormal robot arm position information.

[0119] Furthermore, in one embodiment of this application, after generating a processing strategy, the relevant decision events are added to a monitoring list, and the processing strategy is further monitored to ensure that the abnormal information is handled effectively. That is, if the processing result meets expectations, the reliability coefficient corresponding to the processing plan is adjusted based on whether the processing strategy effectively handles the abnormal information. The reliability coefficient will affect whether the processing plan can be adopted in the later stages.

[0120] See Figure 5 In one embodiment of this application, the robot decision-making method mainly includes the following steps S501 to S508.

[0121] Step S501: Obtain abnormal information about the robot.

[0122] Step S502: Based on the abnormal information and event classification rules, determine the abnormal event type of the robot. If the abnormal event type is the first type, proceed to step S503a; if the abnormal event type is the second type, proceed to step S503b; if the abnormal event type is the third type, proceed to step S503c.

[0123] Step S503a: Obtain the robot's auxiliary data, and based on the auxiliary data and the corresponding handling plan in the contingency plan database, generate a handling strategy corresponding to the abnormal information, and proceed to step S504.

[0124] Step S503b: Use the corresponding processing plan for the abnormal information in the contingency plan database as the processing strategy for the abnormal information, and proceed to step S504.

[0125] Step S503c: Generate feedback information representing the inability to process the abnormal information.

[0126] Step S504: Add the corresponding handling plan to the monitoring list.

[0127] Step S505: Whenever the corresponding abnormal information is effectively handled by the corresponding handling plan, proceed to step S506a; whenever the corresponding abnormal information is not effectively handled by the corresponding handling plan, proceed to step S506b.

[0128] Step S506a: Determine whether the reliability coefficient of the processing plan corresponding to the abnormal information reaches the second threshold. If not, proceed to step S507.

[0129] Step S507: Increase the reliability coefficient of the handling plan corresponding to the abnormal information by a first value.

[0130] Step S506b: Determine whether the reliability coefficient of the processing plan corresponding to the abnormal information has dropped below the first threshold. If not, proceed to step S508a; if yes, proceed to step S508b.

[0131] Step S508a: Lower the second value of the reliability coefficient of the handling plan corresponding to the abnormal information.

[0132] Step S508b: Discard the processing plan corresponding to the abnormal information.

[0133] It should be noted that the first threshold is less than the second threshold. The first and second thresholds are values ​​set according to requirements. In one embodiment of this application, the first threshold is 0 and the second threshold is 3. Similarly, the first and second values ​​are values ​​set according to requirements. The first and second values ​​can be the same or different. In one embodiment of this application, both the first and second values ​​are 1.

[0134] It should be noted that in other embodiments, the second threshold may not be set, that is, step S506a may not be executed. If the corresponding abnormal information is effectively processed by the processing plan corresponding to the abnormal information in step S505, the process directly proceeds to step S507.

[0135] It should be noted that after step S503, step S504 can be entered periodically, that is, the processing strategy is monitored periodically to see if it effectively handles the abnormal information.

[0136] By monitoring whether the processing strategy effectively handles the abnormal information, and adjusting the reliability coefficient of the corresponding processing plan based on whether the processing strategy effectively handles the abnormal information, and using the processing plan with the reliability coefficient reaching the preset threshold for decision-making, the accuracy of the decision-making is higher.

[0137] Furthermore, for unprocessable event information, in one embodiment of this application, after generating feedback information representing unprocessable event information, the event information is continuously monitored. If the event information is detected to be effectively processed, an effective processing solution for the event information is obtained, and a processing plan for the event is further generated and updated to the plan database.

[0138] See Figure 6 In one embodiment of this application, after generating feedback information representing unprocessable event information, the subsequent processing steps include the following steps S601 to S604.

[0139] Step S601: Monitor whether the unprocessable event information has been effectively processed. If so, proceed to step S602.

[0140] Step S602: Obtain a processing plan for the event information.

[0141] It should be noted that for event information that cannot be handled, it must be handled manually on-site by professionals. During the process of handling the event information manually on-site by professionals, the robot's controller can record the operation steps for handling the event information, that is, the handling plan.

[0142] Step S603: Based on the processing scheme, generate a processing plan for the event information.

[0143] Step S604: Add the generated processing plan to the plan database.

[0144] This embodiment enables automatic learning of processing solutions for unprocessable event information and generates processing solutions that are stored in a contingency plan database. When the same or similar event information is obtained again, the corresponding processing solution can be found from the contingency plan database. In other words, the third type of event that could not be processed is transformed into the first or second type that can be processed, thereby improving decision-making ability.

[0145] Furthermore, in one embodiment of this application, after generating a processing plan for the event information, a reliability coefficient is further used to measure the reliability of the generated processing plan, and the processing results of the subsequent processing of the abnormal information using the processing scheme corresponding to the generated processing plan are monitored to see if they meet expectations.

[0146] See Figure 7In one embodiment of this application, after the generated processing plan is added to the plan database, the subsequent processing steps include the following steps S701 to S705.

[0147] Step S701: Set the reliability coefficient of the generated processing plan to a preset initial value.

[0148] Step S702: Monitor whether the corresponding abnormal information is effectively handled using the processing plan corresponding to the processing plan. If yes, proceed to step S703a; otherwise, proceed to step S703b.

[0149] It should be noted that if the monitoring detects that the corresponding abnormal information is not handled using the corresponding processing plan or is not effectively handled, it means that the corresponding abnormal information has not been effectively handled using the corresponding processing plan.

[0150] It should be noted that the corresponding abnormal information refers to abnormal information that is the same as or similar to the abnormal information originally corresponding to the generated handling plan.

[0151] Step S703a: Determine whether the reliability coefficient of the generated processing plan reaches the second threshold. If not, proceed to step S704.

[0152] S704, increase the reliability coefficient of the generated processing plan by the first value.

[0153] Step S703b: Determine whether the reliability coefficient of the generated processing plan has dropped below the first threshold. If not, proceed to step S705a; if yes, proceed to step S705b.

[0154] Step S705a: Lower the second value of the reliability coefficient of the generated processing plan.

[0155] Step S705b: Discard the generated processing plan.

[0156] It should be noted that the first threshold is less than the second threshold. The first and second thresholds are values ​​set according to requirements. In one embodiment of this application, the first threshold is 0 and the second threshold is 3. Similarly, the first and second values ​​are values ​​set according to requirements; they can be the same or different. In one embodiment of this application, both the first and second values ​​are 1. Likewise, the preset initial value is a value set according to requirements. In one embodiment of this application, the preset initial value is -2.

[0157] It should be noted that in other embodiments, the second threshold may not be set, that is, step S703a may not be executed. If the abnormal information is effectively handled by the processing scheme corresponding to the generated processing plan in step S702, the process may directly proceed to step S704.

[0158] It should be noted that in step S702, if the corresponding abnormal information is detected and other processing solutions are used to effectively handle it, the other processing solution is updated to the processing solution corresponding to the abnormal information, and a processing plan is further generated and saved to the plan database.

[0159] In one embodiment of this application, multiple communication channels are configured. Event information and request auxiliary data are obtained through a first communication channel; auxiliary data and processing strategies are received through a second communication channel; and a processing solution for unprocessable event information and the result of processing using the processing strategy are obtained through a third communication channel.

[0160] In summary, this application identifies robot event information and proactively generates decision-making schemes such as environmental configuration and anomaly elimination through technologies such as databases, event classification, decision generation, monitoring feedback, and automatic learning. It can further notify the control system to execute these schemes. This achieves intelligent processing effects that replace manual handling, enabling robot operation with minimal manual intervention, improving robot reliability, and ultimately lowering the barrier to entry and learning cost for robot use. Furthermore, it makes robot operation simpler and more efficient.

[0161] The following are embodiments of the electronic device described in this application, which can be used to execute the robot decision-making method embodiments described above. For details not disclosed in the embodiments of the electronic device described in this application, please refer to the robot decision-making method embodiments described above.

[0162] Figure 8 This is a block diagram illustrating an electronic device 100 according to an exemplary embodiment. The electronic device 100 can be applied to a robot, specifically a robot controller loaded with the robot decision-making method of this application, to execute... Figures 1 to 7 All or part of the steps of any of the robot decision-making methods shown. For example... Figure 8 As shown, the electronic device 100 includes, but is not limited to: an information acquisition module 110, an event classification module 120, a decision generation module 130, and a contingency plan database 140.

[0163] The information acquisition module 110 is used to acquire event information of the robot.

[0164] The event classification module 120 is used to determine the event type of the robot based on event information and event classification rules.

[0165] The decision generation module 130 is used to acquire auxiliary data of the robot when the event type is the first type, and generate a processing strategy corresponding to the event information based on the auxiliary data and the processing plan corresponding to the event information in the plan database.

[0166] Contingency plan database 140 is used to store and process contingency plans.

[0167] In an exemplary embodiment, the decision generation module 130 is further configured to, when the event type is a second type, use the processing plan corresponding to the event information in the plan database as the event information processing strategy.

[0168] In one exemplary embodiment, the decision generation module 130 is further configured to generate feedback information representing the inability to process event information when the event type is a third type.

[0169] In an exemplary embodiment, the electronic device 100 further includes a monitoring module 150 and an automatic learning module 160. The monitoring module 150 is used to monitor whether the event information is effectively processed, and if the event information is effectively processed, to obtain a processing plan for the event information. The automatic learning module 160 is used to generate a processing plan for the event information based on the processing plan, and to add the generated processing plan to the plan database.

[0170] In an exemplary embodiment, if the event information is abnormal information, the automatic learning module 160 electronic device 100 will also set the reliability coefficient of the generated processing plan to a preset initial value. The reliability coefficient affects whether the processing plan can be adopted. When the monitoring module 150 monitors that the corresponding abnormal information is effectively processed by the processing plan, the automatic learning module 160 will increase the reliability coefficient of the generated processing plan by a first value.

[0171] In an exemplary embodiment, when the monitoring module 150 detects that the corresponding abnormal information has not been processed or has not been effectively processed, the automatic learning module 160 lowers the reliability coefficient of the generated processing plan by a second value; when the reliability coefficient of the generated processing plan drops below a first threshold, the processing plan is removed from the plan database, where the first threshold is less than a preset initial value.

[0172] In an exemplary embodiment, the event classification module 120 classifies the robot's event type into a first type or a second type for abnormal information in the contingency plan database that has a processing contingency plan with a reliability coefficient of more than a first threshold; and classifies the robot's event type into a third type for abnormal information in the contingency plan database that has no corresponding processing contingency plan or whose corresponding processing contingency plan has a reliability coefficient of less than the first threshold.

[0173] In an exemplary embodiment, if the event information is abnormal information, after the decision generation module 130 generates a processing strategy corresponding to the event information, the monitoring module 150 adds the processing plan corresponding to the abnormal information to the monitoring list; when it is monitored that the processing plan corresponding to the abnormal information effectively processes the corresponding abnormal information, the automatic learning module 160 increases the reliability coefficient of the processing plan corresponding to the abnormal information by a first value; when the monitoring module 150 monitors that the processing plan corresponding to the abnormal information does not effectively process the corresponding abnormal information, the automatic learning module 160 decreases the reliability coefficient of the processing plan corresponding to the abnormal information by a second value; when the reliability coefficient of the processing plan corresponding to the abnormal information drops below a first threshold, the processing plan corresponding to the abnormal information is removed from the plan database.

[0174] In one exemplary embodiment, event information and request auxiliary data are obtained through a first communication channel; auxiliary data and processing strategies are received through a second communication channel; and a processing plan for unprocessable event information and the result of processing using the processing strategy are obtained through a third communication channel.

[0175] In one exemplary embodiment, the event information includes priority information. The event classification module 120 obtains the priority information from the event information and determines the event type of the robot based on the event information and the event classification rules, in order from high priority to low priority.

[0176] The specific implementation process of the functions and roles of each module in the aforementioned electronic device 100 can be found in the implementation process of the corresponding steps in the aforementioned robot decision-making method, and will not be repeated here.

[0177] Figure 9 This is a block diagram illustrating a robot according to an exemplary embodiment, such as... Figure 9 As shown, robot 200 includes robot body 210, data acquisition device 220 and electronic device 230.

[0178] The data acquisition device 220 is used to collect at least some auxiliary data from the robot body 210. For example, the data acquisition device 220 can be an image acquisition device to collect data on the surrounding environment of the robot body 210, load image data, etc. As another example, the data acquisition device 220 can be a radar device to obtain data on the surrounding environment of the robot body 210.

[0179] Electronic device 230 is communicatively connected to data acquisition device 220 to obtain auxiliary data. For example, electronic device 230 is a robot controller, which, in addition to including a control system to perform the basic function of robot control, further integrates the robot decision system of this application. The robot decision system interacts with the robot control system through a communication channel to obtain event information, request auxiliary data, receive auxiliary data, send processing strategies, obtain processing solutions for unprocessable event information, and obtain the results of processing using the processing strategies.

[0180] In one embodiment of this application, a first communication channel, a second communication channel, and a third communication channel are established between the robot decision-making system and the robot control system. The robot decision-making system obtains event information and requests auxiliary data through the first communication channel; receives auxiliary data and sends processing strategies through the second communication channel; and obtains processing solutions for unprocessable event information and the results of processing using the processing strategies through the third communication channel.

[0181] In one embodiment of this application, the communication between the control system and the decision system adopts a synchronous processing mode. After the control system sends a message to the decision system, it needs to wait for the decision system to reply with a decision result before the control system can continue to execute subsequent commands.

[0182] It should be noted that the auxiliary data collected by the data acquisition device 220 is first sent to the control system, which then feeds it back to the robot decision-making system. Some of the auxiliary data for the robot body 210 can be generated by the control system.

[0183] In one embodiment of this application, both the data acquisition device 220 and the electronic device 230 are mounted on the robot body 210.

[0184] Figure 10 This is a computer system architecture block diagram illustrating an electronic device for implementing embodiments of the present application, according to an exemplary embodiment.

[0185] It should be noted that, Figure 10 The computer system shown is merely an example and should not impose any limitation on the functionality and scope of use of the embodiments of this application.

[0186] like Figure 10As shown, the computer system 300 includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes based on programs stored in read-only memory (ROM) 302 or programs loaded from storage section 303 into random access memory (RAM) 304. The RAM 304 also stores various programs and data required for device operation. The CPU 301, ROM 302, and RAM 304 are interconnected via a bus 305. An input / output interface 306 (I / O interface) is also connected to the bus 305.

[0187] The following components are connected to the input / output interface 306: an input section 307 including a keyboard, mouse, etc.; an output section 308 including a cathode ray tube (CRT), liquid crystal display (LCD), etc., and speakers, etc.; a storage section 303 including a hard disk, etc.; and a communication section 309 including a network interface card such as a local area network card, modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the input / output interface 306 as needed. A removable medium 311, such as a disk, optical disk, magneto-optical disk, semiconductor memory, etc., is installed on the drive 310 as needed so that computer programs read from it can be installed into the storage section 303 as needed.

[0188] Specifically, according to embodiments of this application, the processes described in the various method flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication section 309, and / or installed from removable medium 311. When the computer program is executed by central processing unit 301, it performs the various functions defined in the apparatus of this application.

[0189] It should be noted that the computer-readable medium shown in the embodiments of this application can be a computer-readable signal medium or a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor device, apparatus, or device, or any combination thereof. More specific examples of a computer-readable storage medium may include, but are not limited to: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), flash memory, optical fiber, portable compact disc read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this application, a computer-readable storage medium can be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution apparatus, device, or device. In this application, a computer-readable signal medium can include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such transmitted data signals can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. The computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in connection with an instruction execution device, apparatus, or apparatus. The program code contained on the computer-readable medium can be transmitted using any suitable medium, including but not limited to wireless, wired, etc., or any suitable combination thereof.

[0190] Those skilled in the art will recognize that, in one or more of the examples above, the functions described in this application can be implemented using hardware, software, firmware, or any combination thereof. When implemented in software, these functions can be stored in a computer-readable storage medium or transmitted as one or more instructions or code on a computer-readable storage medium.

[0191] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0192] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the modular division is only a logical functional division, and other division methods may exist in actual implementation. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed.

[0193] It should be understood that this application is not limited to the precise structures described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

Claims

1. A robot decision-making method, characterized in that, include: Obtain event information from the robot; Based on the event information and event classification rules, the event type of the robot is determined. The event type includes a first type, a second type, and a third type. The first type is an event for which a corresponding processing plan exists in the plan database and a processing strategy needs to be generated based on auxiliary data. The second type is an event for which a corresponding processing plan exists in the plan database and can be processed directly based on the corresponding processing plan in the plan database. The third type is an event for which no corresponding processing plan exists in the plan database. If the event type is the first type, obtain the robot's auxiliary data, and based on the auxiliary data and the processing plan corresponding to the event information in the plan database, generate a processing strategy corresponding to the event information; If the event type is the second type, the corresponding processing plan in the contingency plan database will be used as the processing strategy for the event information. If the event type is the third type, generate feedback information indicating that the event information cannot be processed, and monitor whether the event information is effectively processed; If the monitored event information is effectively processed, obtain a processing solution for the event information; Based on the processing scheme, a processing plan for the event information is generated; Add the generated processing plan to the plan database; The step of determining the event type of the robot based on the event information and event classification rules includes: For abnormal information in the contingency plan database that contains a processing plan with a reliability coefficient exceeding the first threshold, the event type of the robot is classified into a first type or a second type. The reliability coefficient affects whether the processing plan can be adopted. For abnormal information in the contingency plan database where there is no corresponding processing plan or the reliability coefficient of the corresponding processing plan is below the first threshold, the event type of the robot is classified into the third type.

2. The robot decision-making method according to claim 1, characterized in that, If the event information is abnormal, after generating a processing plan for the event information based on the processing scheme, the following further steps are included: Set the reliability coefficient of the generated processing plan to a preset initial value; When the monitoring shows that the corresponding abnormal information is effectively handled using the processing scheme, the reliability coefficient of the generated processing plan is increased by a first value.

3. The robot decision-making method according to claim 2, characterized in that, After setting the reliability coefficient of the generated processing plan to a preset initial value, the method further includes: When it is detected that the corresponding abnormal information is not processed using the processing scheme or is not effectively processed, the reliability coefficient of the generated processing plan will be lowered by a second value. When the reliability coefficient of the generated processing plan drops below a first threshold, the generated processing plan is discarded. The first threshold is less than the preset initial value.

4. The robot decision-making method according to claim 1, characterized in that, If the event information is abnormal information, after generating a processing strategy corresponding to the event information, the following steps are also included: Add the corresponding handling plan for the abnormal information to the monitoring list; When it is detected that the corresponding abnormal information is effectively handled by the corresponding handling plan, the reliability coefficient of the corresponding handling plan is increased by a first value. When it is detected that the processing plan corresponding to the abnormal information does not effectively handle the corresponding abnormal information, the reliability coefficient of the processing plan corresponding to the abnormal information is lowered by a second value. When the reliability coefficient of the processing plan corresponding to the abnormal information drops below the first threshold, the processing plan corresponding to the abnormal information is discarded.

5. The robot decision-making method according to claim 1, characterized in that, The event information and request for assistance data are obtained through the first communication channel; The auxiliary data is received and the processing strategy is sent through the second communication channel; The third communication channel is used to obtain the processing plan for unprocessable event information and the result of processing using the stated processing strategy.

6. The robot decision-making method according to claim 1, characterized in that, The event information includes priority information. Determining the event type of the robot based on the event information and event classification rules includes: Obtain the priority information from the event information; Based on the event information and event classification rules, the event type of the robot is determined in order from high priority to low priority.

7. A robot decision-making system, characterized in that, include: The information acquisition module is used to acquire event information of the robot; An event classification module is used to determine the event type of the robot based on the event information and event classification rules. The event types include a first type, a second type, and a third type. The first type is an event for which a corresponding processing plan exists in the contingency plan database and a processing strategy needs to be generated based on auxiliary data. The second type is an event for which a corresponding processing plan exists in the contingency plan database and can be directly processed based on the corresponding processing plan in the database. The third type is an event for which no corresponding processing plan exists in the contingency plan database. Determining the event type of the robot based on the event information and event classification rules includes: for abnormal information where a processing plan with a reliability coefficient exceeding a first threshold exists in the contingency plan database, the robot's event type is classified as either the first type or the second type. The reliability coefficient affects whether the processing plan can be adopted. For abnormal information where no corresponding processing plan exists in the contingency plan database or where the reliability coefficient of the corresponding processing plan is below the first threshold, the robot's event type is classified as the third type. The decision generation module is configured to: acquire robot auxiliary data when the event type is a first type; generate a processing strategy corresponding to the event information based on the auxiliary data and the corresponding processing plan in the contingency plan database; use the corresponding processing plan in the contingency plan database as the processing strategy for the event information when the event type is a second type; generate feedback information indicating that the event information cannot be processed when the event type is a third type, and monitor whether the event information is effectively processed; if the event information is effectively processed, acquire a processing plan for the event information; generate a processing plan for the event information based on the processing plan; and add the generated processing plan to the contingency plan database.

8. An electronic device, characterized in that, include: One or more processors; A memory for storing one or more programs, which, when executed by one or more processors, cause the processors to implement the robot decision-making method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer-readable instructions that, when executed by a computer's processor, cause the computer to perform the robot decision-making method as described in any one of claims 1 to 6.

10. A robot, characterized in that, include: Robot body; A data acquisition device for acquiring at least some auxiliary data of the robot body; An electronic device, as described in claim 8, is communicatively connected to the data acquisition device to obtain the auxiliary data.

Images