Robot control method, apparatus, medium, and electronic device

Abstract

The present disclosure relates to a robot control method, device, medium and electronic equipment, belonging to the field of robots, which can reduce the failure rate of robots executing tasks. A robot control method comprises: obtaining a current task difficulty and a current damage condition of each joint actuator; based on the current task difficulty and the current damage condition, for each action, planning a path, predicting the damage condition of each joint actuator when the current task is completed; if the prediction result indicates that the corresponding joint actuator does not appear abnormal in the corresponding action planning path when the current task is completed, controlling the corresponding joint actuator to execute the current task along the corresponding action planning path.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the field of robots, in particular, to a robot control method, device, medium and electronic equipment. BACKGROUND

[0002] In the related art, after receiving an action execution instruction, a robot (especially a robot installed with an effector) directly executes the action according to the instruction, resulting in a high failure rate of the task. SUMMARY

[0003] The purpose of the present disclosure is to provide a robot control method, device, medium and electronic equipment, which can reduce the failure rate of the robot executing a task.

[0004] To achieve the above purpose, the present disclosure provides a robot control method, comprising: obtaining a current task difficulty and a current damage situation of each joint effector; based on the current task difficulty and the current damage situation, predicting a damage situation of each joint effector when the current task is completed for each action planning path; if the prediction result indicates that the corresponding joint effector does not appear abnormal in the corresponding action planning path when the current task is completed, controlling the corresponding joint effector to execute the current task along the corresponding action planning path.

[0005] Optionally, the method further comprises: if the prediction result indicates that the corresponding joint effector appears abnormal in the corresponding action planning path when the current task is completed, controlling a component composed of joint effectors predicted not to appear abnormal to execute the current task along the corresponding action planning path.

[0006] Optionally, in the case where the current task needs to be jointly executed by parent and child joint effectors, the prediction of the damage situation of each joint effector when the current task is completed comprises: predicting the damage situation of each joint effector when the current task is completed based on the task proportion weight of the parent joint effector and the child joint effector in the parent and child joint effectors.

[0007] Optionally, the abnormality includes at least one of the following: joint / rotation shaft overpressure abnormality, joint / rotation shaft underpressure abnormality, joint / rotation shaft stuck abnormality, joint / rotation shaft overheating abnormality, joint / rotation shaft read / write parameter abnormality, joint / rotation shaft multi-turn count abnormality, temperature sensor abnormality, CAN communication abnormality, step exceeding a preset threshold, DRV protection, encoder abnormality, brake error, emergency frame corresponding timeout, SOE corresponding timeout.

[0008] Optionally, the method further comprises: controlling the respective joint actuator to perform a subsequent task within a preset time from controlling the respective joint actuator to perform the current task along the respective motion planning path.

[0009] Optionally, the method further comprises: feeding back the prediction result to a user.

[0010] The present disclosure also provides a robot control device, comprising: an acquisition module configured to acquire a current task difficulty and a current damage condition of each joint actuator; a prediction module configured to, based on the current task difficulty and the current damage condition, predict a damage condition of each joint actuator when a current task is completed for each motion planning path; and a control module configured to, if a prediction result indicates that a corresponding joint actuator does not appear abnormal in a corresponding motion planning path when the current task is completed, control the corresponding joint actuator to perform the current task along the corresponding motion planning path.

[0011] Optionally, the control module is further configured to, if the prediction result indicates that a corresponding joint actuator appears abnormal in a corresponding motion planning path when the current task is completed, control a component composed of joint actuators predicted not to appear abnormal to perform the current task along a motion planning path corresponding thereto.

[0012] Optionally, the prediction module is further configured to, in a case where the current task needs to be jointly performed by parent and child joint actuators, predict a damage condition of each joint actuator when the current task is completed based on a task proportion weight of a parent joint actuator and a child joint actuator in the parent and child joint actuators.

[0013] Optionally, the abnormality comprises at least one of the following: joint / revolute abnormality, joint / revolute abnormality, joint / revolute abnormality, joint / revolute abnormality, joint / revolute abnormality, joint / revolute abnormality, temperature sensor abnormality, CAN communication abnormality, step exceeding a preset threshold, DRV protection, encoder abnormality, brake error, emergency frame corresponding timeout, SOE corresponding timeout.

[0014] Optionally, the control module is further configured to, within a preset time from controlling the respective joint actuator to perform the current task along the respective motion planning path, control the respective joint actuator to perform a subsequent task.

[0015] Optionally, the device further comprises a feedback module configured to feed back the prediction result to a user.

[0016] The present disclosure also provides a computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the method of the present disclosure.

[0017] The present disclosure also provides an electronic device comprising a memory having stored thereon a computer program; and a processor configured to execute the computer program in the memory to implement the steps of the method of the present disclosure.

[0018] By adopting the above technical solution, since the path for each action can be planned based on the current task difficulty and the current damage condition, the damage condition of each joint actuator when the current task is completed can be predicted, and in the case that the prediction result indicates that the corresponding joint actuator does not appear abnormal in the corresponding action planning path when the current task is completed, the corresponding joint actuator is controlled to execute the current task along the corresponding action planning path, thus the influence of the damaged joint on the task success rate can be reduced, and the failure rate of the robot in executing the task can be greatly reduced.

[0019] Other features and advantages of the present disclosure will be described in detail in the following detailed description section. BRIEF DESCRIPTION OF DRAWINGS

[0020] The accompanying drawings are included to provide a further understanding of the present disclosure and constitute a part of the specification, which together with the following detailed description, serve to explain the present disclosure. In the drawings:

[0021] Figure 1 is a flowchart of a robot control method according to an embodiment of the present disclosure.

[0022] Figure 2 is a schematic block diagram of a robot control device according to an embodiment of the present disclosure.

[0023] Figure 3 is a block diagram of an electronic device according to an exemplary embodiment. DETAILED DESCRIPTION

[0024] The specific embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely intended to illustrate and explain the present disclosure, and are not intended to limit the present disclosure.

[0025] Figure 1 is a flowchart of a robot control method according to an embodiment of the present disclosure. As shown in Figure 1 , the method comprises the following steps S11 to S13.

[0026] In step S11, the current task difficulty and the current damage condition of each joint actuator are obtained.

[0027] The task difficulty can be preset, for example, the difficulty level of the robot grabbing a cup can be preset as 6, and the difficulty level of the robot grabbing a paper can be preset as 7, and the like. The higher the difficulty level, the greater the task difficulty.

[0028] The current damage of each joint actuator can be reported by the robot to the server.

[0029] In step S12, based on the current task difficulty and the current damage, the path of each action is planned, and the damage of each joint actuator when the current task is completed is predicted.

[0030] In this step, any feasible prediction method can be used to predict the damage of each joint actuator when the current task is completed, for example, a neural network can be used for prediction.

[0031] The action planning path is a path planned by the server for the robot to complete the current task by means of a visual camera.

[0032] In some embodiments, in the case where the current task needs to be jointly executed by parent and child joint actuators, the damage of each joint actuator when the current task is completed can be predicted based on the task proportion weight of the parent joint actuator and the child joint actuator in the parent and child joint actuators. That is, the parent joint actuator has a heavy task proportion, and the child joint actuator has a light task proportion. For example, performing a horizontal lifting action will use shoulder joint, elbow joint and wrist joint, and the shoulder joint plays a key role, so the task proportion of the shoulder joint can be preset as 70%, the task proportion of the elbow joint can be preset as 20%, and the task proportion of the wrist joint can be preset as 10%. In this way, the joint condition of each joint actuator when the current task is completed can be more reasonably predicted according to the task proportion weight of each joint actuator.

[0033] In step S13, if the prediction result indicates that the corresponding joint actuator does not appear abnormally in the corresponding action planning path when the current task is completed, the corresponding joint actuator is controlled to execute the current task along the corresponding action planning path.

[0034] The abnormality can include at least one of the following: joint / revolute abnormality of over-pressing, joint / revolute abnormality of under-pressing, joint / revolute abnormality of stuck, joint / revolute abnormality of overheating, joint / revolute abnormality of read-write parameter, joint / revolute abnormality of multi-turn counting, temperature sensor abnormality, Controller Area Network (CAN) communication abnormality, step exceeding a preset threshold, DRV protection, encoder abnormality, brake error, emergency frame corresponding timeout, SOE corresponding timeout, and the like. If any of the above abnormalities of the joint actuator is predicted, it means that the joint actuator cannot work normally, and if none of the above abnormalities occurs, it means that the joint actuator can normally complete the task. For example, if the temperature of the joint / revolute exceeds 50 degrees, the joint / revolute cannot work normally, and after the prediction process according to the embodiments of the present disclosure, the temperature of the joint / revolute after completing the current task is 40 degrees, it is considered that the joint / revolute does not have an overheating abnormality and can perform the current task. On the contrary, if the temperature of the joint / revolute after completing the current task is 60 degrees after the prediction process according to the embodiments of the present disclosure, it is considered that the joint / revolute will have an overheating abnormality and will not be able to perform the current task.

[0035] By adopting the above technical solution, since the current task difficulty and the current damage situation can be used to predict the damage situation of each joint actuator after completing the current task, and the corresponding joint actuator is controlled to perform the current task along the corresponding motion planning path when the prediction result indicates that the corresponding joint actuator does not have an abnormality in the corresponding motion planning path after completing the current task, the influence of the damaged joint on the task success rate can be reduced, and the failure rate of the robot in performing the task can be greatly reduced.

[0036] In some embodiments, the robot control method according to the embodiments of the present disclosure further includes: using the corresponding joint actuator to perform the subsequent task within a preset time after controlling the corresponding joint actuator to perform the current task along the corresponding motion planning path. For example, it is assumed that the left hand of the robot is predicted to be able to perform the current task, and the subsequent task is performed by the left hand of the robot within a preset time. Since the probability of damage of the joint actuator within a short time is relatively low, by such configuration, the consumption of the operation resources of the server can be greatly reduced, and the control efficiency of the robot can be provided.

[0037] In some embodiments, the method according to the embodiments of the present disclosure further includes: feeding back the prediction result to the user, for example, the prediction result can be fed back to the user through the robot limbs, voice, etc. By feeding back the prediction result to the user, the user can more intuitively understand the situation of each joint actuator performing the task.

[0038] In some embodiments, the method according to an embodiment of the present disclosure further comprises: if the prediction result indicates that the corresponding joint actuator has an abnormality in the corresponding motion planning path when the current task is completed, controlling a component composed of joint actuators predicted not to have an abnormality to perform the current task along the motion planning path corresponding thereto. For example, assuming that the elbow joint of the left arm of the robot is predicted to have an abnormality when the current task is completed, the right arm of the robot is controlled to perform the current task based on the prediction result. By using the technical solution described above, when the joint damage degree of one execution component (i.e., a robot execution component including at least one joint actuator to complete a task, such as a left arm) is high, another execution component (such as a right arm) is used to perform the current task, thereby greatly reducing the failure rate of the robot performing the task.

[0039] Figure 2 is a schematic block diagram of a robot control device according to an embodiment of the present disclosure. As shown in Figure 2 the device comprises: an acquisition module 21 configured to acquire a current task difficulty and a current damage condition of each joint actuator; a prediction module 22 configured to predict, based on the current task difficulty and the current damage condition, a damage condition of each joint actuator when the current task is completed for each motion planning path; and a control module 23 configured to, if the prediction result indicates that the corresponding joint actuator does not have an abnormality in the corresponding motion planning path when the current task is completed, control the corresponding joint actuator to perform the current task along the corresponding motion planning path.

[0040] By using the technical solution described above, since the damage condition of each joint actuator when the current task is completed for each motion planning path can be predicted based on the current task difficulty and the current damage condition, and the corresponding joint actuator is controlled to perform the current task along the corresponding motion planning path if the prediction result indicates that the corresponding joint actuator does not have an abnormality in the corresponding motion planning path when the current task is completed, the influence of the damaged joint on the success rate of the task can be reduced, and the failure rate of the robot performing the task can be greatly reduced.

[0041] Optionally, the control module 23 is further configured to, if the prediction result indicates that the corresponding joint actuator has an abnormality in the corresponding motion planning path when the current task is completed, control a component composed of joint actuators predicted not to have an abnormality to perform the current task along the motion planning path corresponding thereto.

[0042] Optionally, the prediction module 22 is further configured to, if the current task needs to be jointly performed by parent and child joint actuators, predict the damage condition of each joint actuator when the current task is completed based on a task proportion weight of the parent joint actuator and the child joint actuator in the parent and child joint actuators.

[0043] Optionally, the anomaly comprises at least one of the following: joint / revolute over-press anomaly, joint / revolute under-press anomaly, joint / revolute stall anomaly, joint / revolute overheat anomaly, joint / revolute read-write parameter anomaly, joint / revolute multi-turn count anomaly, temperature sensor anomaly, CAN communication anomaly, step exceeding preset threshold, DRV protection, encoder anomaly, brake error, emergency frame corresponding timeout, SOE corresponding timeout.

[0044] Optionally, the control module 23 is further configured to control the corresponding joint actuator to execute a task after the current task within a preset time after controlling the corresponding joint actuator to execute the current task along the corresponding motion planning path.

[0045] Optionally, the robot control device further comprises a feedback module configured to feed back the prediction result to a user.

[0046] As to the apparatus in the above-mentioned embodiments, the specific manners in which various modules perform operations have been described in detail in the embodiments of the method, and thus will not be described in detail here.

[0047] Figure 3 is a block diagram of an electronic device 700 according to an example embodiment. As shown in Figure 3 The electronic device 700 can include one or more of a processor 701, a memory 702, a multimedia component 703, an input / output (I / O) interface 704, and a communication component 705.

[0048] The processor 701 is configured to control overall operations of the electronic device 700 to complete all or part of the steps of the robot control method described above. The memory 702 is configured to store various types of data to support operations of the electronic device 700, which can include, for example, instructions for operating any application or method on the electronic device 700, and application-related data, such as contact data, transmitted and received messages, pictures, audio, video, and the like. The memory 702 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as a static random access memory (SRAM), an electrically erasable programmable read-only memory (EEPROM), an erasable programmable read-only memory (EPROM), a programmable read-only memory (PROM), a read-only memory (ROM), a magnetic storage, a flash memory, a magnetic disk, or an optical disk. The multimedia component 703 can include a screen and an audio component. The screen can be, for example, a touch screen, and the audio component is configured to output and / or input audio signals. For example, the audio component can include a microphone configured to receive external audio signals. The received audio signals can be further stored in the memory 702 or transmitted through the communication component 705. The audio component further includes at least one speaker configured to output audio signals. The I / O interface 704 provides an interface between the processor 701 and other interface modules, which can be a keyboard, a mouse, a button, and the like. The buttons can be virtual buttons or physical buttons. The communication component 705 is configured to perform wired or wireless communication between the electronic device 700 and other devices. The wireless communication, such as Wi-Fi, Bluetooth, near field communication (NFC), 2G, 3G, 4G, NB-IOT, eMTC, or other 5G, and the like, or a combination of one or more of them, is not limited herein. Therefore, the communication component 705 can include, for example, a Wi-Fi module, a Bluetooth module, an NFC module, and the like.

[0049] In an exemplary embodiment, the electronic device 700 can be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), Programmable Logic Devices (PLDs), Field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for performing the robot control method described above.

[0050] In another exemplary embodiment, a computer-readable storage medium including program instructions is also provided, which, when executed by a processor, implement the steps of the robot control method described above. For example, the computer-readable storage medium can be the memory 702 described above including program instructions, which can be executed by the processor 701 of the electronic device 700 to complete the robot control method described above.

[0051] The preferred embodiments of the present disclosure are described in detail above with reference to the accompanying drawings, but the present disclosure is not limited to the specific details of the above-described embodiments. Various simple modifications can be made to the technical solutions of the present disclosure within the scope of the technical concept of the present disclosure, and these simple modifications all belong to the protection scope of the present disclosure.

[0052] In addition, it should be noted that each specific technical feature described in the above specific embodiments can be combined in any appropriate manner without contradiction. In order to avoid unnecessary repetition, various possible combinations are not described again in the present disclosure.

[0053] Furthermore, any combination of various different embodiments of the present disclosure can also be made, as long as it does not deviate from the idea of the present disclosure, and it should also be considered as disclosed by the present disclosure.

Claims

1. A robot control method characterized by, The method comprises: obtaining a current task difficulty and a current damage condition of each joint actuator, wherein the task difficulty is determined based on a difficulty level; based on the current task difficulty and the current damage condition, predicting a damage condition of each joint actuator when the current task is completed for each action planning path; if the prediction result indicates that the corresponding joint actuator does not appear abnormal in the corresponding action planning path when the current task is completed, controlling the corresponding joint actuator to execute the current task along the corresponding action planning path; in the case where the current task needs to be jointly executed by parent-child joint actuators, the prediction of the damage condition of each joint actuator when the current task is completed comprises: based on the task proportion weight of the parent joint actuator and the child joint actuator in the parent-child joint actuators, predicting the damage condition of each joint actuator when the current task is completed.

2. The method of claim 1, wherein, The method further comprises: if the prediction result indicates that the corresponding joint actuator appears abnormal in the corresponding action planning path when the current task is completed, controlling a component composed of joint actuators predicted not to appear abnormal to execute the current task along the corresponding action planning path.

3. The method of claim 1, wherein, The abnormality includes at least one of the following: joint / rotation abnormality, joint / rotation abnormality, joint / rotation abnormality, joint / rotation abnormality, joint / rotation abnormality, joint / rotation abnormality, joint / rotation abnormality, temperature sensor abnormality, CAN communication abnormality, step exceeding a preset threshold, DRV protection, encoder abnormality, brake error, emergency frame corresponding timeout, SOE corresponding timeout.

4. The method of claim 1, wherein, The method further comprises: within a preset time from controlling the corresponding joint actuator to execute the current task along the corresponding action planning path, all subsequent tasks are executed using the corresponding joint actuator.

5. The method of claim 1, wherein, The method further comprises: feeding back the prediction result to the user.

6. A robot control device characterized by comprising: The method comprises: an acquisition module for acquiring a current task difficulty and a current damage condition of each joint actuator, wherein the task difficulty is determined based on a difficulty level; a prediction module for predicting a damage condition of each joint actuator when the current task is completed for each action planning path based on the current task difficulty and the current damage condition; a control module for controlling the corresponding joint actuator to execute the current task along the corresponding action planning path if the prediction result indicates that the corresponding joint actuator does not appear abnormal in the corresponding action planning path when the current task is completed; the prediction module is further used for, in the case where the current task needs to be jointly executed by parent-child joint actuators, predicting a damage condition of each joint actuator when the current task is completed based on the task proportion weight of the parent joint actuator and the child joint actuator in the parent-child joint actuators.

7. The apparatus of claim 6, wherein, The control module is further configured to, if the prediction result indicates that an abnormality occurs in the corresponding joint actuator in the corresponding motion planning path when the current task is completed, control a component composed of joint actuators predicted not to have the abnormality to execute the current task along the motion planning path corresponding thereto.

8. A computer readable storage medium having stored thereon a computer program, characterized in that, The program, when executed by a processor, implements the steps of the method of any one of claims 1-5.

9. An electronic device, comprising: Comprising: a memory having a computer program stored thereon; a processor configured to execute the computer program in the memory to implement the steps of the method of any one of claims 1-5.

Images