Robot performance detection method and device and electronic equipment

Abstract

The invention provides a robot performance detection method and device and electronic equipment, and relates to the technical field of artificial intelligence, and the method comprises the steps: receiving the detection operation input of a user; determining an abnormal joint module based on the detection operation input; and highlighting the abnormal joint module. According to the embodiment of the invention, automatic detection and fault positioning can be carried out on the abnormal joint module of the robot based on the detection operation input by the user, manual analysis is reduced, the fault positioning efficiency of the robot is improved, and the convenience of fault detection is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of artificial intelligence, and in particular to a robot performance detection method and device and electronic equipment. BACKGROUND

[0002] A humanoid robot has high dynamic, high load and multi-freedom coupling motion characteristics, which greatly damages the joint module. At present, when the joint module of the robot has a fault, the user needs to analyze the behavior of the robot after the fault occurs to locate the fault position, and this positioning method is low in efficiency. SUMMARY

[0003] The robot performance detection method and device and electronic equipment provided by the embodiments of the present application solve the problem of low efficiency of robot fault positioning.

[0004] To solve the above technical problems, the present application is implemented as follows: In a first aspect, the embodiments of the present application provide a robot performance detection method, which comprises the following steps: receiving a detection operation input of a user; determining an abnormal joint module based on the detection operation input; highlighting the abnormal joint module.

[0005] In a second aspect, the embodiments of the present application provide a robot performance detection device, which comprises the following modules: a first input module configured to receive a detection operation input of a user; a processing module configured to determine an abnormal joint module based on the detection operation input; a first output module configured to highlight the abnormal joint module.

[0006] In a third aspect, the embodiments of the present application provide an electronic equipment, which comprises a processor, a memory and a program stored in the memory and executable on the processor, and the program, when executed by the processor, implements the steps of the robot performance detection method of the first aspect.

[0007] In a fourth aspect, the embodiments of the present application provide a computer readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the robot performance detection method of the first aspect.

[0008] In a fifth aspect, a computer program product is provided, which comprises computer instructions, and the computer instructions, when executed by a processor, implement the steps of the robot performance detection method of the first aspect.

[0009] In the embodiment of the present application, the abnormal joint module of the robot can be automatically detected and fault located based on the detection operation input by the user, reducing manual analysis, improving the fault location efficiency of the robot, and improving the convenience of fault detection. BRIEF DESCRIPTION OF DRAWINGS

[0010] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings needed to be used in the description of the embodiments of the present application will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0011] Figure 1 is a flowchart of a robot performance detection method provided by the embodiment of the present application; Figure 2 is one of the interface schematic diagrams of an electronic device provided by the embodiment of the present application; Figure 3 is the second interface schematic diagram of an electronic device provided by the embodiment of the present application; Figure 4 is the third interface schematic diagram of an electronic device provided by the embodiment of the present application; Figure 5 is a structural schematic diagram of a robot performance detection device provided by the embodiment of the present application; Figure 6 is a structural schematic diagram of an electronic device provided by the embodiment of the present application. DETAILED DESCRIPTION

[0012] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0013] The embodiment of the present application provides a robot performance detection method, device and electronic device to solve the problem of low robot fault location efficiency. In the prior art, the fault location in the robot motion control is located by code environment, such as virtual machine command line, which is low in efficiency and high in requirement, and only algorithm personnel can locate.

[0014] Referring to Figure 1 , Figure 1 is a flowchart of a robot performance detection method provided by the embodiment of the present application, as shown in Figure 1 , the method comprises the following steps: Step 101, receiving a detection operation input of a user; Step 102, determining an abnormal joint module based on the detection operation input; Step 103, highlighting the abnormal joint module.

[0015] The detection operation input can be triggered by the operation of the user on the electronic device, for example, as shown in the figure, a control "start detection" of robot performance detection is displayed on the interface of the electronic device, and the user triggers the detection operation by clicking the control. In addition, the detection operation input can also be an input triggered by voice input or other operations. Figure 2

[0016] The joint module can be a joint module of a robot, for example, a joint module of a humanoid robot or a joint module of an animal robot.

[0017] In some embodiments, all joint modules or joint modules of a specific category can be selected for detection. For example, the joint modules of the hands or the joint modules of the legs of a humanoid robot are selected, and corresponding detection parameters are input for detection.

[0018] In some embodiments, the same motion can be performed for joint modules with the same motion function. For example, swing motion is uniformly performed for all hand joint modules, and walking motion is uniformly performed for all leg joint modules.

[0019] In some embodiments, the joint modules can also be customized for detection, and the user selects one or more joint modules for detection.

[0020] When detecting the performance of the joint modules of the robot, the performance data (for example, dynamic position parameters, dynamic torque parameters, etc.) of all joint modules can be collected and compared according to a preset rule. For example, the performance data of the joint modules is compared with the benchmark performance data to determine whether there is a fault.

[0021] The running data (for example, temperature, motion trajectory deviation, etc.) of the joint modules can also be compared with the benchmark range to determine whether there is a fault.

[0022] The abnormal joint module can be understood as a joint module with a fault, including a joint module with a mechanical problem causing a fault, for example, broken gear teeth, bearing fragmentation, output shaft deformation, etc. It can also include a joint module with a chronic injury causing a fault, for example, increased viscosity of lubricating grease, gear pitting, bearing raceway fatigue shedding, etc.

[0023] By automatically detecting the performance of the joint modules of the robot, the abnormal joint module is highlighted in the case of an abnormal joint module. ​

[0024] The highlight mark is used to visually identify the abnormal joint, for example, highlighting, color marking, border thickening, flickering, etc., so that the user can quickly identify the abnormal position.

[0025] For example, the abnormal joint is automatically highlighted, turned red and flickered, a label "gear pitting" is displayed beside the joint module, and the abnormal level "slight abnormality" is displayed.

[0026] As shown in Figure 3 After the detection is completed, the electronic device displays the abnormal joint as a red mark (indicated by an arrow in the figure, and the color is not shown in the figure). The user can click the "detection report" control displayed on the interface to view the detection result.

[0027] In some embodiments, the joint module with an abnormality is highlighted, and when the user operates the abnormal joint module, detailed performance information of the joint module is further displayed.

[0028] The embodiments of the present application can automatically detect and locate the abnormal joint module of the robot based on the detection operation input by the user, reduce manual analysis for fault location, improve the fault location efficiency of the robot, and improve the convenience of fault detection. For some hidden faults caused by chronic damage that are usually difficult to identify, precise and rapid detection can also be performed, and the detection efficiency is improved.

[0029] Optionally, the method further comprises: receiving a viewing operation input of the user for the abnormal joint module; displaying a performance parameter comparison result of the abnormal joint module; the performance parameter comparison result includes at least one of the similarity, the maximum threshold deviation, and the minimum threshold deviation of the actual performance parameter curve and the benchmark performance parameter curve of the abnormal joint module.

[0030] The viewing operation input can be a click operation input, a voice operation input, etc. of the user on the abnormal joint module or the abnormality indicating mark, so as to trigger the electronic device to display the detailed information of the abnormal joint module.

[0031] The electronic device displays the comparison result of the actual performance parameter curve and the benchmark performance parameter curve of the abnormal joint module in response to the viewing operation input.

[0032] The actual performance parameters of the joint module can include quantifiable performance indicators such as the position and torque of the joint module of the robot during movement. In some embodiments, dynamic parameters of the joint module are collected, and combined with environmental sensor data (such as temperature, humidity, vibration) and working load information to construct multiple performance parameters.

[0033] In addition, baseline performance parameters of the robot are obtained. These parameters characterize the theoretical values ​​of the joint module's performance parameters when the robot performs the motion in a healthy state. For example, the baseline performance parameters can be calculated by simulating the robot's motion task, or they can be the theoretical values ​​of the joint module's baseline performance parameters obtained through calculation when the robot performs the motion task.

[0034] Obtain the actual performance parameter curves as the actual performance parameters change over time and the baseline performance parameter curves as the baseline performance parameters change over time.

[0035] The comparison results are generated by comparing the actual performance parameter curves and the benchmark performance parameter curves. The comparison results may include the actual performance parameter curves and the benchmark performance parameter curves, as well as the similarity between the actual performance parameter curves and the benchmark performance parameter curves and the deviation of the feature values ​​on the curves (such as the maximum threshold deviation and the minimum threshold deviation).

[0036] In some implementations, the Dynamic Time Warping (DTW) algorithm is used to calculate the shape similarity between the actual curve and the reference curve. This algorithm can effectively handle the offset on the time axis and calculate the similarity of the curve shapes.

[0037] In addition, the deviations between the actual performance parameter curve and the benchmark performance parameter curve at the maximum and minimum thresholds are calculated, namely the maximum threshold deviation and the minimum threshold deviation.

[0038] For example, such as Figure 4 As shown, an image of the robot is displayed on the electronic device's screen. When the user clicks on the highlighted left knee joint in the robot image (indicated by the arrow in the image), a comparison chart of the actual position curve (actual performance parameter curve) and the theoretical position curve (benchmark performance parameter curve) of the left knee joint is automatically displayed in the right-hand display area, along with a comparison chart of the actual torque curve (actual performance parameter curve) and the theoretical torque curve (benchmark performance parameter curve). Key difference values ​​are also displayed: similarity, maximum threshold deviation, and minimum threshold deviation. Detailed comparison information is obtained through interactive operation, allowing users to analyze visualized data and reducing the error rate of human judgment.

[0039] In addition, a message indicating "Decreased performance of the left knee joint" can be displayed. Alternatively, when the user clicks on the highlighted left knee joint in the robot image, a separate interface can pop up displaying the aforementioned information, thus resolving the issue of an overly dense and inaccessible interface affecting the visual experience when there is too much information.

[0040] The DTW algorithm can accurately calculate the curve shape similarity, quantify the difference between the actual performance and the theoretical performance, intuitively show the degree of performance decline, and improve the detection effect of the robot joint module performance.

[0041] In some embodiments, the comparison result is dynamically generated based on historical performance data and current environmental conditions through a machine learning model. According to the current comparison result, the current similarity or difference is calculated, the difference trend in the future preset period is analyzed, the performance degradation trend of the joint is predicted, and the comparison result containing the trend prediction is generated.

[0042] For example, the performance similarity of the right shoulder joint of the robot decreases from 95% to 88% in the past week, with a decrease rate of 1.5% / day. The comparison result not only shows the current difference, but also predicts that the joint will have a performance decline to the critical point within 72 hours.

[0043] In some embodiments, different levels of prompt information are output according to the degree of performance decline and the degree of urgency. The prompt information can also include performance parameters, comparison results, decline degree, urgency degree, and preventive maintenance suggestions.

[0044] For example, when the similarity is determined to be 87% (yellow warning) according to the comparison result, the output is "right shoulder joint performance slightly decreased, similarity 87%, suggest checking within 3 days", and the performance trend chart in the past 30 days and maintenance suggestions are displayed.

[0045] In the above manner, for the chronic damage of the joint module of the robot, the performance problem of the joint can be accurately located, the indicators can be quantified, the degree of performance decline can be intuitively displayed, and the detection efficiency is improved.

[0046] Optionally, the user is a human or a robot; the robot includes one of a robot with a physical entity and a software agent.

[0047] In this embodiment, the user can operate the robot to realize task configuration, motion task setting, start detection, stop detection, end detection, view detection report, and the like according to actual needs.

[0048] The robot can also operate itself or be operated by other robots, software agents, and the like to realize task configuration, motion task setting, start detection, stop detection, end detection, view detection report, and the like. Automatic detection can be realized, human operation can be reduced, and detection efficiency can be improved.

[0049] Optionally, the detection operation input includes at least one of the following operation inputs: Operation input for starting detection control; An operation input for the pause detection control; An operation input for the end detection control.

[0050] As shown in Figure 3 , the electronic device can display the start detection control, the pause detection control and the end detection control. As known from the above, the response of highlighting the abnormal joint module can occur at any link of the detection process, such as can be after clicking the start detection control, or can be before (the user finds the abnormal joint module and clicks to view the specific information after clicking the pause, improving the efficiency) or after clicking the pause detection control, or can be after clicking the end detection control.

[0051] In the case where the user operates the start detection control, the joint module of the robot is detected, and in the case where an abnormal joint module is detected, the abnormal joint module is highlighted. If the detection result needs to be viewed, the detection report control or the corresponding joint module can also be operated.

[0052] In the case where the user operates the pause detection control, the joint module of the robot is paused, and in the case where an abnormal joint module is detected, the abnormal joint module is highlighted. If the continue detection control is operated again, the performance detection can be continued, and flexible control of the detection progress can be achieved.

[0053] In the case where the user operates the end detection control, the joint module of the robot is ended, and in the case where an abnormal joint module is detected, the abnormal joint module is highlighted.

[0054] In some embodiments, in the case of ending the detection, a detection report can be generated.

[0055] Through the above operations, flexible control of the detection process can be achieved, and the detection efficiency can be improved.

[0056] Optionally, in the case where the detection operation input is the operation input for the start detection control, a start instruction is sent to the robot through at least one of Bluetooth, wireless, and a server, to control the robot to start executing a motion task, that is, the start instruction can be regarded as one of a remote boot instruction, a remote detection instruction, or a combination thereof.

[0057] The user can send a start instruction to the robot through at least one of Bluetooth, wireless, and a server, to detect the performance of the robot.

[0058] After sending the start instruction to the robot, an excitation signal can be input to the robot, the robot executes a motion task according to the excitation signal, and the performance parameters of the joint module during the execution of the motion task can be collected to detect the performance of the robot based on the performance parameters.

[0059] In this way, the operation of the user can be reduced, the operation convenience can be improved, and the detection efficiency can be improved.

[0060] Optionally, before receiving the detection operation input of the user, the method further includes: receiving a selection operation input of the user for the motion task; the selection operation input is used to select a motion task type of the robot; the motion task type includes at least one of the following motion task types: standing in place, sitting down, squatting, standing up, adjusting height in place, stepping in place, turning left, turning right, turning back, walking forward, walking back, walking left, walking right, running forward, running back, running left, running right, jumping forward, jumping back, jumping left, jumping right, somersaulting forward, somersaulting back, somersaulting left, somersaulting right, crawling forward.

[0061] The robot described above can be a humanoid robot.

[0062] The user can select a specific motion type of the motion task, which can specifically include a combination of one or more motions, or a plurality of motion types executed in sequence according to an order. In this way, the relevant joint module can be detected for different tasks or task sequences (a plurality of motion tasks executed in sequence), and the efficiency of motion control development can be improved.

[0063] In some embodiments, the motion type can be divided into task types according to specific motion content. The user can select one or more types of tasks.

[0064] For example, basic postures: standing in place, sitting down, squatting, standing up; Direction transformation: turning left, turning right, turning back; Moving tasks: stepping in place, walking forward, walking back, walking left, walking right; Jumping tasks: jumping forward, jumping back, jumping left, jumping right; High-speed movement: running forward, running back, running left, running right.

[0065] The above only lists some classification methods as examples.

[0066] The motion task can also be divided according to the difficulty of the motion, and the user can select a task of any difficulty.

[0067] In this way, the robot can be controlled to perform a specified motion task to detect the performance of the robot in performing the motion task, and the comprehensiveness of the performance detection of the robot can be improved.

[0068] In some embodiments, the motion task is a combined motion of a plurality of sub-motion tasks, and the method further comprises: receiving a selection input of a user on the plurality of motion task types; combining the plurality of motion task types to obtain the motion task; applying an excitation signal corresponding to the motion task to the first joint module of the robot.

[0069] For a first joint module (including one or more joint modules) that needs to perform multiple motions, a plurality of motion types can be combined in sequence, for example, walking and then sitting.

[0070] When there are multiple joint modules, the multiple joint modules can perform the motion task in the same way as described above, i.e., the motion start time is the same, and the motion period is the same. In addition, according to the actual application of the robot, for the joint that is used more and may have problems, corresponding motion test can be performed.

[0071] In some embodiments, the motion task can be generated based on the current health status of the robot.

[0072] By applying the corresponding excitation signal to the target joint module, the test efficiency and test accuracy can be improved.

[0073] Optionally, before receiving the selection operation input of the user on the motion task, the method further comprises: receiving a configuration operation input of a user on a task configuration control; the configuration operation input is used to input parameter configuration information of the motion task; the parameter configuration information includes a type of the motion task, a joint module participating in the motion task, and an excitation signal, a motion start time of the joint module.

[0074] According to the configuration operation input, the configuration of the motion task is completed.

[0075] As shown in Figure 2 , the electronic device displays a task configuration control, and the user can operate the task configuration control to configure the parameters of the task.

[0076] In some embodiments, the type of the motion task can be configured, for example, one or more motion task types are selected. When the motion task is displayed, information such as joint module applicable to the motion task can also be displayed to facilitate selection.

[0077] The configuration information of the joint module can include all joint modules, introduction information of each joint module, and display of applicable motion tasks to facilitate selection of the motion task.

[0078] The configuration information of the excitation signal can include frequency range, amplitude range, phase, etc. of the excitation signal, and can also display a waveform diagram of the excitation signal.

[0079] The configuration information of the motion time can include a time selector, which can be used to select a starting time, including real-time detection or timing detection.

[0080] During the detection, information such as detection progress can also be displayed.

[0081] Through the above configuration parameter setting, the detection scene can be accurately set according to the user's demand, and the detection accuracy is improved.

[0082] Optionally, the abnormal joint module is a joint module whose actual value and reference value of the performance parameter are inconsistent during the robot performing the motion task; the performance parameter includes at least one of position parameter, torque parameter, speed, acceleration, jerk, friction damping, and energy consumption.

[0083] The actual value and the reference value of the performance parameter being inconsistent can be understood as that the difference between the actual value and the reference value is greater than a pre-set value, or the proportion of the difference is greater than a pre-set proportion value.

[0084] In some embodiments, the humanoid robot is fixed on a test tool in a non-falling hanging manner, and an excitation signal is applied to the robot to drive the robot to perform a motion task. During the motion task of the robot, one or more of the performance parameters of each joint module, including position parameter, torque parameter, speed, acceleration, jerk, friction damping, and energy consumption, can be collected in real time.

[0085] The position parameter of the joint module includes the rotation angle of the output shaft in the joint module.

[0086] For example, the actual positions and torques of each joint module in any 2 cycles during the first motion of the robot are obtained, and the actual position curve and dynamic torque curve of the joint module are generated.

[0087] The friction damping can be the internal friction damping of the joint, and the energy consumption can be the energy consumption of the joint module during the motion.

[0088] Through multi-parameter collaborative analysis, more comprehensive joint performance evaluation can be obtained. Different problems can be located by different parameters, such as increased friction damping indicating lubrication problems and torque deviation indicating mechanical problems, which can improve the accuracy of problem diagnosis and improve the detection efficiency. Through multi-parameter detection, the misjudgment of a single parameter is reduced.

[0089] Optionally, the highlighting of the abnormal joint module includes: In the distribution diagram of the joint modules of the robot, the abnormal joint module is highlighted in a manner different from other joint modules so as to quickly attract the attention of the user.

[0090] In the case where the abnormal joint module is detected, in the distribution diagram of the joint modules of the robot, the abnormal joint module is highlighted in a manner different from other joint modules so as to quickly attract the attention of the user.

[0091] In some embodiments, before detecting the performance of the joint module, a distribution diagram of the joint modules of the robot including all modules of the robot is displayed on the interface of the electronic device, and the user can select the joint module for which the performance detection is required. After the detection is completed, the abnormal joint module is highlighted on the distribution diagram of the joint modules, and in addition, the type of the abnormality, the cause of the abnormality, the maintenance suggestion, etc. can be displayed beside the abnormal joint module so that the user can quickly obtain the position of the abnormal joint module.

[0092] Optionally, the method further comprises: receiving a viewing operation input of the user for the detection report control; displaying the detection report; the content of the detection report includes the type of the motion task, the performance analysis of the abnormal joint module participating in the motion task, and the suggestion.

[0093] The interface of the electronic device can further display a detection report control, and in the case where the user operates the detection report control, i.e. a viewing operation input, the detection report is displayed.

[0094] The detection report includes the type of the motion task performed by the robot, the performance analysis of the abnormal joint module (such as the comparison result of the actual performance parameter curve and the benchmark performance parameter curve), and can further display the performance score (such as 90 points) reflecting the performance state of the joint module, the performance state description (such as slight performance decline, serious performance decline), the type of the abnormality of the abnormal joint module, the cause, the future performance decline trend, and the suggestion for maintenance measures, etc.

[0095] In the above manner, the user can quickly obtain the detection result of the performance of the joint module of the robot, and the user operation can be reduced, and the processing efficiency of the robot can be improved.

[0096] Optionally, the method further comprises: In the case where the sharing operation input of the user is received, the detection report is sent to the target user; the sharing operation input includes the target user information; the target user at least includes one of the test group member, the supplier of the abnormal joint module, and the manufacturer of the robot, so as to improve the communication efficiency of operation and maintenance and upstream and downstream cooperation.

[0097] The interface of the electronic device can further display a sharing operation control or icon. A user can input target user information by operating the control or icon, and send the detection report of the robot to the target user.

[0098] In some embodiments, one or more target users to be shared can be preset. In a case where a user performs a sharing operation input, the detection report of the robot is sent to the preset target users.

[0099] In some embodiments, one or more target users to be shared can be preset. In a case where a user performs a sharing operation input, the detection report of the robot is sent to the preset target users.

[0100] The performance analysis report is sent to a user device associated with the joint module, for example, a user device of an abnormal joint module supplier, a user device of a test group member, or a user device of a robot manufacturer.

[0101] For example, when the performance of the right shoulder joint module of the robot is detected to decrease, the performance analysis report includes: similarity to the reference performance: 82% (slight decrease); maximum threshold deviation: 12%; minimum threshold deviation: 15%; comprehensive score: 78 points; performance status: slight performance decrease; recommended maintenance measure: slight performance decrease of the right shoulder joint, it is recommended to check the lubrication system, and it is predicted that the performance will further decrease within 72 hours. The performance analysis report is sent to the supplier and the tester. By generating the performance analysis report, the performance status of the joint module can be quickly and comprehensively obtained, so that corresponding processing can be performed.

[0102] In the above manner, the detection report of the robot can be quickly sent to the target user, so that the target user can obtain the performance information of the robot, and take corresponding measures, thereby reducing user operations and improving operation convenience and efficiency.

[0103] Optionally, the determining of the abnormal joint module based on the detection operation input comprises: determining a motion task performed by the robot based on the detection operation input; obtaining an actual value of a performance parameter of a joint module participating in the motion task based on the motion task; comparing the actual value of the performance parameter with a reference value to obtain a performance parameter comparison result; the performance parameter comparison result is used to represent the difference between the actual value of the performance parameter of the joint module and the reference value; in a case where the performance parameter comparison result is greater than a preset value, the joint module is determined as an abnormal joint module.

[0104] In the case that the user inputs the detection operation, the motion task performed by the robot is acquired, such as walking, turning right, etc. The motion task can be a pre-set motion task, or a motion task input by the user before the detection operation.

[0105] The robot is input with an excitation signal to drive the robot to perform the motion task. In the process of performing the motion task by the robot, the actual value of the performance parameter of the joint module performing the motion task is acquired, i.e., the performance parameter acquired in real time.

[0106] For example, in the walking task, the joints involved include the left knee joint, the right knee joint, and the hip joint. The performance parameters of these joint modules are collected in real time through the sensor network. In addition, the reference value of the performance parameter, i.e., the theoretical value of the performance parameter of the robot in a healthy state, is acquired.

[0107] In the case that the difference between the actual value and the reference value is greater than a preset value according to the comparison result of the performance parameter, the joint module is determined as an abnormal joint module.

[0108] In some embodiments, the curve of the actual value changing over time and the curve of the theoretical value changing over time can be acquired, and the difference between the two curves is acquired. In the case that the difference is greater than a preset value, the joint module is determined as an abnormal joint module.

[0109] In some embodiments, a plurality of performance parameters can be acquired, such as position parameters, torque parameters, etc.

[0110] In the case that the difference between at least two performance parameters in the plurality of performance parameters is greater than a preset value, the joint module is determined as an abnormal joint module, reducing the false judgment caused by a single parameter.

[0111] In the case that the difference between any one of the plurality of performance parameters is greater than a preset value, the joint module is determined as an abnormal joint module, reducing the missed identification of the abnormal joint module.

[0112] In the case that the abnormal joint module is identified, a prompt information can be output, which can include an abnormal joint position identifier, a difference degree, a curve comparison graph, etc., facilitating the user to quickly locate the problem.

[0113] Through the above parameter comparison and analysis, the accuracy of detecting the abnormal joint module can be improved.

[0114] Optionally, the comparison of the actual value of the performance parameter with the reference value to obtain a performance parameter comparison result comprises: generating an actual curve according to the actual value of the performance parameter, and generating a reference curve according to the reference value of the performance parameter; The performance parameter comparison results are obtained by comparing the actual curve and the benchmark curve; the performance parameter comparison results include at least one of the following: the similarity of the curve shape of the actual curve and the benchmark curve, the maximum threshold deviation between the actual curve and the benchmark curve, and the minimum threshold deviation between the actual curve and the benchmark curve.

[0115] The actual curve is the curve showing the actual value of the performance parameter changing over time, while the reference curve is the curve showing the reference value of the performance parameter changing over time.

[0116] like Figure 4 As shown, a curve comparing the theoretical position and the actual position of the generated left leg joint module, as well as a curve comparing the theoretical torque and the actual torque, are presented.

[0117] By comparing the actual curve with the reference curve, we can obtain the shape similarity between the two curves, as well as the maximum and minimum threshold deviations. The maximum and minimum thresholds can be the maximum and minimum values ​​on the curves, respectively.

[0118] By comparing the actual curve with the benchmark curve using multiple parameters, the accuracy and comprehensiveness of the comparison results can be improved.

[0119] Optionally, after identifying the abnormal joint module, the method further includes: By combining artificial intelligence (AI), a detection report is automatically generated; the content of the detection report includes: the type of motion task, the performance analysis of the abnormal joint module participating in the motion task, and suggestions.

[0120] A template for the performance test report can be pre-defined, including the specific items to be generated, such as test time, robot model, motion task type, joint modules involved in the motion task, performance analysis, and maintenance recommendations.

[0121] For abnormal joint modules, the comparison results between actual performance and benchmark performance can be further displayed.

[0122] For abnormal joint modules, the system can display the type of abnormality and corresponding maintenance suggestions.

[0123] By using the methods described above, the efficiency and accuracy of test report generation can be improved, avoiding errors caused by manual writing.

[0124] Optionally, the number of joint modules performing the motion task is multiple; before obtaining the actual values ​​of the performance parameters of the joint modules participating in the motion task, the method further includes: Apply excitation signals to a plurality of joint modules participating in the motion task, respectively, to drive the joint modules of the robot to perform the motion task together. The motion start time and the motion cycle of the plurality of joint modules are the same, and the motion amplitudes of at least some joint modules in the plurality of joint modules are different.

[0125] The plurality of joint modules participating in performing the motion task can be joint modules corresponding to a plurality of joints for achieving the same motion function (for example, for leg joints), or can be all joint modules of the robot. When the number of joint modules is large, performance comparison between different joint modules can be performed.

[0126] The excitation signals are applied to the plurality of joint modules of the robot performing the motion task, the phases of the excitation signals of all joints are the same, and the frequency bands are the same, so that the motion start time of the plurality of joints is the same, and the motion cycle is the same. For example, input the excitation signal of the sine wave with the same phase and the same frequency band.

[0127] When the plurality of joint modules include joints for achieving different motion functions, the motion amplitudes of the joint modules of different motion functions are different. For example, the motion amplitude (maximum motion amplitude) of the leg and the motion amplitude of the hand are different.

[0128] The plurality of joint modules perform the same motion, the motion start time and the motion cycle are consistent, which can reduce the mutual interference between the plurality of joints, and can reduce the misjudgment caused by the coupling of the plurality of joint modules (that is, the influence caused by the simultaneous motion of the plurality of joint modules) during subsequent performance comparison.

[0129] Referring to Figure 5 , Figure 5 is a structural schematic diagram of a robot performance detection device provided by an embodiment of the present application, as Figure 5 shown, the robot performance detection device 500 includes: A first receiving module 501 configured to receive a detection operation input of a user. A determination module 502 configured to determine an abnormal joint module based on the detection operation input. A first display module 503 configured to highlight the abnormal joint module.

[0130] Optionally, the device further includes: A second receiving module configured to receive a viewing operation input of the user for the abnormal joint module. The second display module is configured to display a performance parameter comparison result of the abnormal joint module, wherein the performance parameter comparison result comprises at least one of a similarity, a maximum threshold deviation, and a minimum threshold deviation between an actual performance parameter curve of the abnormal joint module and a benchmark performance parameter curve.

[0131] Optionally, the user is a human or a robot; the robot comprises one of a robot having a physical entity and a software agent.

[0132] Optionally, the detection operation input comprises at least one of the following operation inputs: an operation input for starting detection control; an operation input for pausing detection control; an operation input for ending detection control.

[0133] Optionally, in the case of the operation input for starting detection control, a start instruction is sent to the robot through at least one of Bluetooth, wireless communication, and a server to control the robot to start performing a motion task.

[0134] Optionally, the apparatus further comprises: a third receiving module configured to receive a selection operation input of a user for a motion task; the selection operation input is used to select a motion task type of a robot; the motion task type comprises at least one of the following motion task types: standing in place, sitting down, squatting down, standing up, adjusting height in place, stepping in place, turning left, turning right, turning back, walking forward, walking backward, walking left, walking right, running forward, running backward, running left, running right, jumping forward, jumping backward, jumping left, jumping right, somersaulting forward, somersaulting backward, somersaulting left, somersaulting right, crawling forward.

[0135] Optionally, the apparatus further comprises: a fourth receiving module configured to receive a configuration operation input of a user for a task configuration control; the configuration operation input is used to input parameter configuration information of a motion task; the parameter configuration information comprises a type of the motion task, a joint module participating in the motion task, and an excitation signal and a motion start time of the joint module.

[0136] a configuration module configured to complete configuration of the motion task according to the configuration operation input.

[0137] Optionally, the abnormal joint module is a joint module whose actual value and benchmark value of a performance parameter are inconsistent during execution of a motion task by a robot; the performance parameter comprises at least one of a position parameter, a torque parameter, a speed, an acceleration, a jerk, a frictional damping, and an energy consumption.

[0138] Optionally, the first display module is specifically configured to: highlight the abnormal joint module in a distribution diagram of the joint modules of the robot.

[0139] Optionally, the apparatus further comprises: a fifth receiving module configured to receive a viewing operation input of a user for the detection report control; a third display module configured to display the detection report; the content of the detection report comprises a motion task type, performance analysis of the abnormal joint module participating in the motion task, and a suggestion.

[0140] Optionally, the apparatus further comprises: a sending module configured to, in a case where a sharing operation input of a user is received, send the detection report to a target user; the sharing operation input comprises target user information; the target user at least comprises one of a test group member, a supplier of the abnormal joint module, and a manufacturer of the robot.

[0141] Optionally, the determining module comprises: a determining sub-module configured to determine a motion task performed by the robot based on the detection operation input; an acquiring sub-module configured to acquire an actual value of a performance parameter of a joint module participating in the motion task based on the motion task; a comparing sub-module configured to compare the actual value of the performance parameter with a reference value to obtain a performance parameter comparison result; the performance parameter comparison result is used to represent a difference between the actual value and the reference value of the performance parameter of the joint module; in a case where the performance parameter comparison result is greater than a preset value, determine the joint module as an abnormal joint module.

[0142] Optionally, the comparing sub-module is specifically configured to: generate an actual curve according to the actual value of the performance parameter, and generate a reference curve according to the reference value of the performance parameter; compare the actual curve and the reference curve to obtain the performance parameter comparison result; the performance parameter comparison result comprises at least one of a similarity of curve shapes of the actual curve and the reference curve, a maximum threshold deviation on the actual curve and the reference curve, and a minimum threshold deviation on the actual curve and the reference curve.

[0143] Optionally, the apparatus further comprises: The generating module is used for automatically generating a detection report in combination with AI; the content of the detection report includes: a movement task type, performance analysis of the abnormal joint module participating in the movement task, and a suggestion.

[0144] The detection device for robot performance can realize Figure 1 the processes in the method embodiments, and achieve the same technical effects. To avoid repetition, details are not repeated here.

[0145] As Figure 6 shown, the embodiments of the present application also provide an electronic device 600, which comprises a processor 601, a memory 602, and a program stored in the memory 602 and executable on the processor 601. The program is executed by the processor 601 to realize the processes of the above-mentioned robot performance detection method embodiments, and achieve the same technical effects. To avoid repetition, details are not repeated here.

[0146] The embodiments of the present application also provide a computer readable storage medium, which stores a computer program. The computer program is executed by a processor to realize the processes of the above-mentioned robot performance detection method embodiments, and achieve the same technical effects. To avoid repetition, details are not repeated here. The computer readable storage medium includes a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0147] The embodiments of the present application also provide a computer program product, which comprises computer instructions. The computer instructions are executed by a processor to realize the processes of the above-mentioned method embodiments, and achieve the same technical effects. To avoid repetition, details are not repeated here. Figure 1

[0148] It should be noted that in this document, the terms "comprising", "including", or any other variant thereof are intended to cover non-exclusive inclusion, so that processes, methods, articles, or devices including a series of elements not only include those elements, but also include other elements not explicitly listed, or inherent to such processes, methods, articles, or devices. Without more limitations, the element defined by the statement "comprising a" does not exclude the presence of other identical elements in the process, method, article, or device including the element.

[0149] ​Those skilled in the art can clearly understand the above-mentioned embodiment method can be realized by means of software and the necessary general hardware platform, of course, also can be through hardware, but many cases the former is the better embodiment. Based on such understanding, the technical solutions of the present application essentially or say the part of the contribution to the prior art can be embodied in the form of software products, the computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disc), including a number of instructions to make a terminal (may be a mobile phone, computer, server, air conditioner, or network equipment, etc.) executes the method described in various embodiments of the present application.

[0150] The embodiments of the present application are described above in conjunction with the drawings, but the present application is not limited to the above-mentioned specific embodiments, the above-mentioned specific embodiments are only illustrative, but not limited, those skilled in the art can make many forms without departing from the purpose of the present application and the scope of the claims under the inspiration of the present application, all belong to the protection of the present application.

Claims

1. A method for detecting robot performance, characterized in that, include: Receive user input for detection operations; Based on the detection operation input, abnormal joint modules are identified; The abnormal joint module is highlighted.

2. The method according to claim 1, characterized in that, The method further includes: Receive user input for viewing the abnormal joint module; The display shows the performance parameter comparison results of the abnormal joint module; the performance parameter comparison results include at least one of the following: the similarity between the actual performance parameter curve of the abnormal joint module and the benchmark performance parameter curve, the maximum threshold deviation, and the minimum threshold deviation.

3. The method according to claim 1, characterized in that, The user may be a human or a robot; the robot may be either a robot with a physical entity or a software intelligent agent.

4. The method according to claim 1, characterized in that, The detection operation input includes at least one of the following operation inputs: For input operations related to starting the detection control; Input for pausing the detection control; Input for the operation of ending the detection control.

5. The method according to claim 4, characterized in that, When the detection operation input is the operation input for the start detection control, a start command is sent to the robot via at least one of Bluetooth, wireless, or server to control the robot to start performing the movement task.

6. The method according to claim 1, characterized in that, Before receiving the user's detection operation input, the method further includes: The robot receives user input for selecting a motion task; the selection input is used to select the type of motion task for the robot; the type of motion task includes at least one of the following: Stand in place, sit down, squat down, stand up, raise your head in place, march in place, turn left, turn right, turn around, walk forward, walk backward, walk left, walk right, run forward, run backward, run left, run right, jump forward, jump backward, jump left, jump right, somersault forward, somersault backward, somersault left, somersault right, crawl forward.

7. The method according to claim 6, characterized in that, Before receiving user input regarding a selection action for a motion task, the method further includes: The system receives configuration operation input from the user for the task configuration control; the configuration operation input is used to input parameter configuration information for the motion task; the parameter configuration information includes the type of the motion task, the joint modules participating in the motion task, and the excitation signal and motion start time of the joint modules; Based on the configuration operation input, complete the configuration of the exercise task.

8. The method according to claim 1, characterized in that, The abnormal joint module is a joint module whose actual performance parameters do not match the reference values ​​during the robot's motion task; the performance parameters include at least one of position parameters, torque parameters, velocity, acceleration, jerk, friction damping, and energy consumption.

9. The method according to claim 1, characterized in that, The highlighted abnormal joint module includes: The abnormal joint module is highlighted in the schematic diagram of the robot joint module distribution.

10. The method according to claim 1, characterized in that, The method further includes: Receive user input for viewing the test report control; The detection report is displayed; the content of the detection report includes: the type of motion task, the performance analysis and recommendations of the abnormal joint module participating in the motion task.

11. The method according to claim 10, characterized in that, The method further includes: Upon receiving a user's sharing operation input, the detection report is sent to the target user; the sharing operation input includes target user information; the target user includes at least one of the test team members, the supplier of the abnormal joint module, and the robot manufacturer.

12. The method according to claim 1, characterized in that, The step of determining abnormal joint modules based on the detection operation input includes: Based on the detection operation input, the motion task to be performed by the robot is determined; Based on the motion task, obtain the actual values ​​of the performance parameters of the joint modules participating in the motion task; The actual values ​​of the performance parameters are compared with the benchmark values ​​to obtain the performance parameter comparison results; the performance parameter comparison results are used to characterize the difference between the actual values ​​and the benchmark values ​​of the performance parameters of the joint module. If the performance parameter comparison result is greater than the preset value, the joint module is identified as an abnormal joint module.

13. The method according to claim 12, characterized in that, The step of comparing the actual value of the performance parameter with the benchmark value to obtain the performance parameter comparison result includes: Based on the actual values ​​of the performance parameters, generate the actual curve, and based on the benchmark values ​​of the performance parameters, generate the benchmark curve. The performance parameter comparison results are obtained by comparing the actual curve and the benchmark curve; the performance parameter comparison results include at least one of the following: the similarity of the curve shape of the actual curve and the benchmark curve, the maximum threshold deviation between the actual curve and the benchmark curve, and the minimum threshold deviation between the actual curve and the benchmark curve.

14. The method according to claim 1, characterized in that, After identifying the abnormal joint module, the method further includes: By combining AI, a detection report is automatically generated; the content of the detection report includes: the type of motion task, the performance analysis of the abnormal joint module participating in the motion task, and suggestions.

15. A device for detecting robot performance, characterized in that, include: The first input module is used to receive user input for detection operations. The processing module is used to determine abnormal joint modules based on the detection operation input; The first output module is used to highlight the abnormal joint module.

16. An electronic device, characterized in that, include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein the program, when executed by the processor, implements the steps of the method for detecting robot performance as described in any one of claims 1 to 14.

17. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program that, when executed by a processor, implements the steps of the robot performance detection method as described in any one of claims 1 to 14.

18. A computer program product, characterized in that, It includes computer instructions that, when executed by a processor, implement the steps of the method for detecting robot performance as described in any one of claims 1 to 14.

Images