Abnormity determination method and device of robot and nonvolatile storage medium

Abstract

The invention discloses a robot anomaly determination method and device and a nonvolatile storage medium. The method comprises the following steps: acquiring an initial load deviation threshold value of a target robot and a joint feedback torque in a static state; the joint feedback torque is compared with a preset theoretical gravitational torque, and torque deviation is determined; determining a kinematic model corresponding to the target robot; based on the kinematic model, determining a Jacobian matrix corresponding to the target robot; according to the Jacobian matrix and preset static friction force corresponding to the target robot, the initial load deviation threshold value is adjusted, and a target load deviation threshold value is obtained; and determining an abnormal detection result of the target robot according to the torque deviation and the target load deviation threshold. According to the method, the technical problem that unexpected movement occurs when the robot is dragged and demonstrated due to the fact that the collaborative robot lacks an effective mechanism to verify the accuracy of the load parameters under the static condition is solved.

Description

Technical Field

[0001] This invention relates to the field of robotics, and more specifically, to a method, apparatus, and non-volatile storage medium for determining anomalies in a robot. Background Technology

[0002] Currently, most collaborative robots have near-zero force drag teaching capabilities. The basic principle is to put each joint of the robot into torque control mode. Based on the robot's current state, the theoretical torque of each joint is calculated to precisely counteract the robot's gravitational torque. At this point, the robot will move in response to the applied force, thus completing the teaching operation. The core of this function is that the theoretical torque must precisely counteract the robot's gravitational torque. If the theoretical torque is too large, the robot will automatically lift up; if the theoretical torque is too small, the robot will automatically fall, both of which could be dangerous.

[0003] When a robot's own dynamic parameters are accurate, the accuracy of the theoretical torque largely depends on the accuracy of the robot's load settings. Most existing technologies identify the robot's accurate load by moving it, but there's a possibility that the user might arbitrarily set an incorrect load without proper identification. This could lead to unexpected robot movements and potential hazards when the user enters the drag-and-drop teaching function.

[0004] There is currently no effective solution to the above problems. Summary of the Invention

[0005] This invention provides a method, apparatus, and non-volatile storage medium for determining robot anomalies, at least to address the technical problem of unexpected robot movement during drag-and-teach caused by the lack of an effective mechanism to verify the accuracy of load parameters under static conditions.

[0006] According to one aspect of the present invention, a method for determining anomalies in a robot is provided, comprising: acquiring an initial load deviation threshold and a joint feedback torque in a static state of a target robot, wherein the initial load deviation threshold characterizes the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is a torque measured by a torque sensor at a joint of the target robot; comparing the joint feedback torque with a preset theoretical gravitational torque to determine a torque deviation; determining a kinematic model corresponding to the target robot; determining a Jacobian matrix corresponding to the target robot based on the kinematic model; adjusting the initial load deviation threshold according to the Jacobian matrix and a preset static friction force corresponding to the target robot to obtain a target load deviation threshold; and determining anomaly detection results of the target robot based on the torque deviation and the target load deviation threshold.

[0007] Optionally, the initial load deviation threshold is adjusted according to the Jacobian matrix and the preset static friction force to obtain the target load deviation threshold, including: obtaining the rank of the Jacobian matrix; if the rank of the Jacobian matrix is ​​not full rank, comparing the initial load deviation threshold with the preset static friction force threshold; if the initial load deviation threshold is less than the preset static friction force threshold, expanding the initial load deviation threshold by a preset multiple to determine the target load deviation threshold; if the initial load deviation threshold is not less than the preset static friction force threshold, determining the initial load deviation threshold as the target load deviation threshold.

[0008] Optionally, the joint feedback torque is compared with the preset theoretical gravity torque to determine the torque deviation, including: obtaining the projection length from the end effector of the target robot to each of the multiple joints; determining the joints whose projection length exceeds a preset length threshold as target joints; and determining the torque deviation based on the feedback torque corresponding to the target joint in the joint feedback torque and the preset theoretical gravity torque.

[0009] Optionally, the initial load deviation threshold includes an initial warning deviation threshold and an initial error deviation threshold, and the target load deviation threshold includes a target warning deviation threshold and a target error deviation threshold.

[0010] Optionally, based on the torque deviation and the target load deviation threshold, the abnormal detection result of the target robot is determined, including: if the torque deviation exceeds the target warning deviation threshold but does not exceed the target error deviation threshold, the abnormal detection result is determined to be abnormal and an early warning message is generated; the early warning message is sent; a drag prompt is received based on the feedback of the early warning message; and the state of the target robot is adjusted based on the drag prompt.

[0011] Optionally, the abnormal detection result of the target robot is determined based on the torque deviation and the target load deviation threshold, including: if the torque deviation exceeds the target error deviation threshold, the abnormal detection result is determined to be abnormal and an abnormal prompt is generated; the abnormal prompt is sent and the target robot is controlled to remain stationary.

[0012] According to another aspect of the present invention, an anomaly determination device for a robot is also provided, comprising: an acquisition module, configured to acquire an initial load deviation threshold and a joint feedback torque in a static state of a target robot, wherein the initial load deviation threshold characterizes the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is a torque measured by a torque sensor at a joint of the target robot; a comparison module, configured to compare the joint feedback torque with a preset theoretical gravitational torque to determine a torque deviation; a first determination module, configured to determine a kinematic model corresponding to the target robot; a second determination module, configured to determine a Jacobian matrix corresponding to the target robot based on the kinematic model; an adjustment module, configured to adjust the initial load deviation threshold according to the Jacobian matrix and a preset static friction force corresponding to the target robot to obtain a target load deviation threshold; and a third determination module, configured to determine an anomaly detection result of the target robot based on the torque deviation and the target load deviation threshold.

[0013] According to another aspect of the present invention, a non-volatile storage medium is also provided, the non-volatile storage medium including a stored program, wherein, when the program is running, the device where the non-volatile storage medium is located is controlled to execute any of the above-described methods for determining the anomaly of a robot.

[0014] According to another aspect of the present invention, a computer device is also provided, the computer device including a processor, the processor being configured to run a program, wherein the program executes any of the above-described methods for determining the anomaly of a robot.

[0015] According to another aspect of the present invention, a computer program product is also provided, including a computer program that, when executed by a processor, implements any of the above-described methods for determining the anomaly of a robot.

[0016] In this embodiment of the invention, an anomaly detection method for robots is employed. This method acquires the initial load deviation threshold and the joint feedback torque in a static state of the target robot. The initial load deviation threshold represents the deviation threshold between the actual load of the target robot and a preset load. The joint feedback torque is the torque measured by torque sensors at the joints of the target robot. The joint feedback torque is compared with a preset theoretical gravitational torque to determine the torque deviation. The kinematic model corresponding to the target robot is then determined. Based on the kinematic model, the Jacobian matrix corresponding to the target robot is determined. The initial load deviation threshold is adjusted according to the Jacobian matrix and the preset static friction force corresponding to the target robot to obtain the target load deviation threshold. Based on the torque deviation and the target load deviation threshold, the anomaly detection result of the target robot is determined. This achieves the goal of monitoring whether there is a deviation in the load setting in a non-moving state, thereby improving the technical effect of robot safety. Furthermore, it solves the technical problem of unexpected movement of collaborative robots during drag-and-teach operations caused by the lack of an effective mechanism to verify the accuracy of load parameters under static conditions. Attached Figure Description

[0017] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this application, illustrate exemplary embodiments of the invention and, together with their description, serve to explain the invention and do not constitute an undue limitation thereof. In the drawings:

[0018] Figure 1 A hardware block diagram of a computer terminal for implementing an anomaly determination method for a robot is shown.

[0019] Figure 2 This is a flowchart illustrating a method for determining anomalies in a robot according to an embodiment of the present invention.

[0020] Figure 3 This is a structural block diagram of an anomaly determination device for a robot provided according to an embodiment of the present invention. Detailed Implementation

[0021] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0022] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0023] First, some nouns or terms that appear in the description of the embodiments of this application shall be interpreted as follows:

[0024] Jacobian matrix: The Jacobian matrix represents the differential relationship between the robot's joint space and operating space. It is mainly used to describe the relationship between the linear and angular velocities of the robot's end effector and the joint velocities.

[0025] The Jacobian matrix J describes the relationship between the velocities (including linear and angular velocities) of a robot's end effector and the velocities of its individual joints. Given an n-DOF robot, if the pose (position and orientation) of the end effector is determined by 6 independent coordinates... If we represent it this way, then the Jacobian matrix J is a... The matrix.

[0026] According to an embodiment of the present invention, a method embodiment for determining anomalies in a robot is provided. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0027] The method embodiment provided in Embodiment 1 of this application can be executed on a mobile terminal, computer terminal, or similar computing device. Figure 1 A hardware block diagram of a computer terminal for implementing an anomaly detection method for robots is shown. Figure 1As shown, the computer terminal 10 may include one or more processors (shown as 102a, 102b, ..., 102n in the figure) (the processor may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data. In addition, it may also include: a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which may be included as one of the ports of a BUS bus), a network interface, a power supply, and / or a camera. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the aforementioned electronic device. For example, computer terminal 10 may also include... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0028] It should be noted that the aforementioned one or more processors and / or other data processing circuits are generally referred to herein as "data processing circuits". These data processing circuits may be embodied, in whole or in part, in software, hardware, firmware, or any other combination thereof. Furthermore, the data processing circuits may be a single, independent processing module, or may be integrated, in whole or in part, into any other element within the computer terminal 10. As involved in the embodiments of this application, the data processing circuits serve as a processor control mechanism (e.g., selection of a variable resistor termination path connected to an interface).

[0029] The memory 104 can be used to store software programs and modules of application software, such as the program instructions / data storage device corresponding to the robot anomaly determination method in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory 104, thereby implementing the robot anomaly determination method of the aforementioned application. The memory 104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory 104 may further include memory remotely located relative to the processor, and these remote memories can be connected to the computer terminal 10 via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0030] The display can be, for example, a touchscreen liquid crystal display (LCD) that allows the user to interact with the user interface of the computer terminal 10.

[0031] Figure 2 This is a flowchart illustrating a robot anomaly determination method provided according to an embodiment of the present invention, as shown below. Figure 2 As shown, the method includes the following steps:

[0032] Step S202: Obtain the initial load deviation threshold and the joint feedback torque in the static state of the target robot. The initial load deviation threshold represents the deviation threshold between the actual load of the target robot and the preset load. The joint feedback torque is the torque measured by the torque sensor at the joint of the target robot.

[0033] First, the load deviation detection thresholds can be set via an app that communicates with the robot controller. There are two thresholds: a warning threshold (initial warning deviation threshold) and an error threshold (initial error deviation threshold). The warning threshold must be lower than the error threshold. Specific values ​​can be entered in the app's interface, representing the acceptable deviation range between the robot's actual load and the preset load. For example, a user can set the warning threshold to 2kg and the error threshold to 5kg. This means that if the detected load deviation exceeds 2kg but does not exceed 5kg, a warning will be issued; if it exceeds 5kg, it will be considered an error.

[0034] Furthermore, the joint feedback torque of the target robot is acquired, which is measured by torque sensors at the robot's joints. When the robot is in a static state, the torque sensors continuously monitor the torque changes at the joints, reflecting the actual gravity and any possible external forces acting on the robot. When acquiring the joint feedback torque, it is ensured that the robot is completely stationary to avoid the influence of dynamic forces.

[0035] The acquisition of feedback torque requires ensuring data accuracy and real-time performance. After acquiring the joint feedback torque, this data should be preprocessed, such as filtered to remove noise, to ensure that subsequent torque deviation calculations are based on clean and accurate data. Furthermore, the acquisition time of the joint feedback torque should be recorded to account for the time factor in subsequent anomaly detection.

[0036] Specifically, the joint feedback torque can be repeatedly collected to ensure the stability and reliability of the data. For example, the joint feedback torque can be collected every 100 milliseconds for 10 consecutive times, and then the average of these 10 data points can be taken as the final feedback torque.

[0037] Step S204: Compare the joint feedback torque with the preset theoretical gravity torque to determine the torque deviation.

[0038] This step may include the following steps:

[0039] Step S204.1: Ensure the target robot is in a completely static state, meaning no active motion commands are being executed and all joints of the robot are stationary. At this time, the feedback torque of each joint of the target robot is collected using torque sensors.

[0040] Step S204.2: Based on the target robot's dynamic model and current attitude information, calculate the theoretical gravitational torque of the robot's end effector and its load under the influence of Earth's gravity. This requires consideration of, but is not limited to, the robot's own weight, the weight of the end effector, and the weight and distribution of the load, as well as the robot's joint angles.

[0041] Step S204.3 involves comparing the joint feedback torque collected in step S204.1 with the theoretical gravitational torque calculated in step S204.2. The torque deviation can be calculated using simple subtraction, i.e., the difference between the feedback torque and the theoretical gravitational torque for each joint. The sign of the torque deviation reflects the difference in direction between the actual torque and the theoretical torque acting on the robot joint.

[0042] Step S204.4: Calculate the torque deviations of all joints and analyze these deviations to determine if there are any significant deviations. Significant deviations indicate a potential mismatch between the actual load and the set load, or inaccurate settings of the robot's dynamic parameters. By comparing the torque deviations with preset deviation thresholds, it is determined which joints' torque deviations exceed the allowable range, thereby determining the overall degree of torque deviation.

[0043] Step S204.5: Take into account the torque deviation of all joints. If the torque deviation of any one or more joints exceeds the preset abnormality detection threshold, it can be determined that the target robot has an abnormal load parameter setting in a static state.

[0044] Step S206: Determine the kinematic model corresponding to the target robot.

[0045] In this step, the geometric parameters of the target robot are acquired through sensors, including but not limited to the rotation axes of each joint, link lengths, link offsets, and link torsional angles. A suitable coordinate system is selected for each joint and end effector. Typically, a base coordinate system is chosen, and then, based on the robot's structure, the joint coordinate system and the end effector coordinate system are gradually established. Once the coordinate systems are determined, the Denavit-Hartenberg (DH) parametric method is used to describe the relative positional relationships between the robot's joints. Using the DH parameters, a forward kinematic equation is constructed from joint variables to the end effector pose, explicitly expressing how the robot's current joint position affects the position and orientation of its end effector.

[0046] Furthermore, the kinematic model needs to be checked to ensure that all joint parameters and coordinate system settings are correct. The model also needs to be optimized, for example, by using symbolic or numerical computation methods to improve computational efficiency and accuracy. In real-time robot control, the computational speed of the kinematic model is crucial; real-time performance can be improved by simplifying the model or utilizing caching techniques. Considering potential future changes in robot structure, the kinematic model should be designed to be sufficiently flexible, easily expandable, and modifiable.

[0047] Step S208: Based on the kinematic model, determine the Jacobian matrix corresponding to the target robot.

[0048] In this step, we first obtain the current joint angle information of the target robot. The Jacobian matrix is ​​related to the robot's specific posture; different joint angles will correspond to different Jacobian matrices. Based on the forward kinematic equations in the kinematic model, we calculate the position and orientation of the robot's end effector at the current joint angle, i.e., the robot's operand space state.

[0049] Furthermore, each element of the Jacobian matrix is ​​calculated. The Jacobian matrix is ​​a 6×n matrix, where n is the number of robot degrees of freedom. The first three rows of each column represent the effect of joint velocities on the linear velocity of the end effector, while the last three rows represent the effect of joint velocities on the angular velocity of the end effector. Specifically, a numerical method can be used to approximate the calculation of the Jacobian matrix. This method involves adding a small perturbation to the current joint angle, then recalculating the position and orientation of the end effector, and estimating the elements of the Jacobian matrix by comparing the changes in the end effector's position and orientation before and after the perturbation.

[0050] After calculating the Jacobian matrix, check if its rank is full rank. The rank of the Jacobian matrix directly reflects the kinematic redundancy of the robot in its current posture. If the rank of the Jacobian matrix is ​​not full rank, it indicates that the robot is in a singular configuration or that the movement of some joints does not directly affect the position and posture of the end effector. In this case, the calculated Jacobian matrix may not accurately reflect the robot's dynamic characteristics and requires further processing, such as correcting the load deviation threshold in subsequent steps.

[0051] Step S210: Adjust the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot to obtain the target load deviation threshold.

[0052] In this step, the rank of the Jacobian matrix is ​​obtained. The rank of the Jacobian matrix reflects the degree of coupling between the robot's end effector and joints. If the rank of the Jacobian matrix is ​​full rank, there is a one-to-one correspondence between the robot's end effector velocity and joint velocity. It can be assumed that the robot's kinematic model accurately reflects the relationship between the end effector and joints; therefore, the initial load deviation threshold does not need adjustment and can be directly used as the target load deviation threshold. If the rank of the Jacobian matrix is ​​not full rank, it indicates that the correlation between the robot's current kinematic model and the actual end effector and joints is reduced. This may be due to the robot being in some special postures, such as redundant degrees of freedom between joints. In this case, even if there is a load deviation at the end effector, this deviation may not be fully reflected in the output torque of all joints, thus reducing the confidence of torque deviation detection. Therefore, the initial load deviation threshold can be adjusted to improve the confidence.

[0053] Specifically, the initial load deviation threshold is compared with a preset static friction threshold. The preset static friction threshold is pre-set based on the friction characteristics of the robot joints, representing the maximum static friction that may exist at the joints even without an external load. If the initial load deviation threshold is less than the preset static friction threshold, the current threshold setting may not be sufficient to effectively distinguish between static friction and torque deviation caused by load deviation. Therefore, the initial load deviation threshold needs to be increased by a preset factor (e.g., 1.2 times or other suitable coefficient) to ensure accurate detection of load anomalies under the influence of static friction. If the initial load deviation threshold is not less than the preset static friction threshold, it indicates that the current threshold setting has already considered the influence of static friction and no further adjustment is needed.

[0054] Step S212: Determine the anomaly detection result of the target robot based on the torque deviation and the target load deviation threshold.

[0055] First, after obtaining the torque deviation, it is necessary to determine the magnitude of the torque deviation, compare the torque deviation value with the previously adjusted target load deviation threshold, and determine the anomaly detection result based on the comparison result between the torque deviation value and the target load deviation threshold.

[0056] Specifically, if the torque deviation value exceeds the target warning deviation threshold but does not reach the target error deviation threshold, it indicates a slight deviation in the robot's load settings. This deviation is insufficient to cause the robot to immediately exhibit unexpected movement, but it may affect the accuracy of drag teaching. In this case, the anomaly detection result should be "abnormal," generating a warning message to notify the user that the load may be deviated, but the robot can still be dragged. The warning message will be displayed through the user interface (such as an app or the robot's display), and the user can choose to continue the dragging operation after receiving the warning message. If the torque deviation value exceeds the target error deviation threshold, it indicates a serious deviation in the robot's load settings, which may cause the robot to exhibit violent, unexpected movement during drag teaching, or even pose a safety risk. In this case, the anomaly detection result is determined to be "serious abnormal," generating an anomaly prompt and sending the prompt through the user interface. Simultaneously, the robot is kept stationary and drag teaching mode is not allowed until the load settings are recalibrated or confirmed.

[0057] Once the anomaly detection results are confirmed, corresponding response measures can be taken. For minor load deviations (i.e., reaching the target warning deviation threshold but not the target error deviation threshold), a warning message is sent to alert the user, indicating that the load parameters may need to be checked and adjusted. For severe load deviations (i.e., exceeding the target error deviation threshold), an anomaly alert is sent, and the robot is kept stationary. At the same time, a warning window pops up through the APP or the robot's user interface, asking the user to confirm whether to continue the dragging operation. If the user chooses to continue, the robot will enter a low-speed, cautious dragging mode.

[0058] Through the above steps, the technical effect of improving robot safety can be achieved, thereby solving the technical problem of unexpected movement of the robot during drag-and-teach caused by the lack of an effective mechanism to verify the accuracy of load parameters under static conditions.

[0059] As an optional embodiment, this can be achieved through the following steps: adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force to obtain the target load deviation threshold, including: obtaining the rank of the Jacobian matrix; if the rank of the Jacobian matrix is ​​not full rank, comparing the initial load deviation threshold with the preset static friction force threshold; if the initial load deviation threshold is less than the preset static friction force threshold, expanding the initial load deviation threshold by a preset factor to determine the target load deviation threshold; if the initial load deviation threshold is not less than the preset static friction force threshold, determining the initial load deviation threshold as the target load deviation threshold.

[0060] Optionally, the rank of the Jacobian matrix in the current pose of the target robot should be obtained. The Jacobian matrix is ​​a matrix that describes the relationship between the velocity of the robot's end effector and the joint velocities, and the rank reflects the linear independence of the matrix. In robotics, the rank of a Jacobian matrix gives the relationship between the robot's degrees of freedom (DOF) and the degrees of freedom of its end effector in space.

[0061] Furthermore, check if the acquired Jacobian matrix is ​​full rank. If the rank of the Jacobian matrix equals the number of its rows (the number of rows is usually equal to the number of velocity components of the end effector, such as 6, representing the three components of linear velocity and angular velocity), then the matrix is ​​full rank, indicating that the motion of all joints independently affects the motion of the end effector. If the rank of the Jacobian matrix is ​​less than the number of its rows, then the matrix is ​​not full rank, indicating that there may be redundant joint motions or the robot is in a singularity configuration. In this case, the motion of some joints has no direct effect on the motion of the end effector.

[0062] When the rank of the Jacobian matrix is ​​not full rank, the feedback torque of some joints may not accurately reflect the torque change caused by load deviation. Threshold adjustments are necessary to improve the robustness of load deviation detection. Specifically, the initial load deviation threshold is compared with a preset static friction threshold. The static friction threshold is a preset torque value that characterizes the maximum torque deviation that may occur at the joints due to friction when the robot is stationary.

[0063] If the detected initial load deviation threshold is less than the preset static friction threshold, it indicates that the detected load deviation may be caused by friction rather than actual load changes in the presence of static friction. To reduce false alarms, this threshold is adjusted. The adjustment is made by increasing the initial load deviation threshold by a preset factor to ensure that torque changes caused by load deviation can be distinguished even in the presence of static friction. The preset factor is an empirical value and may vary depending on the specific robot model and application environment.

[0064] As an optional embodiment, this can be achieved through the following steps: comparing the joint feedback torque with the preset theoretical gravity torque to determine the torque deviation, including: obtaining the projection lengths from the end effector of the target robot to each of the multiple joints; determining the joints whose projection lengths exceed a preset length threshold as target joints; and determining the torque deviation based on the feedback torque corresponding to the target joint in the joint feedback torque and the preset theoretical gravity torque.

[0065] Optionally, the robot's current posture and structure can be identified first, and the projected length of the straight-line distance from the robot's end effector (i.e., the tool end that interacts with the operator) to each joint can be calculated along the axis of each joint to filter out joints that are more affected by load. After obtaining the projected lengths of all joints, a preset length threshold is set, which is determined based on the robot's specific design parameters and load detection accuracy requirements. If the projected length of a joint is greater than this threshold, then this joint is defined as a "target joint." The selection of target joints is based on theoretical analysis and includes, but is not limited to, joints that are far from the end effector and have long projected lengths.

[0066] After identifying the target joints, the actual measured joint feedback torques at these joints are compared with the preset theoretical gravity torque calculated based on the robot's kinematic model. The preset theoretical gravity torque is a theoretical value calculated based on the robot's dynamic parameters, current posture, and user-preset load parameters. For each target joint, the difference between its feedback torque and the theoretical gravity torque (i.e., torque deviation) is calculated, and it is determined whether this deviation exceeds the load deviation threshold set by the user. Specifically, for multi-joint robots, the torque deviations of all target joints can be accumulated, or statistical methods such as average or maximum values ​​can be used to obtain an overall load deviation.

[0067] As an optional embodiment, it can be achieved through the following steps: the initial load deviation threshold includes an initial warning deviation threshold and an initial error deviation threshold, and the target load deviation threshold includes a target warning deviation threshold and a target error deviation threshold.

[0068] First, the system presets or the user manually sets the initial warning deviation threshold via the APP device. and initial error deviation threshold The settings of these two thresholds must meet the following requirements. This ensures that the system can issue a warning first when the load deviation gradually increases.

[0069] Furthermore, based on the robot's current kinematic model and posture, the rank of the Jacobian matrix is ​​calculated. If the rank of the Jacobian matrix is ​​not full rank, it indicates the existence of redundancy or dependency between joints, which will affect the system's detection capability to some extent. The system will then check the relationship between the initial load deviation threshold and the preset static friction threshold to determine whether adjustment is needed.

[0070] If the initial load deviation threshold is found to be less than the preset static friction threshold, then... or If the torque change caused by load deviation is difficult to distinguish from the torque change caused by static friction in a low signal-to-noise ratio environment, then the initial warning deviation threshold and / or the initial error deviation threshold are increased by a preset factor to enhance the robustness of detection and reduce the possibility of false alarms. The adjusted new threshold is the target warning deviation threshold. and target error deviation threshold .

[0071] If the initial load deviation threshold is already high enough, i.e. and If no adjustment is needed, the initial threshold can be directly used as the target threshold. and .

[0072] As an optional embodiment, this can be achieved through the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating a warning message when the torque deviation exceeds the target warning deviation threshold but does not exceed the target error deviation threshold; sending the warning message; receiving a drag prompt based on the warning message feedback; and adjusting the state of the target robot based on the drag prompt.

[0073] When the torque deviation exceeds the set target warning deviation threshold, the control system immediately identifies a possible error in the load parameter settings and automatically generates a warning message. This message details the detected anomaly, including the specific joint torque deviation, possible load setting problems, and suggested operating procedures. The warning message is generated based on real-time monitoring and comparison of torque data.

[0074] Specifically, the generated warning messages will be sent to the user's device, such as a mobile application or human-machine interface, via the robot's communication interface. The information can be transmitted wirelessly, such as via Bluetooth or Wi-Fi, or wiredly, such as via USB connection. Upon receiving the information, the user's device will immediately display the warning, including but not limited to pop-ups, audio alerts, or vibrations, to ensure that the user is promptly aware of any abnormal robot status.

[0075] Upon receiving the warning message, users can follow the instructions provided to offer further dragging prompts via a device connected to the robot or a physical button on the robot itself. If the user decides to continue, they can send a "confirm drag" command via the device or directly press the drag button on the robot to indicate that they have noticed the warning and are willing to assume the corresponding risks.

[0076] Once the user confirms continued operation via drag-and-drop, the robot's control system will adjust the robot's state based on the user's confirmation to accommodate the direct dragging action. This adjustment might be achieved by reducing friction limits at the joints to increase joint flexibility, or by other means to ensure the user can safely drag the robot for teaching even with incorrect load parameters. For example, the system might limit the maximum speed or acceleration of the joints to prevent accidental rapid movement.

[0077] As an optional embodiment, this can be achieved through the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating an abnormal prompt when the torque deviation exceeds the target error deviation threshold; sending the abnormal prompt and controlling the target robot to remain stationary.

[0078] Specifically, the system continuously monitors the joint feedback torque of the target robot and compares it in real time with the preset theoretical gravitational torque, calculating the torque deviation between the two. When the torque deviation of a joint exceeds the target error deviation threshold, it indicates a significant difference between the actual load and the preset load, possibly due to incorrect load settings or actual changes in the robot's structural parameters exceeding acceptable limits. Once the torque deviation is confirmed to exceed the target error deviation threshold, the system immediately generates an anomaly alert containing specific anomaly information, such as which joint's torque deviation exceeded the threshold and the specific value of the torque deviation. The anomaly alert is then sent to the user's terminal device, such as a smartphone, tablet, or dedicated control panel.

[0079] Furthermore, to avoid unexpected movements caused by incorrect load parameters, the target robot should be brought to a standstill simultaneously with the generation of an anomaly alert. This means all joint motors will be disabled to prevent any uncontrolled movement. In some embodiments, the system may also include additional safety measures, such as joint locking. Upon receiving the anomaly alert, the user will be guided through a series of interactive operations to confirm the existence of the anomaly and determine the subsequent handling method. For example, the user can input commands through the control panel to instruct the robot to recalibrate the load parameters, or manually check and adjust the robot's actual load conditions.

[0080] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that the present invention is not limited to the described order of actions, because according to the present invention, some steps can be performed in other orders or simultaneously. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to the present invention.

[0081] Through the above description of the embodiments, those skilled in the art can clearly understand that the robot anomaly determination method according to the above embodiments can be implemented by means of software plus necessary general-purpose hardware platform. Of course, it can also be implemented by hardware, but in many cases the former is a better implementation method. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes several instructions to cause a terminal device (which may be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present invention.

[0082] According to embodiments of the present invention, an anomaly determination apparatus for a robot implementing the above-described robot anomaly determination method is also provided. Figure 3 This is a structural block diagram of a robot anomaly determination device provided according to an embodiment of the present invention, such as... Figure 3 As shown, the anomaly determination device for the robot includes: an acquisition module 302, a comparison module 304, a first determination module 306, a second determination module 308, an adjustment module 310, and a third determination module 312. The anomaly determination device for the robot will be described below.

[0083] The acquisition module 302 is used to acquire the initial load deviation threshold and the joint feedback torque in the static state of the target robot. The initial load deviation threshold represents the deviation threshold between the actual load of the target robot and the preset load, and the joint feedback torque is the torque measured by the torque sensor at the joint of the target robot.

[0084] The comparison module 304, connected to the acquisition module 302, is used to compare the joint feedback torque with the preset theoretical gravity torque to determine the torque deviation.

[0085] The first determining module 306, connected to the comparison module 304, is used to determine the kinematic model corresponding to the target robot.

[0086] The second determining module 308, connected to the first determining module 306, is used to determine the Jacobian matrix corresponding to the target robot based on the kinematic model.

[0087] The adjustment module 310, connected to the second determination module 308, is used to adjust the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot, so as to obtain the target load deviation threshold.

[0088] The third determining module 312, connected to the adjusting module 310, is used to determine the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold.

[0089] It should be noted that the acquisition module 302, comparison module 304, first determination module 306, second determination module 308, adjustment module 310, and third determination module 312 mentioned above correspond to steps S202 to S212 in the embodiments. Multiple modules and their corresponding steps implement the same instances and application scenarios, but are not limited to the content disclosed in the above embodiments. It should also be noted that the above modules, as part of the device, can run on the computer terminal 10 provided in the embodiments.

[0090] Embodiments of the present invention may provide a computer device. Optionally, in this embodiment, the computer device may be located in at least one of a plurality of network devices in a computer network. The computer device includes a memory and a processor.

[0091] The memory can be used to store software programs and modules, such as the program instructions / modules corresponding to the robot anomaly determination method and apparatus in this embodiment of the invention. The processor executes various functional applications and data processing by running the software programs and modules stored in the memory, thereby realizing the aforementioned robot anomaly determination method. The memory may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some instances, the memory may further include memory remotely located relative to the processor, and these remote memories can be connected to a computer terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0092] The processor can access information and applications stored in the memory via a transmission device to perform the following steps: acquiring the initial load deviation threshold and the joint feedback torque in a static state of the target robot, wherein the initial load deviation threshold characterizes the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is the torque measured by torque sensors at the joints of the target robot; comparing the joint feedback torque with a preset theoretical gravitational torque to determine the torque deviation; determining the kinematic model corresponding to the target robot; determining the Jacobian matrix corresponding to the target robot based on the kinematic model; adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot to obtain the target load deviation threshold; and determining the anomaly detection result of the target robot based on the torque deviation and the target load deviation threshold.

[0093] Optionally, the processor may also execute program code for the following steps: adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force to obtain the target load deviation threshold, including: obtaining the rank of the Jacobian matrix; if the rank of the Jacobian matrix is ​​not full rank, comparing the initial load deviation threshold with the preset static friction force threshold; if the initial load deviation threshold is less than the preset static friction force threshold, expanding the initial load deviation threshold by a preset factor to determine the target load deviation threshold; if the initial load deviation threshold is not less than the preset static friction force threshold, determining the initial load deviation threshold as the target load deviation threshold.

[0094] Optionally, the processor may also execute program code for the following steps: comparing the joint feedback torque with the preset theoretical gravitational torque to determine the torque deviation, including: obtaining the projection length from the end effector of the target robot to each of the multiple joints; determining the joint whose projection length exceeds a preset length threshold as the target joint; and determining the torque deviation based on the feedback torque corresponding to the target joint in the joint feedback torque and the preset theoretical gravitational torque.

[0095] Optionally, the processor may also execute program code that includes the following steps: the initial load deviation threshold includes an initial warning deviation threshold and an initial error deviation threshold, and the target load deviation threshold includes a target warning deviation threshold and a target error deviation threshold.

[0096] Optionally, the processor may also execute program code for the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating a warning message when the torque deviation exceeds the target warning deviation threshold but does not exceed the target error deviation threshold; sending the warning message; receiving a drag prompt based on the warning message feedback; and adjusting the state of the target robot based on the drag prompt.

[0097] Optionally, the processor may also execute program code that performs the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating an abnormal prompt when the torque deviation exceeds the target error deviation threshold; sending the abnormal prompt and controlling the target robot to remain stationary.

[0098] This invention provides a method for determining robot anomalies. By acquiring the initial load deviation threshold and the joint feedback torque in a static state of the target robot, where the initial load deviation threshold represents the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is the torque measured by torque sensors at the joints of the target robot; the joint feedback torque is compared with a preset theoretical gravitational torque to determine the torque deviation; the kinematic model corresponding to the target robot is determined; based on the kinematic model, the Jacobian matrix corresponding to the target robot is determined; according to the Jacobian matrix and the preset static friction force corresponding to the target robot, the initial load deviation threshold is adjusted to obtain the target load deviation threshold; based on the torque deviation and the target load deviation threshold, the anomaly detection result of the target robot is determined, thereby achieving the purpose of monitoring whether there is a deviation in the load setting in a non-moving state, realizing the technical effect of improving robot safety, and solving the technical problem of unexpected movement of the robot during drag-and-teach caused by the lack of an effective mechanism to verify the accuracy of load parameters under static conditions in collaborative robots.

[0099] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a non-volatile storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0100] Embodiments of the present invention also provide a non-volatile storage medium. Optionally, in this embodiment, the aforementioned non-volatile storage medium can be used to store the program code executed by the robot anomaly determination method provided in the above embodiments.

[0101] Optionally, in this embodiment, the non-volatile storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0102] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: obtaining the initial load deviation threshold and the joint feedback torque in a static state of the target robot, wherein the initial load deviation threshold characterizes the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is the torque measured by a torque sensor at the joint of the target robot; comparing the joint feedback torque with a preset theoretical gravitational torque to determine the torque deviation; determining the kinematic model corresponding to the target robot; determining the Jacobian matrix corresponding to the target robot based on the kinematic model; adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot to obtain the target load deviation threshold; and determining the anomaly detection result of the target robot according to the torque deviation and the target load deviation threshold.

[0103] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force to obtain the target load deviation threshold, including: obtaining the rank of the Jacobian matrix; if the rank of the Jacobian matrix is ​​not full rank, comparing the initial load deviation threshold with the preset static friction force threshold; if the initial load deviation threshold is less than the preset static friction force threshold, expanding the initial load deviation threshold by a preset factor to determine the target load deviation threshold; if the initial load deviation threshold is not less than the preset static friction force threshold, determining the initial load deviation threshold as the target load deviation threshold.

[0104] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: The processor can also execute program code for the following steps: comparing the joint feedback torque with the preset theoretical gravitational torque to determine the torque deviation, including: obtaining the projection length from the end effector of the target robot to each of the multiple joints; determining the joint whose projection length exceeds a preset length threshold as the target joint; and determining the torque deviation based on the feedback torque corresponding to the target joint in the joint feedback torque and the preset theoretical gravitational torque.

[0105] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: the initial load deviation threshold includes an initial warning deviation threshold and an initial error deviation threshold, and the target load deviation threshold includes a target warning deviation threshold and a target error deviation threshold.

[0106] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: The processor can also execute program code for the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating a warning message when the torque deviation exceeds the target warning deviation threshold but does not exceed the target error deviation threshold; sending the warning message; receiving a drag prompt based on the warning message feedback; and adjusting the state of the target robot based on the drag prompt.

[0107] Optionally, in this embodiment, the non-volatile storage medium is configured to store program code for performing the following steps: determining the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold, including: determining the abnormal detection result as abnormal and generating an abnormal prompt when the torque deviation exceeds the target error deviation threshold; sending the abnormal prompt and controlling the target robot to remain stationary.

[0108] Embodiments of the present invention also provide a computer program product, including a computer program. Optionally, in this embodiment, when the computer program is executed by a processor, it can: acquire the initial load deviation threshold and the joint feedback torque in a static state of the target robot, wherein the initial load deviation threshold characterizes the deviation threshold between the actual load of the target robot and a preset load, and the joint feedback torque is the torque measured by a torque sensor at the joint of the target robot; compare the joint feedback torque with a preset theoretical gravitational torque to determine the torque deviation; determine the kinematic model corresponding to the target robot; determine the Jacobian matrix corresponding to the target robot based on the kinematic model; adjust the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot to obtain the target load deviation threshold; and determine the abnormal detection result of the target robot according to the torque deviation and the target load deviation threshold.

[0109] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0110] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0111] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. The device embodiments described above are merely illustrative; for example, the division of units can be a logical functional division, and in actual implementation, there may be other division methods. For instance, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the displayed or discussed mutual coupling, direct coupling, or communication connection may be through some interfaces; the indirect coupling or communication connection between units or modules may be electrical or other forms.

[0112] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0113] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0114] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a non-volatile storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.

[0115] The above description is only a preferred embodiment of the present invention. It should be noted that for those skilled in the art, several improvements and modifications can be made without departing from the principle of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for determining anomalies in a robot, characterized in that, include: The initial load deviation threshold and the joint feedback torque in a static state of the target robot are obtained, wherein the initial load deviation threshold represents the deviation threshold between the actual load of the target robot and the preset load, and the joint feedback torque is the torque measured by the torque sensor at the joint of the target robot. The joint feedback torque is compared with the preset theoretical gravitational torque to determine the torque deviation; Determine the kinematic model corresponding to the target robot; Based on the kinematic model, determine the Jacobian matrix corresponding to the target robot; Based on the Jacobian matrix and the preset static friction force corresponding to the target robot, the initial load deviation threshold is adjusted to obtain the target load deviation threshold; The anomaly detection result of the target robot is determined based on the torque deviation and the target load deviation threshold.

2. The method according to claim 1, characterized in that, The step of adjusting the initial load deviation threshold according to the Jacobian matrix and the preset static friction force to obtain the target load deviation threshold includes: Obtain the rank of the Jacobian matrix; If the rank of the Jacobian matrix is ​​not full rank, the initial load deviation threshold is compared with the preset static friction threshold. If the initial load deviation threshold is less than the preset static friction threshold, the initial load deviation threshold is increased by a preset multiple to determine the target load deviation threshold; If the initial load deviation threshold is not less than the preset static friction threshold, the initial load deviation threshold is determined to be the target load deviation threshold.

3. The method according to claim 1, characterized in that, The step of comparing the joint feedback torque with the preset theoretical gravitational torque to determine the torque deviation includes: Obtain the projection lengths from the end effector of the target robot to each of its multiple joints; Joints whose projected length exceeds a preset length threshold are identified as target joints; The torque deviation is determined based on the feedback torque corresponding to the target joint in the joint feedback torque and the preset theoretical gravity torque.

4. The method according to claim 1, characterized in that, The initial load deviation threshold includes an initial warning deviation threshold and an initial error deviation threshold, and the target load deviation threshold includes a target warning deviation threshold and a target error deviation threshold.

5. The method according to claim 4, characterized in that, The step of determining the anomaly detection result of the target robot based on the torque deviation and the target load deviation threshold includes: If the torque deviation exceeds the target warning deviation threshold but does not exceed the target error deviation threshold, the abnormal detection result is determined to be abnormal and an early warning message is generated; Send the aforementioned warning message; Receive drag-and-drop prompts based on the aforementioned warning information; Adjust the state of the target robot based on the drag prompt.

6. The method according to claim 4, characterized in that, The step of determining the anomaly detection result of the target robot based on the torque deviation and the target load deviation threshold includes: If the torque deviation exceeds the target error deviation threshold, the abnormal detection result is determined to be abnormal and an abnormal prompt is generated; Send the error message and control the target robot to remain stationary.

7. An anomaly detection device for a robot, characterized in that, include: The acquisition module is used to acquire the initial load deviation threshold and the joint feedback torque in the static state of the target robot, wherein the initial load deviation threshold represents the deviation threshold between the actual load of the target robot and the preset load, and the joint feedback torque is the torque measured by the torque sensor at the joint of the target robot. The comparison module is used to compare the joint feedback torque with the preset theoretical gravitational torque to determine the torque deviation; The first determining module is used to determine the kinematic model corresponding to the target robot; The second determining module is used to determine the Jacobian matrix corresponding to the target robot based on the kinematic model. The adjustment module is used to adjust the initial load deviation threshold according to the Jacobian matrix and the preset static friction force corresponding to the target robot, so as to obtain the target load deviation threshold. The third determining module is used to determine the abnormal detection result of the target robot based on the torque deviation and the target load deviation threshold.

8. A non-volatile storage medium, characterized in that, The non-volatile storage medium includes a stored program, wherein, when the program is executed, it controls the device containing the non-volatile storage medium to perform the anomaly determination method of the robot according to any one of claims 1 to 6.

9. A computer device, characterized in that, include: Memory and processor The memory stores computer programs; The processor is configured to execute a computer program stored in the memory, wherein when the computer program is executed, the processor performs the anomaly determination method for the robot according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the anomaly determination method for the robot according to any one of claims 1 to 6.

Images