Abnormality detection method for surgical robot system, medium, and surgical robot system

Abstract

The application provides an abnormality detection method of a surgical robot system, a medium and the surgical robot system. The surgical robot system comprises a manipulator assembly. The method comprises: acquiring actual motion information of the manipulator assembly, the actual motion information being information obtained by actually measuring motion information of the manipulator assembly; comparing the actual motion information with reference motion information to obtain a comparison result, the reference motion information comprising at least one of expected motion information and a threshold interval of motion information, the expected motion information being motion information required for the manipulator assembly to perform expected motion; and detecting motion abnormality of the manipulator assembly based on the comparison result. The application timely and accurately realizes motion abnormality detection, and effectively improves safety and reliability of the surgical robot system.

Description

Technical Field

[0001] This application relates to the field of surgical robot control technology, and in particular to an anomaly detection method, medium, and surgical robot system for a surgical robot system. Background Technology

[0002] With the rapid development of medical technology, surgical robots are increasingly widely used in surgery. Through precise control and operation, surgical robots significantly improve the accuracy and safety of surgeries, and reduce surgical risks. However, surgical robots may encounter various abnormal situations during actual operation, such as vibration and loss of control. If these abnormalities are not detected and addressed in a timely manner, they may seriously affect the surgical outcome and even endanger patient safety. Summary of the Invention

[0003] To overcome the problems existing in related technologies, this application provides an anomaly detection method, medium, and surgical robot system for a surgical robot system.

[0004] According to a first aspect of the present application, an anomaly detection method for a surgical robot system is provided, the surgical robot system including a manipulator assembly; the method includes:

[0005] Obtain the actual motion information of the manipulator component, wherein the actual motion information is obtained by actually measuring the motion information of the manipulator component;

[0006] The actual motion information is compared with the reference motion information to obtain a comparison result. The reference motion information includes at least one of the desired motion information and a threshold range of motion information. The desired motion information is the motion information required to make the manipulator component perform the desired motion.

[0007] Based on the comparison results, motion abnormalities of the manipulator component are detected.

[0008] According to a second aspect of the embodiments of this application, a computer-readable storage medium is provided, which stores a computer program that, when executed by a processor, implements the steps of the above-described anomaly detection method.

[0009] According to a third aspect of the embodiments of this application, a surgical robot system is provided, including: a manipulator assembly and a control device, the control device being configured to perform the steps of the above-described anomaly detection method.

[0010] The technical solutions provided by the embodiments of this application may include the following beneficial effects:

[0011] In this embodiment, by comparing and analyzing the actual motion information and reference motion information of the manipulator components in the surgical robot, motion anomaly detection can be achieved in a timely and accurate manner, effectively improving the safety and reliability of the surgical robot system.

[0012] It should be understood that the above general description and the following detailed description are exemplary and explanatory only, and do not limit this application. Attached Figure Description

[0013] The accompanying drawings, which are incorporated in and form part of this application, illustrate embodiments consistent with this application and, together with the description, serve to explain the principles of this application.

[0014] Figure 1 This is a schematic diagram of the structure of a surgical robot system according to an exemplary embodiment of this application.

[0015] Figure 2 This is a schematic diagram illustrating the control principle of a closed-loop control device containing only a position feedback loop, according to an exemplary embodiment of this application.

[0016] Figure 3 This application illustrates a schematic diagram of the control principle of a closed-loop control device that simultaneously includes position, speed, and current feedback loops, according to an exemplary embodiment.

[0017] Figure 4 This application illustrates a schematic diagram of the control principle of a closed-loop control device including an observer according to an exemplary embodiment.

[0018] Figure 5 This is a flowchart illustrating an anomaly detection method according to an exemplary embodiment of this application.

[0019] Figure 6 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application.

[0020] Figure 7 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application.

[0021] Figure 8 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application.

[0022] Figure 9 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application. Detailed Implementation

[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numbers in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of apparatuses and methods consistent with some aspects of this application as detailed in the appended claims.

[0024] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any or all possible combinations of one or more of the associated listed items.

[0025] It should be understood that although the terms first, second, third, etc., may be used in this application to describe various information, such information should not be limited to these terms. These terms are only used to distinguish information of the same type from one another. For example, without departing from the scope of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the word "if" as used herein may be interpreted as "when," "when," or "in response to determination."

[0026] This application relates to an anomaly detection method for a surgical robot system, aiming to detect abnormal movements of manipulator components in a timely and accurate manner, thereby improving the safety and reliability of the surgical robot system. To better illustrate this application, a detailed description of the surgical robot system to which the anomaly detection method is applied will be provided first.

[0027] Figure 1 This is a schematic diagram illustrating the structure of a surgical robot system according to an exemplary embodiment of this application. Figure 1 As shown, the surgical robot system 10 includes: an operating table 101, a patient-side manipulator 102, an auxiliary processing system 103, and a control device 104.

[0028] The control panel 101 includes a display unit and a main controller. The display unit has an observation window for showing the surgical environment for the doctor to observe. The main controller has multiple links connected by joints, supporting multiple degrees of freedom of movement for the doctor to operate. This main controller can be coupled or decoupled from the patient-side controller 102. When the main controller is coupled to the patient-side controller 102, the patient-side controller 102 can be remotely operated via the main controller. Remote operation refers to the control device 104 generating control commands in response to the operation of the main controller on the control panel 101. These control commands contain desired motion information instructing the patient-side controller 102 to perform a driven operation, such as the desired position of the patient-side controller 102, so that the patient-side controller 102 responds to the control command and executes the corresponding driven operation. When the main controller is decoupled from the patient-side controller 102, the main controller can remain in a designated position or act as an input device for human-machine interaction with the control panel 101. The main controller can perform closed-loop control when coupled or decoupled from the patient-side controller 102. For example, when coupled, it can perform current closed-loop control, and when decoupled, it can perform position closed-loop control. In addition, the control panel 101 may also include other control switches that are easy to touch or press with your hand or foot to perform various functions and complete human-machine interaction.

[0029] The patient-side manipulator 102 can be any device in the surgical robot system that can respond to control commands, such as a robotic arm. It can include several robotic arms, each with several connecting arms. Adjacent connecting arms move relative to each other with specific degrees of freedom, allowing the end effector of the robotic arm to achieve multiple degrees of freedom (e.g., 7 degrees of freedom, depending on the instrument). An instrument actuator is mounted on the end effector of the robotic arm, and surgical instruments or endoscopes are detachably mounted on the instrument actuator. The patient-side manipulator 102 can perform closed-loop control when coupled or decoupled from the main manipulator. For example, when coupled, it can perform at least one of position closed-loop control, speed closed-loop control, or current closed-loop control; when decoupled, it can also perform position closed-loop control, etc.

[0030] The auxiliary processing system 103 includes a display screen, an endoscope controller, system electronics, an image processor, etc., and is used to observe and control the movement and viewing angle of the endoscope and process the data, providing clear images of the surgical site to help doctors accurately identify and locate the surgical site and assist in surgical operations.

[0031] The control device 104 can be communicatively coupled to the operating console 101, the patient-side manipulator 102, or the auxiliary treatment system 103, or can be located in any one of the operating console 101, the patient-side manipulator 102, or the auxiliary treatment system 103.

[0032] The surgical robot system 10 also includes a manipulator assembly, which refers to a component in the surgical robot system 10 that can be controlled in a closed loop. For example, the manipulator assembly can be the main manipulator of the operating table 101 or the patient-side manipulator 102.

[0033] During closed-loop control of the manipulator components in the surgical robot system 10, such as the main manipulator of the operating table 101 or the patient-side manipulator 102, various interference factors may cause abnormalities in the manipulator components, such as vibration or loss of control. If these abnormalities are not detected and handled in a timely manner, they may seriously affect the surgical outcome and even endanger patient safety. Therefore, this application proposes a method for timely and accurate detection of abnormal movement of manipulator components, and configures the control device 104 in the surgical robot to execute the steps of the abnormality detection method to improve the safety and reliability of the surgical robot.

[0034] The control device 104 can be broadly classified into two categories: open-loop control devices and closed-loop control devices.

[0035] Open-loop control devices typically do not include a feedback loop and rely solely on preset control commands to drive the controlled object. They cannot adjust the input based on the actual output, thus limiting control accuracy and stability. In contrast, closed-loop control devices typically include a feedback loop. They can use sensors to monitor the actual output of the controlled object and compare it with the desired output indicated by the control command. The controller adjusts the control signal based on the difference in the comparison, thereby achieving higher control accuracy and stability. Therefore, the control device 104 in this embodiment can preferably be a closed-loop control device.

[0036] In closed-loop control devices, different structural designs can be adopted according to the complexity and accuracy requirements of the control task. Generally, there are two types: single-loop control devices and multi-loop control devices.

[0037] A single-loop control device can be understood as focusing on the regulation of a single variable parameter of the controlled object, such as speed, position, or current. The device contains only one feedback loop corresponding to the regulated variable. (See reference...) Figure 2 , Figure 2This diagram illustrates the control principle of a closed-loop control device containing only a position feedback loop. When the position controller receives a control command, it obtains the desired angle information for each joint of the manipulator assembly based on the desired position information in the command. Then, it controls the actuators M of each joint to move the manipulator assembly to or maintain the desired position. However, in some cases, the manipulator assembly cannot accurately move to or maintain the desired position. Therefore, a position feedback loop is typically used to determine the deviation between the actual angle information and the desired angle information of each joint to compensate for the deviation, thereby enabling the manipulator assembly to move to or maintain the desired position.

[0038] A multi-loop control device can be understood as one that focuses on regulating multiple variable parameters of the controlled object, such as simultaneously regulating speed, position, and current. The device contains multiple feedback loops corresponding to these multiple variable parameters. (See reference...) Figure 3 , Figure 3 A schematic diagram of the control principle of a closed-loop control device that simultaneously includes position, velocity, and current feedback loops is shown. Motion control of the manipulator assembly is performed based on the desired motion information of the control command. In this embodiment, the actuator of the manipulator assembly can be driven and controlled based on one or more of the current feedback loop, velocity feedback loop, or position feedback loop. Upon receiving the desired motion information of the control command, the control device calculates and sends the required command to the actuator M based on the position deviation Δθ between the desired position and the actual position, the velocity deviation ΔV between the desired velocity and the actual velocity, and the current deviation ΔI between the desired current and the actual current, thereby driving the various joints of the manipulator assembly to move.

[0039] In some special cases, closed-loop control devices may not include traditional feedback loops. Instead, they may use observers to estimate the system's internal state and then adjust the control strategy based on the estimates. The observer can be a software algorithm that uses the input and output information of the control device to estimate the device's internal state, such as position, velocity, and acceleration. Observers can be used to replace physical sensors or in combination with sensor data to improve the performance and robustness of the control device. (See reference...) Figure 4 , Figure 4 A schematic diagram of the control principle of a closed-loop control device including an observer is shown.

[0040] Figure 5 This is a flowchart illustrating an anomaly detection method for a surgical robot system according to an exemplary embodiment of this application. Figure 5 As shown, the anomaly detection method includes:

[0041] S501. Obtain the actual motion information of the control component. The actual motion information is the information obtained by actually measuring the motion information of the control component.

[0042] The actual motion information of the manipulator assembly may include, but is not limited to, the actual angle information, actual velocity information, and actual torque information of each joint of the manipulator assembly. The actual angle information refers to the actual angular position of each joint of the manipulator assembly relative to a preset reference point during motion. The actual velocity information refers to the actual velocity of each joint of the manipulator assembly during motion, which may include linear velocity and angular velocity. The actual torque information refers to the actual output torque of each joint of the manipulator assembly during motion.

[0043] To acquire this actual motion information, the control device can integrate various sensors, such as angle sensors, speed sensors, current sensors, and torque sensors, to ensure real-time and accurate monitoring and recording of the manipulator components' motion information. The actual motion information can also be estimated based on the observer's output. The actual motion information of the manipulator components reflects their actual motion state.

[0044] S502. Compare the actual motion information with the reference motion information to obtain a comparison result. The reference motion information includes at least one of the desired motion information and a threshold range for motion information.

[0045] Desired motion information refers to the motion information required for the manipulator assembly to perform the desired motion. For example, when the manipulator assembly is a patient-side manipulator 102, the desired motion information is the desired motion information in the control command generated in response to the operation of the master manipulator of the control panel 101, used to instruct the patient-side manipulator 102 to perform a driven operation. When the manipulator assembly is the master manipulator of the control panel 101, the desired motion information can be position information such as when the master manipulator is decoupled from the patient-side manipulator 102. This desired motion information may include desired angle information, desired velocity information, desired torque information, or desired acceleration, etc. Desired angle information refers to the angles of each joint of the manipulator assembly required to move the manipulator assembly to or maintain the desired position. Desired velocity information refers to the velocities of each joint of the manipulator assembly required to move the manipulator assembly at the desired velocity.

[0046] The threshold range for motion information refers to the allowable fluctuation range of various motion data of the manipulator component during normal operation, such as the velocity threshold range and the angle threshold range. The threshold range for motion information can be set based on the performance parameters of the manipulator component, the specific requirements of the surgical environment, and the expected surgical accuracy. For example, the velocity threshold range can refer to the allowable speed range during normal manipulator component movement, and can be used to assess whether the movement speed of the manipulator component is within the normal range.

[0047] Reference motion information is the expected motion data of a control component under ideal or normal operating conditions. It can be used to characterize the standard motion state of the control component under normal or undisturbed conditions. Therefore, by comparing and analyzing the actual motion information with the reference motion information, it is possible to quickly and effectively detect whether the actual motion state of the control component deviates from the standard motion state, i.e., whether motion abnormalities have occurred.

[0048] S503. Based on the comparison results, detect abnormal movement of the manipulator component.

[0049] Specifically, the motion anomalies that may occur in the control unit mainly fall into two categories: vibration and loss of control. Vibration manifests as abnormal vibration of the control unit around a specific frequency, while loss of control manifests as the control unit losing control during movement and being unable to move according to a predetermined trajectory or speed, such as moving rapidly in one direction, also known as runaway.

[0050] Different motion anomalies occur in the manipulator components, and the specific detection methods also differ. The anomaly detection methods proposed in this application are described below for the two main types of motion anomalies: vibration and loss of control.

[0051] For possible vibration-related motion abnormalities in the control components, please refer to... Figure 6 , Figure 6 This is a flowchart illustrating another anomaly detection method for a surgical robot system according to an exemplary embodiment of this application. In this embodiment, the reference motion information includes a threshold range of motion information, specifically including an amplitude threshold range.

[0052] like Figure 6 As shown, the anomaly detection method includes:

[0053] S601, Obtain the actual motion information of the manipulator component. Figure 5 Similar to S501, it will not be described in detail here.

[0054] S602. Perform frequency domain transformation on the actual motion information, compare the amplitude of the frequency domain transformed actual motion information with the amplitude threshold range, and obtain the comparison result.

[0055] S603. If the comparison result shows that the amplitude of the actual motion information after frequency domain conversion is outside the amplitude threshold range, then the motion abnormality of the manipulator component is detected as vibration.

[0056] In surgical robot systems, the actual motion information of manipulator components obtained by sensors or observers in the control device is usually in the form of a time series, such as collecting data on the angle, velocity, or torque of the manipulator components at different time points. Detecting the vibration of the manipulator components requires analyzing the frequency components in the motion information. Therefore, a frequency domain transformation operation can be performed on the actual motion information of the manipulator components beforehand to convert the time-domain signal into a frequency-domain signal for analysis. The frequency domain transformation process can be specifically implemented using a Fast Fourier Transform (FFT).

[0057] The amplitude threshold range represents the vibration amplitude range that the controller component should be in during normal operation, and can be preset according to the vibration characteristics of the controller component during normal operation. If the amplitude of the actual motion information after frequency domain conversion falls outside the preset amplitude threshold range, it indicates that the current vibration of the controller component exceeds the normal range and there is abnormal vibration. The abnormal vibration frequency is the frequency corresponding to the amplitude that exceeds the amplitude threshold range.

[0058] Furthermore, considering that various noises and interferences may accompany the acquisition of actual motion information of the manipulator components, these noises and interferences will affect the accuracy of frequency domain analysis. Therefore, in some embodiments, to improve the accuracy and reliability of frequency domain analysis, the anomaly detection method may further include at least one of the following before performing frequency domain transformation on the actual motion information:

[0059] Perform high-pass filtering on the actual motion information; or...

[0060] Apply a window function to the actual motion information; or,

[0061] Perform high-pass filtering on the actual motion information;

[0062] The actual motion information after high-pass filtering is processed using a window function.

[0063] High-pass filtering effectively removes low-frequency components from a signal while preserving or enhancing high-frequency components. In anomaly detection, high-pass filtering helps remove low-frequency interference signals generated by the movement of manipulator components, thus highlighting abnormal vibration signals. For example, during normal operation, manipulator components may generate low-frequency vibrations due to mechanical wear or environmental factors, which may interfere with the detection of abnormal vibrations. High-pass filtering reduces this interference, making the abnormal vibration signal more apparent.

[0064] Window function processing is a technique used to reduce spectral leakage. During Fast Fourier Transform (FFT), if the signal is not periodic, or its length is not an integer multiple of the FFT points, a phenomenon known as "spectral leakage" may occur in the frequency domain—energy leaking from one frequency component to others. By applying a window function, the signal amplitude can be gradually reduced at the beginning and end of the signal, thereby reducing spectral leakage caused by signal truncation and improving the accuracy of frequency domain analysis.

[0065] To address potential uncontrolled motion anomalies in manipulator components, which typically manifest as an inability to move along a predetermined trajectory, speed, or torque, and a deviation from normal speed, this application proposes an improved anomaly detection method. This method detects, during the detection process, whether the manipulator component fails to move along a predetermined trajectory, speed, or torque, and whether its speed deviates from normal speed.

[0066] Specifically, this method divides the actual motion information into two parts: first actual motion information and second actual motion information. The second actual motion information is the actual velocity information. Simultaneously, the reference motion information is also divided into two parts: desired motion information and a threshold range for motion information. The threshold range includes a velocity threshold range. The first actual motion information is then compared with the desired motion information, and the actual velocity information is compared with the velocity threshold range, respectively, to obtain a comparison result between the actual motion information and the reference motion information. Based on this comparison result, it is determined whether a loss of control of the manipulator component has been detected. The first actual motion information includes actual angle information, and the desired motion information includes desired angle information; or the first actual motion information includes actual velocity information, and the desired motion information includes desired velocity information; or the first actual motion information includes actual torque information, and the desired motion information includes desired torque information.

[0067] When comparing the first actual motion information with the expected motion information and the actual speed information with the speed threshold range, there are two specific implementation methods.

[0068] In some embodiments, please refer to Figure 7 , Figure 7 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application. In this embodiment, the anomaly detection method includes:

[0069] S701, Obtain the first actual motion information and actual speed information of the control component. Figure 5 Similar to S501, it will not be described in detail here.

[0070] S702. Compare the first actual motion information with the expected motion information, and compare the actual speed information with the speed threshold range to obtain the comparison result.

[0071] S703. If the comparison result shows that the difference between the first actual motion information and the expected motion information exceeds the preset difference threshold, and the actual speed information exceeds the speed threshold range, then the motion abnormality of the manipulator component is detected as out of control.

[0072] Furthermore, considering that runaway anomalies manifest in various ways, such as the inability to move according to a predetermined trajectory, speed, or torque, and that each anomaly is associated with a specific type of motion information from the manipulator components, and that different feedback loops within the control device are responsible for regulating this motion information in surgical robot systems, different anomaly detection methods can be provided for control devices with different feedback loops, based on the methods described in the above embodiments, to ensure targeted runaway anomaly detection. This ensures that the detection method can accurately identify anomalies associated with specific feedback loops, thereby improving the accuracy and efficiency of anomaly detection.

[0073] For example, for a control device with a position feedback loop, the first actual motion information can be specifically selected as the actual angle information, and the desired motion information as the desired angle information, for manipulator component malfunction detection. Alternatively, for a control device with a speed feedback loop, the first actual motion information can be specifically selected as the actual speed information, and the desired motion information as the desired speed information, for manipulator component malfunction detection. Or, for a control device with a torque feedback loop, the first actual motion information can be specifically selected as the actual torque information, and the desired motion information as the desired torque information, for manipulator component malfunction detection.

[0074] In other embodiments, please refer to Figure 8 , Figure 8 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application. In this embodiment, the anomaly detection method includes:

[0075] S801, Obtain the first actual motion information and actual speed information of the manipulator component. Figure 5 Similar to S501, it will not be described in detail here.

[0076] S802. Determine whether the difference between the first actual motion information and the expected motion information is continuously saturated, and compare the actual speed information with the speed threshold range to obtain the comparison result.

[0077] S803. If the comparison result shows that the difference between the first actual motion information and the expected motion information continues to saturate, and the actual speed information exceeds the speed threshold range, then the motion abnormality of the manipulator component is detected as out of control.

[0078] Similarly, based on the method of this embodiment, different anomaly detection methods can also be provided for control devices with different feedback loops. For example, for a control device with a position feedback loop, the first actual motion information can be specifically selected as the actual angle information, and the desired motion information as the desired angle information, for manipulator component malfunction detection. Alternatively, for a control device with a speed feedback loop, the first actual motion information can be specifically selected as the actual speed information, and the desired motion information as the desired speed information, for manipulator component malfunction detection. Or, for a control device with a torque feedback loop, the first actual motion information can be specifically selected as the actual torque information, and the desired motion information as the desired torque information, for manipulator component malfunction detection.

[0079] Furthermore, in step S802 of the method described in the above embodiments, in order to further improve the accuracy and reliability of anomaly detection in the surgical robot system, in some embodiments, determining whether the difference value is continuously saturated includes:

[0080] Determine the duration for which the difference reaches a preset difference threshold. If the duration exceeds the preset duration threshold, then the difference is determined to be continuously saturated.

[0081] Specifically, in order to accurately and quickly detect the duration for which the difference reaches a preset difference threshold, in some embodiments, determining the duration for which the difference reaches the preset difference threshold may include:

[0082] Construct a judgment signal to indicate whether the difference has reached a preset difference threshold;

[0083] If the difference reaches the preset difference threshold, the signal value of the judgment signal is set to the first signal value; if the difference does not reach the preset difference threshold, the signal value of the judgment signal is set to the second signal value.

[0084] The judgment signal is input into a low-pass filter, and the output of the low-pass filter is used as the duration for which the difference reaches a preset difference threshold.

[0085] The judgment signal can be set to include any two types of signals to indicate whether the difference has reached a preset difference threshold. For example, the judgment signal can be set to a binary signal. When the difference reaches the preset difference threshold, the judgment signal is set to "1", indicating that the difference is in a saturated state. Conversely, if the difference does not reach the preset difference threshold, the judgment signal is set to "0", indicating that the difference is in a normal unsaturated range.

[0086] Low-pass filters can be used to smooth signals and reduce misjudgments caused by brief signal fluctuations. At the same time, the output of a low-pass filter reflects the smoothing trend of the signal; if the difference continues to exceed a preset difference threshold, the filter's output will gradually increase, thus allowing the duration for which the difference reaches saturation to be determined through the filter's output.

[0087] For control devices equipped with observers, the lack of physical sensors or controllers to directly measure or regulate motion data makes the observer the primary tool. The observer's output can be used to estimate the internal state of the manipulator components, such as actual torque and speed information. When a manipulator component runs away uncontrollably in a certain direction, its motion state is severely inconsistent with the control commands input by the control device. This causes the control device to attempt to correct this abnormal behavior by increasing torque output. However, due to the uncontrolled motion of the manipulator component, the torque output of the control device will continue to increase and reach its maximum value, i.e., torque saturation. Therefore, whether the actual torque information of the manipulator component is saturated can also be directly used as an important indicator for detecting its uncontrolled anomaly.

[0088] Please refer to Figure 9 , Figure 9 This is a flowchart illustrating another anomaly detection method according to an exemplary embodiment of this application. In this embodiment, the actual motion information includes actual torque information and actual velocity information, and the reference motion information includes a threshold range of motion information, the threshold range including a velocity threshold range.

[0089] like Figure 9 As shown, the anomaly detection method includes:

[0090] S901, Obtain the actual torque information and actual speed information of the control component.

[0091] S902. Determine whether the actual torque information is continuously saturated, and compare the actual speed information with the speed threshold range to obtain the comparison result.

[0092] S903. If the comparison result shows that the actual torque information is continuously saturated and the actual speed information exceeds the speed threshold range, then the abnormal movement of the manipulator component is detected as out of control.

[0093] The actual torque and actual speed information of the manipulator can be estimated based on the observer output, reflecting the actual motion state of the manipulator component. If the actual torque information is continuously saturated, it means that the manipulator component may currently need to continuously output torque to overcome motion anomalies. If the actual speed information exceeds the speed threshold range, it indicates that the current motion speed of the manipulator component is abnormal. When both torque and speed are abnormally detected simultaneously, it can be considered that the current manipulator component is experiencing motion anomalies.

[0094] In this embodiment, step S902 determines whether the actual torque information is continuously saturated. Figure 8 The principle of determining whether the difference is continuously saturated in step S802 of the embodiment method is the same. For details, please refer to the description of step S802, which will not be repeated here.

[0095] Furthermore, in order to monitor and analyze the motion state of the manipulator components in real time, it is necessary to continuously acquire their motion information for anomaly detection. Therefore, in some embodiments, acquiring the actual motion information of the manipulator components includes:

[0096] When at least one sample point of actual motion information is collected, the currently collected sample point is added to a pre-established detection queue.

[0097] According to the order in which each sample point is added to the detection queue, a preset number of sample points are obtained from the detection queue in sequence;

[0098] The actual motion information containing a preset number of sample points is determined as the actual motion information of the manipulator component.

[0099] In this context, a single sample point can be understood as the real-time motion data of the manipulator component collected at each data acquisition time point, and a preset number of sample points can be understood as the motion data of the manipulator component collected within a certain continuous time window. In this embodiment, a detection queue is used to manage the collected actual motion information so that the motion information of the manipulator component can be continuously obtained from the detection queue in chronological order, ensuring the real-time performance and accuracy of anomaly detection.

[0100] Furthermore, considering that in traditional detection methods, the detection queue typically needs to be completely filled before a single detection can be performed, this significantly limits the detection frequency, causing motion anomalies in the surgical robot system to go undetected in a timely manner. Therefore, to overcome this limitation, in some embodiments, the anomaly detection method further includes the following step before adding the currently acquired sample points to the pre-established detection queue:

[0101] Delete the earliest sample point added to the detection queue.

[0102] In this embodiment, after the detection queue is full, each time a new sample point is added, the oldest sample point added to the queue is deleted first. This ensures that the detection queue can always remain full while containing the latest data, so that anomaly detection can be performed immediately when a new sample point is added. This significantly improves the detection frequency and ensures that motion anomalies of the manipulator component can be identified and responded to in a timely manner.

[0103] When an abnormal movement of the manipulator component is detected using the above-described anomaly detection method, appropriate measures should be taken promptly to minimize the impact of the abnormal movement on the operation of the surgical robot system and ensure the safety of the surgery. Therefore, in some embodiments, the anomaly detection method may further include: if an abnormal movement of the manipulator component is detected, controlling the manipulator component to stop moving and / or issuing an anomaly warning message and / or performing anomaly reporting processing.

[0104] Specifically, stopping the movement of the control unit refers to immediately stopping the abnormal movement of the control unit to prevent the abnormal situation from worsening or causing harm to the patient; issuing abnormal prompts can be done by generating alarms through visual, auditory, or tactile means to remind the operator to pay attention to the abnormal situation and take appropriate measures; abnormal reporting and processing can involve recording detailed information about the abnormal event, such as the type of abnormality, the time of occurrence, and the scope of impact, and reporting this information to the operator.

[0105] In other embodiments, in order to handle motion abnormalities of the control component more precisely, the abnormality detection method may further include: if a motion abnormality of the control component is detected, classifying the motion abnormality into a hazard level; and handling the motion abnormality according to the hazard level of the motion abnormality.

[0106] Specifically, motion anomalies can be categorized into different risk levels based on factors such as their nature, scope of impact, and potential damage, including low, medium, and high risk levels. Corresponding measures can then be taken for each risk level. For example, for low-risk anomalies, only the anomaly information can be recorded and monitored, awaiting further instructions or automatic recovery. For medium-risk anomalies, a warning message can be issued to alert operators for intervention. For high-risk anomalies, immediate emergency measures can be taken, such as canceling control commands or stopping the movement of the manipulator components.

[0107] It is understood that the above embodiments are merely illustrative examples of the risk classification and treatment methods for motion abnormalities, and do not constitute any limitation.

[0108] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the motion control method for the control arm described above.

[0109] The foregoing has described specific embodiments of this application. Other embodiments are within the scope of the appended claims. In some cases, the actions or steps recited in the claims may be performed in a different order than that shown in the embodiments and may still achieve the desired results. Furthermore, the processes depicted in the drawings do not necessarily require the specific or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0110] Other embodiments of this application will readily occur to those skilled in the art upon consideration of the specification and practice of the invention filed herein. This application is intended to cover any variations, uses, or adaptations of this application that follow the general principles of this application and include common knowledge or customary techniques in the art not claimed herein. The specification and examples are to be considered exemplary only, and the true scope and spirit of this application are indicated by the following claims.

[0111] It should be understood that this application is not limited to the precise structure described above and shown in the accompanying drawings, and various modifications and changes can be made without departing from its scope. The scope of this application is limited only by the appended claims.

[0112] The above description is merely a preferred embodiment of this application and is not intended to limit this application. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. An anomaly detection method for a surgical robot system, characterized in that, The surgical robot system includes a manipulator assembly; the method includes: Obtain the actual motion information of the manipulator component, wherein the actual motion information is obtained by actually measuring the motion information of the manipulator component; The actual motion information is compared with the reference motion information to obtain a comparison result. The reference motion information includes at least one of the desired motion information and a threshold range of motion information. The desired motion information is the motion information required to make the manipulator component perform the desired motion. Based on the comparison results, motion abnormalities of the manipulator assembly are detected; The step of obtaining the actual motion information of the manipulator component includes: When at least one sample point of the actual motion information is collected, the earliest sample point added to the pre-established detection queue is deleted, and the currently collected sample point is added to the detection queue. According to the time order in which each sample point is added to the detection queue, a preset number of sample points are sequentially obtained from the detection queue; The actual motion information containing the preset number of sample points is determined as the actual motion information of the manipulator component.

2. The method according to claim 1, characterized in that, The reference motion information includes a threshold range for motion information, and the threshold range includes an amplitude threshold range; comparing the actual motion information with the reference motion information to obtain a comparison result includes: The actual motion information is converted to the frequency domain, and the amplitude of the converted actual motion information is compared with the amplitude threshold range to obtain the comparison result.

3. The method according to claim 2, characterized in that, The step of detecting motion abnormalities in the manipulator component based on the comparison result includes: If the comparison result shows that the amplitude of the actual motion information after frequency domain conversion is outside the amplitude threshold range, then the motion abnormality of the manipulator component is detected as vibration.

4. The method according to claim 2 or 3, characterized in that, Before performing frequency domain transformation on the actual motion information, the method further includes at least one of the following: The actual motion information is subjected to high-pass filtering; or, The actual motion information is processed using a window function; or, The actual motion information is subjected to high-pass filtering, and the high-pass filtered actual motion information is then subjected to window function processing.

5. The method according to claim 1, characterized in that, The actual motion information includes first actual motion information and second actual motion information, wherein the second actual motion information is actual speed information; the reference motion information includes the desired motion information and a threshold range of motion information, wherein the threshold range includes a speed threshold range; the step of comparing the actual motion information with the reference motion information to obtain a comparison result includes: The first actual motion information is compared with the expected motion information, and the actual speed information is compared with the speed threshold range to obtain a comparison result.

6. The method according to claim 5, characterized in that, The step of detecting motion abnormalities in the manipulator component based on the comparison result includes: If the comparison result shows that the difference between the first actual motion information and the expected motion information exceeds a preset difference threshold, and the actual speed information exceeds the speed threshold range, then the motion abnormality of the manipulator component is detected as out of control.

7. The method according to claim 1, characterized in that, The actual motion information includes first actual motion information and second actual motion information, wherein the second actual motion information is actual speed information; the reference motion information includes the desired motion information and a threshold range of motion information, wherein the threshold range includes a speed threshold range; the step of comparing the actual motion information with the reference motion information to obtain a comparison result includes: Determine whether the difference between the first actual motion information and the expected motion information is continuously saturated, and compare the actual speed information with the speed threshold range to obtain a comparison result.

8. The method according to claim 7, characterized in that, Determining whether the difference is continuously saturated includes: The duration for which the difference reaches a preset difference threshold is determined. If the duration exceeds the preset duration threshold, the difference is determined to be continuously saturated.

9. The method according to claim 7, characterized in that, The step of detecting motion abnormalities in the manipulator component based on the comparison result includes: If the comparison result shows that the difference between the first actual motion information and the expected motion information continues to saturate, and the actual speed information exceeds the speed threshold range, then the motion abnormality of the manipulator component is detected as out of control.

10. The method according to any one of claims 5-9, characterized in that, The first actual motion information includes actual angle information, and the desired motion information includes desired angle information; or The first actual motion information includes actual speed information, and the desired motion information includes desired speed information; or The first actual motion information includes actual torque information, and the expected motion information includes expected torque information.

11. The method according to claim 1, characterized in that, The actual motion information includes actual torque information and actual velocity information; the reference motion information includes a threshold range for motion information, and the threshold range includes a velocity threshold range; comparing the actual motion information with the reference motion information to obtain a comparison result includes: Determine whether the actual torque information is continuously saturated, and compare the actual speed information with the speed threshold range to obtain the comparison result.

12. The method according to claim 11, characterized in that, The step of detecting motion abnormalities in the manipulator component based on the comparison result includes: If the comparison result shows that the actual torque information is continuously saturated and the actual speed information exceeds the speed threshold range, then the abnormal movement of the manipulator component is detected as out of control.

13. The method according to claim 1, characterized in that, The method further includes: If an abnormal movement of the manipulator component is detected, the manipulator component is controlled to stop moving and / or an abnormal prompt message is issued and / or an abnormal reporting process is performed.

14. The method according to claim 1, characterized in that, The method further includes: If an abnormal movement of the manipulator component is detected, the abnormal movement is classified into risks. Motion abnormalities are treated according to the risk classification of the abnormality.

15. The method according to claim 1, characterized in that, The manipulator component is either the main manipulator of the surgical robot system or the patient-side manipulator of the surgical robot system.

16. A computer-readable storage medium storing a computer program, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 15.

17. A surgical robot system, characterized in that, include: A manipulator assembly and a control device configured to perform the steps of the method according to any one of claims 1 to 15.

Images