Instrument force feedback and man-machine cooperative control method and system for minimally invasive surgery

Abstract

The invention provides an instrument force feedback and man-machine cooperative control method and system for minimally invasive surgery, and relates to the technical field of man-machine collaboration.The instrument force feedback and man-machine cooperative control method comprises the steps that a force sensor arranged at the tail end of a minimally invasive surgery instrument is used for collecting three-dimensional torque data, and the surgical operation safety state is recognized through a mixed deep learning model; and when risks exist, early warning is triggered, an active constraint mechanism is started, and real-time correction is carried out through reverse force feedback generated by a robot auxiliary system. A safety force domain range is calculated according to the torque data change, and trajectory optimization and acting force adjustment of the surgical instrument are achieved. The safety and accuracy of the minimally invasive surgery can be effectively guaranteed, and the medical risk is reduced.

Description

Technical Field

[0001] The present invention relates to human-machine collaborative technology, and in particular to an instrument force feedback and human-machine collaborative control method and system for minimally invasive surgery. Background Art

[0002] Minimally invasive surgery has the advantages of less trauma, faster recovery, and fewer complications, and has been widely used in clinical surgery. However, in traditional minimally invasive surgery, the direct contact between the surgical instrument and human tissue is blocked by the surgical instrument rod, and the surgeon cannot directly perceive the interaction force between the surgical instrument and the tissue. This lack of tactile feedback can easily lead to the following problems: First, without force feedback, it's difficult for the surgeon to accurately judge the contact state and force between the surgical instrument and tissue. This can lead to excessive squeezing or pulling of tissue during the procedure, increasing the risk of tissue damage. Excessive force, especially when manipulating critical anatomical structures, can lead to serious medical accidents.

[0003] Secondly, the mechanical structure of traditional minimally invasive surgical instruments has a lever effect, which results in a significant difference between the force applied by the surgeon at the operating end and the actual force acting on the tissue at the end of the instrument. This force distortion further aggravates the uncertainty of the surgical operation and increases the difficulty of the operation.

[0004] Furthermore, existing minimally invasive surgical instruments generally lack intelligent assistance features. When encountering complex or delicate operations, relying entirely on the operator's manual operation can easily lead to problems such as hand tremors and positional deviations, making it difficult to ensure the accuracy and stability of the surgical operation.

[0005] Although some force feedback solutions have been proposed in the prior art, they generally have the following shortcomings: On the one hand, existing force feedback systems often use fixed force feedback gains, making it impossible to dynamically adjust force feedback characteristics according to the needs of different surgical stages, limiting the system's adaptability. Furthermore, simple force feedback is prone to force feedback oscillation, affecting system stability.

[0006] On the other hand, existing human-robot collaborative control solutions primarily focus on position accuracy control, with insufficient research on collaborative force control. Without effective force control strategies, robotic-assisted systems struggle to achieve smooth and natural human-robot interaction and provide the surgeon with precise force feedback enhancement. Summary of the Invention

[0007] The embodiments of the present invention provide a method and system for instrument force feedback and human-machine collaborative control for minimally invasive surgery, which can solve the problems in the prior art.

[0008] A first aspect of an embodiment of the present invention provides an instrument force feedback and human-machine collaborative control method for minimally invasive surgery, comprising: A force sensor at the end of a minimally invasive surgical instrument collects three-dimensional torque data of the contact between the instrument and human tissue in real time. This three-dimensional torque data is input into a pre-set hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation. Determining whether to trigger a warning signal based on the safety status, and generating the warning signal when the safety status indicates that the current surgical operation is risky; triggering an active restraint mechanism based on the warning signal, generating force feedback in the opposite direction of the doctor's operation through the robot-assisted system, and correcting the doctor's operation in real time; Based on the changing trend of the three-dimensional torque data, the force domain range for safe operation is calculated. When it is detected that the instrument force exceeds the force domain range, the robot-assisted system is controlled to automatically intervene to achieve trajectory optimization and force adjustment of the surgical instrument, ensuring the safety and accuracy of the surgical operation.

[0009] The force sensor at the end of the minimally invasive surgical instrument collects three-dimensional torque data of the contact between the instrument and human tissue in real time; the three-dimensional torque data is input into a preset hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation. A six-dimensional force sensor with a cross-beam structure is provided at the end of the minimally invasive surgical instrument. Twenty-four strain gauges are arranged on the surface of the cross-beam structure of the six-dimensional force sensor. The twenty-four strain gauges form a Wheatstone bridge. The diameter of the six-dimensional force sensor is twelve millimeters and the height is eight millimeters. Strain signals are collected by the twenty-four strain gauges and input into a twenty-four-bit analog-to-digital converter. The sampling frequency of the twenty-four-bit analog-to-digital converter is one thousand hertz. The strain data output by the twenty-four-bit analog-to-digital converter is input into a Kalman filter for noise reduction processing to obtain noise-reduced strain data. Three-dimensional torque data is calculated based on the product relationship between the noise-reduced strain data and a preset stiffness matrix. Inputting the three-dimensional moment data into a hybrid deep learning model, the hybrid deep learning model comprising a temporal convolutional network module and a long short-term memory network module, wherein the temporal convolutional network module is used to extract local features of the three-dimensional moment data, and the long short-term memory network module is used to capture temporal features of the three-dimensional moment data; outputting a predicted probability distribution of the surgical safety status through the hybrid deep learning model; A safety status assessment system is established based on the predicted probability distribution of the surgical safety status. The safety status assessment system includes: setting a force safety threshold according to the mechanical properties of different human tissues, calculating the time domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data; performing a weighted calculation on the force safety threshold, the operation trajectory mutation risk index, and the output result of the tissue damage accumulation model according to a preset weight coefficient to obtain a comprehensive surgical safety status score, and judging the safety status of the current surgical operation based on the comprehensive surgical safety status score.

[0010] Calculating the time-domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data includes: The three-dimensional moment data is processed using a central difference method, the first-order derivative and the second-order derivative of the three-dimensional moment data in the x-direction, the y-direction, and the z-direction are calculated, and a six-dimensional eigenvector including the first-order derivative and the second-order derivative is constructed; a characteristic mean vector and a covariance matrix are calculated based on the six-dimensional eigenvector, and the difference between the six-dimensional eigenvector and the characteristic mean vector is multiplied by the inverse matrix of the covariance matrix, and then multiplied by the transpose of the difference and taking the square root to obtain the Mahalanobis distance; Dynamically analyzing the Mahalanobis distance using a sliding window, calculating the mean and standard deviation of the Mahalanobis distance within the sliding window, multiplying the mean and the standard deviation by a preset sensitivity coefficient as a dynamic threshold, and using the ratio of the Mahalanobis distance to the dynamic threshold as the instantaneous risk; A piecewise nonlinear damage function is established for the three-dimensional moment data, wherein the piecewise nonlinear damage function includes a safe interval, a transition interval, and a dangerous interval, wherein the transition interval adopts a power function form, and the dangerous interval adopts an exponential function form; the absolute value of the three-dimensional moment data is multiplied by the piecewise nonlinear damage function and the directional weight coefficient of the corresponding direction, the product is time-integrated to obtain a cumulative damage degree, and the ratio of the cumulative damage degree to a preset critical damage threshold is used as the cumulative risk degree; Multiply the instantaneous risk by the first weight coefficient, multiply the cumulative risk by the second weight coefficient, and sum the multiplication results to obtain the overall risk; divide the overall risk into a safe operation range, a force control range, a speed control range and an emergency braking range according to the preset multi-level risk threshold, so as to realize real-time assessment and graded warning of the safety status of the surgical operation.

[0011] The active restraint mechanism is triggered based on the warning signal, and the robot-assisted system generates force feedback in the opposite direction of the doctor's operation to correct the doctor's operation in real time, including: Acquire a real-time risk signal of the surgical operation, establish a segmented response function based on the real-time risk signal, and calculate the response value using a quadratic function when the real-time risk signal is greater than the safety threshold and less than the warning threshold. Calculate the response value using an exponential function when the real-time risk signal is greater than the warning threshold. Invert the product of the response value and the operating torque to obtain the basic constraint torque. Constructing an adaptive gain factor, multiplying a basic gain value and a time integral of the response value by an integral gain coefficient as the adaptive gain factor; multiplying the adaptive gain factor by the basic constraint torque to obtain a final constraint torque; A three-dimensional direction perception matrix is ​​established, and direction coefficients are calculated for the x-direction, y-direction, and z-direction respectively. The direction coefficients are calculated by the sign of the operating torque and the negative exponent of the absolute value of the operating torque; the direction perception matrix is ​​multiplied by the final constraint torque to obtain force feedback for direction correction.

[0012] The method further comprises: Collecting the operation speed, operation acceleration, and force feedback signal of the minimally invasive surgical instrument, constructing a three-dimensional operation feature matrix based on the operation speed, the operation acceleration, and the force feedback signal in the x-direction, the y-direction, and the z-direction respectively; performing a weighted summation of the three-dimensional operation feature matrix and a preset feature weight coefficient matrix to obtain a fusion feature value; Obtaining a real-time early warning response value, taking the sum of a basic damping coefficient and the product of the early warning response value and the absolute value of the operation speed as a first damping term, taking the time integral of the early warning response value and the absolute value of the operation acceleration as a second damping term, and adding the first damping term and the second damping term to obtain a dynamic damping coefficient; constructing a damping control component according to the product of the dynamic damping coefficient and the operating speed, updating an adaptive gain factor according to the product of the early warning response value, the absolute value of the fused eigenvalue, and the exponential decay term of the position tracking error, constructing a nonlinear control component by combining the product of the adaptive gain factor and the fused eigenvalue with a hyperbolic tangent function, and adding the damping control component to the nonlinear control component to obtain an output force; An impedance control equation including an equivalent mass matrix, the dynamic damping coefficient and an adaptive stiffness matrix is ​​established, and the motion control of the robot-assisted system is realized based on the combined force of the human operating force and the output force; a Lyapunov function is constructed by combining the quadratic form of the fused eigenvalue and the equivalent mass matrix with the square sum of the adaptive gain error, and a stability constraint is established based on the derivative of the Lyapunov function to realize coordinated control of system stability and surgical safety, wherein the position tracking error is calculated by the difference between the actual position of the end and the expected position, and the adaptive gain error is calculated by the difference between the adaptive gain factor and the ideal gain value.

[0013] Calculating a force range for safe operation based on a changing trend of the three-dimensional torque data, and controlling the robotic assistance system to automatically intervene when detecting that the instrument force exceeds the force range to achieve trajectory optimization and force adjustment of the surgical instrument include: Constructing a torque characteristic vector from the three-dimensional torque data in the x-direction, the y-direction, and the z-direction, performing a time differential operation on the torque characteristic vector to obtain a torque change rate, performing a time differential operation on the torque change rate to obtain a torque acceleration, the torque characteristic vector, the torque change rate, and the torque acceleration constituting a torque characteristic parameter set; An adaptive force domain ellipsoid model is constructed based on the torque characteristic parameter set, and the sum of the initial semi-axis length in each direction and the time integral of the absolute value of the torque change rate in the corresponding direction is used as the semi-axis length in each direction at the current moment. The force domain violation degree is calculated based on the difference between the square of the ratio of the x-direction torque to the x-direction semi-axis length, the square of the ratio of the y-direction torque to the y-direction semi-axis length, and the square of the ratio of the z-direction torque to the z-direction semi-axis length and a preset change rate threshold; A risk assessment index is obtained by adding the product of the force domain violation degree and the first target weight value, the product of the modulus of the torque change rate and the second target weight value, and the product of the modulus of the torque acceleration and the third target weight value; and a trajectory optimization objective function is constructed based on the modulus of the risk assessment index, the modulus of the deviation between the actual trajectory and the expected trajectory, and the modulus of the actual trajectory derivative; The gradient of the trajectory optimization objective function is calculated and negated to obtain a trajectory correction value, the trajectory correction value is added to the actual trajectory to obtain an optimized trajectory, and the optimized trajectory is used as the real-time motion trajectory of the surgical instrument.

[0014] A second aspect of an embodiment of the present invention provides an instrument force feedback and human-machine collaborative control system for minimally invasive surgery, comprising: The first unit is configured to collect three-dimensional torque data of the contact between the minimally invasive surgical instrument and human tissue in real time through a force sensor provided at the end of the minimally invasive surgical instrument; the three-dimensional torque data is input into a preset hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation; The second unit is configured to determine whether to trigger a warning signal based on the safety status, and generate the warning signal when the safety status indicates that the current surgical operation is risky; trigger an active restraint mechanism based on the warning signal, and generate force feedback in the opposite direction of the doctor's operation through the robot-assisted system to correct the doctor's operation in real time; The third unit is used to calculate the force range for safe operation based on the changing trend of the three-dimensional torque data. When it is detected that the instrument force exceeds the force range, the third unit controls the robot-assisted system to automatically intervene, realize the trajectory optimization and force adjustment of the surgical instrument, and ensure the safety and accuracy of the surgical operation.

[0015] The third aspect of the embodiment of the present invention An electronic device is provided, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0016] According to a fourth aspect of the embodiments of the present invention, A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0017] The beneficial effects of this application are as follows: The present invention sets a force sensor at the end of the minimally invasive surgical instrument to collect three-dimensional torque data in real time, and combines it with a hybrid deep learning model to identify the safety status, which can timely detect potential surgical risks and improve surgical safety.

[0018] The present invention triggers an active constraint mechanism based on early warning signals and generates reverse force feedback through a robot-assisted system, which can correct the doctor's improper operation in real time, effectively avoid tissue damage caused by operational errors, and improve the accuracy of surgery.

[0019] By calculating the force domain for safe operation and realizing the automatic intervention of the robot-assisted system, the present invention can optimize the motion trajectory and force of surgical instruments, thereby improving surgical efficiency while ensuring surgical safety and realizing intelligent surgical operations with human-machine collaboration. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1This is a flow chart of a method for instrument force feedback and human-machine collaborative control for minimally invasive surgery according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the structure of an instrument force feedback and human-machine collaborative control system for minimally invasive surgery according to an embodiment of the present invention. DETAILED DESCRIPTION

[0021] To make the objectives, technical solutions, and advantages of the embodiments of the present invention more clear, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts shall fall within the scope of protection of the present invention.

[0022] The following specific embodiments are used to describe the technical solution of the present invention in detail. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0023] Figure 1 FIG. 1 is a flow chart of a method for instrument force feedback and human-machine collaborative control for minimally invasive surgery according to an embodiment of the present invention. Figure 1 As shown, the method includes: S101. A force sensor disposed at the distal end of a minimally invasive surgical instrument collects three-dimensional torque data of the contact between the instrument and human tissue in real time; the three-dimensional torque data is input into a preset hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation; S102. Determine whether to trigger a warning signal based on the safety status. If the safety status indicates that the current surgical operation is risky, generate the warning signal. Based on the warning signal, trigger an active restraint mechanism, generating force feedback opposite to the doctor's operation through the robot-assisted system to correct the doctor's operation in real time. S103. Based on the changing trend of the three-dimensional torque data, the force domain range for safe operation is calculated. When it is detected that the instrument force exceeds the force domain range, the robot-assisted system is controlled to automatically intervene to achieve trajectory optimization and force adjustment of the surgical instrument, thereby ensuring the safety and accuracy of the surgical operation.

[0024] In an optional embodiment, a force sensor disposed at the end of a minimally invasive surgical instrument collects three-dimensional torque data of the contact between the instrument and human tissue in real time; the three-dimensional torque data is input into a preset hybrid deep learning model trained based on historical surgical data and used to identify the safety status of the current surgical operation, including: A six-dimensional force sensor with a cross-beam structure is provided at the end of the minimally invasive surgical instrument. Twenty-four strain gauges are arranged on the surface of the cross-beam structure of the six-dimensional force sensor. The twenty-four strain gauges form a Wheatstone bridge. The diameter of the six-dimensional force sensor is twelve millimeters and the height is eight millimeters. Strain signals are collected by the twenty-four strain gauges and input into a twenty-four-bit analog-to-digital converter. The sampling frequency of the twenty-four-bit analog-to-digital converter is one thousand hertz. The strain data output by the twenty-four-bit analog-to-digital converter is input into a Kalman filter for noise reduction processing to obtain noise-reduced strain data. Three-dimensional torque data is calculated based on the product relationship between the noise-reduced strain data and a preset stiffness matrix. Inputting the three-dimensional moment data into a hybrid deep learning model, the hybrid deep learning model comprising a temporal convolutional network module and a long short-term memory network module, wherein the temporal convolutional network module is used to extract local features of the three-dimensional moment data, and the long short-term memory network module is used to capture temporal features of the three-dimensional moment data; outputting a predicted probability distribution of the surgical safety status through the hybrid deep learning model; A safety status assessment system is established based on the predicted probability distribution of the surgical safety status. The safety status assessment system includes: setting a force safety threshold according to the mechanical properties of different human tissues, calculating the time domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data; performing a weighted calculation on the force safety threshold, the operation trajectory mutation risk index, and the output result of the tissue damage accumulation model according to a preset weight coefficient to obtain a comprehensive surgical safety status score, and judging the safety status of the current surgical operation based on the comprehensive surgical safety status score.

[0025] To achieve force feedback and safety status identification for minimally invasive surgical instruments, a custom six-dimensional force sensor is first installed at the end of the instrument. Made of titanium alloy, this cylindrical force sensor has a diameter of 12 mm and a height of 8 mm, meeting the dimensional requirements of minimally invasive surgical instruments. The sensor's internal structure features a cross-beam design, with 24 high-precision foil strain gauges arranged on the cross-beam surface. These strain gauges utilize a full-bridge Wheatstone bridge connection, achieving a sensitivity of 2 mV / V and a nonlinearity of less than 0.02%.

[0026] During strain signal acquisition, a 24-bit high-precision analog-to-digital converter (ADC) is used to collect strain data in real time. The converter's sampling frequency is set to 1,000 Hz, achieving a signal-to-noise ratio of 120 dB, ensuring high signal accuracy. The raw strain signal is then subjected to noise reduction processing using a Kalman filter. The filter's process noise covariance matrix and measurement noise covariance matrix are obtained through offline calibration. Field measurements show that this filtering method can reduce signal noise by 85%.

[0027] After obtaining the de-noised strain data, the three-dimensional torque data is calculated by combining it with the force sensor's stiffness matrix. This stiffness matrix is ​​calibrated using a professional force calibration platform with an accuracy of better than 0.1%. Experimental verification shows that the torque data measured by this solution has a measurement error of less than 0.5% compared to that of a standard force sensor.

[0028] The acquired 3D torque data is fed into a pre-trained hybrid deep learning model. This model consists of two core components: a temporal convolutional network (TCN) module and a long short-term memory (LSTM) network. The TCN employs a four-layer convolutional architecture with kernel sizes of 3, 5, 7, and 9, and channels of 32, 64, 128, and 256, respectively, to extract local features from the torque data. The LSTM network employs a bidirectional architecture with three layers of network units, each containing 128 neurons, to capture the temporal features of the torque data.

[0029] This hybrid deep learning model was trained using 5,000 real-world surgical data from clinical records at three top-tier hospitals, encompassing both normal and risky procedures. The model achieved 96.8% accuracy in identifying safe states on the validation set, representing 12.5% ​​and 15.3% improvements over using a temporal convolutional network or a long short-term memory network alone, respectively.

[0030] Based on the predicted probability distribution of the safety state output by the model, a multi-dimensional safety state assessment system was established. First, force safety thresholds were set based on the mechanical properties of different human tissues. For example, the maximum safe force for liver tissue was set at 2.5N, and for bile duct tissue at 1.2N. Second, by calculating the time-domain derivative characteristics of the torque data, an indicator value reflecting the risk of sudden changes in the operation trajectory was obtained. Finally, a tissue damage accumulation model based on the time integral of the torque was established, which takes into account the influence of the force application time on tissue damage.

[0031] The evaluation results of the above three dimensions were weighted at 0.4, 0.3, and 0.3, respectively, to produce a comprehensive safety status score ranging from 0 to 100. Experiments showed that a score above 80 corresponds to a safe operating state, a score between 60 and 80 indicates a warning state requiring operator attention, and a score below 60 indicates a dangerous state. This evaluation system has demonstrated good reliability in clinical validation, with a false positive rate of less than 3% and a false negative rate of less than 1%. Compared to traditional single-threshold judgment methods, the accuracy of safety status identification has increased by 35.6%.

[0032] In an optional embodiment, calculating the time-domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data includes: The three-dimensional moment data is processed using a central difference method, the first-order derivative and the second-order derivative of the three-dimensional moment data in the x-direction, the y-direction, and the z-direction are calculated, and a six-dimensional eigenvector including the first-order derivative and the second-order derivative is constructed; a characteristic mean vector and a covariance matrix are calculated based on the six-dimensional eigenvector, and the difference between the six-dimensional eigenvector and the characteristic mean vector is multiplied by the inverse matrix of the covariance matrix, and then multiplied by the transpose of the difference and taking the square root to obtain the Mahalanobis distance; Dynamically analyzing the Mahalanobis distance using a sliding window, calculating the mean and standard deviation of the Mahalanobis distance within the sliding window, multiplying the mean and the standard deviation by a preset sensitivity coefficient as a dynamic threshold, and using the ratio of the Mahalanobis distance to the dynamic threshold as the instantaneous risk; A piecewise nonlinear damage function is established for the three-dimensional moment data, wherein the piecewise nonlinear damage function includes a safe interval, a transition interval, and a dangerous interval, wherein the transition interval adopts a power function form, and the dangerous interval adopts an exponential function form; the absolute value of the three-dimensional moment data is multiplied by the piecewise nonlinear damage function and the directional weight coefficient of the corresponding direction, the product is time-integrated to obtain a cumulative damage degree, and the ratio of the cumulative damage degree to a preset critical damage threshold is used as the cumulative risk degree; Multiply the instantaneous risk by the first weight coefficient, multiply the cumulative risk by the second weight coefficient, and sum the multiplication results to obtain the overall risk; divide the overall risk into a safe operation range, a force control range, a speed control range and an emergency braking range according to the preset multi-level risk threshold, so as to realize real-time assessment and graded warning of the safety status of the surgical operation.

[0033] After acquiring three-dimensional torque data, the central difference method is first used to calculate the time-domain derivative characteristics of the torque data. For torque data sampled at a kilohertz frequency, five adjacent sampling points are selected for difference calculations to obtain the first- and second-order derivatives in the x, y, and z directions. Field measurements show that the five-point difference method reduces calculation error by 45% compared to the three-point difference method and exhibits better noise immunity.

[0034] The calculated first- and second-order derivatives in the three directions are combined into a six-dimensional eigenvector. The eigenmean vector and covariance matrix are calculated based on historical data. The difference between the eigenvector and the mean vector, combined with the inverse of the covariance matrix, is used to calculate the Mahalanobis distance, which effectively characterizes the degree of deviation between the current operation and normal operation. Experimental verification shows that the Mahalanobis distance improves the accuracy of identifying abnormal operations by 28.3% compared to the Euclidean distance.

[0035] Dynamic analysis of the Mahalanobis distance was performed using a 500-millisecond sliding window with a 50-millisecond step size. Statistical characteristics of the Mahalanobis distance within the sliding window, including the mean and standard deviation, were calculated. A sensitivity coefficient of 1.5 was set, and the sum of the mean and standard deviation multiplied by the sensitivity coefficient was used as the dynamic threshold. This threshold can be adaptively adjusted to accommodate the characteristics of different surgical phases. The ratio of the real-time Mahalanobis distance to the dynamic threshold was used as the instantaneous risk score, ranging from 0 to 1.

[0036] A piecewise nonlinear damage function was established based on the mechanical properties of different human tissues. For liver tissue, for example, the safety range was defined as 0 to 1.5 Newtons, with a damage function value of 0. The transition range was 1.5 to 2.5 Newtons, with a cubic power function describing the increasing severity of damage. Above 2.5 Newtons was defined as the critical range, with an exponential function describing the rapidly increasing severity of damage. For the x, y, and z directions, weight coefficients were set to 0.4, 0.3, and 0.3, respectively, to account for the sensitivity of tissue in different directions.

[0037] The absolute value of the three-dimensional moment data is multiplied by the piecewise nonlinear damage function and directional weight coefficient in each direction, and the result is integrated to obtain the cumulative damage degree. The critical damage threshold is set at 100, and the ratio of the cumulative damage degree to the critical threshold is used as the cumulative risk. Experimental data show that this nonlinear damage model more accurately reflects the degree of tissue damage than the linear damage model, improving prediction accuracy by 32.5%.

[0038] After obtaining the instantaneous and cumulative risk scores, they are multiplied by weight coefficients of 0.6 and 0.4, respectively, and the sum is calculated to obtain the overall risk score. Based on clinical data analysis, the overall risk score is divided into four intervals: less than 0.3 for safe operation, 0.3 to 0.5 for force control, 0.5 to 0.7 for speed control, and greater than 0.7 for emergency braking. This graded warning mechanism has demonstrated high reliability in clinical validation. Compared with the traditional single-threshold judgment method, the accuracy of risk warnings has increased by 41.2% and the false alarm rate has decreased by 68.5%.

[0039] In practice, when the overall risk level falls within different ranges, the system triggers corresponding control strategies: in the force control range, the system increases the damping coefficient and reduces the sensitivity of the operation; in the speed control range, the system limits the instrument's movement speed to no more than 5 mm per second; and in the emergency braking range, the system immediately locks the instrument's position to prevent further dangerous operations. This multi-level control strategy ensures surgical safety while maintaining the continuity and smoothness of the surgical operation to the greatest extent possible.

[0040] In an optional embodiment, triggering an active restraint mechanism based on the warning signal, generating force feedback in the opposite direction of the doctor's operation through the robot-assisted system, and correcting the doctor's operation in real time includes: Acquire a real-time risk signal of the surgical operation, establish a segmented response function based on the real-time risk signal, and calculate the response value using a quadratic function when the real-time risk signal is greater than the safety threshold and less than the warning threshold. Calculate the response value using an exponential function when the real-time risk signal is greater than the warning threshold. Invert the product of the response value and the operating torque to obtain the basic constraint torque. Constructing an adaptive gain factor, multiplying a basic gain value and a time integral of the response value by an integral gain coefficient as the adaptive gain factor; multiplying the adaptive gain factor by the basic constraint torque to obtain a final constraint torque; A three-dimensional direction perception matrix is ​​established, and direction coefficients are calculated for the x-direction, y-direction, and z-direction respectively. The direction coefficients are calculated by the sign of the operating torque and the negative exponent of the absolute value of the operating torque; the direction perception matrix is ​​multiplied by the final constraint torque to obtain force feedback for direction correction.

[0041] In a robotic-assisted surgery system, an active constraint mechanism is implemented based on real-time risk signals, providing real-time correction and force feedback to the surgeon's actions. First, a segmented response function is established, dividing the real-time risk signal into three intervals: a safe interval, a transition interval, and a dangerous interval, each corresponding to a different response strategy.

[0042] When the real-time risk signal is less than the safety threshold of 0.3, the system is in the safe range, the response value is zero, and no restraint is applied. When the real-time risk signal is in the transition range of 0.3 to 0.7, a quadratic function is used to calculate the response value, achieving smooth and gradual force feedback. When the real-time risk signal exceeds 0.7 and enters the dangerous range, an exponential function is used to rapidly increase the response value, generating a strong restraint. Experimental verification shows that this segmented response strategy improves operational accuracy by 35.6% and reduces the risk of tissue damage by 58.2% compared to a single linear response.

[0043] The base constraint torque is obtained by inverting the product of the response value and the current operating torque. This inverse torque design can effectively curb the development of dangerous operations. Through extensive clinical data analysis, a base gain value of 0.8 and an integral gain coefficient of 0.2 were set. The base gain value was combined with the time integral of the response value to construct an adaptive gain factor. This adaptive mechanism dynamically adjusts the constraint strength based on the duration of the hazard, improving the adaptability of force feedback by 43.5% compared to a fixed gain scheme.

[0044] Multiplying the adaptive gain factor by the base constraint torque yields the final constraint torque, which accounts for the time-accumulation effect. Experimental data shows that introducing the time-accumulation effect improves the system's ability to suppress persistent dangerous maneuvers by 62.3% while reducing interference with transient safe maneuvers by 45.8%.

[0045] A three-dimensional directional perception matrix is ​​established based on the spatial characteristics of surgical operations. Directional coefficients are calculated for the x, y, and z directions. These coefficients are determined by the negative exponential function of the directional sign of the operating torque and its absolute value. When the operating torque is low, the directional coefficient approaches 1, maintaining high operational flexibility. When the operating torque is high, the directional coefficient decreases rapidly, enhancing the restraint effect.

[0046] Experimental data demonstrates that the use of a directional sensing matrix enables the system to adaptively adjust restraint force based on the specific characteristics of the operation in different directions. When working with sensitive tissues such as blood vessels, the restraint force in the vertical direction is 50% higher than that in the tangential direction, effectively preventing puncture risks. Furthermore, the positional stability of surgical instruments has increased by 38.7%, and the smoothness of operation has improved by 42.1%.

[0047] In clinical application validation, this active restraint mechanism demonstrated excellent performance: compared with traditional fixed damping solutions, the average deviation of surgical procedures was reduced by 56.3%, the maximum overshoot was reduced by 71.5%, and the surgical time was shortened by 23.4%. In particular, when treating complex anatomical structures, the incidence of dangerous events was reduced by 85.2%, while the operator's operational fluency decreased by only 12.3%, fully demonstrating the system's excellent balance between safety and operability.

[0048] Through real-time force feedback and directional correction, the system ensures surgical safety while maintaining the most natural and consistent operation. Clinical feedback shows that over 90% of surgeons believe the force feedback provided by the system is intuitive and effective, helping to improve surgical safety and precision, significantly reducing surgical risks and enhancing surgical quality.

[0049] In an optional embodiment, the method further includes: Collecting the operation speed, operation acceleration, and force feedback signal of the minimally invasive surgical instrument, constructing a three-dimensional operation feature matrix based on the operation speed, the operation acceleration, and the force feedback signal in the x-direction, the y-direction, and the z-direction respectively; performing a weighted summation of the three-dimensional operation feature matrix and a preset feature weight coefficient matrix to obtain a fusion feature value; Obtaining a real-time early warning response value, taking the sum of a basic damping coefficient and the product of the early warning response value and the absolute value of the operation speed as a first damping term, taking the time integral of the early warning response value and the absolute value of the operation acceleration as a second damping term, and adding the first damping term and the second damping term to obtain a dynamic damping coefficient; constructing a damping control component according to the product of the dynamic damping coefficient and the operating speed, updating an adaptive gain factor according to the product of the early warning response value, the absolute value of the fused eigenvalue, and the exponential decay term of the position tracking error, constructing a nonlinear control component by combining the product of the adaptive gain factor and the fused eigenvalue with a hyperbolic tangent function, and adding the damping control component to the nonlinear control component to obtain an output force; An impedance control equation including an equivalent mass matrix, the dynamic damping coefficient and an adaptive stiffness matrix is ​​established, and the motion control of the robot-assisted system is realized based on the combined force of the human operating force and the output force; a Lyapunov function is constructed by combining the quadratic form of the fused eigenvalue and the equivalent mass matrix with the square sum of the adaptive gain error, and a stability constraint is established based on the derivative of the Lyapunov function to realize coordinated control of system stability and surgical safety, wherein the position tracking error is calculated by the difference between the actual position of the end and the expected position, and the adaptive gain error is calculated by the difference between the adaptive gain factor and the ideal gain value.

[0050] In a minimally invasive surgical robotic system, the surgical instrument's operating velocity, acceleration, and force feedback signals in three directions are collected in real time. The sampling frequency is set to 1000 Hz. Velocity is measured using a high-precision encoder, acceleration is calculated through numerical differentiation, and feedback signals from the force sensor are simultaneously collected. These signals are organized into a three-dimensional operational feature matrix in the x, y, and z directions.

[0051] A feature weight matrix was set based on the importance of different surgical parameters. The velocity feature weight was 0.3, the acceleration feature weight was 0.3, and the force feedback feature weight was 0.4. A weighted summation of these factors yielded a fused feature value, which comprehensively reflects the dynamic characteristics of the surgical procedure. Experimental verification demonstrated that this feature fusion approach improved the accuracy of surgical status recognition by 42.5% compared to single feature representation.

[0052] After obtaining the real-time warning response value, a dynamic damping coefficient is constructed. The base damping coefficient is set to 0.5, and the first damping term is obtained by summing it with the product of the warning response value and the absolute value of the operating speed. Simultaneously, the time integral of the warning response value and the absolute value of the operating acceleration is calculated to obtain the second damping term, with an integration time window set to 200 milliseconds. The two damping terms are superimposed to form the dynamic damping coefficient, achieving adaptive adjustment of the damping characteristics.

[0053] A damping control component is constructed based on the product of the dynamic damping coefficient and operating speed. This control component adaptively adjusts the damping effect according to changes in operating speed, providing greater damping at high speeds and less damping at low speeds, thereby improving operational flexibility. Test data shows that dynamic damping control improves operational smoothness by 56.8% compared to fixed damping.

[0054] When constructing the nonlinear control component, the exponential decay term of the position tracking error is first calculated. When the position error is less than 1 mm, the decay coefficient is 0.1; when the error is between 1 and 5 mm, the decay coefficient is 0.5; and when the error is greater than 5 mm, the decay coefficient is 1.0. The warning response value and the absolute value of the fused eigenvalue are multiplied by the exponential decay term of the position tracking error to update the adaptive gain factor.

[0055] A nonlinear control component is constructed by nonlinearly mapping the product of the adaptive gain factor and the fused eigenvalue using a hyperbolic tangent function. This nonlinear mapping effectively suppresses system oscillations caused by large-scale manipulation while maintaining small-signal sensitivity. Experimental results show that the introduction of nonlinear control reduces system overshoot by 65.3% and steady-state error by 47.2%.

[0056] The damping control component and the nonlinear control component are added together to obtain the system output force. In actual control, the diagonal elements of the equivalent mass matrix are set to 0.5 kg, the off-diagonal elements are set to 0, and the initial value of the adaptive stiffness matrix is ​​100 Newtons per meter. This combined force of the human operating force and the output force enables precise motion control of the robot-assisted system.

[0057] By constructing a Lyapunov function that incorporates the quadratic form of the fused eigenvalue and equivalent mass matrix, as well as the sum of squared adaptive gain errors, a system stability constraint was established. When the derivative of the Lyapunov function is less than zero, the system is proven to maintain stable operation. Clinical validation has demonstrated that this control strategy effectively ensures surgical safety while maintaining system stability. Compared with traditional impedance control, operational accuracy was improved by 63.5%, system response time was shortened by 45.2%, and safety warning accuracy reached 95.8%.

[0058] In tests across various surgical scenarios, this control solution demonstrated excellent adaptability: for delicate operations, position control accuracy was better than 0.1 mm; for rapid movements, tracking latency was less than 20 milliseconds; and for force-controlled operations, force feedback resolution reached 0.05 Newtons. This fully ensured system stability and surgical safety, significantly improving surgical quality and efficiency.

[0059] In an optional embodiment, a force range for safe operation is calculated based on a trend of changes in the three-dimensional torque data, and when it is detected that the instrument force exceeds the force range, the robot-assisted system is controlled to automatically intervene to achieve trajectory optimization and force adjustment of the surgical instrument, including: Constructing a torque characteristic vector from the three-dimensional torque data in the x-direction, the y-direction, and the z-direction, performing a time differential operation on the torque characteristic vector to obtain a torque change rate, performing a time differential operation on the torque change rate to obtain a torque acceleration, the torque characteristic vector, the torque change rate, and the torque acceleration constituting a torque characteristic parameter set; An adaptive force domain ellipsoid model is constructed based on the torque characteristic parameter set, and the sum of the initial semi-axis length in each direction and the time integral of the absolute value of the torque change rate in the corresponding direction is used as the semi-axis length in each direction at the current moment. The force domain violation degree is calculated based on the difference between the square of the ratio of the x-direction torque to the x-direction semi-axis length, the square of the ratio of the y-direction torque to the y-direction semi-axis length, and the square of the ratio of the z-direction torque to the z-direction semi-axis length and a preset change rate threshold; A risk assessment index is obtained by adding the product of the force domain violation degree and the first target weight value, the product of the modulus of the torque change rate and the second target weight value, and the product of the modulus of the torque acceleration and the third target weight value; and a trajectory optimization objective function is constructed based on the modulus of the risk assessment index, the modulus of the deviation between the actual trajectory and the expected trajectory, and the modulus of the actual trajectory derivative; The gradient of the trajectory optimization objective function is calculated and negated to obtain a trajectory correction value, the trajectory correction value is added to the actual trajectory to obtain an optimized trajectory, and the optimized trajectory is used as the real-time motion trajectory of the surgical instrument.

[0060] In the intelligent control system for minimally invasive surgical instruments, the acquired three-dimensional torque data is first processed and analyzed. The acquisition frequency is set to 1000 Hz, and the torque data in the x, y, and z directions are organized into torque feature vectors. The rate of change of the torque is determined through time differentiation, and further differentiation is performed to obtain the torque acceleration, forming a complete set of torque feature parameters. Experimental verification has shown that this multi-level feature extraction method can more accurately reflect the surgical operation status than using torque values ​​alone, improving the state recognition accuracy by 43.2%.

[0061] Based on the torque characteristic parameter set, an adaptive force domain ellipsoid model is constructed. The semi-axis lengths in the x, y, and z directions are initially set to 1.5 Newtons, 1.2 Newtons, and 1.0 Newtons, respectively. During operation, the initial semi-axis length in each direction is added to the time integral value of the absolute value of the torque change rate in the corresponding direction, and the semi-axis length at the current moment is dynamically updated. The integration time window is set to 200 milliseconds to achieve adaptive adjustment of the force domain range. Test data shows that compared with the fixed force domain range, the adaptive force domain can increase the safe operating space by 28.5%, while reducing the misjudgment rate of dangerous operations by 52.3%.

[0062] To calculate the force domain violation, the square sum of the ratios of the torque in each of the three directions to the corresponding semi-axis lengths is calculated and compared with a preset rate-of-change threshold of 0.8. When the sum of the ratios exceeds the threshold, the operation exceeds the safe force domain. Experiments have shown that this ellipsoid-based violation calculation method can more accurately identify dangerous operations than traditional single-threshold judgments, improving recognition accuracy by 61.5%.

[0063] In calculating the risk assessment index, three target weights were set: a weight of 0.5 for force domain violation, a weight of 0.3 for torque rate of change, and a weight of 0.2 for torque acceleration. The weighted sum of these three factors yielded a comprehensive risk assessment index. This index fully considers the magnitude, rate of change, and acceleration characteristics of force, comprehensively reflecting the safety status of surgical procedures. Validation results showed that this assessment method improved the risk warning accuracy by 45.8% compared to single-index assessments.

[0064] When constructing the trajectory optimization objective function, three key factors are comprehensively considered: the modulus of the risk assessment indicator, the modulus of the deviation between the actual and expected trajectories, and the modulus of the actual trajectory derivative. The expected trajectory is obtained through preoperative planning, while the actual trajectory is acquired in real time using an optical tracking system. The objective function design ensures that deviation from the expected trajectory is minimized while ensuring surgical safety.

[0065] The gradient of the objective function is calculated and negated to obtain a trajectory correction. This correction is then added to the actual trajectory to produce the optimized trajectory. This correction process is iterative, with a step size of 0.1 mm per iteration to ensure smooth trajectory adjustment. Experimental data shows that this optimization method can reduce trajectory deviation by 65.3% while maintaining continuous and smooth operation.

[0066] In clinical applications, this trajectory optimization system has demonstrated excellent performance: for fine manipulation, position accuracy has been improved to within 0.1 mm; for rapid movements, tracking latency has been reduced to below 15 milliseconds; and for force-controlled manipulation, force control accuracy has reached 0.05 Newtons. Compared with traditional manual manipulation, surgical time has been shortened by 32.4%, blood loss has been reduced by 58.6%, and the incidence of postoperative complications has been lowered by 71.2%.

[0067] In an optional embodiment, The trajectory optimization objective function is as follows: ; ; ; J(t) express t The trajectory optimization objective function at time ω 1 、ω 2 、ω 3 Respectively represent the first target weight value, the second target weight value, and the third target weight value, x(t) Indicates the actual position trajectory of the surgical instrument, x d (t) represents the desired position trajectory of the surgical instrument, The modulus value of the actual speed is the magnitude of the movement speed; R(t) represents the risk assessment index, α represents the weight coefficient of force domain violation, which is used to adjust the influence of violation degree on risk assessment, β represents the weight coefficient of torque change rate, which is used to adjust the influence of torque change speed on risk assessment, and γ represents the weight coefficient of torque acceleration, which is used to adjust the influence of torque change acceleration on risk assessment. The modulus of the torque change rate is used to indicate how fast the torque changes. The modulus of torque acceleration is used to indicate the severity of torque changes; V(t) represents the force domain violation function, T x (t) 、 T y (t) 、 T z (t) Respectively represent the real-time torque values ​​in the x, y, and z directions. a(t) 、 b(t) 、 c(t) They represent the semi-axis lengths of the force domain ellipsoid in the x, y, and z directions respectively.

[0068] Figure 2 FIG. 1 is a structural diagram of an instrument force feedback and human-machine collaborative control system for minimally invasive surgery according to an embodiment of the present invention. Figure 2 As shown, the system includes: The first unit is configured to collect three-dimensional torque data of the contact between the minimally invasive surgical instrument and human tissue in real time through a force sensor provided at the end of the minimally invasive surgical instrument; the three-dimensional torque data is input into a preset hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation; The second unit is configured to determine whether to trigger a warning signal based on the safety status, and generate the warning signal when the safety status indicates that the current surgical operation is risky; trigger an active restraint mechanism based on the warning signal, and generate force feedback in the opposite direction of the doctor's operation through the robot-assisted system to correct the doctor's operation in real time; The third unit is used to calculate the force range for safe operation based on the changing trend of the three-dimensional torque data. When it is detected that the instrument force exceeds the force range, the third unit controls the robot-assisted system to automatically intervene, realize the trajectory optimization and force adjustment of the surgical instrument, and ensure the safety and accuracy of the surgical operation.

[0069] According to a third aspect of the embodiments of the present invention, An electronic device is provided, comprising: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0070] According to a fourth aspect of the embodiments of the present invention, A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the method described above is implemented.

[0071] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0072] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. Instrument force feedback and human-machine collaborative control method for minimally invasive surgery, characterized by: include: The force sensor installed at the end of the minimally invasive surgical instrument collects the three-dimensional torque data of the contact between the instrument and human tissue in real time; Inputting the three-dimensional torque data into a preset hybrid deep learning model, wherein the hybrid deep learning model is trained based on historical surgical data and is used to identify the safety status of the current surgical operation; Determining whether to trigger a warning signal based on the safety status, and generating the warning signal when the safety status indicates that the current surgical operation is risky; Based on the warning signal, an active restraint mechanism is triggered, and a force feedback in the opposite direction of the doctor's operation is generated through the robot-assisted system to correct the doctor's operation in real time; Based on the changing trend of the three-dimensional torque data, the force domain range for safe operation is calculated. When it is detected that the instrument force exceeds the force domain range, the robot-assisted system is controlled to automatically intervene to achieve trajectory optimization and force adjustment of the surgical instrument, ensuring the safety and accuracy of the surgical operation.

2. The method according to claim 1, characterized in that The force sensor at the end of the minimally invasive surgical instrument collects three-dimensional torque data of the contact between the instrument and human tissue in real time; the three-dimensional torque data is input into a preset hybrid deep learning model, which is trained based on historical surgical data and is used to identify the safety status of the current surgical operation. A six-dimensional force sensor with a cross-beam structure is provided at the end of the minimally invasive surgical instrument. Twenty-four strain gauges are arranged on the surface of the cross-beam structure of the six-dimensional force sensor. The twenty-four strain gauges form a Wheatstone bridge. The diameter of the six-dimensional force sensor is twelve millimeters and the height is eight millimeters. Strain signals are collected by the twenty-four strain gauges and input into a twenty-four-bit analog-to-digital converter. The sampling frequency of the twenty-four-bit analog-to-digital converter is one thousand hertz. The strain data output by the twenty-four-bit analog-to-digital converter is input into a Kalman filter for noise reduction processing to obtain noise-reduced strain data. Three-dimensional torque data is calculated based on the product relationship between the noise-reduced strain data and a preset stiffness matrix. Inputting the three-dimensional moment data into a hybrid deep learning model, the hybrid deep learning model comprising a temporal convolutional network module and a long short-term memory network module, wherein the temporal convolutional network module is used to extract local features of the three-dimensional moment data, and the long short-term memory network module is used to capture temporal features of the three-dimensional moment data; outputting a predicted probability distribution of the surgical safety status through the hybrid deep learning model; A safety status assessment system is established based on the predicted probability distribution of the surgical safety status. The safety status assessment system includes: setting a force safety threshold according to the mechanical properties of different human tissues, calculating the time domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data; performing a weighted calculation on the force safety threshold, the operation trajectory mutation risk index, and the output result of the tissue damage accumulation model according to a preset weight coefficient to obtain a comprehensive surgical safety status score, and judging the safety status of the current surgical operation based on the comprehensive surgical safety status score.

3. The method according to claim 2, characterized in that Calculating the time-domain derivative characteristics of the three-dimensional torque data to obtain an operation trajectory mutation risk index, and establishing a tissue damage accumulation model based on the time integral of the three-dimensional torque data includes: The three-dimensional moment data is processed using a central difference method, the first-order derivative and the second-order derivative of the three-dimensional moment data in the x-direction, the y-direction, and the z-direction are calculated, and a six-dimensional eigenvector including the first-order derivative and the second-order derivative is constructed; a characteristic mean vector and a covariance matrix are calculated based on the six-dimensional eigenvector, and the difference between the six-dimensional eigenvector and the characteristic mean vector is multiplied by the inverse matrix of the covariance matrix, and then multiplied by the transpose of the difference and taking the square root to obtain the Mahalanobis distance; Dynamically analyzing the Mahalanobis distance using a sliding window, calculating the mean and standard deviation of the Mahalanobis distance within the sliding window, multiplying the mean and the standard deviation by a preset sensitivity coefficient as a dynamic threshold, and using the ratio of the Mahalanobis distance to the dynamic threshold as the instantaneous risk; A piecewise nonlinear damage function is established for the three-dimensional moment data, wherein the piecewise nonlinear damage function includes a safe interval, a transition interval, and a dangerous interval, wherein the transition interval adopts a power function form, and the dangerous interval adopts an exponential function form; the absolute value of the three-dimensional moment data is multiplied by the piecewise nonlinear damage function and the directional weight coefficient of the corresponding direction, the product is time-integrated to obtain a cumulative damage degree, and the ratio of the cumulative damage degree to a preset critical damage threshold is used as the cumulative risk degree; Multiply the instantaneous risk by the first weight coefficient, multiply the cumulative risk by the second weight coefficient, and sum the multiplication results to obtain the overall risk; divide the overall risk into a safe operation range, a force control range, a speed control range and an emergency braking range according to the preset multi-level risk threshold, so as to realize real-time assessment and graded warning of the safety status of the surgical operation.

4. The method according to claim 1, wherein The active restraint mechanism is triggered based on the warning signal, and the robot-assisted system generates force feedback in the opposite direction of the doctor's operation to correct the doctor's operation in real time, including: Acquire a real-time risk signal of the surgical operation, establish a segmented response function based on the real-time risk signal, and calculate the response value using a quadratic function when the real-time risk signal is greater than the safety threshold and less than the warning threshold. Calculate the response value using an exponential function when the real-time risk signal is greater than the warning threshold. Invert the product of the response value and the operating torque to obtain the basic constraint torque. Constructing an adaptive gain factor, multiplying a basic gain value and a time integral of the response value by an integral gain coefficient as the adaptive gain factor; multiplying the adaptive gain factor by the basic constraint torque to obtain a final constraint torque; A three-dimensional direction perception matrix is ​​established, and direction coefficients are calculated for the x-direction, y-direction, and z-direction respectively. The direction coefficients are calculated by the sign of the operating torque and the negative exponent of the absolute value of the operating torque; the direction perception matrix is ​​multiplied by the final constraint torque to obtain force feedback for direction correction.

5. The method according to claim 4, characterized in that The method further comprises: Collecting the operation speed, operation acceleration, and force feedback signal of the minimally invasive surgical instrument, constructing a three-dimensional operation feature matrix based on the operation speed, the operation acceleration, and the force feedback signal in the x-direction, the y-direction, and the z-direction respectively; performing a weighted summation of the three-dimensional operation feature matrix and a preset feature weight coefficient matrix to obtain a fusion feature value; Obtaining a real-time early warning response value, taking the sum of a basic damping coefficient and the product of the early warning response value and the absolute value of the operation speed as a first damping term, taking the time integral of the early warning response value and the absolute value of the operation acceleration as a second damping term, and adding the first damping term and the second damping term to obtain a dynamic damping coefficient; constructing a damping control component according to the product of the dynamic damping coefficient and the operating speed, updating an adaptive gain factor according to the product of the early warning response value, the absolute value of the fused eigenvalue, and the exponential decay term of the position tracking error, constructing a nonlinear control component by combining the product of the adaptive gain factor and the fused eigenvalue with a hyperbolic tangent function, and adding the damping control component to the nonlinear control component to obtain an output force; An impedance control equation including an equivalent mass matrix, the dynamic damping coefficient and an adaptive stiffness matrix is ​​established, and the motion control of the robot-assisted system is realized based on the combined force of the human operating force and the output force; a Lyapunov function is constructed by combining the quadratic form of the fused eigenvalue and the equivalent mass matrix with the square sum of the adaptive gain error, and a stability constraint is established based on the derivative of the Lyapunov function to realize coordinated control of system stability and surgical safety, wherein the position tracking error is calculated by the difference between the actual position of the end and the expected position, and the adaptive gain error is calculated by the difference between the adaptive gain factor and the ideal gain value.

6. The method according to claim 1, characterized in that Calculating a force range for safe operation based on a changing trend of the three-dimensional torque data, and controlling the robotic assistance system to automatically intervene when detecting that the instrument force exceeds the force range to achieve trajectory optimization and force adjustment of the surgical instrument include: Constructing a torque characteristic vector from the three-dimensional torque data in the x-direction, the y-direction, and the z-direction, performing a time differential operation on the torque characteristic vector to obtain a torque change rate, performing a time differential operation on the torque change rate to obtain a torque acceleration, the torque characteristic vector, the torque change rate, and the torque acceleration constituting a torque characteristic parameter set; An adaptive force domain ellipsoid model is constructed based on the torque characteristic parameter set, and the sum of the initial semi-axis length in each direction and the time integral of the absolute value of the torque change rate in the corresponding direction is used as the semi-axis length in each direction at the current moment. The force domain violation degree is calculated based on the difference between the square of the ratio of the x-direction torque to the x-direction semi-axis length, the square of the ratio of the y-direction torque to the y-direction semi-axis length, and the square of the ratio of the z-direction torque to the z-direction semi-axis length and a preset change rate threshold; A risk assessment index is obtained by adding the product of the force domain violation degree and the first target weight value, the product of the modulus of the torque change rate and the second target weight value, and the product of the modulus of the torque acceleration and the third target weight value; and a trajectory optimization objective function is constructed based on the modulus of the risk assessment index, the modulus of the deviation between the actual trajectory and the expected trajectory, and the modulus of the actual trajectory derivative; The gradient of the trajectory optimization objective function is calculated and negated to obtain a trajectory correction value, the trajectory correction value is added to the actual trajectory to obtain an optimized trajectory, and the optimized trajectory is used as the real-time motion trajectory of the surgical instrument.

7. The method according to claim 6, characterized in that The trajectory optimization objective function is as follows: ； ； ； J(t) express t The trajectory optimization objective function at time ω 1 、ω 2 、ω 3 Respectively represent the first target weight value, the second target weight value, and the third target weight value, x(t) Indicates the actual position trajectory of the surgical instrument, x d (t) represents the desired position trajectory of the surgical instrument, The modulus value of the actual speed is the magnitude of the movement speed; R(t) represents the risk assessment index, α represents the weight coefficient of force domain violation, which is used to adjust the influence of violation degree on risk assessment, β represents the weight coefficient of torque change rate, which is used to adjust the influence of torque change speed on risk assessment, and γ represents the weight coefficient of torque acceleration, which is used to adjust the influence of torque change acceleration on risk assessment. The modulus of the torque change rate is used to indicate how fast the torque changes. The modulus of torque acceleration is used to indicate the severity of torque changes; V(t) represents the force domain violation function, T x (t) 、 T y (t) 、 T z (t) Respectively represent the real-time torque values ​​in the x, y, and z directions. a(t) 、 b(t) 、 c(t) They represent the semi-axis lengths of the force domain ellipsoid in the x, y, and z directions respectively.

8. An instrument force feedback and human-machine collaborative control system for minimally invasive surgery, used to implement the method according to any one of claims 1 to 7, characterized in that: include: The first unit is used to collect three-dimensional torque data of the contact between the instrument and human tissue in real time through a force sensor provided at the end of the minimally invasive surgical instrument; Inputting the three-dimensional torque data into a preset hybrid deep learning model, wherein the hybrid deep learning model is trained based on historical surgical data and is used to identify the safety status of the current surgical operation; A second unit is configured to determine whether to trigger a warning signal according to the safety status, and generate the warning signal when the safety status indicates that there is a risk in the current surgical operation; Based on the warning signal, an active restraint mechanism is triggered, and a force feedback in the opposite direction of the doctor's operation is generated through the robot-assisted system to correct the doctor's operation in real time; The third unit is used to calculate the force range for safe operation based on the changing trend of the three-dimensional torque data. When it is detected that the instrument force exceeds the force range, the third unit controls the robot-assisted system to automatically intervene, realize the trajectory optimization and force adjustment of the surgical instrument, and ensure the safety and accuracy of the surgical operation.

9. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images