An orthopedic surgery imitation learning system for sparse data and small samples

Abstract

The application provides an orthopedic surgery imitation learning system for sparse data and small samples, which combines imitation learning with data interpolation and data prediction, can generate complete and effective demonstration data according to small samples and sparse demonstration data, and regenerates the action of a robot through an imitation learning algorithm, improves the operation precision of the robot, and reduces the burden of doctors; therefore, the application can solve the problem of imitation learning precision decline caused by data loss in the collection process of demonstration data, and overcome the defect that the operation time is greatly prolonged due to the need of a large number of demonstration data samples for learning in the traditional imitation learning algorithm.

Description

Technical Field

[0001] The present invention belongs to the technical field of imitation learning, and in particular relates to an orthopedic surgery imitation learning system for sparse data and small samples. Background Art

[0002] Robots' precise positioning and rapid response capabilities have led to their widespread use in the medical field. Orthopedic surgery involves relatively simple and repetitive operations that strain the surgeon's physical strength. Imitation learning can significantly reduce this burden. For a robot to mimic a surgeon's surgical procedures, a large amount of data samples is required for the robot to learn. However, doctors often lack sufficient time to demonstrate their procedures before surgery, and data samples from their demonstrations may be lost. Consequently, methods have emerged that allow doctors to provide small samples of demonstration data, even in sparse data environments, while still enabling robot imitation learning.

[0003] In existing technologies, robots are often taught to perform certain operations through programming or offline programming. However, these methods have poor environmental adaptability and cannot be used in unstructured surgical environments. Imitation learning is a method that can quickly learn operational skills from instructional data provided by the instructor. Common imitation learning algorithms include dynamic motion primitives (DMPs), Gaussian mixture models (GMMs), kernel motion primitives (KMPs), and probabilistic motion primitives (ProMPs), which are commonly used in industry. An algorithm for imitation learning during surgery is the Surgical Robot Transformer, but this algorithm is only suitable for laparoscopic surgery and requires a large number of learning samples. Therefore, this method is not suitable for imitation learning in orthopedic surgery. Summary of the Invention

[0004] To solve the above problems, the present invention provides an orthopedic surgery imitation learning system for sparse data and small samples, which can improve the operation accuracy of the robot and reduce the burden on doctors.

[0005] An orthopedic surgery imitation learning system for sparse data and small samples, including a data acquisition module, an imitation learning module, a motion vector acquisition module, a node mapping module, and a motion control module;

[0006] The data acquisition module is used to construct a small sample data set based on the actual trajectory of the surgical instrument held by the doctor within a set time period, wherein each sample consists of the trajectory position information x0, speed information x1 and x2 of the surgical instrument at each moment. and the actual operating force F0 between the surgical instrument and the bone tissue;

[0007] The imitation learning module is used to simulate the trajectory position information x0 and speed information x1 of the surgical instrument in the small sample data set according to the Gaussian mixture regression method. and the actual operating force F0 to perform imitation learning, and obtain the probability distribution of the operating force F used to characterize the mapping relationship between the robot's motion trajectory and the operating force;

[0008] The motion vector acquisition module is used to obtain the starting point P of the robot motion trajectory represented by the operating force F according to its probability distribution. s Point to the next end point P e Motion vector

[0009] The node mapping module is used to determine the initial position of the robot according to the doctor's designated position for the bone tissue to be removed. and the next moment motion vector Get the next moment end point of the actual resection trajectory of the bone tissue to be resected

[0010] The motion control module is used to adjust the initial position and the next moment end Control the robot's movements so that it can remove the bone tissue according to the set actual removal trajectory.

[0011] Furthermore, an orthopedic surgery imitation learning system for sparse data and small samples also includes a data processing module;

[0012] The data processing module is used to use a data interpolation algorithm to fill missing data in the small sample data set, then use a time series prediction algorithm to extend the time period covered by the small sample data set after the missing data is filled, and finally use a time alignment algorithm to time align the small sample data set after the time extension is completed, so as to obtain a time-continuous small sample data set for the imitation learning module to perform imitation learning.

[0013] Furthermore, the next moment end point of the actual resection trajectory of the bone tissue to be resected The method to obtain is:

[0014]

[0015] Among them, R is the set scale factor.

[0016] Furthermore, the data acquisition module acquires the trajectory position information x and speed information of the surgical instrument. And the operating force F between the surgical instrument and the bone tissue is:

[0017] Optical navigation markers and force sensors are mounted on surgical instruments, and data collection is completed by direct demonstration by the doctor holding the surgical instruments.

[0018] Furthermore, the data acquisition module acquires the trajectory position information x and speed information of the surgical instrument. And the operating force F between the surgical instrument and the bone tissue is:

[0019] The surgical instruments are installed on a robotic arm, and the doctor drags the robotic arm or performs remote teleoperation for demonstration, thereby completing data collection.

[0020] Furthermore, the probability distribution of the operating force F is obtained as follows:

[0021] According to the actual operating force F0, the small sample data set is divided into K segments of sample data, and each segment of sample data corresponds to a Gaussian distribution;

[0022] The occurrence probability p(F0) of each actual operation force F0 in the small sample data set is constructed by the Gaussian mixture model as follows:

[0023]

[0024] in, is the prior probability of the k-th Gaussian distribution of the small sample data set, and μ k is the mean value of the kth Gaussian distribution of the small sample data set; Σ k is the covariance matrix of the k-th Gaussian distribution of the small sample data set; is the probability density function of the kth Gaussian distribution of the small sample data set;

[0025] Obtain the unknown parameters in the probability of occurrence p(F0) through the expectation maximization algorithm μ k ,Σ k ;

[0026] Gaussian mixture regression μ k ,Σ k The determined occurrence probability p(F0) is regressed and fitted to obtain the probability distribution p(F|x) of any operating force F:

[0027]

[0028] Among them, p(k|x) is the prior probability of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the probability density function of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the mean of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the covariance matrix of the kth Gaussian distribution with any robot motion trajectory position information x as input variable.

[0029] Beneficial effects:

[0030] The present invention provides an orthopedic surgery imitation learning system for sparse data and small samples, which combines imitation learning with data interpolation and data prediction. It can generate complete and effective demonstration data based on small samples and sparse demonstration data, and regenerate the robot's movements through an imitation learning algorithm, thereby improving the robot's operating accuracy and reducing the burden on doctors. Therefore, the present invention can solve the problem of reduced imitation learning accuracy due to inevitable data loss during the collection process of demonstration data, and overcome the defect that traditional imitation learning algorithms require a large number of demonstration data samples for learning, which greatly prolongs the operation time. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 This is a block diagram of the principle of an orthopedic surgery imitation learning system for sparse data and small samples provided by the present invention;

[0032] Figure 2 A flowchart of an orthopedic surgery imitation learning method for sparse data and small samples provided by the present invention;

[0033] Figure 3 This is a new task effect diagram generated by the imitation learning provided by the present invention. DETAILED DESCRIPTION

[0034] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0035] Traditional imitation learning algorithms require a large number of demonstration data samples for learning, which significantly prolongs surgical procedures. Furthermore, due to the inevitable data loss during the demonstration data acquisition process, this can lead to a decrease in imitation learning accuracy. Therefore, this invention combines imitation learning with data interpolation and data prediction, generating complete and valid demonstration data from small samples and sparse demonstration data, and regenerating the movements using an imitation learning algorithm.

[0036] like Figure 1 As shown, an orthopedic surgery imitation learning system for sparse data and small samples includes a data acquisition module, a data processing module, an imitation learning module, a motion vector acquisition module, a node mapping module, and a motion control module;

[0037] The data acquisition module is used to construct a small sample data set based on the actual trajectory of the surgical instrument held by the doctor within a set time period, wherein each sample consists of the trajectory position information x0, speed information x1 and x2 of the surgical instrument at each moment. And the actual operating force F0 between the surgical instrument and the bone tissue.

[0038] For example, the doctor demonstrates the operation of the corresponding surgical equipment for 2-5 minutes before the operation, and records the position information x0 and speed information of the doctor's handheld instrument operation trajectory. Together with the operating force information F0, a small sample data set is formed. To record the operation trajectory and operating force, optical navigation markers and force sensors can be mounted on surgical instruments, allowing the surgeon to hold the instruments for direct demonstration data collection. Alternatively, the surgical instruments can be mounted on a robotic arm, which the surgeon can then drag or remotely operate to collect demonstration data.

[0039] The data processing module is used to use a data interpolation algorithm to fill missing data in the small sample data set, then use a time series prediction algorithm to extend the time period covered by the small sample data set after the missing data is filled, and finally use a time alignment algorithm to time align the small sample data set after the time extension is completed, so as to obtain a time-continuous small sample data set for the imitation learning module to perform imitation learning.

[0040] It should be noted that due to the disconnection of sensor communication or the obstruction of optical navigation markers during the doctor's demonstration, the demonstration data at a certain moment may be lost, so the data interpolation algorithm is used to fill the missing data. Since the doctor's demonstration time is short, only 2-5 minutes, and the actual working time may be much longer than the demonstration time, the time series prediction algorithm is used to predict the demonstration data of a small sample to generate the data length required for the actual working time. Since the doctor cannot guarantee the consistency of the start time and time length in the demonstration data collection of different groups during the data collection process, the time alignment algorithm is used to find the best matching relationship between the data of different groups to achieve time alignment. It is worth noting that there are many types of algorithms for data interpolation algorithms, time series prediction algorithms, and time alignment algorithms that can achieve the above functions, including but not limited to:

[0041] 1. Data interpolation algorithms: principal component analysis interpolation, Bayesian interpolation, random forest interpolation, K-nearest neighbor interpolation, mean / median / mode interpolation, etc.

[0042] 2. Time series prediction algorithms: Long Short-Term Memory Network (LSTM), TimesNet, Transformer, etc.

[0043] 3. Time alignment algorithms: dynamic time warping (DTW), cross-correlation, phase synchronization, feature alignment, etc.

[0044] The imitation learning module is used to simulate the trajectory position information x0 and speed information x1 of the surgical instrument in the small sample data set according to the Gaussian mixture regression method. The mapping relationship between the robot motion trajectory and the actual operating force F0 is imitated and learned to obtain the probability distribution of the operating force F used to characterize the mapping relationship between the robot motion trajectory and the operating force.

[0045] The motion vector acquisition module is used to obtain the starting point P of the robot motion trajectory represented by the operating force F according to its probability distribution. s Point to the next end point P e Motion vector

[0046] The node mapping module is used to determine the initial position of the robot according to the doctor's designated position for the bone tissue to be removed. and the next moment motion vector Get the next moment end point of the actual resection trajectory of the bone tissue to be resected Among them, R is the set scale factor.

[0047] The motion control module is used to adjust the initial position and the next moment end Control the robot's movements so that it can remove the bone tissue according to the set actual removal trajectory.

[0048] It can be seen that the present invention aims to map the robot motion trajectory and the initial point of the operating force of the new bone tissue resection task to the target surgical position through node mapping, and move the robot to the target surgical position. In order to adapt to the unstructured environment, it is necessary to ensure that the surgical position arbitrarily selected by the doctor can be used as the starting point of the new task trajectory and force data. Therefore, the present invention proposes a node mapping method that can map the data generated by imitation learning to the real surgical environment. The doctor then selects a suitable position as the initial position of the robot operation In the actual operation process, the trajectory information or force information has a certain method ratio, so the design scale factor is K, and the trajectory position and operation force information end point of the actual operation are

[0049] It should be noted that this method can also map arbitrary trajectory positions and operational force information, but the prerequisite is to determine the relative relationship of any point in the task trajectory position and force information generated by imitation learning relative to the starting / end points. The surgical robot then begins performing the surgical operation according to the task trajectory and force information obtained through imitation learning. After mapping the imitation-learned task trajectory and force information to the surgical environment, the robot begins executing according to the established trajectory and force. The relevant control algorithm can be MPC, LQR, etc.

[0050] Furthermore, the motion vector acquisition module re-uses the end point P at the previous moment. e As a new starting point s , calculate the motion vector at the next moment The node mapping module then calculates the motion vector at the next moment. Get the end point of the next moment And so on, until the bone tissue is completely removed.

[0051] The following is a detailed introduction to the method of obtaining the probability distribution of the operating force F by the imitation learning module:

[0052] According to the actual operating force F0, the small sample data set is divided into K segments of sample data, and each segment of sample data corresponds to a Gaussian distribution;

[0053] The occurrence probability p(F0) of each actual operation force F0 in the small sample data set is constructed by Gaussian mixture model (GMM) as follows:

[0054]

[0055] in, is the prior probability of the k-th Gaussian distribution of the small sample data set, and μ k is the mean value of the kth Gaussian distribution of the small sample data set; Σ k is the covariance matrix of the k-th Gaussian distribution of the small sample data set; is the probability density function of the k-th Gaussian distribution of a small sample data set, and the probability density function can be calculated by the distance from the data point to the mean:

[0056]

[0057] Obtain the unknown parameters in the probability of occurrence p(F0) through the expectation maximization algorithm (EM) μ k ,Σ k ;

[0058] Gaussian mixture regression μ k,Σ k The determined occurrence probability p(F0) is regressed and fitted to obtain the probability distribution p(F|x) of any operating force F:

[0059]

[0060] Among them, p(k|x) is the prior probability of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the probability density function of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the mean of the kth Gaussian distribution with any robot motion trajectory position information x as input variable, is the covariance matrix of the kth Gaussian distribution with any robot motion trajectory position information x as input variable.

[0061] In other words, in order to associate trajectory position information with operating force information, the present invention uses trajectory position information as an input variable and operating force information as an output variable. The probability distribution of operating force information is calculated using a Gaussian mixture model, and ultimately the conditional expectation of operating force can be calculated when the trajectory position information is given:

[0062]

[0063] The mean and covariance matrix of the Gaussian components are iteratively solved using the EM algorithm. The method of calculating the conditional expectation of the output through the input variables is called Gaussian mixture regression. This method ultimately obtains the new task trajectory and force data based on imitation learning. The effect is as follows Figure 2 shown.

[0064] Figure 3 Generate a new task effect diagram for imitation learning, where each ellipse is a Gaussian mixture model, and the smooth curve in the middle is the task data generated by imitation learning, which contains trajectory position and operation force information.

[0065] In summary, the present invention provides an orthopedic surgery imitation learning system for sparse data and small samples, including a data acquisition module, an imitation learning module, a motion vector acquisition module, a node mapping module, and a motion control module;

[0066] Among them, the data acquisition module is used to collect the doctor's demonstration data before the operation; the data processing module is used to perform time alignment, data interpolation and prediction on the demonstration data to generate complete and valid demonstration data; the motion vector acquisition module is used to obtain the motion direction; the node mapping module generates new task data through the Gaussian mixture regression algorithm and maps it to the corresponding surgical environment; the motion control module is used to execute the task data generated by imitation learning in the surgical environment; the present invention can generate complete and valid demonstration data based on small samples and sparse demonstration data, and regenerate the robot's movements through the imitation learning algorithm, thereby improving the robot's operating accuracy and reducing the burden on doctors.

[0067] Of course, the present invention may have many other embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art may of course make various corresponding changes and modifications based on the present invention, but these corresponding changes and modifications should all fall within the scope of protection of the claims attached to the present invention.

Claims

1. An orthopedic surgery imitation learning system for sparse data and small samples, characterized by: It includes data acquisition module, imitation learning module, motion vector acquisition module, node mapping module, motion control module and data processing module; The data acquisition module is used to construct a small sample data set based on the actual trajectory of the surgical instrument held by the doctor within a set time period, wherein each sample consists of the trajectory position information of the surgical instrument at each moment. , speed information and the actual operating force between surgical instruments and bone tissue constitute; The imitation learning module is used to simulate the trajectory position information of surgical instruments in a small sample data set according to the Gaussian mixture regression method. , speed information and practical operational capabilities The mapping relationship between the robot motion trajectory and the operating force is simulated and learned to obtain the operating force used to characterize the mapping relationship between the robot motion trajectory and the operating force. The probability distribution of The motion vector acquisition module is used to obtain the motion vector according to the operation force. The probability distribution of the robot motion trajectory is obtained by Pointing to the next end point Motion vector ; The node mapping module is used to determine the initial position of the robot according to the doctor's designated position for the bone tissue to be removed. and the next moment motion vector Get the next moment end point of the actual resection trajectory of the bone tissue to be resected ; The motion control module is used to adjust the initial position and the next moment end Control the robot's movements so that it can resect the bone tissue according to the set actual resection trajectory; The data processing module is used to use a data interpolation algorithm to fill missing data in the small sample data set, then use a time series prediction algorithm to extend the time period covered by the small sample data set after the missing data is filled, and finally use a time alignment algorithm to time align the small sample data set after the time extension is completed, so as to obtain a time-continuous small sample data set for the imitation learning module to perform imitation learning.

2. The orthopedic surgery imitation learning system for sparse data and small samples according to claim 1, characterized in that: The next endpoint of the actual resection trajectory of the bone tissue to be resected The method to obtain is: in, is the set scaling factor.

3. The orthopedic surgery imitation learning system for sparse data and small samples according to claim 1, characterized in that: The data acquisition module collects the trajectory position information of the surgical instrument , speed information and the operating forces between surgical instruments and bone tissue The method is: Optical navigation markers and force sensors are mounted on surgical instruments, and data collection is completed by direct demonstration by the doctor holding the surgical instruments.

4. The orthopedic surgery imitation learning system for sparse data and small samples according to claim 1, characterized in that: The data acquisition module collects the trajectory position information of the surgical instrument , speed information and the operating forces between surgical instruments and bone tissue The method is: The surgical instruments are installed on a robotic arm, and the doctor drags the robotic arm or performs remote teleoperation for demonstration, thereby completing data collection.

5. The orthopedic surgery imitation learning system for sparse data and small samples according to claim 1, characterized in that: Operating force The probability distribution of is obtained as follows: According to actual operating force The small sample data set is divided into K segments of sample data, and each segment of sample data corresponds to a Gaussian distribution; Constructing the actual operating forces in a small sample data set through Gaussian mixture model Probability of occurrence in a small sample data set as follows: in, For the small sample data set The prior probability of a Gaussian distribution, and ; For the small sample data set The mean of a Gaussian distribution; For the small sample data set The covariance matrix of a Gaussian distribution; For the small sample data set The probability density function of a Gaussian distribution; Obtain the probability of occurrence through the expectation maximization algorithm Unknown parameters in ; Gaussian mixture regression Determined probability of occurrence Perform regression fitting to obtain any operating force The probability distribution of : in, The position information of any robot motion trajectory The first input variable The prior probability of a Gaussian distribution, The position information of any robot motion trajectory The first input variable The probability density function of a Gaussian distribution, The position information of any robot motion trajectory The first input variable The mean of a Gaussian distribution, The position information of any robot motion trajectory The first input variable The covariance matrix of a Gaussian distribution.

Images