Multi-objective autonomous traction method of surgical robot based on fuzzy logic

Abstract

The present application provides a multi-objective autonomous traction method for a surgical robot based on fuzzy logic, which relates to the field of medical device technology. The method includes: assembling an actuator at the end of the robot, simplifying the end motion of the actuator into a spring-mass damped linear control system, and constructing multiple target controllers; respectively calculating the predicted evaluation gradient descent value for each control target and constructing a state feedback mechanism; weighted fusion of the multi-objective control quantities based on a preset state feedback fusion mechanism, and inputting the weighted fused target values ​​into the spring-mass damped linear control system. Aiming at the complexity of the surgical scene, the present application integrates various safety constraints in the operation into the autonomous motion planning of the robot in the form of control targets through a multi-objective constraint control strategy; by pre-defining the traction point, the robot automatically and safely performs tissue traction without requiring any prior knowledge of the surgical scene or tissue model.

Description

Technical Field

[0001] The present invention relates to the technical field of medical devices, and in particular to a multi-target autonomous traction method of a surgical robot based on fuzzy logic. Background Art

[0002] Tissue traction operations in laparoscopic surgery help improve visibility and create a more favorable surgical environment. They also help maintain the tension of pathologically attached tissues. Currently, commonly used tissue traction methods include manual tissue traction methods and fixed mechanical structure tissue traction methods.

[0003] In the manual tissue traction method, a special clamp instrument or surgical hook is used to control the traction of the tissue, and the magnitude and direction of the force are adjusted according to the requirements; in the fixed mechanical structure traction method, a mechanical structure is used to replace the artificial tissue. These mechanical structures usually fix the tissue in certain positions and are adjusted according to the needs of the operation. However, it is impossible to keep the hand stable for a long time during manual traction. The mechanical device usually fixes the tissue in a predetermined position, and the instrument needs to be reset frequently, which affects the fluency and efficiency.

[0004] To this end, in the related technology, robots can be used for assisted traction. Currently, commonly used assisted traction methods include visual methods based on tissue positioning and segmentation, model-free shape control methods, and tissue traction methods based on reinforcement learning; however, the visual method based on tissue positioning and segmentation detects tissue position intermittently, and cannot handle the situation of surgical instrument occlusion, and cannot continuously and in real time pull the tissue to cooperate with sharp dissection; the model-free shape control method has a too slow adjustment speed and cannot meet the needs of large tissue deformation in laparoscopic surgery, and does not give enough consideration to safety constraints; the tissue traction method based on reinforcement learning requires a large amount of training data and time, and is difficult to generalize to various complex surgical scenarios. In addition, the success rate of the tissue traction method based on reinforcement learning after migration to a real robot is not ideal. Summary of the invention

[0005] In response to the shortcomings of the prior art, the present application provides a multi-objective autonomous traction method for a surgical robot based on fuzzy logic, which solves a series of unreliable problems existing in the current robot tissue traction process, such as poor continuity, insufficient safety and unsatisfactory generalization.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions:

[0007] In the first aspect, an embodiment of the present application provides a multi-objective autonomous traction method for a surgical robot based on fuzzy logic, the method comprising: assembling an execution instrument at the end of the robot to build the hardware of the autonomous traction surgical robot; simplifying the end motion of the execution instrument into a spring-mass damped linear control system, and constructing multiple target controllers corresponding to a preset target group according to the actual needs of the traction organization; wherein the preset target group includes a traction angle target, a traction force target and a safety area target; in each target controller, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed; the multi-objective control quantity and the gradient descent value are normalized, and input into a preset fuzzy logic weight allocation algorithm to assign weights to each control target; the multi-objective control quantity is weightedly fused based on a preset state feedback fusion mechanism, and the weighted fused target value is input into the spring-mass damped linear control system to convert the motion speed and the speed of posture change into the joint angle of the robot to perform robot motion control.

[0008] According to a first aspect of the embodiment of the present application, a spring mass damping linear control system is used to characterize the end motion state of the actuator and satisfies the state equation:

[0009]

[0010] in, is the position state of the end of the instrument, is the movement speed of the end of the instrument, is the acceleration at the end of the instrument, is the total control input of the spring-mass damping linear control system, is the inertia parameter, is the damping parameter, is the stiffness parameter; the multiple target controllers include a traction angle controller, a traction force controller and a safety area controller.

[0011] According to a first aspect of the embodiment of the present application, the traction angle controller is used to define the traction angle, and the traction angle satisfies the expression:

[0012]

[0013] In the formula, is the traction angle, Indicates the position of the cutting instrument. is the position state of the end of the instrument, represents the cutting direction vector, express The norm of ;

[0014] The traction angle controller satisfies the expression:

[0015]

[0016]

[0017] In the formula, Indicates the control amount of the traction angle, and To adjust the traction angle controller Control process parameters, is the error derived from the chord length formula, for The first derivative of is the desired angle, is the viewing direction.

[0018] According to a first aspect of the embodiment of the present application, the traction force controller is provided with a desired traction force to maintain tissue tension;

[0019] The dynamic characteristics of the 7-DOF robot corresponding to the spring-mass-damped linear control system in Cartesian space satisfy the expression:

[0020]

[0021] In the formula, represents the vector consisting of force and torque, represents the joint vector, represents the Cartesian inertia matrix, and are the velocity vector and gravity vector in Cartesian space, Represents the position and posture of the robot's end effector in Cartesian space, for The second-order derivative of for The first derivative of ;

[0022] The environmental interaction force acting on the actuator when the robot contacts the environment during motion Satisfies the expression:

[0023]

[0024] in, represents the net force acting on the actuator, The corresponding force mapping relationship satisfies: , represents the joint torque, Represents the Jacobian matrix from joint space to Cartesian space;

[0025] The traction controller satisfies the expression:

[0026]

[0027]

[0028] in, Indicates the control amount of traction, , To adjust the traction controller Control process parameters, For the expected traction, is the current force, is the error between the expected traction force and the current force;

[0029] Current Force Satisfies the expression:

[0030]

[0031] in, is a diagonal matrix with 3 rows and 3 columns, Force and torque vectors for the machine and its interaction with the environment Have corresponding mapping relationships.

[0032] According to a first aspect of the embodiment of the present application, the security area set in the security area controller is a security area with a radius of , Gao Wei The cylindrical area of ​​?

[0033] In the case where the implement exceeds the boundary of the cylindrical area, the safety area controller generates a control amount pointing to the inside of the cylindrical area;

[0034] The safety zone controller satisfies the expression:

[0035]

[0036]

[0037]

[0038] in, represents the control amount of the safe area, and To perform security zone controller Control process parameters, Indicates the deviation between the current position and the safe area. express The first derivative of and Respectively exist Plane and The weight in direction, is the vector pointing toward the central axis, is the distance from the tip of the actuator to the coordinate axis, is the distance from the tip of the actuator to the base of the cylinder.

[0039] According to the first aspect of the embodiment of the present application, in each target controller, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed, including:

[0040] Based on the square of the chord length corresponding to the error between the current traction angle and the desired angle, an evaluation function for the traction angle target is designed;

[0041] An evaluation function of the traction target is designed using the square of the error between the current traction and the expected traction;

[0042] The evaluation function of the safety zone target is designed based on the square of the distance between the tip position of the current executing instrument and the boundary of the established safety zone;

[0043] A state feedback mechanism is constructed in the state space for gradient optimization to make the robot state converge quickly.

[0044] According to a first aspect of the embodiment of the present application, the evaluation function of the traction angle target :

[0045]

[0046] Evaluation function of traction target :

[0047]

[0048] Evaluation function of safe area objective :

[0049]

[0050] in, Represents the predicted distance value from the tip of the actuator to the coordinate axis, It represents the predicted distance from the tip of the actuator to the base of the cylinder. Expressing expectation, represents the current force predicted by the system, is a real variable coefficient, Indicates the current moment, is the time variable, To determine the position of the end of the instrument, Indicates the position of the cutting instrument. is the desired angle, is the prediction angle.

[0051] In the second aspect, an embodiment of the present application provides a multi-objective autonomous traction system for a surgical robot based on fuzzy logic, the system comprising a hardware construction module, a system construction module, a calculation module, a weight distribution module and a fusion module; the hardware construction module is used to assemble an execution instrument at the end of the robot to perform hardware construction of an autonomous traction surgical robot; the system construction module is used to simplify the end motion of the execution instrument into a spring mass damping linear control system, and construct multiple target controllers corresponding to a preset target group according to the actual needs of the traction tissue; the calculation module is used to set an evaluation function for the corresponding control target based on the state error in each target controller, calculate the predicted evaluation gradient descent value for each control target, and construct a state feedback mechanism; the weight distribution module is used to normalize the multi-objective control quantity and the gradient descent value, and input them into a preset fuzzy logic weight distribution algorithm to assign weights to each control target; the fusion module is used to perform weighted fusion of the multi-objective control quantity based on a preset state feedback fusion mechanism, and input the weighted fused target value into the spring mass damping linear control system to convert the motion speed and the speed of posture change into the joint angle of the robot to perform robot motion control.

[0052] In a third aspect, an embodiment of the present application provides an electronic device, comprising: a processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the multi-objective autonomous traction method of a surgical robot based on fuzzy logic in the aforementioned first aspect is implemented.

[0053] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium storing a program or instruction, which, when executed by a processor, implements the multi-objective autonomous traction method of a surgical robot based on fuzzy logic in the aforementioned first aspect.

[0054] This application provides a multi-objective autonomous traction method for a surgical robot based on fuzzy logic. Compared with the prior art, it has the following beneficial effects:

[0055] This application designs multiple target controllers to focus on traction angle targets, traction force targets, and safety area targets to achieve autonomous organization traction by the robot; calculate the predicted evaluation gradient descent value for each control target, build a state feedback mechanism, normalize the multi-target control quantity and the gradient descent value, and assign weights to each control target; perform weighted fusion on the multi-target control quantity, and input the weighted fusion target value into the spring-mass damping linear control system to convert the speed of movement and posture change into the joint angle of the robot for robot motion control. In response to the complexity of the surgical scene, this application integrates multiple safety constraints in the operation into the robot's autonomous motion planning in the form of control targets through a multi-target constraint control strategy; by pre-defining traction points, the robot automatically and safely performs tissue traction without requiring any prior knowledge of the surgical scene or tissue model. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0057] Figure 1 is a flowchart of a multi-objective autonomous traction method for a surgical robot based on fuzzy logic provided in an embodiment of the present application;

[0058] Figure 2 It is a schematic diagram of a framework of a multi-objective autonomous traction method of a surgical robot based on fuzzy logic provided in an embodiment of the present application;

[0059] Figure 3 is a schematic diagram of a trajectory of the tip of the execution instrument provided in an embodiment of the present application;

[0060] Figure 4 is a schematic diagram of the error between the current position of the tip of the actuator and the defined target position provided in an embodiment of the present application;

[0061] Figure 5 It is a snapshot schematic diagram of the edge of the pig liver tissue during the resection process provided in the embodiment of the present application;

[0062] Figure 6 is another schematic diagram of the motion trajectory of the tip of the actuator provided in an embodiment of the present application;

[0063] Figure 7 This is a schematic diagram of angles during the traction process provided by an embodiment of the present application;

[0064] Figure 8It is a force schematic diagram of the traction process provided by an embodiment of the present application;

[0065] Fig. 9 is a structural schematic diagram of a multi-objective autonomous traction system of a surgical robot based on fuzzy logic provided in an embodiment of the present application;

[0066] Fig.10 It is a structural schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0067] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention are clearly and completely described. Obviously, the described embodiments are 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 creative work are within the scope of protection of the present invention.

[0068] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0069] The embodiment of the present application solves a series of unreliable problems such as poor continuity, insufficient safety and unsatisfactory generalization in the current robot tissue traction process by providing a multi-objective autonomous traction method for a surgical robot based on fuzzy logic.

[0070] The technical solution in the embodiment of the present application is to solve the above technical problems, and the overall idea is as follows:

[0071] Tissue traction operations in laparoscopic surgery help improve visibility and create a more favorable surgical environment. They also help maintain the tension of pathologically attached tissues. Currently, commonly used tissue traction methods include manual tissue traction methods and fixed mechanical structure tissue traction methods.

[0072] In the manual traction tissue method, a special clamp instrument or surgical hook is used to control the traction of the tissue, and the magnitude and direction of the force are adjusted as required; in the fixed mechanical structure traction tissue, a mechanical structure is used to replace the artificial tissue. These mechanical structures usually fix the tissue in certain positions and are adjusted according to the needs of the operation. However, it is impossible to maintain hand stability for a long time during manual traction. The mechanical device usually fixes the tissue in a predetermined position. The instrument needs to be reset frequently, affecting fluency and efficiency. Each adjustment of the fixed instrument may cause additional stress or damage to the tissue, increasing the risk to the patient.

[0073] In the related technology, robots can be used for auxiliary traction. The commonly used auxiliary traction methods include visual methods based on tissue positioning and segmentation, model-free shape control methods, and tissue traction methods based on reinforcement learning. The visual method based on tissue positioning and segmentation uses computer vision to locate the tissue that blocks the surgical field of view, segments the tissue edge based on the algorithm, and then uses the robot to pull the blocked tissue away. The model-free shape control method uses multi-mapping relationships to precisely manipulate the snake-like continuum robot and deformable objects, aligns the marker points in the pixel space, and then controls the continuum robot to pull the target point to the desired position. The tissue traction method based on reinforcement learning builds a surgical scene in a virtual environment, and designs a reward function to enable the intelligent agent to learn how to correctly perform the tissue traction task, and finally executes it in a real robot system.

[0074] However, the visual method based on tissue positioning and segmentation detects tissue position intermittently, and cannot handle the situation of occlusion by surgical instruments, and cannot continuously and in real time pull the tissue to cooperate with sharp dissection; the model-free shape control method has a very slow adjustment speed, which cannot meet the needs of large tissue deformation in laparoscopic surgery, and does not give enough consideration to safety constraints; the tissue traction method based on reinforcement learning requires a large amount of training data and time, and is difficult to generalize to various complex surgical scenarios. In addition, the success rate of the tissue traction method based on reinforcement learning after migration to a real robot is not ideal.

[0075] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0076] The following first introduces a multi-objective autonomous traction method for a surgical robot based on fuzzy logic provided in an embodiment of the present application.

[0077] The present application provides a flowchart of a multi-objective autonomous traction method for a surgical robot based on fuzzy logic, as shown in FIG. Figure 1 As shown, the method may include the following steps S110-S150.

[0078] S110. Assemble the execution device at the end of the robot to build the hardware of the autonomous traction surgical robot.

[0079] S120. Simplify the end motion of the actuator into a spring-mass damping linear control system, and construct multiple target controllers corresponding to the preset target group according to the actual needs of the traction organization; wherein the preset target group includes a traction angle target, a traction force target and a safety area target.

[0080] S130. In each target controller, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed.

[0081] S140, normalizing the multi-objective control quantities and the gradient descent values, and inputting them into a preset fuzzy logic weight allocation algorithm to allocate weights to each control objective.

[0082] S150. Based on a preset state feedback fusion mechanism, weighted fusion is performed on the multi-objective control quantities, and the weighted fusion target values ​​are input into the spring-mass damping linear control system to convert the movement speed and the speed of posture change into the joint angle of the robot to perform robot motion control.

[0083] In the embodiments of this application, please refer to Figure 2 , this application designs multiple target controllers to focus on traction angle targets, traction force targets and safety area targets to achieve autonomous organization traction of the robot; calculate the predicted evaluation gradient descent value for each control target, build a state feedback mechanism, normalize the multi-target control quantity and the gradient descent value, and assign weights to each control target; perform weighted fusion on the multi-target control quantity, and input the weighted fusion target value into the spring-mass damping linear control system to convert the movement speed and posture change speed into the robot's joint angle for robot motion control. In response to the complexity of surgical scenarios, this application integrates multiple safety constraints in surgery into the robot's autonomous motion planning in the form of control targets; by pre-defining traction points, the robot automatically and safely performs tissue traction without any prior knowledge of surgical scenarios or tissue models.

[0084] In one example, the aforementioned spring mass damping linear control system is a mass-damper-spring linear system, and the mass-damper-spring linear system is used to characterize the motion state of the robot end assembly actuator.

[0085] In some embodiments, the multiple target controllers include a traction angle controller, a traction force controller, and a safety zone controller. The spring mass damping linear control system is used to characterize the end motion state of the actuator and satisfies the state equation:

[0086]

[0087] in, is the position state of the end of the instrument, is the movement speed of the end of the instrument, is the acceleration at the end of the instrument, is the total control input of the spring-mass damping linear control system, is the inertia parameter, is the damping parameter, is the stiffness parameter.

[0088] In some embodiments, the traction angle controller is used to define the traction angle, and the traction angle satisfies the expression:

[0089]

[0090] In the formula, is the traction angle, Indicates the position of the cutting instrument. is the position state of the end of the instrument, represents the cutting direction vector, express The norm of

[0091] The traction angle controller satisfies the expression:

[0092]

[0093]

[0094] In the formula, Indicates the control amount of the traction angle, and To adjust the traction angle controller Control process parameters, is the error derived from the chord length formula, for The first derivative of is the desired angle, is the viewing direction.

[0095] In some embodiments, the traction controller is provided with a desired traction force to maintain tissue tension; the dynamic characteristics of the 7-DOF robot corresponding to the spring-mass damping linear control system in Cartesian space satisfy the expression:

[0096]

[0097] In the above formula, represents the vector consisting of force and torque, represents the joint vector, represents the Cartesian inertia matrix, and are the velocity vector and gravity vector in Cartesian space, Represents the position and posture of the robot's end effector in Cartesian space, for The second-order derivative of for The first derivative of .

[0098] In one example, when the robot is in contact with the environment during motion, the environmental interaction force acting on the actuator Satisfies the expression:

[0099]

[0100] in, represents the net force acting on the actuator, The corresponding force mapping relationship satisfies: , represents the joint torque, Represents the Jacobian matrix from joint space to Cartesian space.

[0101] In one example, the traction controller satisfies the expression:

[0102]

[0103]

[0104] in, Indicates the control amount of traction, , To adjust the traction controller Control process parameters, For the expected traction, is the current force, is the error between the expected traction force and the current force.

[0105] In one example, the current force Satisfies the expression:

[0106]

[0107] in, is a diagonal matrix with 3 rows and 3 columns, Force and torque vectors for the machine and its interaction with the environment Have corresponding mapping relationships.

[0108] In some embodiments, the safety zone set in the safety zone controller is a zone with a radius of , Gao Wei cylindrical area; when the actuator exceeds the boundary of the cylindrical area, the safety area controller generates a control amount pointing to the inside of the cylindrical area.

[0109] The safety zone controller satisfies the expression:

[0110]

[0111]

[0112]

[0113] in, represents the control amount of the safe area, and To perform security zone controller Control process parameters, Indicates the deviation between the current position and the safe area. express The first derivative of and Respectively exist Plane and The weight in direction, is the vector pointing toward the central axis, is the distance from the tip of the actuator to the coordinate axis, is the distance from the tip of the actuator to the base of the cylinder.

[0114] In some embodiments, in each target controller, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed, that is, the aforementioned S130 may specifically include the following steps:

[0115] S210 . Design an evaluation function of the traction angle target based on the square of the chord length corresponding to the error between the current traction angle and the desired angle.

[0116] S220: Design an evaluation function of the traction target based on the square of the error between the current traction and the expected traction.

[0117] S230, designing an evaluation function of the safety zone target based on the square of the distance between the current execution instrument tip position and the established safety zone boundary.

[0118] S240. Construct a state feedback mechanism in the state space to perform gradient optimization so that the robot state converges quickly.

[0119] In one example, the evaluation function for the traction angle target is :

[0120]

[0121] Evaluation function of traction target :

[0122]

[0123] Evaluation function of safe area objective :

[0124]

[0125] in, Represents the predicted distance value from the tip of the actuator to the coordinate axis, It represents the predicted distance from the tip of the actuator to the base of the cylinder. Expressing expectation, represents the current force predicted by the system, is a real variable coefficient, Indicates the current moment, is the time variable, To determine the position of the end of the instrument, Indicates the position of the cutting instrument. is the desired angle, is the prediction angle.

[0126] In some embodiments, it can be understood that in the state space, the gradient direction is the direction of fastest convergence, and the gradient direction can be expressed as:

[0127]

[0128] In order to limit the size of the gradient to a reasonable range, this application designs a saturation suppression function , the saturation suppression function Satisfies the expression:

[0129]

[0130] in, is the saturation suppression parameter, To control the cumulative gradient descent of the target,

[0131] The single-objective controller after adding the state feedback mechanism is expressed as:

[0132]

[0133] Get the input after single objective optimization:

[0134]

[0135] in, is the state feedback coefficient, is the initial control quantity, is the control amount after adding the state feedback mechanism, Indicates the control target, Corresponding status, represents the optimal state, is the parameter corresponding to the saturation suppression function.

[0136] In some embodiments, the present application performs weight assignment based on fuzzy logic, and weightedly fuses the multi-objective control quantities optimized by the three controllers;

[0137] It is understandable that simply centralizing the traction angle target, traction force target and safety zone target cannot solve the inherent conflicts between different targets. Therefore, dynamic weight allocation for each target is essential. According to the actual requirements of tissue traction during surgery, fuzzy logic is used for dynamic weight allocation. This application performs normalized proportional calculation on the control input and gradient value of each control target to obtain the proportional factor Respectively represent and Respectively represent , expressed as:

[0138]

[0139]

[0140] This application designs three fuzzy sets of different sizes for each input. Each fuzzy set corresponds to a specific membership function, and a specific function is designed to ensure smoothness:

[0141]

[0142]

[0143]

[0144] in, , and Corresponding to three fuzzy sets of different sizes, the parameters , , and , determines the specific shape of the membership function. This application designs 9 fuzzy rules to cover all different scenarios; the traction angle target, traction force target and safety area target each correspond to 6 output sets; the defuzzification process is based on the membership of the output set, using the centroid method, each output set corresponds to the generation of an important index parameter , expressed as:

[0145]

[0146] Construct a judgment matrix to evaluate the relative importance of each pair of control objectives, as shown below:

[0147]

[0148]

[0149] in, Corresponding to the traction angle target, Corresponding to the traction target, Corresponding to the safe area target, Indicates control objectives and control objectives The relative importance between them. The overall importance of the control target in the whole problem can be expressed by its geometric mean Given, Satisfies the expression:

[0150]

[0151] The weight of a single control target in the global environment is obtained as:

[0152]

[0153] The motion fusion of multiple targets in the traction process is achieved by fusing the optimal input of each controller state feedback, which can be expressed as:

[0154]

[0155]

[0156] In the formula, is the actual system input, is the weight corresponding to the pulling angle target, is the weight corresponding to the traction target, is the weight corresponding to the safe area target, , and are the optimal inputs including traction angle, traction force and safety space constraint target state feedback, It is the cumulative gradient descent of the three control targets: traction angle target, traction force target and safety area target.

[0157] In some embodiments, the robot motion control considers the constraint of a fixed distal motion center, which is expressed as:

[0158]

[0159]

[0160]

[0161]

[0162]

[0163]

[0164] in, represents the distal motion center point, express The posture matrix at the moment Axis vector, express The posture matrix at the moment Axis vector, Represents the attitude matrix Axis vector, For the corresponding The position of the axis, Represents the attitude matrix Axis vector, is the posture of the robot movement, function Indicates the conversion of the attitude rotation matrix into the Euler angle in the Cartesian coordinate system. is the Euler angle in Cartesian coordinate system, is the speed of change of Euler angles, is the speed at which the robot end effector changes position in Cartesian space, is the rotation speed of the robot joint angle, represents the Jacobian matrix from joint space to Cartesian space, is the inverse of the Jacobian matrix.

[0165] In some embodiments, in order to verify the effectiveness of the multi-target autonomous traction method proposed in this application in traction of flexible tissues in a confined space, a target point traction experiment was conducted. Four points were defined in space, and the four points were located at different positions inside and outside the safe area. The multi-target autonomous traction method proposed in this application was used to control the robot to hold the prosthetic tissue and traction to each target point in turn. The target points were marked from 1 to 4. The results are shown in Figure 2. Figure 3As shown, Figure 3 shows the trajectory of the actuator tip, Figure 4 The error between the current position of the tip of the actuator and the defined target position is described; for point 1 located in the defined safety area, the robot successfully pulls the tissue to the target point, and points 2, 3, and 4 are located at different positions outside the safety zone, respectively, and the tip of the actuator is finally constrained to the boundary outside the safety zone; the experiment verifies the effectiveness of this method in improving the safety of robot autonomous traction.

[0166] In addition, in the in vitro experiment, in order to simulate tissue traction in a more realistic environment and evaluate the performance of the multi-target autonomous traction method proposed in this application in assisting the actual removal of attached tissue, pig liver tissue separated from the animal body was selected as the experimental object and traction and cutting operations were performed. Partial removal of the edge of the pig liver tissue was completed within 50 seconds. Figure 5 shows a snapshot of the experiment during the excision process, Figure 6 The motion trajectory of the tip of the actuator is shown. Figure 7 and Figure 8 They are respectively the curves of angle and force changes during the traction process; the experimental results show that the multi-objective autonomous traction method of the surgical robot based on fuzzy logic provided in this application can assist the operator in completing the task of partial resection of pig liver tissue.

[0167] In some embodiments, please refer to Fig. 9 The present application also provides a multi-objective autonomous traction system 300 for implementing a surgical robot based on fuzzy logic, the system 300 comprising:

[0168] The hardware construction module 310 is used to assemble the execution instrument at the end of the robot to carry out the hardware construction of the autonomous traction surgical robot.

[0169] The system construction module 320 is used to simplify the end motion of the actuator into a spring-mass damping linear control system, and to construct multiple target controllers corresponding to the preset target group according to the actual needs of the traction tissue.

[0170] The calculation module 330 is used to set an evaluation function for the corresponding control target based on the state error in each target controller, calculate the predicted evaluation gradient descent value for each control target, and build a state feedback mechanism.

[0171] The weight allocation module 340 is used to normalize the multi-objective control quantities and the gradient descent values, and input them into a preset fuzzy logic weight allocation algorithm to allocate weights to each control objective.

[0172] The fusion module 350 is used to perform weighted fusion on the multi-objective control quantities based on a preset state feedback fusion mechanism, and input the weighted fused target values ​​into the spring mass damping linear control system to convert the movement speed and the speed of posture change into the joint angle of the robot for robot motion control.

[0173] In some embodiments, the aforementioned calculation module 330 may be specifically used for:

[0174] Based on the square of the chord length corresponding to the error between the current traction angle and the desired angle, an evaluation function for the traction angle target is designed;

[0175] An evaluation function of the traction target is designed using the square of the error between the current traction and the expected traction;

[0176] The evaluation function of the safety zone target is designed based on the square of the distance between the tip position of the current executing instrument and the boundary of the established safety zone;

[0177] A state feedback mechanism is constructed in the state space for gradient optimization to make the robot state converge quickly.

[0178] In some embodiments, the present application provides an electronic device, the structure diagram of the electronic device is as follows Fig.10 shown.

[0179] The electronic device may include a processor 410 and a memory 420 storing computer program instructions.

[0180] Specifically, the processor 410 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiments of the present application.

[0181] The memory 420 may include a large capacity memory for data or instructions. By way of example and not limitation, the memory 420 may include a hard disk drive (HDD), a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 420 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 420 may be inside or outside the integrated gateway disaster recovery device. In a specific embodiment, the memory 420 is a non-volatile solid-state memory.

[0182] The memory 420 may include a read-only memory (ROM), a random access memory (RAM), a magnetic disk storage medium device, an optical storage medium device, a flash memory device, an electrical, optical or other physical / tangible memory storage device. Therefore, generally, the memory 420 includes one or more tangible (non-transitory) computer-readable storage media (e.g., a memory device) encoded with software including computer-executable instructions, and when the software is executed (e.g., by one or more processors), it can perform the operations described in any of the multi-objective autonomous traction methods for surgical robots based on fuzzy logic in the above-mentioned embodiments.

[0183] The processor 410 reads and executes the computer program instructions stored in the memory 420 to implement any one of the multi-objective autonomous traction methods for a surgical robot based on fuzzy logic in the above-mentioned embodiments.

[0184] In one example, the electronic device may further include a communication interface 430 and a bus 400. Fig.10 As shown, the processor 410, the memory 420, and the communication interface 430 are connected via a bus 400 and communicate with each other.

[0185] The communication interface 430 is mainly used to implement communication between various modules, devices, units and / or equipment in the embodiments of the present application.

[0186] Bus 400 includes hardware, software or both, and the parts of online data flow billing equipment are coupled to each other. For example, but not limitation, bus may include accelerated graphics port (AGP) or other graphics bus, enhanced industrial standard architecture (EISA) bus, front-end bus (FSB), hypertransport (HT) interconnection, industrial standard architecture (ISA) bus, infinite bandwidth interconnection, low pin count (LPC) bus, memory bus, micro channel architecture (MCA) bus, peripheral component interconnection (PCI) bus, PCI-Express (PCI-X) bus, serial advanced technology attachment (SATA) bus, video electronics standard association local (VLB) bus or other suitable bus or two or more of these combinations. In appropriate cases, bus 400 may include one or more buses. Although the present application embodiment describes and shows a specific bus, the present application considers any suitable bus or interconnection.

[0187] In addition, in combination with the multi-objective autonomous traction method of a surgical robot based on fuzzy logic in the above embodiments, the present application embodiment can provide a computer storage medium for implementation. The computer storage medium stores computer program instructions; when the computer program instructions are executed by a processor, any multi-objective autonomous traction method of a surgical robot based on fuzzy logic in the above embodiments is implemented.

[0188] It should be clear that the present application is not limited to the specific configuration and processing described above and shown in the figures. For the sake of simplicity, a detailed description of the known method is omitted here. In the above embodiments, several specific steps are described and shown as examples. However, the method process of the present application is not limited to the specific steps described and shown, and those skilled in the art can make various changes, modifications and additions, or change the order between the steps after understanding the spirit of the present application.

[0189] The functional blocks shown in the above block diagram can be implemented as hardware, software, firmware or a combination thereof. When implemented in hardware, it can be, for example, an electronic circuit, an application specific integrated circuit (ASIC), appropriate firmware, a plug-in, a function card, etc. When implemented in software, the elements of the present application are programs or code segments that are used to perform the required tasks. The program or code segment can be stored in a machine-readable medium, or transmitted on a transmission medium or a communication link by a data signal carried in a carrier wave. "Machine-readable medium" can include any medium capable of storing or transmitting information. Examples of machine-readable media include electronic circuits, semiconductor memory devices, ROM, flash memory, erasable ROM (EROM), floppy disks, CD-ROMs, optical disks, hard disks, optical fiber media, radio frequency (RF) links, etc. The code segment can be downloaded via a computer network such as the Internet, an intranet, etc.

[0190] It should also be noted that the exemplary embodiments mentioned in this application describe some methods or systems based on a series of steps or devices. However, this application is not limited to the order of the above steps, that is, the steps can be performed in the order mentioned in the embodiment, or in a different order from the embodiment, or several steps can be performed simultaneously.

[0191] Aspects of the present disclosure are described above with reference to the flowchart and / or block diagram of the method, device (system) and computer program product according to the embodiment of the present disclosure. It should be understood that each box in the flowchart and / or block diagram and the combination of each box in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device to produce a machine so that these instructions executed by the processor of the computer or other programmable data processing device enable the implementation of the function / action specified in one or more boxes of the flowchart and / or block diagram. Such a processor can be, but is not limited to, a general-purpose processor, a special-purpose processor, a special application processor, or a field programmable logic circuit. It can also be understood that each box in the block diagram and / or flowchart and the combination of boxes in the block diagram and / or flowchart can also be implemented by dedicated hardware that performs a specified function or action, or can be implemented by a combination of dedicated hardware and computer instructions.

[0192] In summary, compared with the prior art, this application has the following beneficial effects:

[0193] 1. This application converts various motion constraints in surgery into control targets, designs multiple target controllers to focus on traction angle targets, traction force targets and safety area targets, enables the robot to autonomously organize traction, converts the movement speed and posture change speed into the robot's joint angle, and performs robot motion control.

[0194] 2. In response to the complexity of surgical scenarios, this application integrates various safety constraints in surgery into the robot's autonomous motion planning in the form of control objectives through a multi-objective constraint control strategy; by pre-defining traction points, the robot automatically and safely performs tissue traction without requiring any prior knowledge of the surgical scenario or tissue model.

[0195] 3. The present application provides a multi-objective autonomous traction method for a surgical robot based on fuzzy logic, which can perform flexible tissue traction and save labor costs. Based on fuzzy logic, multiple control objectives are integrated into the robot's autonomous motion planning, solving a series of problems existing in the current robot's tissue traction process, such as poor continuity, insufficient safety, and unsatisfactory generalization.

[0196] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A multi-objective autonomous traction method for a surgical robot based on fuzzy logic, characterized in that: include: Assemble the actuator at the end of the robot to build the hardware of the autonomous traction surgical robot; The end motion of the actuator is simplified into a spring-mass damping linear control system, and multiple target controllers corresponding to the preset target group are constructed according to the actual needs of the traction organization; wherein the preset target group includes a traction angle target, a traction force target and a safety area target; In each of the target controllers, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each of the control targets, and a state feedback mechanism is constructed; Normalizing the multi-objective control amount and the gradient descent value, and inputting them into a preset fuzzy logic weight allocation algorithm to allocate weights to each of the control objectives; Based on a preset state feedback fusion mechanism, the multi-objective control quantities are weightedly fused, and the weighted fused target values ​​are input into the spring-mass damping linear control system to convert the movement speed and the speed of posture change into the joint angle of the robot to perform robot motion control; In each of the target controllers, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed, including: Based on the square of the chord length corresponding to the error between the current traction angle and the desired angle, an evaluation function for the traction angle target is designed; An evaluation function of the traction target is designed using the square of the error between the current traction and the expected traction; The evaluation function of the safety zone target is designed based on the square of the distance between the tip position of the current executing instrument and the boundary of the established safety zone; Construct a state feedback mechanism in the state space for gradient optimization to make the robot state converge quickly; The spring mass damping linear control system is a mass-damping-spring linear system to characterize the motion state of the robot end assembly actuator; the multiple target controllers include a traction angle controller, a traction force controller and a safety area controller; The spring-mass damping linear control system satisfies the state equation: in, is the position state of the end of the instrument, is the movement speed of the end of the instrument, is the acceleration at the end of the instrument, is the total control input of the spring-mass damping linear control system, is the inertia parameter, is the damping parameter, is the stiffness parameter; The traction angle controller is used to define the traction angle, and the traction angle satisfies the expression: In the formula, is the traction angle, Indicates the position of the cutting instrument. is the position state of the end of the instrument, represents the cutting direction vector, express The norm of ; The traction angle controller satisfies the expression: In the formula, Indicates the control amount of the traction angle, and To adjust the traction angle controller Control process parameters, is the error derived from the chord length formula, for The first derivative of is the desired angle, is the viewing direction; The traction controller is provided with a desired traction force to maintain tissue tension, and the traction controller satisfies the expression: in, Indicates the control amount of traction, , To adjust the traction control Control process parameters, For the expected traction, is the current force, is the error between the expected traction force and the current force; The safety zone set in the safety zone controller is a zone with a radius of , Gao Wei The cylindrical area of ​​​​the safety area controller satisfies the expression: in, represents the control amount of the safe area, and To perform security zone controller Control process parameters, Indicates the deviation between the current position and the safe area. express The first derivative of and Respectively exist Plane and The weight in direction, is the vector pointing toward the central axis, is the distance from the tip of the actuator to the coordinate axis, is the distance from the tip of the actuator to the base of the cylinder.

2. The multi-objective autonomous traction method of a surgical robot based on fuzzy logic as claimed in claim 1, characterized in that: The dynamic characteristics of the 7-DOF robot corresponding to the spring-mass damping linear control system in Cartesian space satisfy the expression: In the formula, represents the vector consisting of force and torque, represents the joint vector, represents the Cartesian inertia matrix, and are the velocity vector and gravity vector in Cartesian space, Represents the position and posture of the robot's end effector in Cartesian space, for The second-order derivative of for The first derivative of ; When the robot contacts the environment during movement, the environmental interaction force acting on the actuator Satisfies the expression: in, represents the net force acting on the actuator, The corresponding force mapping relationship satisfies: , represents the joint torque, Represents the Jacobian matrix from joint space to Cartesian space; The current force Satisfies the expression: in, is a diagonal matrix with 3 rows and 3 columns, is the force and torque vector of the actuator, and the interaction force with the environment Have corresponding mapping relationships.

3. The multi-objective autonomous traction method of a surgical robot based on fuzzy logic as claimed in claim 1, characterized in that: When the actuator exceeds the boundary of the cylindrical region, the safety area controller generates a control variable directed to the inside of the cylindrical region.

4. The multi-objective autonomous traction method of a surgical robot based on fuzzy logic as claimed in claim 3, characterized in that: The evaluation function of the traction angle target : The evaluation function of the traction target : The evaluation function of the safety area target : in, Represents the predicted distance value from the tip of the actuator to the coordinate axis, It represents the predicted distance from the tip of the actuator to the base of the cylinder. Expressing expectation, represents the current force predicted by the system, is a real variable coefficient, Indicates the current moment, is the time variable, To determine the position of the end of the instrument, Indicates the position of the cutting instrument. is the desired angle, is the prediction angle.

5. A multi-objective autonomous traction system for a surgical robot based on fuzzy logic, characterized in that: include: A hardware construction module is used to assemble the actuator at the end of the robot to build the hardware of the autonomous traction surgical robot; A system construction module, used to simplify the end motion of the actuator into a spring-mass damping linear control system, and to construct a plurality of target controllers corresponding to a preset target group according to the actual needs of the traction tissue; A calculation module, used for setting an evaluation function for a corresponding control target based on a state error in each of the target controllers, respectively calculating a predicted evaluation gradient descent value for each of the control targets, and constructing a state feedback mechanism; A weight allocation module, used for normalizing the multi-objective control amount and the gradient descent value, and inputting them into a preset fuzzy logic weight allocation algorithm to allocate weights to each of the control objectives; A fusion module is used to perform weighted fusion on the multi-objective control quantities based on a preset state feedback fusion mechanism, and input the weighted fused target values ​​into the spring mass damping linear control system to convert the motion speed and the speed of posture change into the joint angle of the robot to perform robot motion control; In each of the target controllers, an evaluation function is set for the corresponding control target based on the state error, a predicted evaluation gradient descent value is calculated for each control target, and a state feedback mechanism is constructed, including: Based on the square of the chord length corresponding to the error between the current traction angle and the desired angle, an evaluation function for the traction angle target is designed; An evaluation function of the traction target is designed using the square of the error between the current traction and the expected traction; The evaluation function of the safety zone target is designed based on the square of the distance between the tip position of the current executing instrument and the boundary of the established safety zone; Construct a state feedback mechanism in the state space for gradient optimization to make the robot state converge quickly; The spring mass damping linear control system is a mass-damping-spring linear system to characterize the motion state of the robot end assembly actuator; the multiple target controllers include a traction angle controller, a traction force controller and a safety area controller; The spring-mass damping linear control system satisfies the state equation: in, is the position state of the end of the instrument, is the movement speed of the end of the instrument, is the acceleration at the end of the instrument, is the total control input of the spring-mass damping linear control system, is the inertia parameter, is the damping parameter, is the stiffness parameter; The traction angle controller is used to define the traction angle, and the traction angle satisfies the expression: In the formula, is the traction angle, Indicates the position of the cutting instrument. is the position state of the end of the instrument, represents the cutting direction vector, express The norm of The traction angle controller satisfies the expression: In the formula, Indicates the control amount of the traction angle, and To adjust the traction angle controller Control process parameters, is the error derived from the chord length formula, for The first derivative of is the desired angle, is the viewing direction; The traction controller is provided with a desired traction force to maintain tissue tension, and the traction controller satisfies the expression: in, Indicates the control amount of traction, , To adjust the traction controller Control process parameters, For the expected traction, is the current force, is the error between the expected traction force and the current force; The safety zone set in the safety zone controller is a zone with a radius of , Gao Wei The cylindrical area of ​​​​the safety area controller satisfies the expression: in, represents the control amount of the safe area, and To perform security zone controller Control process parameters, Indicates the deviation between the current position and the safe area. express The first derivative of and Respectively exist Plane and The weight in direction, is the vector pointing toward the central axis, is the distance from the tip of the actuator to the coordinate axis, is the distance from the tip of the actuator to the base of the cylinder.

6. An electronic device, characterized in that: include: A processor, a memory, and a program stored in the memory and executable on the processor, wherein when the program is executed by the processor, the multi-objective autonomous traction method of a surgical robot based on fuzzy logic as described in any one of claims 1 to 4 is implemented.

7. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores programs or instructions, and when the programs or instructions are executed by the processor, the multi-objective autonomous traction method of the surgical robot based on fuzzy logic as described in any one of claims 1 to 4 is implemented.

Images