A motion trajectory planning system for a needle knife robot

Abstract

The application relates to the technical field of robot control, and discloses a motion trajectory planning system for a needle knife robot, which comprises a sensor module, a kinematics modeling module, a path generation and correction module, an optimization module and an intelligent control module; the path generation and correction module and the optimization module are arranged, the basic trajectory is obtained by dynamically correcting the path in combination with a tissue deformation prediction model, real-time force feedback and tissue deformation data are combined, the dynamic adaptability is improved, trajectory deviation is effectively prevented, a smooth speed curve is generated based on the basic trajectory by adopting a quintic polynomial interpolation method, the smoothness of the trajectory and the continuity of acceleration are ensured, impact control is performed on the needle knife robot by a dynamic compensation algorithm, mechanical vibration caused by acceleration mutation of the needle knife robot in a surgical process is prevented, surgical risks are reduced, and surgical safety is improved.

Description

Technical Field

[0001] This invention relates to the field of robot control technology, and more specifically to a motion trajectory planning system for a needle knife robot. Background Technology

[0002] As a minimally invasive surgical method, needle knife technique has the advantages of small trauma, fast recovery and few complications. However, traditional manual needle knife surgery has certain limitations, such as low surgical precision and high operation difficulty. With the development of robotics technology, combining needle knife technique with robots to develop needle knife robot systems can effectively improve surgical precision and efficiency.

[0003] However, existing needle knife robots mostly use Cartesian space interpolation or discrete point control in joint space for trajectory planning, which still has some shortcomings:

[0004] 1. The failure to combine real-time force feedback and tissue deformation data led to trajectory deviation and insufficient dynamic adaptability;

[0005] 2. Lack of impact control for the needle knife robot: If the needle knife robot experiences sudden acceleration changes during surgery, it is prone to mechanical vibration, which affects the safety of the surgery and increases the surgical risk.

[0006] 3. The existence of path redundancy and the lack of global optimization during multi-axis cooperative motion can lead to low efficiency.

[0007] In view of this, the present invention proposes a motion trajectory planning system for a needle knife robot. Summary of the Invention

[0008] To overcome the aforementioned deficiencies in the prior art, this invention provides a motion trajectory planning system for a needle knife robot. This system provides real-time feedback on the force and tissue deformation data of the needle knife robot, suppresses possible acceleration abrupt changes through a dynamic compensation algorithm, and dynamically corrects and optimizes the surgical path to solve the problems existing in the background art.

[0009] This invention provides the following technical solution: a motion trajectory planning system for a needle knife robot, comprising a sensor module, a kinematic modeling module, a path generation and correction module, an optimization module, and an intelligent control module;

[0010] The sensor module integrates a torque sensor, an optical positioning module, and a strain gauge to collect force, position, and tissue deformation data at the tip of the needle knife in real time.

[0011] The kinematic modeling module is based on computer-aided design to build a three-dimensional model of the needle knife robot; it obtains the preoperative planning path point set, initializes the robotic arm configuration through the DH parameter table, and establishes the mapping relationship from joint space to operating space.

[0012] The path generation and correction module determines the surgical path and surgical area based on the preoperative planned path point set, generates an initial trajectory, and dynamically corrects the path to obtain the basic trajectory by combining the tissue deformation prediction model.

[0013] The optimization module generates a smooth velocity curve based on the basic trajectory using a fifth-order polynomial interpolation method, and at the same time suppresses sudden acceleration changes through a dynamic compensation algorithm to generate an optimized trajectory.

[0014] The intelligent control module enables intelligent control of the needle knife robot based on the optimized trajectory.

[0015] Preferably, the method for obtaining the preoperative planning path point set is as follows:

[0016] Acquire preoperative CT and MRI data and import them into preoperative planning software; extract key structures from the CT and MRI data based on the preoperative planning software and construct a three-dimensional surface model of the surgical tissue.

[0017] Based on the preoperative planning software and the three-dimensional surface model of the surgical tissue, a set of preoperative planning path points is obtained; the set of preoperative planning path points is denoted as P = {P1, P2, P3, ..., P...} n}; where P represents the preoperative planning path point set, P i Let P represent the spatial coordinates of the i-th preoperative planning path point. i =(x i ,y i ,z i ); where x i Let y represent the coordinates of the i-th preoperative planning path point on the x-axis. i Let z represent the coordinates of the i-th preoperative planning path point on the y-axis. i Let represent the coordinates of the i-th preoperative planning path point on the z-axis; n represents the total number of preoperative planning path points, i = 1, 2, 3, ..., n.

[0018] Preferably, the specific method for initializing the robotic arm configuration through the DH parameter table and establishing the mapping relationship from joint space to operating space is as follows:

[0019] Based on the mechanical structure of the needle knife robot, a DH parameter table for each joint is defined, and a homogeneous transformation relationship between the joint coordinate systems is established. The DH parameter table includes the rotation angle of the joint around the z-axis, the link offset along the z-axis, the link length along the x-axis, and the joint angle.

[0020] By using the forward kinematics model, the joint angles are mapped to the pose of the end effector, forming a mapping from joint space to operating space;

[0021] If the needle knife robot has m joints, then for the j-th joint, the rotation angle around the z-axis is expressed as α. j The length of the link along the x-axis is denoted as b. j The offset of the link along the z-axis is expressed as c. j The joint rotation angle is expressed as d. j j = 1, 2, 3, ..., m.

[0022] Preferably, the forward kinematic model is expressed by the formula:

[0023] in, This represents the mapping from the joint angles of the needle knife robot to the pose of the end effector. This represents the transformation matrix from the (j-1)th joint to the j-th joint; Represented in matrix form as follows:

[0024]

[0025] Preferably, the path generation and correction module determines the surgical path and surgical area based on the preoperative planned path point set in the following specific way:

[0026] The surgical path is determined based on the preoperative planned path point set;

[0027] Based on the CT and MRI data, a safety boundary constraint function is set.

[0028] Dangerous areas within the surgical area that satisfy the safety boundary constraint function are marked.

[0029] Preferably, in the process of dynamically correcting the path using the tissue deformation prediction model to obtain the basic trajectory, the tissue deformation prediction model is expressed by the following formula:

[0030] F(k,t)=λ1I+λ2B+λ3B 2 Wherein, F(k,t) represents the deformation state at position k at time t, used to characterize the deformation of soft tissue in different directions and degrees; k represents the spatial vector coordinates of the soft tissue, representing the specific position of the soft tissue in space; t represents the time when the soft tissue deformation occurs, used to characterize the change of deformation over time; λ1, λ2, and λ3 represent material parameters, representing the response characteristics of the soft tissue under different deformation states; I represents the unit tensor, used to characterize the rigid part of the soft tissue, i.e., the initial state before deformation; B represents the deformation tensor, used to characterize the metric change of the soft tissue before and after deformation.

[0031] Preferably, the specific method for obtaining the dynamically corrected path in the basic trajectory by combining the tissue deformation prediction model with the dynamically corrected path is as follows:

[0032] Based on the tissue deformation prediction model, the predicted deformation area and the corresponding predicted deformation displacement are obtained. The predicted deformation area is the area where deformation is predicted to occur.

[0033] Get the current path point P new The intersection probability U(P) with the predicted deformation region new );

[0034] If U(P) new If )>YU, then dynamic correction is triggered, and the corrected path point set P is obtained. * ;

[0035] Perform the above operation on all waypoints to generate the base trajectory based on the last dynamically corrected set of waypoints.

[0036] Preferably, the dynamic compensation algorithm is expressed by the following formula:

[0037] Among them, A comp (t) represents the acceleration compensation value at time t; K p K represents the proportionality coefficient. d K represents the differential coefficient. p =0.8, K d =0.2; ΔL(t) represents the difference between the real-time force feedback value and the preset value at time t.

[0038] Preferably, the danger zone is represented as: R Danger ={(x,y,z)|vascular or nerve boundary}; where R Danger The area represents the danger zone; (x,y,z) represents the coordinate points, corresponding to the x-axis, y-axis, and z-axis coordinate points respectively.

[0039] Preferably, the safety boundary constraint function is expressed as: d(P) i ,R Danger )≥δ;where, d(P i ,R Danger ) represents P i The minimum safe distance from the hazardous area, where δ represents the safety boundary layer.

[0040] The technical effects and advantages of this invention are as follows:

[0041] This invention incorporates a path generation and correction module and an optimization module. It facilitates the dynamic correction of the path to obtain the basic trajectory by combining a tissue deformation prediction model. By integrating real-time force feedback and tissue deformation data, it improves dynamic adaptability and effectively prevents trajectory deviation. Simultaneously, based on the basic trajectory, a smooth velocity curve is generated using a fifth-order polynomial interpolation method, ensuring trajectory smoothness and acceleration continuity. Furthermore, a dynamic compensation algorithm suppresses abrupt acceleration changes, providing impact control for the needle knife robot and preventing mechanical vibrations caused by sudden acceleration changes during surgery, thus reducing surgical risks and improving surgical safety. The construction of a three-dimensional model and the adoption of a global optimization mode further enhance the working efficiency of the needle knife robot. Attached Figure Description

[0042] Figure 1 This is a structural diagram of the motion trajectory planning system for a needle knife robot according to the present invention. Detailed Implementation

[0043] The technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. In addition, the forms of the various structures described in the following embodiments are merely illustrative. The motion trajectory planning system for acupuncture robot involved in the present invention is not limited to the structures described in the following embodiments. All other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0044] like Figure 1 As shown, the present invention provides a motion trajectory planning system for a needle knife robot, including a sensor module, a kinematic modeling module, a path generation and correction module, an optimization module, and an intelligent control module;

[0045] The sensor module integrates a torque sensor, an optical positioning module, and a strain gauge to collect force, position, and tissue deformation data at the tip of the needle knife in real time. The tissue deformation data includes, but is not limited to, the position of the soft tissue in space, the time point at which the soft tissue deforms, and the state of the soft tissue before and after deformation.

[0046] The kinematic modeling module is based on computer-aided design such as CAD to create a three-dimensional model of the needle knife robot; it obtains the preoperative planning path point set, initializes the robotic arm configuration through the DH parameter table, and establishes the mapping relationship from joint space to operating space; the three-dimensional model of the needle knife robot includes, but is not limited to, the robotic arm body, needle knife, surgical path, surgical area and human tissue model, etc., and its purpose is to provide a digital foundation for subsequent kinematic analysis and trajectory planning.

[0047] The path generation and correction module is used to determine the surgical path and surgical area based on the preoperative planned path point set, generate an initial trajectory, and dynamically correct the path to obtain a basic trajectory by combining the tissue deformation prediction model. Its purpose is to mark dangerous areas within the surgical area by determining the surgical path and surgical area, so that the surgical path can avoid dangerous areas as much as possible when generating the initial trajectory, thereby reducing the risk.

[0048] The optimization module generates a smooth velocity curve based on the basic trajectory using a fifth-order polynomial interpolation method, ensuring the smoothness of the trajectory and the continuity of acceleration. At the same time, it suppresses abrupt acceleration changes through a dynamic compensation algorithm to generate an optimized trajectory.

[0049] The intelligent control module is used to execute the optimized trajectory decomposition into joint-level commands, and drive the motor through inverse kinematics solution to achieve intelligent control of the needle knife robot.

[0050] In this embodiment, it should be specifically explained that the kinematic modeling module establishes the three-dimensional model of the needle knife robot as follows:

[0051] Modeling the acupuncture knife: Obtain the length, diameter, and cutting edge angle of the acupuncture knife, draw the outline of the acupuncture knife using parametric sketches, and generate a three-dimensional solid model through operations such as extrusion and chamfering;

[0052] Perform robotic arm configuration modeling: Model the key parts of the robotic arm, including but not limited to harmonic reducers, servo motors, end effectors, and end effector interfaces. The end effector is the needle knife, and the end effector interface is the needle knife holder.

[0053] The needle knife length is the effective working length of the needle knife, used to ensure that the cutting range covers the lesion area; the needle knife blade angle is the angle between the surgical cutting surface and the needle knife axis, used to optimize tissue separation efficiency and reduce resistance.

[0054] In this embodiment, it should be specifically noted that the method for obtaining the preoperative planning path point set is as follows:

[0055] Acquire preoperative CT and MRI data and import them into preoperative planning software; based on the preoperative planning software, extract key structures such as nerves and blood vessels from the CT and MRI data and construct a three-dimensional surface model of the surgical tissue.

[0056] Based on the preoperative planning software and the three-dimensional surface model of the surgical tissue, a set of preoperative planning path points is obtained; the set of preoperative planning path points is denoted as P = {P1, P2, P3, ..., P...} n}; where P represents the preoperative planning path point set, P i Let P represent the spatial coordinates of the i-th preoperative planning path point. i =(xi ,y i ,z i ); where x i Let y represent the coordinates of the i-th preoperative planning path point on the x-axis. i Let z represent the coordinates of the i-th preoperative planning path point on the y-axis. i This represents the coordinates of the i-th preoperative planning path point on the z-axis; n represents the total number of preoperative planning path points, i = 1, 2, 3, ..., n;

[0057] The acquisition interval of the preoperative planned path point set is set to Δs, and the posture angle is set to θ. The value of Δs can be reasonably set by professionals in the field according to the specific surgical situation and the actual surgical tissue situation to ensure the smoothness of the surgical trajectory. In this embodiment, Δs = 1mm is selected. The posture angle is the angle between the direction of the needle blade and the tissue cutting surface, which satisfies θ ≤ 15°. At the same time, a safety boundary layer can be set to avoid accidental injury during the operation. The safety boundary layer is the minimum distance between the path and the tissue.

[0058] Preoperative planning software such as Mimics is widely used in surgical planning and 3D model building. It can convert medical imaging data such as CT and MRI into high-precision 3D models, providing accurate simulation and planning for clinical surgery, thereby greatly improving the success rate and safety of surgery.

[0059] In this embodiment, it should be specifically explained that the specific method for initializing the robotic arm configuration through the DH parameter table and establishing the mapping relationship from joint space to operating space is as follows:

[0060] Based on the mechanical structure of the needle knife robot, a DH parameter table for each joint is defined, and a homogeneous transformation relationship between the joint coordinate systems is established. The DH parameter table includes the rotation angle of the joint around the z-axis, the link offset along the z-axis, the link length along the x-axis, and the joint angle.

[0061] If the needle knife robot has m joints, then for the j-th joint, the rotation angle around the z-axis is expressed as α. j The length of the link along the x-axis is denoted as b. j The offset of the link along the z-axis is expressed as c. j The joint rotation angle is expressed as d. j j = 1, 2, 3, ..., m; the joint angles determine the pose of the end effector.

[0062] By using a forward kinematics model, joint angles are mapped to the pose of the end effector, forming a mapping from joint space to operational space; the forward kinematics model is expressed by the formula:

[0063] in, This represents the mapping from the joint angles of the needle knife robot to the pose of the end effector. This represents the transformation matrix from the (j-1)th joint to the j-th joint; Represented in matrix form as follows:

[0064]

[0065] In this embodiment, it should be specifically explained that the path generation and correction module determines the surgical path and surgical area based on the preoperative planned path point set in the following way:

[0066] The surgical path is determined based on the preoperative planned path point set;

[0067] Based on the CT and MRI data, a safety boundary constraint function is set; the purpose of this is to clarify the feasible surgical area and provide a basis for dividing the surgical path into several segments.

[0068] Dangerous areas within the surgical area that satisfy the safety boundary constraint function are marked; these can be marked manually by professionals in the field, or extracted using threshold segmentation or deep learning models such as the U-Net model.

[0069] The danger zone is represented as: R Danger ={(x,y,z)|vascular or nerve boundary}; where R Danger This indicates a danger zone; that is, when a pathway point is located at the boundary of a blood vessel or nerve, the area near that pathway point is considered a danger zone.

[0070] The safety boundary constraint function is expressed as: d(P i ,R Danger )≥δ;where, d(P i ,R Danger ) represents P i The minimum safe distance from the danger zone, δ represents the safety boundary layer. In this embodiment, δ = 5 mm is selected. The specific value of the safety boundary layer can be set by those skilled in the art according to the actual situation of different tissues. For example, for tissues with dense blood vessels and many nerves, the value of the safety boundary layer can be appropriately increased, while for tissues with sparse blood vessels and few nerves, the value of the safety boundary layer can be appropriately reduced.

[0071] In calculating P i When at the minimum safe distance from the danger zone, P i The distance to the nearest danger zone boundary is considered the minimum safe distance; the area near the path point is a danger zone, and the division value of the nearby area can be set by those skilled in the art according to the actual situation of the organization. If the division value of the nearby area is 2mm, then the area within 2mm of the path point is a danger zone.

[0072] In this embodiment, it should be specifically noted that when determining the surgical path based on the preoperative planned path point set, the surgical path can be set as straight line segments and curved segments according to the tissue structure characteristics, and the marked danger area should be avoided as much as possible; the tissue structure characteristics include, but are not limited to, tissue hardness, curvature, and blood vessel density, etc.

[0073] For example, regarding tissue hardness, if the tissue hardness E > 50 kPa, the path segment can be set as a straight path; otherwise, it can be set as a curved path. Where PA represents tissue pressure and τ represents tissue deformation; for blood vessel density, if blood vessel density ρ bold When the value is greater than 0.3, the path segment can be set as a curve; otherwise, it can be set as a straight line. The blood vessel density... Where XS represents the number of pixels in the blood vessel and QS represents the area of ​​the region.

[0074] In this embodiment, it should be specifically noted that in the process of dynamically correcting the path to obtain the basic trajectory using the tissue deformation prediction model, the tissue deformation prediction model is expressed by the following formula:

[0075] F(k,t)=λ1I+λ2B+λ3B 2 Wherein, F(k,t) represents the deformation state at position k at time t, which is a second-order tensor used to characterize the deformation of soft tissue in different directions and degrees; k represents the spatial vector coordinates of the soft tissue, representing the specific position of the soft tissue in space, used to accurately locate the location where the deformation occurs; t represents the time when the soft tissue deformation occurs, used to characterize the change of deformation over time; λ1, λ2, and λ3 represent material parameters, characterizing the response characteristics of the soft tissue under different deformation states; I represents the unit tensor, which is a second-order identity matrix used to characterize the rigid part of the soft tissue, i.e., the initial state before deformation; B represents the deformation tensor, which is a second-order tensor used to characterize the metric change of the soft tissue before and after deformation, reflecting the degree of deformation of the soft tissue in different directions;

[0076] The tissue deformation prediction model can also be the Ogden model in the hyperelastic model, which uses the strain energy function to characterize the stress-strain relationship. Since human tissues such as muscles and skin will undergo large deformations when subjected to external forces, and these tissues usually exhibit hyperelastic properties, the Ogden model can be used by those skilled in the art to predict tissue deformation under different load conditions.

[0077] In this embodiment, it should be specifically explained that the specific method for obtaining the dynamically corrected path in the basic trajectory by combining the tissue deformation prediction model with the dynamically corrected path is as follows:

[0078] Based on the tissue deformation prediction model, the predicted deformation area and the corresponding predicted deformation displacement are obtained. The predicted deformation area is the area where deformation is predicted to occur.

[0079] Get the current path point P new The intersection probability U(P) with the predicted deformation region new );

[0080] If U(P) new If )>YU, then dynamic correction is triggered, and the corrected path point set P is obtained. * ;

[0081] Perform the above operation on all waypoints to generate the base trajectory based on the last dynamically corrected set of waypoints.

[0082] In this embodiment, it should be specifically explained that the intersection probability U(P) new This can be expressed as a formula:

[0083] U(P new ) = 1 - e -γ‖ΔX‖ Where, ||ΔX|| represents the predicted deformation displacement in mm; γ represents the risk sensitivity coefficient, γ = 1.5, in mm. -1 ;

[0084] YU represents the trigger threshold, and in this embodiment, YU = 0.3 is selected.

[0085] In this embodiment, it should be specifically noted that the dynamic compensation algorithm is expressed by the following formula:

[0086] Among them, A comp (t) represents the acceleration compensation value at time t; K p K represents the proportionality coefficient. d K represents the differential coefficient. p =0.8, K d =0.2; ΔL(t) represents the difference between the real-time force feedback value and the preset value at time t; its purpose is to dynamically adjust the acceleration through force feedback to suppress mechanical vibration and sudden acceleration changes; the preset value is the pre-set force feedback value.

[0087] In this embodiment, it should be specifically noted that the optimization module can also construct a dynamic repulsion field to achieve millimeter-level obstacle avoidance for the needle knife robot. The dynamic repulsion field is expressed by the formula:

[0088] Among them, U qθ represents the repulsive force, η represents the repulsive force gain coefficient, η takes the value of η=1.2, θ_time represents the real-time obstacle distance, that is, the distance to the obstacle such as blood vessels or nerves and other key structures, θ_safe represents the safety threshold of the obstacle distance, θ_safe≥3mm; ∈(t) represents the time-varying attenuation coefficient, which is positively correlated with the movement speed; ω represents the control period, which satisfies ω∈[1ms,10ms].

[0089] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0090] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A motion trajectory planning system for a needle knife robot, characterized in that: It includes a sensor module, a kinematic modeling module, a path generation and correction module, an optimization module, and an intelligent control module; The sensor module integrates a torque sensor, an optical positioning module, and a strain gauge to collect force, position, and tissue deformation data at the tip of the needle knife in real time. The kinematic modeling module is based on computer-aided design to create a three-dimensional model of the needle knife robot. Obtain the preoperative planned path point set, initialize the robotic arm configuration through the DH parameter table, and establish the mapping relationship from joint space to operating space; The path generation and correction module determines the surgical path and surgical area based on the preoperative planned path point set, generates an initial trajectory, and dynamically corrects the path to obtain the basic trajectory by combining the tissue deformation prediction model. The optimization module generates a smooth velocity curve based on the basic trajectory using a fifth-order polynomial interpolation method, and at the same time suppresses sudden acceleration changes through a dynamic compensation algorithm to generate an optimized trajectory. The intelligent control module achieves intelligent control of the needle knife robot based on the optimized trajectory; In the basic trajectory obtained by dynamically correcting the path using the tissue deformation prediction model, the tissue deformation prediction model is expressed by the following formula: ;in, Indicates the location In time The deformation state at time is used to characterize the deformation of soft tissue in different directions and to varying degrees; the The spatial vector coordinates of soft tissue represent its specific location in space; It indicates the time when soft tissue deformation occurs and is used to characterize how deformation changes over time. , , These represent material parameters and characterize the response properties of soft tissues under different deformation states. The unit tensor is used to characterize the rigid portion of soft tissue, i.e., the initial state before deformation. Represents the deformation tensor, used to characterize the metric changes of soft tissue before and after deformation; The dynamic compensation algorithm is expressed by the following formula: ;in, Indicates time The acceleration compensation value at that time; Represents the proportionality coefficient. Represents the differential coefficient. , ; Indicates time The difference between the real-time force feedback value and the preset value.

2. The motion trajectory planning system for a needle knife robot according to claim 1, characterized in that: The method for obtaining the preoperative planning path point set is as follows: Acquire preoperative CT and MRI data and import them into preoperative planning software; extract key structures from the CT and MRI data based on the preoperative planning software and construct a three-dimensional surface model of the surgical tissue. Based on the preoperative planning software and the three-dimensional surface model of the surgical tissue, the preoperative planning path point set is obtained; The preoperative planning path point set is denoted as... ;in, This represents the set of points used for preoperative planning. Indicates the first Spatial coordinates of the preoperative planning path points ;in, Indicates the first Each preoperative planning pathway point is located at coordinates on the axis Indicates the first Each preoperative planning pathway point is located at coordinates on the axis Indicates the first Each preoperative planning pathway point is located at Coordinate points on the axis; This indicates the total number of preoperative planning pathway points. .

3. The motion trajectory planning system for a needle knife robot according to claim 2, characterized in that: The specific method for initializing the robotic arm configuration through the DH parameter table and establishing the mapping relationship from joint space to operating space is as follows: Based on the mechanical structure of the needle knife robot, a DH parameter table for each joint is defined, and a homogeneous transformation relationship between the joint coordinate systems is established. The DH parameter table includes the rotation angle of the joint around the z-axis, the link offset along the z-axis, the link length along the x-axis, and the joint angle. By using the forward kinematics model, the joint angles are mapped to the pose of the end effector, forming a mapping from joint space to operating space; If the needle knife robot has For the nth joint, then for the nth joint... For each joint, the rotation angle around the z-axis is expressed as: The length of the link along the x-axis is expressed as The link offset along the z-axis is expressed as The joint rotation angle is expressed as ; .

4. The motion trajectory planning system for a needle knife robot according to claim 3, characterized in that: The positive kinematic model is expressed by the following formula: ;in, This represents the mapping from the joint angles of the needle knife robot to the pose of the end effector. Indicates the first The joint to the first The transformation matrix of each joint; Represented in matrix form as follows: 。 5. The motion trajectory planning system for a needle knife robot according to claim 4, characterized in that: The specific method by which the path generation and correction module determines the surgical path and surgical area based on the preoperative planned path point set is as follows: The surgical path is determined based on the preoperative planned path point set; Based on the CT and MRI data, a safety boundary constraint function is set. Dangerous areas within the surgical area that satisfy the safety boundary constraint function are marked.

6. The motion trajectory planning system for a needle knife robot according to claim 5, characterized in that: The specific method for obtaining the dynamically corrected path in the basic trajectory by combining the tissue deformation prediction model with the dynamically corrected path is as follows: Based on the tissue deformation prediction model, the predicted deformation area and the corresponding predicted deformation displacement are obtained. The predicted deformation area is the area where deformation is predicted to occur. Get the current path point Intersection probability with the predicted deformation region ; like This triggers dynamic correction, obtaining the corrected path point set. ; Perform the above operation on all waypoints to generate the base trajectory based on the last dynamically corrected set of waypoints.

7. The motion trajectory planning system for a needle knife robot according to claim 6, characterized in that: The danger zone is represented as follows: ;in, Indicates a dangerous area; Represents the coordinates of the points, respectively corresponding to Axis coordinate points, axis coordinates and Axis coordinate points.

8. The motion trajectory planning system for a needle knife robot according to claim 7, characterized in that: The safety boundary constraint function is expressed as follows: ;in, express Minimum safe distance from danger zone This indicates the safety boundary layer.

Images