An autonomous ultrasound robot multi-modal drag control method and device

Abstract

The application discloses a kind of autonomous ultrasonic robot multimode drag control method and device.The method comprises: obtaining real-time ultrasound image and the force data value of mechanical arm end;Determine whether the pixel value of ROI region of the ultrasound image of continuous preset frame number is greater than preset pixel threshold value: if yes, according to force data value and first initial control parameter, it is calculated to obtain the target displacement amount in X axis direction and Y axis direction, simultaneously, according to force data value, preset expected force and second initial control parameter, it is calculated to obtain the target displacement amount in Z axis direction;Tool coordinate system under target displacement amount is converted into world coordinate system under target displacement amount;Zero force control is implemented in the horizontal direction of probe contact surface, and constant force control is implemented in the vertical direction of probe contact surface, until probe moves to target position.The method improves the operation flexibility and scanning safety by the synergistic effect of zero force control and constant force control.

Description

Technical Field

[0001] This invention relates to a multimodal drag control method and device for an autonomous ultrasonic robot. Background Technology

[0002] The autonomous ultrasound scanning robot deeply integrates precision mechanical control technology, a multimodal perception system, and an artificial intelligence decision engine, forming a highly intelligent medical diagnostic solution. Its core architecture consists of three parts: First, a robotic arm system based on high-precision servo motors and flexible transmission mechanisms achieves millimeter-level motion accuracy of the scanning probe through precise control algorithms, while a force feedback closed-loop control system ensures constant contact pressure between the probe and human tissue. Second, the multimodal perception system integrates a 3D visual positioning module, multi-dimensional force sensors, and an ultrasound machine, dynamically perceiving human anatomical structures through multi-source data fusion technology. Finally, the artificial intelligence decision engine employs a deep learning framework to analyze ultrasound image data in real time, providing high-precision navigation information for the robot's autonomous scanning planning. In the scanning process of the autonomous ultrasound scanning robot, the precise transition from initial positioning to safe contact between the probe and the skin is a crucial step in ensuring scan quality and patient safety. Summary of the Invention

[0003] To increase the selection space of the drag control mode of the autonomous ultrasound robot and improve the operational flexibility of scanning, this invention provides a multimodal drag control method and device for an autonomous ultrasound robot.

[0004] In a first aspect, embodiments of the present invention provide a multimodal drag control method for an autonomous ultrasonic robot, comprising:

[0005] Acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of an autonomous ultrasound robot;

[0006] Determine whether the pixel values ​​of the ROI region in a consecutive preset number of ultrasound images are all greater than a preset pixel threshold:

[0007] If so, using the tool coordinate system as a reference, the target displacement of the robotic arm end in the X-axis and Y-axis directions is calculated based on the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot. At the same time, the target displacement of the robotic arm in the Z-axis direction is calculated based on the force data values ​​of the robotic arm end in the Z-axis direction, the preset expected force, and the second initial control parameters of the autonomous ultrasonic robot.

[0008] The calculated target displacements of the robotic arm end effector in the X, Y, and Z axes of the tool coordinate system are converted into target displacements of the robotic arm end effector in the X, Y, and Z axes of the world coordinate system.

[0009] Based on the target displacement of the robotic arm end effector in the X, Y, and Z axes in the world coordinate system, zero-force control is implemented in the horizontal direction of the probe contact surface, while constant force control is implemented in the vertical direction of the probe contact surface until the probe moves to the target position.

[0010] In one or more optional embodiments, determining whether the pixel values ​​of the ROI regions of consecutive preset number of ultrasound images are all greater than a preset pixel threshold includes:

[0011] Perform the following operations on each frame of ultrasound images according to their chronological order:

[0012] Determine whether the pixel value of the ROI region in the ultrasound image of the current frame is greater than a preset pixel threshold;

[0013] If so, update the number of untouched contacts to zero and increment the number of contacted contacts by one.

[0014] If not, update the contact count to zero and add one no-contact count;

[0015] Determine whether the accumulated number of contacts is greater than the preset number of frames.

[0016] In one or more optional embodiments, determining whether the pixel value of the ROI region of the ultrasound image of the current frame is greater than a preset pixel threshold includes:

[0017] According to Formula 1, the Region of Interest (ROI) of the ultrasound image in the current frame is defined as follows:

[0018]

[0019] In the formula, These are the coordinates of the origin of the ROI region in the ultrasound image coordinate system. The width of the ROI region; The height of the ROI region;

[0020] Convert the ROI region into a grayscale image and calculate the sum of the grayscale values ​​of the ROI region;

[0021] Determine whether the sum of gray values ​​of the calculated ROI region is greater than the preset pixel threshold.

[0022] In one or more optional embodiments, based on the force data values ​​of the robotic arm end effector in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot, the target displacements of the robotic arm end effector in the X-axis and Y-axis directions are calculated respectively, including:

[0023] Based on the force data values ​​of the robotic arm's end effector in the X-axis and Y-axis directions, and the preset force thresholds in the X-axis and Y-axis directions, the force error values ​​of the robotic arm's end effector in the X-axis direction and the force error values ​​in the Y-axis direction are calculated according to Formula 2:

[0024]

[0025] In the formula, This represents the force data value in the X-axis or Y-axis direction at the current moment. When the force data value is in the X-axis direction at the current moment, Preset a force threshold in the X-axis direction. This represents the force error value in the X-axis direction; When the force data value is in the Y-axis direction at the current moment, Preset a force threshold in the Y-axis direction. This represents the force error value in the Y-axis direction;

[0026] Based on the first initial control parameters, the force error value of the robotic arm end in the X-axis direction and the force error value in the Y-axis direction, the adaptive control parameters in the X-axis direction and the adaptive control parameters in the Y-axis direction are calculated according to Formula 3.

[0027]

[0028] In the formula, This refers to the force error value in the X-axis direction or the force error value in the Y-axis direction. These are the first initial control parameters; This is the proportionality coefficient; When the force error value is in the X-axis direction, For adaptive control parameters in the X-axis direction; When the force error value is in the Y-axis direction, These are the adaptive control parameters in the Y-axis direction;

[0029] According to Formula 4, based on the adaptive control parameters in the X-axis direction and the force error value in the X-axis direction, the target displacement of the robotic arm in the X-axis direction is calculated; and based on the adaptive control parameters in the Y-axis direction and the force error value in the Y-axis direction, the target displacement of the robotic arm in the Y-axis direction is calculated.

[0030]

[0031] In the formula: This refers to the force error value in the X-axis direction or the force error value in the Y-axis direction. When the force error value is in the X-axis direction, For adaptive control parameters in the X-axis direction, This represents the target displacement of the robotic arm in the X-axis direction; When the force error value is in the Y-axis direction, For adaptive control parameters in the Y-axis direction, This represents the target displacement of the robotic arm in the Y-axis direction; For integration parameters; is the differential parameter.

[0032] In one or more optional embodiments, the target displacement of the robotic arm in the Z-axis direction is calculated based on the force data value of the robotic arm end effector in the Z-axis direction, a preset desired force, and the second initial control parameters of the autonomous ultrasonic robot, including:

[0033] Determine whether the force data value of the robotic arm end in the Z-axis direction is greater than or less than the preset expected force;

[0034] If it is less than the value, the downward adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force.

[0035] If it is greater than the value, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force.

[0036] Based on the downward adaptive control parameters or lifting adaptive control parameters in the Z-axis direction, the target displacement of the robotic arm in the Z-axis direction is calculated according to Formula 5:

[0037]

[0038] In the formula, This represents the target displacement of the robotic arm in the Z-axis direction; if the current force control is in the downward pressing phase... The down-pressure adaptive control parameters are in the Z-axis direction. , This represents the force data value of the robotic arm's end effector in the Z-axis direction. The preset expected force; For integration parameters; is the differential parameter.

[0039] In one or more optional embodiments, based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force, the downward adaptive control parameters in the Z-axis direction are calculated, including:

[0040] When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is greater than the preset environmental stiffness parameter, based on the second initial control parameter, the force data value of the robotic arm end in the Z-axis direction, the preset expected force, and the preset environmental stiffness parameter, the downward adaptive control parameter in the Z-axis direction is calculated according to Formula 6:

[0041]

[0042] In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is the proportionality coefficient; For auxiliary items;

[0043] When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force, based on the second initial control parameter, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force, the downward adaptive control parameter in the Z-axis direction is calculated according to Formula 7:

[0044]

[0045] In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is the proportionality coefficient; For auxiliary items;

[0046] When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the downward pressure adaptive control parameter in the Z-axis direction is set to be equal to the second initial control parameter.

[0047] In one or more optional embodiments, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force, including:

[0048] When the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset desired force is greater than the preset environmental stiffness parameter, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, the preset desired force, and the preset environmental stiffness parameter, according to Formula 8:

[0049]

[0050] In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is the proportionality coefficient; For auxiliary items;

[0051] When the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset expected force is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force, the lifting adaptive control parameters in the Z-axis direction are calculated according to Formula 9 based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force:

[0052]

[0053] In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is the proportionality coefficient; For auxiliary items;

[0054] When the difference between the force data value of the robotic arm end in the Z-axis direction and the preset expected force is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the downward pressure adaptive control parameter in the Z-axis direction is set to be equal to the second initial control parameter.

[0055] Secondly, embodiments of the present invention provide a multimodal drag control device for an autonomous ultrasonic robot, comprising:

[0056] The acquisition module is used to acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of the autonomous ultrasound robot;

[0057] The judgment module is used to determine whether the pixel values ​​of the ROI region in a consecutive preset number of ultrasound images are all greater than a preset pixel threshold.

[0058] The calculation module is used to calculate the target displacement of the robotic arm end in the X-axis and Y-axis directions based on the tool coordinate system, the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot, respectively. At the same time, it calculates the target displacement of the robotic arm in the Z-axis direction based on the force data value of the robotic arm end in the Z-axis direction, the preset expected force, and the second initial control parameters of the autonomous ultrasonic robot.

[0059] The conversion module is used to convert the calculated target displacements of the robot arm end in the X, Y, and Z axes in the tool coordinate system into the target displacements of the robot arm end in the X, Y, and Z axes in the world coordinate system.

[0060] The control module is used to implement zero-force control in the horizontal direction of the probe contact surface and constant force control in the vertical direction of the probe contact surface, based on the target displacement of the robotic arm end in the X-axis, Y-axis and Z-axis directions in the world coordinate system, until the probe moves to the target position.

[0061] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program / instruction stored thereon, which, when executed by a processor, implements the multimodal drag control method for the autonomous ultrasonic robot described in the first aspect.

[0062] Fourthly, embodiments of the present invention provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the multimodal drag control method for the autonomous ultrasonic robot described in the first aspect.

[0063] The beneficial effects of the above-described technical solutions provided in the embodiments of the present invention include at least the following:

[0064] This invention provides a multimodal drag control method for an autonomous ultrasound robot. This method determines whether the probe has made effective contact with the human skin by analyzing acquired ultrasound images in real time. Directly determining contact based on image results provides a more accurate and effective assessment, rather than relying on a preset force threshold. This solves the problems of patient discomfort caused by rigid probe contact or poor coupling due to probe suspension caused by relying on preset force thresholds. It also helps prevent artifacts and ensure image quality.

[0065] The multimodal drag control method for an autonomous ultrasonic robot provided in this invention calculates the target displacement in the X and Y axes based on real-time force data in the X and Y axes, and calculates the target displacement in the Z axis based on real-time force data and a preset desired force. Once contact is confirmed, the system immediately switches its control strategy. Specifically, based on the calculated target displacement in each direction, it implements zero-force control of the probe in the X and Y axes, allowing the operator to flexibly adjust the probe's posture with extremely low resistance. Constant force control is achieved in the Z axis, ensuring continuous and stable contact force. This solves the problem of balancing drag flexibility and stability. Through the synergistic effect of zero-force control and constant force control, operational flexibility and safety are significantly improved.

[0066] Other features and advantages of the invention will be set forth in the following description, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures particularly pointed out in the written description and the accompanying drawings.

[0067] The technical solution of the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. Attached Figure Description

[0068] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used in conjunction with embodiments of the invention to explain the invention and do not constitute a limitation thereof. In the drawings:

[0069] Figure 1 This is a flowchart illustrating the multimodal drag control method for an autonomous ultrasonic robot provided in an embodiment of the present invention.

[0070] Figure 2 This is a schematic diagram of the structure of the autonomous ultrasonic robot provided in an embodiment of the present invention;

[0071] Figure 3 This is an example diagram of the ROI region provided in an embodiment of the present invention;

[0072] Figure 4 This is a structural block diagram of the autonomous ultrasonic robot multimodal drag control device provided in an embodiment of the present invention. Detailed Implementation

[0073] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0074] The inventors discovered two major technical bottlenecks in the scanning process of the autonomous ultrasonic scanning robot:

[0075] (1) Contact determination relies on physical force sensors: The system usually relies on a preset force threshold to determine contact, which can easily lead to rigid contact of the probe causing patient discomfort or poor coupling due to probe suspension, affecting imaging quality and patient experience.

[0076] (2) Single force control strategy: The single force control strategy used in the dragging process cannot meet the clinical needs of dragging, which requires both flexibility and stability.

[0077] Based on this, the inventors conducted further research and development and came up with this invention, which provides a method and device for multimodal drag control of an autonomous ultrasonic robot.

[0078] Example 1

[0079] This invention provides a multimodal drag control method for an autonomous ultrasonic robot, referring to... Figure 1 As shown, it includes:

[0080] S101: Acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of the autonomous ultrasound robot;

[0081] S102: Determine whether the pixel values ​​of the ROI region of the ultrasound images for a consecutive preset number of frames (recommended value is 20) are all greater than the preset pixel threshold: If yes, execute the following steps S103-S105 in sequence; if no, execute the following steps S106-108 in sequence.

[0082] S103: Using the tool coordinate system as a reference, based on the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot, the target displacement of the robotic arm end in the X-axis and Y-axis directions is calculated respectively. At the same time, based on the force data value of the robotic arm end in the Z-axis direction and the preset expected force, as well as the second initial control parameters of the autonomous ultrasonic robot, the target displacement of the robotic arm in the Z-axis direction is calculated.

[0083] S104: Convert the calculated target displacements of the robot arm end in the X, Y, and Z axes in the tool coordinate system into target displacements of the robot arm end in the X, Y, and Z axes in the world coordinate system.

[0084] S105: Based on the target displacement of the robotic arm end effector in the X-axis, Y-axis and Z-axis directions in the world coordinate system, zero force control is implemented in the horizontal direction of the probe contact surface, and constant force control is implemented in the vertical direction of the probe contact surface until the probe moves to the target position.

[0085] S106: Using the tool coordinate system as a reference, based on the force data values ​​of the robotic arm end in the X-axis, Y-axis and Z-axis directions and the first initial control parameters of the autonomous ultrasonic robot, the target displacement of the robotic arm end in the X-axis, Y-axis and Z-axis directions is calculated respectively.

[0086] S107: Convert the calculated target displacements of the robot arm end in the X, Y, and Z axes in the tool coordinate system into target displacements of the robot arm end in the X, Y, and Z axes in the world coordinate system.

[0087] S108: Based on the target displacement of the robotic arm end effector in the X-axis, Y-axis and Z-axis directions in the world coordinate system, zero force control is implemented in the horizontal direction of the probe contact surface, and simultaneously, zero force control is implemented in the vertical direction of the probe contact surface, until the probe moves to the target position.

[0088] The multimodal dragging control method for an autonomous ultrasound robot provided in this invention analyzes acquired ultrasound images in real time to determine whether the probe has made effective contact with the human skin. Directly determining contact based on image results provides a more accurate and effective assessment, rather than relying on a preset force threshold. This solves the problems of patient discomfort caused by rigid probe contact or poor coupling due to probe suspension caused by relying on preset force thresholds, thus improving the safety and stability of dragging. Furthermore, by judging the Region of Interest (ROI) of multiple consecutive ultrasound images, the randomness of the judgment results can be avoided, further improving the stability of contact determination.

[0089] The multimodal drag control method for an autonomous ultrasonic robot provided in this invention calculates the target displacement in the X and Y axes based on real-time force data in the X and Y axes, and calculates the target displacement in the Z axis based on real-time force data and a preset desired force. Once contact is confirmed, the system immediately switches its control strategy. Specifically, based on the calculated target displacement in each direction, it implements zero-force control of the probe in the X and Y axes, allowing the operator to flexibly adjust the probe's posture with extremely low resistance. Constant force control is achieved in the Z axis, ensuring continuous and stable contact force. This solves the problem of balancing drag flexibility and stability. Through the synergistic effect of zero-force control and constant force control, operational flexibility and scanning safety are significantly improved.

[0090] To facilitate understanding of this solution by those skilled in the art, an example diagram of the ultrasonic robot in the embodiments of this application is given below: Ultrasonic robot device reference Figure 2As shown, the ultrasound robot device includes a robotic arm and a computer. The probe is located at the end of the robotic arm. In this method, the computer will be deployed to control the movement of the robotic arm, enabling the probe to autonomously scan target organs in the human body. Two coordinate systems are present in the figure. Using the world coordinate system, This is the tool coordinate system.

[0091] In this embodiment of the invention, the end effector of the autonomous ultrasound machine is also equipped with a six-dimensional force sensor, which can acquire force data in six directions (positive X-axis, negative X-axis, positive Y-axis, negative Y-axis, positive Z-axis, and negative Z-axis) of the robotic arm in real time. The acquired force data includes force values ​​and torque values.

[0092] In this embodiment of the invention, step S102: determining whether the sum of gray values ​​of the ROI regions of consecutive preset number of ultrasound images is greater than a preset pixel threshold, may specifically include the following steps S1021-S1022:

[0093] S1021: Perform the following steps S10211-S10213 on each frame of ultrasound image according to the chronological order of the ultrasound images:

[0094] S10211: Determine whether the pixel value of the ROI region of the ultrasound image in the current frame is greater than the preset pixel threshold; if yes, proceed to step S102212; if no, proceed to step S10213.

[0095] S10212: Update the number of no contacts to zero and increment the number of contacts by one;

[0096] S10213: Update the contact count to zero and increment the non-contact count by one;

[0097] S1022: Determine whether the accumulated number of contacts is greater than the preset number of frames.

[0098] In this embodiment of the invention, if the cumulative number of contacts is greater than the preset number of frames, it means that the pixel values ​​of the ROI region of the ultrasound images of the preset number of consecutive frames are all greater than the preset pixel threshold, and at this time it can be determined as a stable contact.

[0099] In one specific embodiment, one way to perform the above steps S10211-S10213 on each frame of ultrasound image is as follows:

[0100] First, define a global variable C to represent the contact state, where C = 0 represents the non-contact state and C = 1 represents the contact state. Then define a counter to represent the number of contacts. Define a counter to represent the number of times the contact was not made. Initially, C = 0. = 0, = 0. Perform the following loop check:

[0101] 1) If the ultrasound image of the current frame satisfies ( The pixel values ​​of the ROI region. (Preset pixel threshold)

[0102] (1) Order = 0;

[0103] (2) If C = 1, it means that the current state is contact, and no action is taken at this time;

[0104] (3) If C = 0, it indicates that the current state is untouched. Perform cumulative counting;

[0105] (4) If ( If the contact number threshold (i.e., the preset frame count, with a recommended value of 20) is set, it means that the probe at the end of the robotic arm is in stable contact with the human body. At this point, C is set to 1, which means the current state is updated to the contact state.

[0106] 2) If the current frame image satisfies ( The pixel values ​​of the ROI region. (Preset pixel threshold)

[0107] (1) Order = 0;

[0108] (2) If C = 0, it means that the current state is untouched, and no action is taken.

[0109] (3) If C = 1, it indicates that the current state is one of contact. Perform cumulative counting;

[0110] (4) If ( If the threshold for the number of times no contact has occurred (i.e., the preset number of frames, with a recommended value of 20), it means that the probe at the end of the robotic arm has lost contact with the human body. At this point, C is set to 0, which means the current state is updated to the no-contact state.

[0111] In this embodiment of the invention, by accumulating the number of consecutive contacts and the number of consecutive non-contacts respectively, and determining that the contact is stable when the number of consecutive contacts reaches the contact threshold, the stability of the contact judgment can be improved, the frequent switching of the control strategy caused by accidental interference can be avoided, and the stable execution of subsequent zero-force control and constant-force control can be facilitated.

[0112] In this embodiment of the invention, step S1021, determining whether the pixel value of the ROI region of the ultrasound image in the current frame is greater than a preset pixel threshold, may specifically include the following steps S10211-S10213:

[0113] S10211: Let the input image be... (3-channel BGR format) Define the ROI region of the ultrasound image in the current frame according to Formula 1:

[0114]

[0115] In the formula, These are the coordinates of the origin of the ROI region in the ultrasound image coordinate system; The fixed width of the ROI region is 250; The fixed height for the ROI region is 200; Figure 3 An example of selecting a region of interest (ROI) in an ultrasound image is provided.

[0116] S10212: Convert the ROI region into a grayscale image. The resulting grayscale image satisfies the following formula 10, and the total grayscale value of the ROI region is calculated according to formula 11:

[0117]

[0118] In the formula, , and BGR three-channel image; , and The preceding coefficients are known empirical values;

[0119]

[0120] In the formula, The fixed width of the ROI region; The fixed height of the ROI region; This represents the sum of grayscale values ​​for the ROI region.

[0121] S10213: Determine whether the calculated sum of gray values ​​of the ROI region (gray value is a type of pixel value) is greater than the preset pixel threshold.

[0122] In this embodiment of the invention, the recommended value for the preset pixel threshold is 100,000. If the sum of grayscale values ​​is greater than the preset pixel threshold, it indicates that the image quality meets expectations. Directly judging whether there is contact based on the image results makes the judgment more accurate and reliable. Furthermore, judging the contact status through continuous multi-frame loops can improve the stability of the judgment results.

[0123] In this embodiment of the invention, the autonomous ultrasonic robot is pre-set with first initial control parameters (fixed values, recommended value 0.00006) for controlling the movement of the robotic arm in the horizontal direction (X-axis and Y-axis directions). In step S103 above, using the tool coordinate system as a reference, the target displacement of the robotic arm end in the X-axis and Y-axis directions is calculated based on the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot. Specifically, this may include the following steps S10311-S10313:

[0124] S10311: Based on the force data values ​​of the robotic arm end effector in the X-axis and Y-axis directions, and the preset force thresholds in the X-axis and Y-axis directions, the force error values ​​of the robotic arm end effector in the X-axis direction and the force error values ​​in the Y-axis direction are calculated according to Formula 2.

[0125]

[0126] In the formula, The X-axis direction at the current moment Force data values ​​or force data values ​​in the Y-axis direction ; for hour, Preset force threshold in the X-axis direction This is a fixed value; the recommended value is 2.5N. Force error value in the X-axis direction ; for hour, Preset force threshold in the Y-axis direction This is a fixed value; the recommended value is 2.5N. Force error value in the Y-axis direction .

[0127] S10312: Based on the first initial control parameters, the force error value of the robotic arm end in the X-axis direction and the force error value in the Y-axis direction, the adaptive control parameters in the X-axis direction and the adaptive control parameters in the Y-axis direction are calculated according to Formula 3.

[0128]

[0129] In the formula, Force error value in the X-axis direction Or the force error value in the Y-axis direction ; These are the first initial control parameters; The proportionality coefficient is a fixed value, with a recommended value of 0.00002; for hour, Adaptive control parameters in the X-axis direction ; When the force error value is in the Y-axis direction , Adaptive control parameters in the Y-axis direction .

[0130] S10313: According to Formula 4, based on the adaptive control parameters in the X-axis direction and the force error value in the X-axis direction, the target displacement of the robotic arm in the X-axis direction is calculated; and based on the adaptive control parameters in the Y-axis direction and the force error value in the Y-axis direction, the target displacement of the robotic arm in the Y-axis direction is calculated.

[0131]

[0132] In the formula: Force error value in the X-axis direction Or the force error value in the Y-axis direction ; for hour, Adaptive control parameters in the X-axis direction , The target displacement of the robotic arm in the X-axis direction of the tool coordinate system ; for hour, Adaptive control parameters in the Y-axis direction , The target displacement of the robotic arm in the Y-axis direction of the tool coordinate system ; This is the integration parameter, and it is a fixed value. is the differential parameter, and is a fixed value.

[0133] In this embodiment of the invention, adaptive control parameters are calculated based on the magnitude of the force error value in the horizontal direction, thereby realizing automatic adjustment of the control parameters. This enables the robot to quickly follow changes in the force applied by the human hand, achieving zero-force control. The operator can flexibly adjust the probe's position with extremely low resistance and control the probe to move to the target position.

[0134] In this embodiment of the invention, the autonomous ultrasonic robot is pre-set with second initial control parameters for controlling the movement of the robotic arm in the vertical direction (Z-axis direction). In step S103 above, the target displacement of the robotic arm in the Z-axis direction is calculated based on the force data value of the robotic arm end in the Z-axis direction, the preset desired force, and the second initial control parameters of the autonomous ultrasonic robot. Specifically, this may include the following steps S10321-S10324:

[0135] S10321: Determine whether the force data value of the robotic arm end in the Z-axis direction is greater than or less than the preset expected force; if it is less, execute step S10322; if it is greater, execute S10323.

[0136] S10322: Determine that the current force control is in the downward pressure phase, and calculate the downward pressure adaptive control parameters in the Z-axis direction based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force. ;

[0137] S10323: Determine that the current force control is in the lifting phase, and calculate the lifting adaptive control parameters in the Z-axis direction based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force. (Both the downward adaptive control parameters and the upward adaptive control parameters are adaptive control parameters on the Z-axis) The only difference is the calculation method and specific values ​​during the compression and lifting phases.

[0138] S10324: Based on the downward adaptive control parameters or lifting adaptive control parameters in the Z-axis direction, the target displacement of the robotic arm in the Z-axis direction is calculated according to Formula 5:

[0139]

[0140] In the formula, This represents the target displacement of the robotic arm in the Z-axis direction; if the current force control is in the downward pressing phase... , The down-pressure adaptive control parameters are in the Z-axis direction. , This represents the force data value of the robotic arm's end effector in the Z-axis direction. The preset desired force; if the current force control is in the lifting phase. , These are the lifting adaptive control parameters in the Z-axis direction. , This represents the force data value of the robotic arm's end effector in the Z-axis direction. The preset expected force; This is the integration parameter, and it is a fixed value. is the differential parameter, and is a fixed value.

[0141] It should be noted that if the force data value of the robotic arm end in the Z-axis direction is equal to the preset expected force, it means that stable constant force control has been achieved in the Z-axis direction. There is no need to press down or raise the probe. Therefore, there is no need to calculate the target displacement in the Z-axis direction or adjust the control parameters in the Z-axis direction.

[0142] It should be noted that the preset expected force remains constant during the calculation of the target displacement of the robotic arm in the Z-axis direction at the next moment, based on the force data value of the robotic arm's end effector in the Z-axis direction, the preset expected force, and the second initial control parameters of the autonomous ultrasound robot. However, in actual ultrasound scanning, the preset expected force varies for different scanning sites to ensure safety. For example, the preset expected force for abdominal scanning can be 15N, while the preset expected force for neck scanning can be 5N. Furthermore, a maximum preset expected force for the robotic arm's end effector should also be set, with a recommended value of 30N, to ensure safe scanning and avoid excessive force that could cause compressive damage to local tissues.

[0143] In this embodiment of the invention, adaptive control parameters are calculated based on the force data value in the Z-axis direction and the preset expected force in the Z-axis direction, so as to realize the automatic adjustment of control parameters and constant force control, thereby ensuring continuous and stable contact force. Through the synergistic effect of zero force control and constant force control, the operational flexibility and scanning safety are significantly improved.

[0144] In this embodiment of the invention, the autonomous ultrasonic robot is pre-set with a second initial control parameter (a fixed value, recommended value is 0.0001) for controlling the movement of the robotic arm in the vertical direction (Z-axis direction). To ensure the stability and real-time response of the constant force control in the Z-axis direction, the force control is divided into a pressing stage and an lifting stage, and different control parameter adjustment methods are used for different stages.

[0145] In this embodiment of the invention, in step S10322 above, the downward adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force. Specifically, it may include the following steps S103221-S103223:

[0146] S103221: During the downward pressure phase, if the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is greater than the preset environmental stiffness parameter... (Recommended value is 15) (This indicates that the farther the probe is from the target, the more it needs to accelerate towards the target; this is the adaptive control parameter for downward pressure in the Z-axis direction). The larger the value of the desired force (based on the second initial control parameter, the force data value of the robotic arm end effector in the Z-axis direction, the preset desired force, and the preset environmental stiffness parameter), the greater the desired force (based on the second initial control parameter, the force data value of the robotic arm end effector in the Z-axis direction, the preset desired force, and the preset environmental stiffness parameter). According to Formula 6, the adaptive control parameters for downward pressure in the Z-axis direction are calculated. :

[0147]

[0148] In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is a proportionality coefficient; the recommended value is [value missing]. ; This is an auxiliary item; the reference value is 5.

[0149] S103222: During the downward pressure phase, when the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force... When (indicating a large preset expected force, requiring deceleration to approach the target), based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force, the downward adaptive control parameters in the Z-axis direction are calculated according to Formula 7. :

[0150]

[0151] In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is a proportionality coefficient; the recommended value is [value missing]. ; This is an auxiliary item; the reference value is 5.

[0152] S103223: During the compression phase, when the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the compression adaptive control parameters in the Z-axis direction are... Equal to the second initial control parameter .

[0153] It should be noted that the above steps S103221-S103223 have no specific execution order; one of them may be executed depending on the circumstances.

[0154] In this embodiment of the invention, in step S10323 above, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force. Specifically, it may include the following steps S103231-S103233:

[0155] S103231: During the lifting phase, when the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset desired force is greater than the preset environmental stiffness parameter (indicating the need to accelerate away from the target and release excessive contact force), based on the second initial control parameter, the force data value of the robotic arm end effector in the Z-axis direction, the preset desired force, and the preset environmental stiffness parameter, the lifting adaptive control parameter in the Z-axis direction is calculated according to Formula 8. :

[0156]

[0157] In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is a proportionality coefficient; the recommended value is [value missing]. ; This is an auxiliary item; the reference value is 5.

[0158] S103232: During the lifting phase, when the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset expected force is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force (indicating that the control parameters need to be reduced to ensure the stability of the lifting), based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force, the lifting adaptive control parameters in the Z-axis direction are calculated according to Formula 9. :

[0159]

[0160] In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is a proportionality coefficient; the recommended value is [value missing]. ; This is an auxiliary item; the reference value is 5.

[0161] S103233: During the lifting phase, when the difference between the force data value of the robotic arm end in the Z-axis direction and the preset expected force is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the downward pressure adaptive control parameter in the Z-axis direction is equal to the second initial control parameter.

[0162] It should be noted that the above steps S103231-S103233 have no specific execution order; one of them may be executed depending on the situation.

[0163] In this embodiment of the invention, the target displacement of the robotic arm end effector in each direction at the next moment in the tool coordinate system can be calculated through steps S101-S103. Step S104 above: Calculate the target displacement of the robotic arm end effector in the X-axis, Y-axis, and Z-axis directions in the tool coordinate system. Converting the target displacement of the robotic arm's end effector in the X, Y, and Z axes in the world coordinate system yields the target pose of the probe at the next moment, which can specifically include:

[0164] According to Formula 12, Converting to world coordinates, we obtain the target pose of the probe at the next moment:

[0165]

[0166] In the formula, This is the current position in the world coordinate system. The attitude in the current world coordinate system.

[0167] In this embodiment of the invention, after obtaining the target pose of the probe at the next moment, zero-force control can be implemented in the horizontal direction of the probe contact surface, and constant force control can be implemented in the vertical direction of the probe contact surface until the probe moves to the target position.

[0168] In this embodiment of the invention, if the judgment result of step S102 is negative, it indicates that there is no contact, and zero-force control must also be used in the Z-axis direction. In step S106, the calculation of the target displacement of zero-force control in each direction can be performed with reference to the above steps S10311-S10313. The coordinate transformation in step 107 can be performed with reference to the above step 104. The repeated parts will not be described again.

[0169] The multimodal dragging control method for autonomous ultrasound robots provided in this invention achieves intelligent contact determination through real-time ultrasound image analysis, overcoming the limitations of traditional rigid force thresholds. Combined with a zoned zero-force / constant-force hybrid control strategy, it addresses the adaptability deficiencies of single-force control strategies. In clinical practice, it achieves flexible dragging in the horizontal direction and constant-force contact in the vertical direction, providing crucial technical support for high-quality ultrasound imaging.

[0170] Example 2

[0171] Based on the same inventive concept, embodiments of the present invention provide a multimodal drag control device for an autonomous ultrasonic robot, referring to... Figure 4 As shown, it includes:

[0172] The acquisition module 101 is used to acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of the autonomous ultrasound robot.

[0173] The judgment module 102 is used to determine whether the pixel values ​​of the ROI region of a consecutive preset number of ultrasound images are all greater than a preset pixel threshold.

[0174] The calculation module 103 is used to calculate the target displacement of the robotic arm end in the X-axis and Y-axis directions based on the tool coordinate system, the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot, and to calculate the target displacement of the robotic arm in the Z-axis direction based on the force data values ​​of the robotic arm end in the Z-axis direction, the preset expected force and the second initial control parameters of the autonomous ultrasonic robot.

[0175] The conversion module 104 is used to convert the calculated target displacement of the robot arm end in the X-axis, Y-axis and Z-axis directions in the tool coordinate system into the target displacement of the robot arm end in the X-axis, Y-axis and Z-axis directions in the world coordinate system.

[0176] The control module 105 is used to implement zero-force control in the horizontal direction of the probe contact surface based on the target displacement of the robotic arm end in the X-axis, Y-axis and Z-axis directions in the world coordinate system, and at the same time, implement constant force control in the vertical direction of the probe contact surface until the probe moves to the target position.

[0177] Example 3

[0178] Based on the same inventive concept, embodiments of the present invention also provide a computer-readable storage medium storing a computer program / instruction thereon, which, when executed by a processor, implements the multimodal drag control method for an autonomous ultrasonic robot as described in Embodiment 1 above.

[0179] Example 4

[0180] Based on the same inventive concept, embodiments of the present invention also provide a computer program product, including a computer program / instruction, which, when executed by a processor, implements the multimodal drag control method for an autonomous ultrasonic robot as described in Embodiment 1 above.

[0181] Example 5

[0182] Based on the same inventive concept, this embodiment of the invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory. When the processor executes the computer program, it implements the multimodal drag control method for an autonomous ultrasonic robot as described in Embodiment 1 above.

[0183] The principles by which the above-described apparatus, client, medium, related equipment and system in this embodiment of the invention solve the problem are similar to those of the aforementioned method. Therefore, their implementation can refer to the implementation of the aforementioned method, and repeated details will not be repeated.

[0184] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage and optical storage) containing computer-usable program code.

[0185] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0186] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0187] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0188] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A multimodal drag control method for an autonomous ultrasonic robot, characterized in that, include: Acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of an autonomous ultrasound robot; Determine whether the pixel values ​​of the ROI region in a consecutive preset number of ultrasound images are all greater than a preset pixel threshold: If so, using the tool coordinate system as a reference, the target displacement of the robotic arm end in the X-axis and Y-axis directions is calculated based on the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot. At the same time, the target displacement of the robotic arm in the Z-axis direction is calculated based on the force data values ​​of the robotic arm end in the Z-axis direction, the preset expected force, and the second initial control parameters of the autonomous ultrasonic robot. The calculated target displacements of the robotic arm end effector in the X, Y, and Z axes of the tool coordinate system are converted into target displacements of the robotic arm end effector in the X, Y, and Z axes of the world coordinate system. Based on the target displacement of the robotic arm end effector in the X, Y, and Z axes in the world coordinate system, zero-force control is implemented in the horizontal direction of the probe contact surface, while constant force control is implemented in the vertical direction of the probe contact surface until the probe moves to the target position.

2. The multimodal drag control method for an autonomous ultrasonic robot according to claim 1, characterized in that, The step of determining whether the pixel values ​​of the ROI region of a consecutive preset number of ultrasound images are all greater than a preset pixel threshold includes: Perform the following operations on each frame of ultrasound images according to their chronological order: Determine whether the pixel value of the ROI region in the ultrasound image of the current frame is greater than a preset pixel threshold; If so, update the number of untouched contacts to zero and increment the number of contacted contacts by one. If not, update the contact count to zero and add one no-contact count; Determine whether the accumulated number of contacts is greater than the preset number of frames.

3. The multimodal drag control method for an autonomous ultrasonic robot according to claim 2, characterized in that, The step of determining whether the pixel value of the ROI region of the ultrasound image in the current frame is greater than a preset pixel threshold includes: According to Formula 1, the Region of Interest (ROI) of the ultrasound image in the current frame is defined as follows: In the formula, These are the coordinates of the origin of the ROI region in the ultrasound image coordinate system; The width of the ROI region; The height of the ROI region; Convert the ROI region into a grayscale image and calculate the sum of the grayscale values ​​of the ROI region; Determine whether the sum of gray values ​​of the calculated ROI region is greater than the preset pixel threshold.

4. The multimodal drag control method for an autonomous ultrasonic robot according to claim 1, characterized in that, Based on the force data values ​​of the robotic arm's end effector in the X and Y axes and the first initial control parameters of the autonomous ultrasonic robot, the target displacements of the robotic arm's end effector in the X and Y axes are calculated, including: Based on the force data values ​​of the robotic arm's end effector in the X-axis and Y-axis directions, and the preset force thresholds in the X-axis and Y-axis directions, the force error values ​​of the robotic arm's end effector in the X-axis direction and the force error values ​​in the Y-axis direction are calculated according to Formula 2: In the formula, This represents the force data value in the X-axis or Y-axis direction at the current moment. When the force data value is in the X-axis direction at the current moment, Preset a force threshold in the X-axis direction. This represents the force error value in the X-axis direction; When the force data value is in the Y-axis direction at the current moment, Preset a force threshold in the Y-axis direction. This represents the force error value in the Y-axis direction; Based on the first initial control parameters, the force error value of the robotic arm end in the X-axis direction and the force error value in the Y-axis direction, the adaptive control parameters in the X-axis direction and the adaptive control parameters in the Y-axis direction are calculated according to Formula 3. In the formula, This refers to the force error value in the X-axis direction or the force error value in the Y-axis direction. These are the first initial control parameters; This is the proportionality coefficient; When the force error value is in the X-axis direction, For adaptive control parameters in the X-axis direction; When the force error value is in the Y-axis direction, For adaptive control parameters in the Y-axis direction; According to Formula 4, based on the adaptive control parameters in the X-axis direction and the force error value in the X-axis direction, the target displacement of the robotic arm in the X-axis direction is calculated; and based on the adaptive control parameters in the Y-axis direction and the force error value in the Y-axis direction, the target displacement of the robotic arm in the Y-axis direction is calculated. In the formula: This refers to the force error value in the X-axis direction or the force error value in the Y-axis direction. When the force error value is in the X-axis direction, These are the adaptive control parameters in the X-axis direction. This represents the target displacement of the robotic arm in the X-axis direction; When the force error value is in the Y-axis direction, For adaptive control parameters in the Y-axis direction, This represents the target displacement of the robotic arm in the Y-axis direction; For integration parameters; is the differential parameter.

5. The multimodal drag control method for an autonomous ultrasonic robot according to claim 1, characterized in that, Based on the force data value of the robotic arm's end effector in the Z-axis direction and the preset desired force, as well as the second initial control parameters of the autonomous ultrasonic robot, the target displacement of the robotic arm in the Z-axis direction is calculated, including: Determine whether the force data value of the robotic arm end in the Z-axis direction is greater than or less than the preset expected force; If it is less than the value, the downward adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force. If it is greater than the value, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force. Based on the downward adaptive control parameters or lifting adaptive control parameters in the Z-axis direction, the target displacement of the robotic arm in the Z-axis direction is calculated according to Formula 5: In the formula, This represents the target displacement of the robotic arm in the Z-axis direction; if the current force control is in the downward pressing phase... The down-pressure adaptive control parameters are in the Z-axis direction. , This represents the force data value of the robotic arm's end effector in the Z-axis direction. The preset expected force; if the current force control is in the lifting phase, These are the lifting adaptive control parameters in the Z-axis direction. , This represents the force data value of the robotic arm's end effector in the Z-axis direction. The preset expected force; For integration parameters; is the differential parameter.

6. The multimodal drag control method for an autonomous ultrasonic robot according to claim 5, characterized in that, Based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force, the downward adaptive control parameters in the Z-axis direction are calculated, including: When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is greater than the preset environmental stiffness parameter, based on the second initial control parameter, the force data value of the robotic arm end in the Z-axis direction, the preset expected force, and the preset environmental stiffness parameter, the downward adaptive control parameter in the Z-axis direction is calculated according to Formula 6: In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is the proportionality coefficient; For auxiliary items; When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force, based on the second initial control parameter, the force data value of the robotic arm end in the Z-axis direction, and the preset expected force, the downward adaptive control parameter in the Z-axis direction is calculated according to Formula 7: In the formula, The downward adaptive control parameters are for the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is the proportionality coefficient; For auxiliary items; When the difference between the preset expected force and the force data value of the robotic arm end in the Z-axis direction is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the downward pressure adaptive control parameter in the Z-axis direction is set to be equal to the second initial control parameter.

7. The multimodal drag control method for an autonomous ultrasonic robot according to claim 5, characterized in that, Based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset desired force, the lifting adaptive control parameters in the Z-axis direction are calculated, including: When the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset desired force is greater than the preset environmental stiffness parameter, the lifting adaptive control parameters in the Z-axis direction are calculated based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, the preset desired force, and the preset environmental stiffness parameter, according to Formula 8: In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; Preset environmental stiffness parameters; This is the proportionality coefficient; For auxiliary items; When the difference between the force data value of the robotic arm end effector in the Z-axis direction and the preset expected force is less than or equal to the preset environmental stiffness parameter, and the preset expected force is greater than the preset maximum expected force, the lifting adaptive control parameters in the Z-axis direction are calculated according to Formula 9 based on the second initial control parameters, the force data value of the robotic arm end effector in the Z-axis direction, and the preset expected force: In the formula, These are the lifting adaptive control parameters in the Z-axis direction; This is the second initial control parameter; This represents the force data value of the robotic arm's end effector in the Z-axis direction; To pre-set expectations; This is the proportionality coefficient; For auxiliary items; When the difference between the force data value of the robotic arm end in the Z-axis direction and the preset expected force is not greater than the preset environmental stiffness parameter, and the preset expected force is not greater than the preset maximum expected force, the downward pressure adaptive control parameter in the Z-axis direction is set to be equal to the second initial control parameter.

8. A multimodal drag control device for an autonomous ultrasonic robot, characterized in that, include: The acquisition module is used to acquire real-time ultrasound images and force data values ​​at the end of the robotic arm of the autonomous ultrasound robot; The judgment module is used to determine whether the pixel values ​​of the ROI region in a consecutive preset number of ultrasound images are all greater than a preset pixel threshold. The calculation module is used to calculate the target displacement of the robotic arm end in the X-axis and Y-axis directions based on the tool coordinate system, the force data values ​​of the robotic arm end in the X-axis and Y-axis directions and the first initial control parameters of the autonomous ultrasonic robot, respectively. At the same time, it calculates the target displacement of the robotic arm in the Z-axis direction based on the force data value of the robotic arm end in the Z-axis direction, the preset expected force, and the second initial control parameters of the autonomous ultrasonic robot. The conversion module is used to convert the calculated target displacements of the robot arm end in the X, Y, and Z axes in the tool coordinate system into the target displacements of the robot arm end in the X, Y, and Z axes in the world coordinate system. The control module is used to implement zero-force control in the horizontal direction of the probe contact surface and constant force control in the vertical direction of the probe contact surface, based on the target displacement of the robotic arm end in the X-axis, Y-axis and Z-axis directions in the world coordinate system, until the probe moves to the target position.

9. A computer-readable storage medium having a computer program / instructions stored thereon, characterized in that, When the computer program / instructions are executed by the processor, they implement the multimodal drag control method for the autonomous ultrasonic robot as described in any one of claims 1-7.

10. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the multimodal drag control method for the autonomous ultrasonic robot as described in any one of claims 1-7.

Images