Moxibustion robot control method and system and moxibustion robot

Abstract

The invention provides a moxibustion robot control method and system and a moxibustion robot, and relates to the technical field of robot control, and the method comprises the steps: controlling a camera to collect a human body image of a current user; based on the grid coordinates of the target acupoint in the human body surface grid, determining the pixel coordinates of the target acupoint in the human body image; the grid coordinates are determined after clustering a plurality of normalized grid coordinates of the target acupuncture point in the human body surface grid; based on the pixel coordinates, an internal reference matrix of the camera and a coordinate transformation matrix between a camera coordinate system of the camera and a robot coordinate system of the moxibustion robot, determining space coordinates of the target acupuncture point in the robot coordinate system; the tail end of the mechanical arm is controlled to move to the space coordinates, and the moxibustion device is controlled to conduct moxibustion operation on the current user. According to the method and the system provided by the invention, the moxibustion robot can accurately position the human body acupuncture points on different user individuals, and the comfort and the safety of the user in the moxibustion process are ensured.

Description

Technical Field

[0001] The present invention relates to the field of robot control technology, and in particular to a moxibustion robot control method, system and moxibustion robot. Background Art

[0002] Moxibustion is a health and wellness method. Due to individual differences in acupuncture point distribution and moxibustion protocols, moxibustion is usually performed manually, which is time-consuming and labor-intensive.

[0003] Research has been conducted on intelligent moxibustion robots, aiming to automatically identify acupuncture points and safely perform gentle moxibustion, pecking moxibustion, and circular moxibustion according to pre-programmed procedures. However, existing intelligent moxibustion robots and their associated control methods are unable to accurately locate acupuncture points on the human body, thus failing to ensure user comfort and safety, resulting in a poor user experience.

[0004] Therefore, how to control the moxibustion robot to accurately locate the acupuncture points of the human body, ensure the comfort and safety of the user during the moxibustion process, and improve the user experience has become a technical problem that needs to be urgently solved in the industry. Summary of the Invention

[0005] The present invention provides a moxibustion robot control method, system and moxibustion robot, which are used to solve the technical problem of how to control the moxibustion robot to accurately locate acupuncture points on the human body, ensure the comfort and safety of the user during the moxibustion process, and improve the user experience.

[0006] The present invention provides a moxibustion robot control method, which is applied to the moxibustion robot; the moxibustion robot is provided with a camera, a robotic arm and a moxibustion device; the moxibustion device is provided at the end of the robotic arm; the method comprises: Controlling the camera to capture a human body image of the current user; determining pixel coordinates of the target acupuncture point in the human body image based on grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid; Determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; The end of the robotic arm is controlled to move to the spatial coordinate, and the moxibustion device is controlled to perform moxibustion operation on the current user.

[0007] In some embodiments, determining the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid includes: Based on the correspondence between the pixel coordinates of each point in the human body image and the grid coordinates of each point in the human body surface grid, coordinate mapping is performed on the grid coordinates of the target acupuncture point in the human body surface grid to determine the pixel coordinates of the target acupuncture point in the human body image.

[0008] In some embodiments, the grid coordinates of the target acupuncture point in the human body surface grid are determined based on the following steps: Controlling the camera to capture a sample human body image; wherein the human body in the sample human body image is marked with a plurality of target acupuncture points; Determining the pixel coordinates of each target acupuncture point in the sample human body image; Performing human body posture estimation processing on the sample human body image to determine a human body surface grid; the human body surface grid includes a plurality of human body grid areas and pixel coordinates of vertices of each human body grid area in the sample human body image; Determining normalized grid coordinates of each target acupuncture point in the human body surface grid based on the pixel coordinates of each target acupuncture point in the sample human body image, the human body grid area corresponding to each target acupuncture point, and the pixel coordinates of the vertices of the human body grid area in the sample human body image; performing density clustering on a plurality of normalized grid coordinates of each target acupuncture point in the human body surface grid to obtain a plurality of clusters; Based on the normalized grid coordinates of the core points in each cluster, the grid coordinates of each target acupuncture point in the human body surface grid are determined.

[0009] In some embodiments, determining the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot includes: Determining the spatial coordinates of the target acupuncture point in the camera coordinate system based on the pixel coordinates and the intrinsic parameter matrix of the camera; The spatial coordinates of the target acupuncture point in the robot coordinate system are determined based on the spatial coordinates of the target acupuncture point in the camera coordinate system and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot.

[0010] In some embodiments, a marker is further provided at the end of the robotic arm; the marker is used to mark the end of the robotic arm; The coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot is determined based on the following steps: The coordinate transformation matrix between the camera coordinate system and the robot coordinate system is determined based on the coordinate transformation matrix between the camera coordinate system and the marker coordinate system of the marker, and the coordinate transformation matrix between the marker coordinate system and the robot coordinate system.

[0011] In some embodiments, controlling the end of the robotic arm to move to the spatial coordinates and controlling the moxibustion device to perform moxibustion on the current user includes: Determining a movement trajectory of the end of the robotic arm based on the spatial coordinates of the plurality of target acupuncture points in the robot coordinate system and the moxibustion operation sequence of the plurality of target acupuncture points; Based on the movement trajectory of the end of the robotic arm and the moxibustion operation mode of each target acupuncture point, the moxibustion device is controlled to perform moxibustion operation on the current user.

[0012] In some embodiments, a temperature sensor is further provided at the end of the robotic arm; the temperature sensor is used to collect the surface temperature of each target acupuncture point; the method further includes: The operating parameters of the moxibustion device are adjusted based on the body surface temperature of each target acupuncture point.

[0013] The present invention provides a moxibustion robot control system, which is applied to a moxibustion robot; the moxibustion robot is provided with a camera, a robotic arm, and a moxibustion device; the moxibustion device is provided at the end of the robotic arm; the system comprises: An image acquisition module, used to control the camera to acquire a human body image of the current user; a coordinate determination module, configured to determine pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined by clustering a plurality of normalized grid coordinates of the target acupuncture point in the human body surface grid; a coordinate transformation module, for determining the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; The moxibustion control module is used to control the end of the robotic arm to move to the spatial coordinates and control the moxibustion device to perform moxibustion operations on the current user.

[0014] The present invention provides a moxibustion robot, comprising a camera, a robotic arm, a moxibustion device, and a moxibustion robot control system; The moxibustion robot control system is connected to the camera, the robotic arm and the moxibustion device respectively, and is used to execute the moxibustion robot control method.

[0015] The present invention provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the moxibustion robot control method is implemented.

[0016] The moxibustion robot control method, system and moxibustion robot provided by the present invention control the camera to collect the human body image of the current user; determine the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the camera's internal parameter matrix, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; control the end of the robotic arm to move to the spatial coordinates, and control the moxibustion device to perform moxibustion operation on the current user; because the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid, the human body morphology of different individuals can be standardized, and the large differences between individual users can be eliminated. The pixel coordinates of the target acupuncture point can be accurately determined according to the grid coordinates, and the spatial coordinates can be accurately determined, so that the moxibustion robot can accurately locate the human body acupuncture points on different individual users, ensuring the comfort and safety of the user during the moxibustion process and improving the user's usage experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and, together with the description, serve to explain the principles of the invention.

[0018] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0019] Figure 1 This is one of the flow charts of the moxibustion robot control method provided by the present invention.

[0020] Figure 2 This is a schematic diagram of the conversion between pixel coordinates and grid coordinates provided by the present invention.

[0021] Figure 3 This is the second flow chart of the moxibustion robot control method provided by the present invention.

[0022] Figure 4 It is a structural diagram of the moxibustion robot control system provided by the present invention.

[0023] Figure 5It is a structural schematic diagram of the moxibustion robot provided by the present invention.

[0024] Figure 6 It is a structural schematic diagram of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0025] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," and the like in the present invention are used to distinguish similar objects and are not necessarily used to describe a specific order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having," as well as any variations thereof, are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps, units, or modules is not necessarily limited to those steps, units, or modules that are explicitly listed, but may include other steps, units, or modules that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0027] In the technical solution of the present invention, the collection, storage, use, processing, transmission, provision and disclosure of personal information involved comply with the provisions of relevant laws and regulations, take necessary confidentiality measures, and do not violate public order and good morals.

[0028] Related technologies for intelligent moxibustion robots and their control methods rely on template matching or trajectory teaching to achieve acupoint location. These methods fail to account for individual user differences, requiring manual operation to locate acupoints for newly added users. This inability to accurately locate acupoints hinders user comfort and safety, reducing the user experience.

[0029] In order to solve the shortcomings of related technologies, Figure 1 This is one of the flow charts of the moxibustion robot control method provided by the present invention, such as Figure 1 As shown, the method includes step 110 , step 120 , step 130 and step 140 .

[0030] Step 110: Control the camera to capture the body image of the current user.

[0031] Specifically, the moxibustion robot control method provided in this invention is applied to a moxibustion robot. The moxibustion robot is an intelligent device that integrates modern electronic technology with traditional Chinese medicine moxibustion therapy. It simulates manual moxibustion, utilizing the heat energy and medicinal properties of burning moxa to target specific acupuncture points on the human body, achieving automated and precise moxibustion operations.

[0032] Structurally, the moxibustion robot consists of a camera, a robotic arm, and a moxibustion device. The moxibustion device is located at the end of the robotic arm. The camera is the visual sensor in the moxibustion robot system, capturing images of the human body and providing data support for subsequent acupoint location and posture estimation. The robotic arm is the actuator in the moxibustion robot system, precisely controlling the position and posture of the moxibustion device, enabling automated moxibustion operation. The moxibustion device is the actuator in the moxibustion robot system, generating the heat energy and medicinal effects required for moxibustion, which act on the acupoints on the body.

[0033] The moxibustion robot control method provided in the embodiments of the present invention is implemented by a moxibustion robot control system. This system can be implemented through software, such as a control program running in the moxibustion robot controller, or through hardware, such as a controller that executes the moxibustion robot control method.

[0034] The camera may be a monocular camera. The current user is a user who needs to undergo moxibustion. After the current user is in position, the camera may be controlled to capture an image of the current user's body to obtain a body image.

[0035] Step 120: Determine the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid. The grid coordinates are determined by clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid.

[0036] Specifically, the target acupoint refers to the specific acupoint that the user currently wants to perform moxibustion on. A human surface mesh is a geometric structure that represents the human surface. It typically consists of multiple vertices and faces, each with a coordinate. These vertices are connected to form polygonal faces, thus forming a mesh model of the entire human surface. The human surface mesh accurately represents the shape and surface details of the human body, providing a three-dimensional reference framework for moxibustion operations.

[0037] Grid coordinates refer to the position of each point in the human body surface grid, represented by UV coordinates. UV coordinates are normalized two-dimensional coordinates, usually ranging from [0, 1], and are used to represent the position of a surface point on a three-dimensional model on a two-dimensional texture image.

[0038] Pixel coordinates refer to the position of each pixel in a human body image, represented by (x, y) coordinates. These coordinates are discrete and represent the row and column positions of the pixel in the image.

[0039] Because both the human surface mesh and the human image represent the human body, there is a mapping relationship between points in the human surface mesh (grid vertices) and points in the human image (pixels). Any point in the human surface mesh can be found in the human image. Therefore, the grid coordinates of any point in the human surface mesh can be converted to the pixel coordinates of the corresponding point in the human image.

[0040] Human body images can be processed using a human pose estimation algorithm (such as the DensePose algorithm) to determine the mapping relationship between points in the image and points in the human surface grid. Based on this mapping relationship and the grid coordinates of the target acupuncture point in the human surface grid, the pixel coordinates of the target acupuncture point in the human image can be determined.

[0041] Normalized grid coordinates are coordinates that have been normalized to a specific range. Normalized grid coordinates are typically two-dimensional (U, V) coordinates with values ​​between 0 and 1. This normalization process makes the coordinate values ​​independent of specific resolution or size.

[0042] In an embodiment of the present invention, a large number of human body images of different users can be collected to obtain the grid coordinates of the target acupuncture points of these users in the human body surface grid. The grid coordinates of the target acupuncture points of these users are normalized to obtain multiple normalized grid coordinates of the target acupuncture points in the human body surface grid. Cluster analysis is performed on these multiple normalized grid coordinates, and the grid coordinates of the target acupuncture points in the human body surface grid can be obtained based on the clustering results.

[0043] Through the above normalization and cluster analysis, the human body morphology of different individuals can be standardized so that it can be processed and analyzed in a unified coordinate system. The resulting grid coordinates can eliminate the large differences between individual users and improve the accuracy of target acupoint positioning.

[0044] Step 130: Determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the camera's internal parameter matrix, and the coordinate transformation matrix between the camera coordinate system and the robot coordinate system of the moxibustion robot.

[0045] Specifically, the camera coordinate system is a three-dimensional coordinate system with the camera's optical center as its origin. The camera coordinate system is used to describe the position of a target point (such as a target acupuncture point) relative to the camera.

[0046] The robot coordinate system is a three-dimensional coordinate system with the robot base as its origin. It describes the position of a target point (such as a target acupuncture point) relative to the robot base. Robot controllers typically use the robot coordinate system to plan and execute the motion of the robotic arm.

[0047] The camera's intrinsic parameter matrix, which contains parameters such as the camera's focal length and optical center, is used to project points in the camera coordinate system onto the image plane. By transforming the pixel coordinates of the target acupoint in the human body image based on the intrinsic parameter matrix, the spatial coordinates of the target acupoint in the camera coordinate system can be obtained.

[0048] The coordinate transformation matrix describes the relationship between the camera coordinate system and the robot coordinate system. Generally, the coordinate transformation matrix can be decomposed into a rotation matrix and a translation vector. The rotation matrix represents the rotation of the camera coordinate system relative to the robot coordinate system; the translation vector represents the translation of the camera coordinate system relative to the robot coordinate system.

[0049] According to the coordinate transformation matrix between the camera coordinate system and the robot coordinate system, the spatial coordinates of the target acupuncture point in the camera coordinate system can be transformed to obtain the spatial coordinates of the target acupuncture point in the robot coordinate system.

[0050] Step 140: Control the end of the robotic arm to move to the spatial coordinate, and control the moxibustion device to perform moxibustion operation on the current user.

[0051] Specifically, the spatial coordinates of the target acupuncture point in the robot coordinate system are used as the target position for the end of the robotic arm to move. Based on the difference between the current position of the end of the robotic arm and the target position, a control instruction for the robotic arm is generated, controlling the end of the robotic arm to move to the spatial coordinates. Because the moxibustion device is located at the end of the robotic arm, it can be determined that the moxibustion device is at the location of the target acupuncture point. The moxibustion device can then be controlled to perform moxibustion on the current user.

[0052] The moxibustion robot control method provided by the embodiment of the present invention controls the camera to collect the human body image of the current user; determines the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; determines the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the camera's internal parameter matrix, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; controls the end of the robotic arm to move to the spatial coordinates, and controls the moxibustion device to perform moxibustion operation on the current user; since the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid, the human body morphology of different individuals can be standardized, and the large differences between individual users can be eliminated. The pixel coordinates of the target acupuncture point can be accurately determined according to the grid coordinates, and the spatial coordinates can be accurately determined, so that the moxibustion robot can accurately locate the human body acupuncture points on different individual users, ensuring the comfort and safety of the user during the moxibustion process and improving the user's usage experience.

[0053] It should be noted that each embodiment of the present invention can be freely combined, the order can be changed, or it can be executed separately, and does not need to rely on or depend on a fixed execution order.

[0054] In some embodiments, determining the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid includes: Based on the correspondence between the pixel coordinates of each point in the human body image and the grid coordinates of each point in the human body surface grid, coordinate mapping is performed on the grid coordinates of the target acupuncture point in the human body surface grid to determine the pixel coordinates of the target acupuncture point in the human body image.

[0055] Specifically, a human pose estimation algorithm can process a human image, map each pixel in the two-dimensional human image to the surface of a three-dimensional human model, and generate corresponding grid coordinates. Human pose estimation algorithms can include the DensePose algorithm, etc.

[0056] According to the correspondence between the pixel coordinates of each point in the human body image and the grid coordinates of each point in the human body surface grid, the grid coordinates of the target acupuncture point in the human body surface grid can be reversely mapped to obtain the pixel coordinates of the target acupuncture point in the human body image.

[0057] The moxibustion robot control method provided by the embodiment of the present invention determines the pixel coordinates of the target acupuncture points in the human body image based on the grid coordinates of the target acupuncture points in the human body surface grid, so that the moxibustion robot can accurately locate the human body acupuncture points on the user individual.

[0058] In some embodiments, the grid coordinates of the target acupuncture point in the human body surface grid are determined based on the following steps: Controlling a camera to capture a sample human body image; a human body in the sample human body image is marked with multiple target acupuncture points; Determine the pixel coordinates of each target acupuncture point in the sample human body image; Performing human body posture estimation processing on the sample human body image to determine the human body surface grid; the human body surface grid includes multiple human body grid areas and the pixel coordinates of the vertices of each human body grid area in the sample human body image; Determining the normalized grid coordinates of each target acupuncture point in the human body surface grid based on the pixel coordinates of each target acupuncture point in the sample human body image, the human body grid area corresponding to each target acupuncture point, and the pixel coordinates of the vertices of the human body grid area in the sample human body image; Density clustering is performed on multiple normalized grid coordinates of each target acupuncture point in the human body surface grid to obtain multiple clusters; Based on the normalized grid coordinates of the core points in each cluster, the grid coordinates of each target acupuncture point in the human body surface grid are determined.

[0059] Specifically, a large number of sample human body images can be obtained to determine multiple normalized grid coordinates of the target acupuncture points in the human body surface grid, and these normalized grid coordinates can be modeled and analyzed to finally determine the grid coordinates of the target acupuncture points in the human body surface grid. The specific steps include: The first step is to control the camera to capture a sample human body image; the sample human body image is marked with multiple target acupuncture points. The sample human body images can be images of different sample users (e.g., volunteers and previous users). Multiple professional acupuncturists can mark the target acupuncture points on each sample user's body using small, colored adhesive stickers. Target acupuncture points can include the Dazhui point, the Lung point, the Heart point, the Liver point on the back, and the Zhongji and Guanyuan points on the abdomen. The camera is then controlled to capture images of the acupuncturist-marked human body points to produce a sample human body image.

[0060] The second step is to determine the pixel coordinates of each target acupoint in the sample human image. The pixel coordinates of the corresponding pixels of the target acupoints in the sample human image marked by the acupuncturist can be obtained by clicking on the mouse. This will yield multiple sets of pixel coordinates of target acupoints marked by multiple acupuncturists for multiple sample users.

[0061] In the third step, the human pose estimation algorithm (DensePose) is used to process the sample human body image to obtain an image with successful human pose estimation and clear human body mesh division, that is, the human body surface mesh. The human body surface mesh includes multiple human body mesh areas and the pixel coordinates of the vertices of each human body mesh area in the sample human body image. The human body mesh area is used to represent the human body area, such as the back, abdomen, etc. The human body mesh area can be determined by the connection lines between different vertices. The human pose estimation algorithm can also calculate the pixel coordinates of the vertex in the sample human body image. For example, for a certain human body mesh area, the pixel coordinates of the vertex in the upper left corner in the sample human body image are ( , ), the pixel coordinates of the vertex in the lower right corner in the sample human body image are ( , ).

[0062] Based on the pixel coordinates of each target acupoint in the sample human body image, the human body grid area corresponding to each target acupoint, and the pixel coordinates of the vertices of the human body grid area in the sample human body image, the normalized grid coordinates of each target acupoint in the human body surface grid are determined. For example, if a target acupoint exists in a certain human body grid area, the pixel coordinates of the target acupoint in the sample human body image are ( , ). Figure 2This is a schematic diagram of the conversion between pixel coordinates and grid coordinates provided by the present invention, such as Figure 2 As shown, the normalized grid coordinates of the target acupuncture point in the human body surface grid ( , ) can be expressed as: , .

[0063] Through the above method, a normalized IUV coordinate database of acupoints is established. I represents a human body region, such as the back or abdomen, and UV is similar to the longitude and latitude of that region. The human pose estimation algorithm (DensePose) is used to estimate the human body. This algorithm generates corresponding grid coordinates based on the human body image, that is, the UV coordinates of each pixel on the human body surface.

[0064] The fourth step is to model and analyze these normalized grid coordinates to finally determine the grid coordinates (UV coordinates) of the target acupuncture points in the human body surface grid.

[0065] To analyze the central tendency of differently labeled data, the density-based spatial clustering of applications with noise (DBSCAN) algorithm was used to model and analyze the grid coordinates of different acupoints. Density clustering was performed on the multiple normalized grid coordinates of each target acupoint within the human surface grid, resulting in multiple clusters. This algorithm is insensitive to noisy data and can classify data points into three categories: core points, boundary points, and outliers. Core points form the basis for cluster formation, and a cluster consists of one or more core points and their neighborhood points. Boundary points are located at the edge of a cluster but still belong to it. Outliers are typically considered noise or abnormal points and are not assigned to any cluster.

[0066] The normalized grid coordinates of the core points in each cluster are used as the grid coordinates of each target acupuncture point in the human body surface grid.

[0067] On this basis, DBSCAN cluster analysis can be performed on the acupoint data of males and females respectively to distinguish the possible influence of gender on acupoint location. By analyzing the clustering results, the stable grid coordinates of each target acupoint are obtained.

[0068] The moxibustion robot control method provided by the embodiment of the present invention converts the pixel coordinates of the target acupuncture points in the sample human body image into normalized grid coordinates, and determines the final grid coordinates through a clustering method. This can eliminate the influence caused by the body differences of different individuals, thereby improving the generalization ability and stability.

[0069] In some embodiments, determining the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot includes: Based on the pixel coordinates and the camera's intrinsic parameter matrix, the spatial coordinates of the target acupuncture point in the camera coordinate system are determined; Based on the spatial coordinates of the target acupuncture point in the camera coordinate system and the coordinate transformation matrix between the camera coordinate system and the robot coordinate system of the moxibustion robot, the spatial coordinates of the target acupuncture point in the robot coordinate system are determined.

[0070] Specifically, according to the pixel coordinates of the target acupoint ( , ), and the camera's internal parameter matrix K, determine the spatial coordinates of the target acupoint in the camera coordinate system [ , , ], which can be expressed as: .

[0071] According to the spatial coordinates of the target acupuncture point in the camera coordinate system, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot , determine the spatial coordinates of the target acupuncture point in the robot coordinate system [ , , ], which can be expressed as: .

[0072] The moxibustion robot control method provided by the embodiment of the present invention transforms the pixel coordinates according to the camera's internal parameter matrix and the coordinate transformation matrix between the camera coordinate system and the robot coordinate system to obtain the spatial coordinates of the target acupuncture points in the robot coordinate system, so that the moxibustion robot can accurately locate the human body acupuncture points on the user individual.

[0073] In some embodiments, a marker is further provided at the end of the robotic arm; the marker is used to mark the end of the robotic arm; The coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot is determined based on the following steps: The coordinate transformation matrix between the camera coordinate system and the robot coordinate system is determined based on the coordinate transformation matrix between the camera coordinate system and the marker coordinate system of the marker, and the coordinate transformation matrix between the marker coordinate system and the robot coordinate system.

[0074] Specifically, to facilitate marking the end of the robotic arm so that the camera can accurately identify the current position of the end of the robotic arm, a marker can be placed at the end of the robotic arm. The marker can be an icosahedral marker (ArUco). An icosahedral marker consists of a regular icosahedron and an ArUco code attached to its face. The regular icosahedron is a polyhedron with 20 equilateral triangular faces, each of which has a unique ArUco code attached to it. These ArUco codes are binary square marks with a unique encoding pattern that facilitates rapid detection and recognition by computer vision systems. The marker coordinate system is a three-dimensional coordinate system with the marker as its origin.

[0075] According to the coordinate transformation matrix between the camera coordinate system (c) and the marker coordinate system (m) of the marker , and the coordinate transformation matrix between the marker coordinate system and the robot coordinate system (r) , determine the coordinate transformation matrix between the camera coordinate system and the robot coordinate system , which can be expressed as: .

[0076] in, is the rotation matrix between the marker coordinate system and the robot coordinate system; is the translation vector between the marker coordinate system and the robot coordinate system; is the rotation matrix between the camera coordinate system and the marker coordinate system; is the translation vector between the camera coordinate system and the marker coordinate system.

[0077] The moxibustion robot control method provided in the embodiment of the present invention can accurately identify the current position of the end of the robotic arm by setting markers, so that the moxibustion robot can accurately locate the human acupuncture points on different individual users, ensuring the comfort and safety of the user during the moxibustion process.

[0078] In some embodiments, controlling the end of the robotic arm to move to a spatial coordinate and controlling the moxibustion device to perform a moxibustion operation on the current user includes: Based on the spatial coordinates of the multiple target acupuncture points in the robot coordinate system and the moxibustion operation sequence of the multiple target acupuncture points, the movement trajectory of the end of the robotic arm is determined; Based on the movement trajectory of the end of the robotic arm and the moxibustion operation mode of each target acupuncture point, the moxibustion device is controlled to perform moxibustion operation on the current user.

[0079] Specifically, if the current user needs to perform moxibustion on multiple target acupoints, the path of the end of the robotic arm can be planned based on the spatial coordinates of the multiple target acupoints in the robot coordinate system and the moxibustion operation sequence of the multiple target acupoints, thereby obtaining the movement trajectory of the end of the robotic arm.

[0080] Moxibustion techniques include gentle moxibustion, pecking moxibustion, and circular moxibustion. Gentle moxibustion involves applying moxibustion 2-3 cm above the target acupoint, held still, for 10 minutes. Pecking moxibustion involves moving the moxibustion up and down at a height of 0.5-3 cm above the target acupoint for 10 minutes. Circular moxibustion involves performing circular motions (3 cm in diameter) at a height of 2-3 cm above the target acupoint for 5 minutes. Moxibustion techniques can be programmed to execute on the moxibustion device.

[0081] Dynamic trajectory planning requires consideration of multiple factors, the most critical of which include acupoint positioning accuracy and moxibustion technique requirements. A camera or optical tracking motion trajectory is used, and the error is calculated and the motion trajectory of the end of the robotic arm is optimized based on the proportional-integral-differential (PID) algorithm to ensure that the robot dynamically adjusts the deviation between the actual position and the target position during movement, thereby improving the accuracy and safety of moxibustion.

[0082] The moxibustion robot control method provided by the embodiment of the present invention realizes automatic control of the moxibustion device to perform moxibustion operation on the current user by planning the movement trajectory of the end of the robotic arm.

[0083] In some embodiments, a temperature sensor is further provided at the end of the robotic arm; the temperature sensor is used to collect the surface temperature of each target acupuncture point; and the method further includes: Based on the body surface temperature of each target acupuncture point, the operating parameters of the moxibustion device are adjusted.

[0084] Specifically, the temperature sensor can be an infrared temperature sensor, which has the advantage of being able to obtain temperature data by sensing the radiant heat from the skin surface without contacting the skin. This non-contact measurement method not only avoids interference caused by contact sensors, but also greatly improves the safety and reliability of the measurement.

[0085] Infrared temperature sensors can also obtain the surface temperature of each target acupuncture point in real time, thus providing accurate data support for subsequent control decisions. During moxibustion treatment, precise temperature control is crucial.

[0086] PID algorithm or layered temperature control method (low temperature zone ≤ 40℃, ideal temperature zone 40℃≤T≤48℃, model prediction optimization zone 48℃≤T≤55℃, emergency avoidance zone ≥55℃, the temperature range can be adjusted according to individual adaptability, T is the body surface temperature) can be used to achieve dynamic temperature adjustment. By calculating the temperature deviation, cumulative error and temperature change rate, the key parameters in the moxibustion process, such as the position of the moxa stick and the moxibustion time, can be adjusted to ensure precise temperature control to avoid skin burns or affect the treatment effect due to overheating or excessive cooling, and ensure patient comfort and safety.

[0087] The moxibustion robot control method provided in the embodiment of the present invention integrates temperature detection and control, so that the target acupuncture point area is maintained at an appropriate temperature for a long time, ensuring the comfort and safety of the patient.

[0088] In some embodiments, a visual operation interface can also be provided. By integrating the automatic acupoint identification and positioning method, the moxibustion multiple manipulation trajectory control method, and the temperature detection and control method, a visual operation interface is designed. Users can see the acupoint images from the camera's perspective in real time and independently select the target acupoint and moxibustion operation method.

[0089] Figure 3 This is the second flow chart of the moxibustion robot control method provided by the present invention, as shown in FIG. Figure 3 As shown, the method includes: Step 310: Collect sample human body images with acupuncture points marked by multiple professional physicians; Step 320: Process the sample human body image based on the DensePose human posture recognition algorithm to establish normalized IUV coordinate data of acupoints; Step 330: Perform statistical analysis and modeling on the IUV coordinate data to obtain the predicted IUV coordinates of the acupuncture points; Step 340: Obtain a human body image of the new test user, determine the position of the acupoint of the new test user in the image based on the predicted IUV coordinates of the acupoint, and convert it into spatial coordinates in the robot coordinate system; Step 350: Perform dynamic trajectory planning on the robot's mechanical arm and determine the moxibustion operation mode of the acupoints; Step 360: Using the infrared temperature sensor, perform temperature control and moxibustion on the acupuncture points of the new test user; Step 370: Perform visual presentation to the new test user.

[0090] The moxibustion robot control method provided by the embodiment of the present invention integrates acupoint recognition, trajectory planning, and a visual operation interface of temperature detection control, allowing users to independently configure target acupoints and moxibustion techniques according to their needs and ensuring safe use.

[0091] The following describes an apparatus provided by an embodiment of the present invention. The apparatus described below and the method described above can refer to each other.

[0092] Figure 4 This is a schematic diagram of the structure of the moxibustion robot control system provided by the present invention. Figure 4 As shown in FIG, the control system is applied to a moxibustion robot; the moxibustion robot is provided with a camera, a robotic arm, a moxibustion device, and an infrared temperature sensor; the moxibustion device is provided at the end of the robotic arm. The system includes: The image acquisition module 410 is used to control the camera to acquire the human body image of the current user; A coordinate determination module 420 is configured to determine the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined by clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid; A coordinate transformation module 430 is used to determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; The moxibustion control module 440 is used to control the end of the robotic arm to move to the spatial coordinates and control the moxibustion device to perform moxibustion operations on the current user.

[0093] The moxibustion robot control system provided by the embodiment of the present invention controls the camera to collect the human body image of the current user; determines the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; determines the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the camera's internal parameter matrix, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; controls the end of the robotic arm to move to the spatial coordinates, and controls the moxibustion device to perform moxibustion operation on the current user; since the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid, the human body morphology of different individuals can be standardized, and the large differences between individual users can be eliminated. The pixel coordinates of the target acupuncture point can be accurately determined according to the grid coordinates, and the spatial coordinates can be accurately determined, so that the moxibustion robot can accurately locate the human body acupuncture points on different user individuals, ensuring the comfort and safety of the user during the moxibustion process and improving the user's usage experience.

[0094] Figure 5 This is a schematic diagram of the structure of the moxibustion robot provided by the present invention. Figure 5 As shown, the moxibustion robot 500 includes a camera 510, a robotic arm 520, a moxibustion device 530, a moxibustion robot control system 540, and an infrared temperature sensor 550. In the figure, dotted lines represent electrical connections, and solid lines represent mechanical connections.

[0095] The moxibustion robot control system is connected to the camera, the robotic arm and the infrared temperature sensor respectively, and is used to execute the moxibustion robot control method in the above embodiment.

[0096] Specifically, the moxibustion robot utilizes a serial positioning arm composed of three revolute-revolute-revolute (3RRR) joints and a parallel robotic wrist composed of six revolute-spherical-universal (6RSU) joints. This hybrid serial-parallel mechanism offers superior flexibility and high-precision control. The 6RSU parallel robotic wrist consists of a static platform, a dynamic platform, and six branches, each comprised of a revolute joint, a spherical joint, and a universal joint. This allows the robot to freely position itself and perform tasks in three-dimensional space. This combination of serial and parallel structures allows the robot to balance rigidity and flexibility in complex spatial environments, ensuring high stability and adaptability when performing precise tasks.

[0097] The moxibustion robot provided by the embodiment of the present invention, by executing the moxibustion robot control method of the above embodiment, can accurately locate human acupuncture points on different users, ensuring the user's comfort and safety during the moxibustion process and improving the user experience. The moxibustion robot is miniaturized and portable through the 3RRR and 6RSU actuators, which can facilitate the robot's multi-scene application and position transfer. Through the trajectory planning control of the moxibustion technique, the operator's wrist is freed and the accuracy of the moxibustion trajectory is improved.

[0098] Figure 6 Schematic diagram of the structure of the electronic device provided by the present invention, such as Figure 6 As shown, the electronic device may include: a processor (Processor) 610, a communication interface (Communications Interface) 620, a memory (Memory) 630 and a communication bus (Communications Bus) 640, wherein the processor 610, the communication interface 620, and the memory 630 communicate with each other via the communication bus 640. The processor 610 may call the logic commands in the memory 630 to execute the method described in the above embodiment, for example: Control the camera to capture the human body image of the current user; determine the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid; determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the camera's intrinsic parameter matrix, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; control the end of the robotic arm to move to the spatial coordinates, and control the moxibustion device to perform moxibustion on the current user.

[0099] Furthermore, the logical commands in the aforementioned memory can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the portion that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several commands for causing a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in various embodiments of the present invention. The aforementioned storage media include various media capable of storing program code, such as USB flash drives, mobile hard drives, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical disks.

[0100] The processor in the electronic device provided by the embodiment of the present invention can call the logic instructions in the memory to implement the above method. Its specific implementation method is consistent with the implementation method of the above method and can achieve the same beneficial effects, which will not be repeated here.

[0101] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method provided in the above embodiments is executed.

[0102] Its specific implementation is consistent with the aforementioned method implementation and can achieve the same beneficial effects, so it will not be repeated here.

[0103] An embodiment of the present invention provides a computer program product, including a computer program, which implements the above method when executed by a processor.

[0104] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.

[0105] Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented using software plus a necessary general-purpose hardware platform, or of course, hardware. Based on this understanding, the essence of the above technical solution, or the portion that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, or an optical disk, and includes a number of instructions for causing a computer device (such as a personal computer, server, or network device) to execute the methods described in each embodiment or certain portions of the embodiments.

[0106] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.

Claims

1. A moxibustion robot control method, characterized in that: Applied to moxibustion robots; The moxibustion robot is provided with a camera, a robotic arm and a moxibustion device; The moxibustion device is provided at the end of the robotic arm; the method comprises: Controlling the camera to capture a human body image of the current user; determining pixel coordinates of the target acupuncture point in the human body image based on grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined after clustering multiple normalized grid coordinates of the target acupuncture point in the human body surface grid; Determine the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; The end of the robotic arm is controlled to move to the spatial coordinate, and the moxibustion device is controlled to perform moxibustion operation on the current user.

2. The moxibustion robot control method according to claim 1, characterized in that: The step of determining the pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid includes: Based on the correspondence between the pixel coordinates of each point in the human body image and the grid coordinates of each point in the human body surface grid, coordinate mapping is performed on the grid coordinates of the target acupuncture point in the human body surface grid to determine the pixel coordinates of the target acupuncture point in the human body image.

3. The moxibustion robot control method according to claim 1, characterized in that: The grid coordinates of the target acupuncture point in the human body surface grid are determined based on the following steps: Controlling the camera to capture a sample human body image; wherein the human body in the sample human body image is marked with a plurality of target acupuncture points; Determining the pixel coordinates of each target acupuncture point in the sample human body image; Performing human body posture estimation processing on the sample human body image to determine a human body surface grid; the human body surface grid includes a plurality of human body grid areas and pixel coordinates of vertices of each human body grid area in the sample human body image; Determining normalized grid coordinates of each target acupuncture point in the human body surface grid based on the pixel coordinates of each target acupuncture point in the sample human body image, the human body grid area corresponding to each target acupuncture point, and the pixel coordinates of the vertices of the human body grid area in the sample human body image; performing density clustering on a plurality of normalized grid coordinates of each target acupuncture point in the human body surface grid to obtain a plurality of clusters; Based on the normalized grid coordinates of the core points in each cluster, the grid coordinates of each target acupuncture point in the human body surface grid are determined.

4. The moxibustion robot control method according to claim 1, characterized in that: The determining of the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot includes: Determining the spatial coordinates of the target acupuncture point in the camera coordinate system based on the pixel coordinates and the intrinsic parameter matrix of the camera; The spatial coordinates of the target acupuncture point in the robot coordinate system are determined based on the spatial coordinates of the target acupuncture point in the camera coordinate system and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot.

5. The moxibustion robot control method according to claim 4, characterized in that: The end of the robotic arm is also provided with a marker; the marker is used to mark the end of the robotic arm; The coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot is determined based on the following steps: The coordinate transformation matrix between the camera coordinate system and the robot coordinate system is determined based on the coordinate transformation matrix between the camera coordinate system and the marker coordinate system of the marker, and the coordinate transformation matrix between the marker coordinate system and the robot coordinate system.

6. The moxibustion robot control method according to any one of claims 1 to 5, characterized in that: The controlling the end of the robotic arm to move to the spatial coordinates and controlling the moxibustion device to perform a moxibustion operation on the current user includes: Determining a movement trajectory of the end of the robotic arm based on the spatial coordinates of the plurality of target acupuncture points in the robot coordinate system and the moxibustion operation sequence of the plurality of target acupuncture points; Based on the movement trajectory of the end of the robotic arm and the moxibustion operation mode of each target acupuncture point, the moxibustion device is controlled to perform moxibustion operation on the current user.

7. The moxibustion robot control method according to claim 6, characterized in that: The end of the robotic arm is further provided with a temperature sensor; the temperature sensor is used to collect the surface temperature of each target acupuncture point; the method further includes: The operating parameters of the moxibustion device are adjusted based on the body surface temperature of each target acupuncture point.

8. A moxibustion robot control system, characterized in that: Applied to moxibustion robots; The moxibustion robot is provided with a camera, a robotic arm and a moxibustion device; the moxibustion device is provided at the end of the robotic arm; the system includes: An image acquisition module, used to control the camera to acquire a human body image of the current user; a coordinate determination module, configured to determine pixel coordinates of the target acupuncture point in the human body image based on the grid coordinates of the target acupuncture point in the human body surface grid; the grid coordinates are determined by clustering a plurality of normalized grid coordinates of the target acupuncture point in the human body surface grid; a coordinate transformation module, for determining the spatial coordinates of the target acupuncture point in the robot coordinate system based on the pixel coordinates, the intrinsic parameter matrix of the camera, and the coordinate transformation matrix between the camera coordinate system of the camera and the robot coordinate system of the moxibustion robot; The moxibustion control module is used to control the end of the robotic arm to move to the spatial coordinates and control the moxibustion device to perform moxibustion operations on the current user.

9. A moxibustion robot, characterized in that: Includes camera, robotic arm, moxibustion device and moxibustion robot control system; The moxibustion robot control system is connected to the camera, the robotic arm and the moxibustion device respectively, and is used to execute the moxibustion robot control method according to any one of claims 1 to 7.

10. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the moxibustion robot control method according to any one of claims 1 to 7 is implemented.

Images