Cupping mechanical arm movement track generation method and electronic equipment thereof

Abstract

The embodiment of the invention provides a cupping mechanical arm movement track generation method, device and system. The cupping mechanical arm movement track generation method comprises the steps that first calibration data and first depth information of at least one target acupuncture point are determined; processing the first calibration data and the first depth information through a coordinate fitting algorithm to obtain second calibration data and second depth information of the mechanical arm; based on the second calibration data and the second depth information, a target track point is determined in the coordinate axis of the mechanical arm; and on the basis of a preset physiotherapy demand and the feature information of the target track point, generating movement track data of the mechanical arm. The coordinates in the image data are mapped, and are converted into the moving coordinates of the mechanical arm according to the depth information and the calibration data, so that high-precision conversion from the image coordinates to the coordinates of the mechanical arm is realized, various cupping techniques are adapted, and the accuracy and individuation degree of physiotherapy are improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control, and particularly to a method, device, system, electronic device and storage medium for generating a moving trajectory of a cupping manipulator. Background Art

[0002] With the development of intelligent medical devices, manipulators have been gradually introduced into cupping devices to achieve automated cupping operations. However, in the prior art, the generation of the trajectory of the cupping manipulator still faces many challenges, such as inaccurate acupoint positioning, large errors in the coordinate conversion between the image and the manipulator, single trajectory type, and inability to dynamically adjust trajectory parameters according to different physiotherapy requirements.

[0003] Therefore, the existing methods for generating the moving trajectory of the cupping manipulator have problems such as being unable to complete the acupoint coordinate conversion and flexibly generating diverse trajectory paths according to different physiotherapy techniques. Summary of the Invention

[0004] An embodiment of the present invention provides a method for generating a moving trajectory of a cupping manipulator to solve the problems that the existing methods for generating the moving trajectory of the cupping manipulator are unable to complete the acupoint coordinate conversion and flexibly generate diverse trajectory paths according to different physiotherapy techniques.

[0005] In a first aspect, an embodiment of the present invention provides a method for generating a moving trajectory of a cupping manipulator, the method including the following steps: Determine the first calibration data and the first depth information of at least one target acupoint; Process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the manipulator; Based on the second calibration data and the second depth information, determine target trajectory points in the manipulator coordinate axes; Generate the moving trajectory data of the manipulator based on a preset physiotherapy requirement and the feature information of the target trajectory points.

[0006] Optionally, the determining the first calibration data and the first depth information of at least one target acupoint includes: Obtain back image data; Perform acupoint matching and recognition on the back image data through an acupoint recognition algorithm, and determine at least one target acupoint in the back image data; Based on the depth algorithm, perform positioning measurement on the at least one target acupoint to obtain the first calibration data and the first depth information of the at least one target acupoint.

[0007] Optionally, the processing of the first calibration data and the first depth information by a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm includes: Processing the first calibration data and the first depth information through a coordinate fitting algorithm to determine a mapping relationship between a coordinate axis corresponding to the back image data and a coordinate axis of the robotic arm; Based on the mapping relationship, the second calibration data and the second depth information of the target acupuncture point mapped on the robotic arm corresponding to the robotic arm coordinate axis are determined.

[0008] Optionally, determining a target trajectory point in a robot arm coordinate axis based on the second calibration data and the second depth information includes: Constructing spatial reference layer data of the robot arm coordinate axis according to at least one of the second calibration data and the second depth information, wherein the spatial reference layer data includes depth data and layer number data, and the depth data corresponds to the layer number data; Based on the preset trajectory type and depth data, starting from the current reference space layer, generating a plurality of trajectory points; Based on the multiple track points and the layer number data, target track points at corresponding layers are generated.

[0009] Optionally, the generating of the movement trajectory data of the robot arm based on the preset physical therapy requirements and the characteristic information of the target trajectory point includes: Based on the preset physical therapy needs, determining physical therapy parameters, the physical therapy parameters including cupping duration, cupping technique, and cupping negative pressure intensity; Determine characteristic information of the target trajectory point in the robot arm coordinate axis, the characteristic information including point spacing, distribution shape, and surface normal angle; Based on the therapy parameters and feature information, movement trajectory data of the robotic arm is generated.

[0010] Optionally, the method further comprises: generating movement trajectory data of the robot arm based on the physical therapy parameters and the characteristic information; According to the feature information, interpolation calculation is performed on the target trajectory points to generate a continuous spatial path; Based on the therapy parameters, determine the moving speed, acceleration and dwell time of each spatial path; According to the surface normal angle corresponding to each segment of the space path, the posture angle of the end of the robot arm at each target trajectory point is determined.

[0011] In a second aspect, an embodiment of the present invention further provides a device for generating a movement trajectory of a cupping robot arm, the device comprising: The first determination module is configured to determine the first calibration data and the first depth information of at least one target acupoint; The first acquisition module is configured to process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm; The second determination module is configured to determine target trajectory points in the robotic arm coordinate axes based on the second calibration data and the second depth information; The first generation module is configured to generate the movement trajectory data of the robotic arm based on a preset physiotherapy requirement and the feature information of the target trajectory points.

[0012] In a third aspect, an embodiment of the present invention provides a cupping robotic arm movement trajectory generation system, where the cupping robotic arm movement trajectory generation system includes: a cupping robotic arm movement trajectory generation device, a server, and a cupping robotic arm.

[0013] In a fourth aspect, an embodiment of the present invention provides an electronic device, including: a memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the cupping robotic arm movement trajectory generation method provided by the embodiment of the present invention are implemented.

[0014] In a fifth aspect, an embodiment of the present invention provides a computer-readable storage medium, where a computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps in the cupping robotic arm movement trajectory generation method provided by the embodiment of the invention are implemented.

[0015] In the embodiment of the present invention, the first calibration data and the first depth information of at least one target acupoint are determined; the first calibration data and the first depth information are processed through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm; target trajectory points are determined in the robotic arm coordinate axes based on the second calibration data and the second depth information; and the movement trajectory data of the robotic arm is generated based on a preset physiotherapy requirement and the feature information of the target trajectory points. By mapping the coordinates in the image data and converting them into the movement coordinates of the robotic arm according to the depth information and the calibration data, high-precision conversion from image coordinates to robotic arm coordinates is achieved, adapting to various cupping techniques and improving the accuracy and personalization of physiotherapy. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention, and those of ordinary skill in the art can also obtain other drawings without creative efforts based on these drawings.

[0017] Figure 1 is the architecture diagram of a cupping manipulator movement trajectory generation system adopted in an embodiment of the present invention; Figure 2 is the flowchart of a cupping manipulator movement trajectory generation method provided by an embodiment of the present invention; Figure 3 is the structural schematic diagram of another cupping manipulator movement trajectory generation device provided in an embodiment of the present invention; Figure 4 is the structural schematic diagram of an electronic device provided by an embodiment of the present invention. Detailed implementation manners

[0018] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0019] As Figure 1 shown, Figure 1 is the architecture diagram of a cupping manipulator movement trajectory generation system 100 provided by an embodiment of the present invention. The cupping manipulator movement trajectory generation system includes: a cupping manipulator movement trajectory generation device 300, a server 101, and a cupping manipulator 102. Among them, the above-mentioned cupping manipulator movement trajectory generation device 300 further includes a first determination module, which can be used to determine the first calibration data and the first depth information of at least one target acupoint; a first acquisition module, which can be used to process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the manipulator; a second determination module, which can be used to determine the target trajectory points in the manipulator coordinate axis based on the second calibration data and the second depth information; a first generation module, which can be used to generate the movement trajectory data of the manipulator based on the preset physiotherapy requirements and the characteristic information of the target trajectory points.

[0020] Specifically, the above-mentioned target acupoint can refer to the specific meridian / acupoint position on the human body epidermis where the user currently plans to perform cupping operation. It should be noted that this position can correspond to specific physiological characteristics and treatment requirements, and generally can be selected through the interface or APP of the above-mentioned cupping manipulator movement trajectory generation system. For example, when the user selects the Jianjing acupoint, the above-mentioned cupping manipulator movement trajectory generation system will identify this acupoint as the target acupoint.

[0021] The above first calibration data can be the two-dimensional coordinates of the above target acupoint in the image coordinate system, which can be extracted by the image recognition module and used as the input for subsequent coordinate transformation to guide the movement of the end of the robotic arm. Specifically, after capturing an image of the user's body (such as the back) with a camera, it can be extracted from the image in combination with an acupoint recognition algorithm for subsequent mapping calculation from image coordinates to robotic arm coordinates.

[0022] The above first depth information can refer to the distance value h of the corresponding coordinate point in the depth map in the image, which is usually obtained by an RGB-D camera or a ToF camera, representing the actual depth of the point from the camera and used to generate three-dimensional coordinates.

[0023] In a possible embodiment, the above cupping robotic arm movement trajectory generation system controls the camera module to capture an image of the user's back and collect an RGB image or an RGB-D image: when using an RGB camera, a color image is collected for acupoint recognition; when using a depth camera (such as Intel RealSense, Azure Kinect), the depth information of each pixel point can be collected simultaneously for spatial modeling, and through an AI model or acupoint atlas matching, the acupoints are automatically recognized and located, and finally the first calibration data and the first depth information of the target acupoint are output.

[0024] The above coordinate fitting algorithm can refer to the calculation method of the conversion relationship between image coordinates and robotic arm space coordinates. Generally speaking, a 9-point calibration method can be used in combination with multi-layer height data for fitting calculation. Specifically, by selecting 9 feature points in the image, obtaining the (x, y) of these points in the image and the actual space coordinates (X, Y, Z) of the end of the robotic arm, dividing the depth value h into multiple layers (such as 400mm, 500mm, 600mm, etc.), fitting is performed within each depth layer to obtain the conversion model of different depth layers. By substituting any input image point (x, y) and depth value h into this conversion model, the corresponding second calibration data and second depth information are output.

[0025] The above second calibration data and second depth information are both the three-dimensional coordinates (Xrobot, Yrobot, Zrobot) mapped to the robotic arm coordinate system after transforming the (x, y, h) of the target acupoint in the image through the coordinate fitting algorithm, that is, the precise spatial position used during actual cupping.

[0026] The above robotic arm coordinate axes can be the three-dimensional space reference system based on which the robotic arm operates, with the unit of millimeters, usually bound to the device base or the initial pose. It should be noted that all trajectory points, attitude angles, and path planning can be constructed with reference to this coordinate system.

[0027] The above-mentioned target trajectory points can refer to a series of spatial points generated around the target acupoint through a preset trajectory type. These points can form the desired movement path of the robotic arm and can be generated based on image tracing, custom trajectory functions, or automatic trajectory templates. Specifically, the custom trajectory functions or automatic trajectory templates can include, but are not limited to, forms such as circular trajectories (with the acupoint as the center and the radius set by oneself), spiral trajectories, straight lines plus circles, and hand-drawn trajectories after the user takes a photo.

[0028] The above-mentioned preset physiotherapy requirements can include, but are not limited to, cupping methods: stationary cupping, moving cupping, flash cupping, suction and release, operation duration (such as 60 seconds of stationary cupping at each point, 5 circles during moving cupping), negative pressure intensity (-20 ~ -50 KPa), temperature setting (hot cupping supports temperature holding function (such as 37~45 °C)), etc., which are user settings or a set of cupping operation parameters adjusted according to the individual characteristics of the user.

[0029] The above-mentioned individual characteristics can refer to the individual difference information reflecting the current user receiving physiotherapy in terms of body structure, physiological state, or preference settings, which can be used to guide the generation and adjustment of the robotic arm movement trajectory, such as the offset of the trajectory position, so as to achieve more accurate, flexible, and safe robotic arm trajectory generation.

[0030] The above-mentioned characteristic information can be used to describe the structural characteristics of the target trajectory points in space and is used for path generation and pose calculation. It can include, but is not limited to, point spacing, which is used to control the trajectory accuracy; distribution shape, which is used to judge whether it is closed-loop, unidirectional, spiral, etc.; surface normal angle, which is used to calculate the local surface slope by analyzing the spatial coordinate differences of adjacent points and deduce the pose of the robotic arm end (Rx, Ry, Rz).

[0031] The above-mentioned movement trajectory data can refer to a set of control data used to drive the movement of the robotic arm, usually including: three-dimensional position sequence [(X1, Y1, Z1),..., (Xn, Yn, Zn)]; attitude angle sequence [(Rx1, Ry1, Rz1),...]; speed and acceleration settings for each path segment; dwell time for each point (t1,..., tn), etc. trajectory parameters. It can be understood that the above-mentioned movement trajectory data can generate a continuous and smooth path through an interpolation algorithm to ensure that the robotic arm performs accurate and natural cupping actions.

[0032] In a possible embodiment, the above-mentioned cupping robotic arm movement trajectory generation system combines image recognition, depth measurement, and coordinate fitting, enabling it to automatically identify the position of the target acupoint based on the images and depth data collected by the camera, accurately map it to the robotic arm coordinate system, and generate multi-type cupping paths that meet individual characteristics and treatment requirements through trajectory planning and physiotherapy parameter adaptation, realizing the intelligent control and personalized adjustment of the robotic arm cupping action.

[0033] As shown Figure 2 in Figure 2 Figure 1, it is a flowchart of a method for generating a moving trajectory of a cupping manipulator provided by an embodiment of the present invention. The method for generating a moving trajectory of the cupping manipulator includes the steps of: 201. Determine the first calibration data and the first depth information of at least one target acupoint.

[0034] In the embodiment of the present invention, the above method for generating a moving trajectory of a cupping manipulator can be applied to a system for generating a moving trajectory of a cupping manipulator. The system for generating a moving trajectory of the cupping manipulator has functions such as moving trajectory data processing, moving trajectory data transceiver, and moving trajectory data memory storage, and can be constructed based on a server or a server cluster. The server or the server cluster can be an electronic device with the ability to process moving trajectory data.

[0035] The above target acupoint can refer to a specific meridian / acupoint position on the human body epidermis where the user currently plans to perform cupping operation. It should be noted that this position can correspond to specific physiological characteristics and treatment requirements, and generally can be selected through the interface or APP of the above system for generating a moving trajectory of a cupping manipulator. For example, when the user selects the Jianjing acupoint, the above system for generating a moving trajectory of a cupping manipulator will identify this acupoint as the target acupoint.

[0036] The above first calibration data can be the two-dimensional coordinates of the above target acupoint in the image coordinate system, which can be extracted by an image recognition module and used as the input for subsequent coordinate transformation to guide the movement of the end of the manipulator. Specifically, after taking a picture of the user's body (such as the back) by a camera, it can be extracted from the image in combination with an acupoint recognition algorithm for the subsequent mapping calculation from the image coordinates to the manipulator coordinates.

[0037] The above first depth information can refer to the distance value h of the corresponding coordinate point in the depth map in the image, which is usually obtained by an RGB-D camera or a ToF camera, indicating the actual depth of this point from the camera and used for generating three-dimensional coordinates.

[0038] In a possible embodiment, the above system for generating a moving trajectory of a cupping manipulator controls the camera module to take a picture of the user's back and collect an RGB image or an RGB-D image: when using an RGB camera, a color image is collected for acupoint recognition; when using a depth camera (such as Intel RealSense, Azure Kinect), the depth information of each pixel point can be collected simultaneously for spatial modeling, and the acupoints are automatically recognized and located through an AI model or acupoint atlas matching, and finally the first calibration data and the first depth information of the target acupoint are output.

[0039] 202. Process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm.

[0040] In the embodiments of the present invention, the above-mentioned coordinate fitting algorithm may refer to a calculation method for the conversion relationship between image coordinates and the spatial coordinates of the robotic arm. Generally speaking, a 9-point calibration method combined with multi-layer height data can be used for fitting calculation. Specifically, by selecting 9 feature points in the image, obtaining the (x, y) of these points in the image and the actual spatial coordinates (X, Y, Z) of the end of the robotic arm, dividing the depth value h into multiple layers (such as 400mm, 500mm, 600mm, etc.), and performing fitting within each depth layer to obtain the conversion models for different depth layers. After substituting any input image point (x, y) and depth value h into this conversion model, the corresponding second calibration data and second depth information are output.

[0041] The above-mentioned second calibration data and second depth information are both the three-dimensional coordinates (Xrobot, Yrobot, Zrobot) in the robotic arm coordinate system after mapping the (x, y, h) of the target acupoint in the image through the coordinate fitting algorithm, that is, the precise spatial positions used during actual cupping.

[0042] 203. Determine the target trajectory points in the robotic arm coordinate axes based on the second calibration data and the second depth information.

[0043] In the embodiments of the present invention, the above-mentioned robotic arm coordinate axes may be a three-dimensional space reference system based on which the robotic arm operates, with the unit of millimeters, usually bound to the equipment base or the initial pose. It should be noted that all trajectory points, attitude angles, and path planning can be constructed with reference to this coordinate system.

[0044] The above-mentioned target trajectory points may refer to a series of spatial points generated around the target acupoint through a preset trajectory type. These points can form the desired movement path of the robotic arm and can be generated based on image tracing, custom trajectory functions, or automatic trajectory templates. Specifically, the custom trajectory functions or automatic trajectory templates may include, but are not limited to, circular trajectories (with the acupoint as the center and a self-set radius), spiral trajectories, straight lines plus circles, hand-drawn trajectories after the user takes a photo, etc.

[0045] 204. Generate the movement trajectory data of the robotic arm based on the preset physiotherapy requirements and the characteristic information of the target trajectory points.

[0046] In the embodiments of the present invention, the above characteristic information can be used to describe the structural characteristics of the target trajectory points in space, for path generation and pose calculation, and may include, but is not limited to, point spacing for controlling trajectory accuracy; distribution shape for judging whether it is closed-loop, unidirectional, spiral, etc.; surface normal angle for calculating the local surface slope and deriving the pose (Rx, Ry, Rz) of the end of the robotic arm by analyzing the spatial coordinate differences of adjacent points.

[0047] The above moving trajectory data may refer to a set of control data for driving the movement of the robotic arm, and generally includes: a three-dimensional position sequence [(X1, Y1, Z1),..., (Xn, Yn, Zn)]; an attitude angle sequence [(Rx1, Ry1, Rz1),...]; speed and acceleration settings for each path segment; residence time (t1,..., tn) of each point, and other trajectory parameters. It can be understood that the above moving trajectory data can generate a continuous and smooth path through an interpolation algorithm to ensure that the robotic arm performs accurate and natural cupping actions.

[0048] In a possible embodiment, the above cupping robotic arm moving trajectory generation system combines image recognition, depth measurement, and coordinate fitting, enabling automatic recognition of the target acupoint positions based on the images and depth data collected by the camera, accurately mapping them to the robotic arm coordinate system, and generating various types of cupping paths that meet individual characteristics and treatment requirements through trajectory planning and physiotherapy parameter adaptation, realizing intelligent control and personalized adjustment of the cupping actions of the robotic arm.

[0049] In the embodiments of the present invention, the first calibration data and the first depth information of at least one target acupoint are determined; through a coordinate fitting algorithm, the first calibration data and the first depth information are processed to obtain the second calibration data and the second depth information of the robotic arm; based on the second calibration data and the second depth information, target trajectory points are determined in the robotic arm coordinate axes; based on the preset physiotherapy requirements and the characteristic information of the target trajectory points, the moving trajectory data of the robotic arm is generated. By mapping the coordinates in the image data and converting them into the moving coordinates of the robotic arm according to the depth information and calibration data, high-precision conversion from image coordinates to robotic arm coordinates is achieved, adapting to various cupping techniques and improving the accuracy and personalization of physiotherapy.

[0050] Optionally, in the step of determining the first calibration data and the first depth information of at least one target acupoint, back image data can also be obtained; the back image data is subjected to acupoint matching and recognition through an acupoint recognition algorithm, and at least one target acupoint is determined in the back image data; based on a depth algorithm, positioning and measurement are performed on at least one target acupoint to obtain the first calibration data and the first depth information of at least one target acupoint.

[0051] In an embodiment of the present invention, the above-mentioned back image data may be an image of the human back area acquired by an image acquisition device, including two-dimensional visible light image data (RGB) and / or corresponding depth information (Depth Map), which can be used for target acupoint recognition and three-dimensional position reconstruction.

[0052] The above-mentioned acupoint recognition algorithm may be an algorithm module for recognizing the positions of acupoints in a human body image. Generally, it combines image processing and machine learning methods to achieve the matching of back structure analysis and a standard acupoint atlas.

[0053] The above-mentioned depth algorithm may be an algorithm for extracting corresponding spatial depth information from image pixel positions, usually used in RGB-D images or depth data obtained based on binocular vision, structured light, or ToF technology.

[0054] In a possible embodiment, after the above-mentioned cupping robotic arm movement trajectory generation system recognizes the key back structures, it aligns the standard acupoint atlas with the current image and maps the acupoints marked in the atlas to the corresponding positions in the user's image. Specifically, the alignment of the atlas and the image can be achieved through affine transformation, non-rigid matching, or neural network prediction, so as to construct three-dimensional points (x, y, z) based on the image coordinates (x, y) and depth information z.

[0055] Optionally, in the step of processing the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm, it further includes processing the first calibration data and the first depth information through a coordinate fitting algorithm to determine the mapping relationship between the coordinate axes corresponding to the back image data and the coordinate axes of the robotic arm; based on the mapping relationship, determining the second calibration data and the second depth information corresponding to the target acupoints mapped on the robotic arm in the coordinate axes of the robotic arm.

[0056] In an embodiment of the present invention, the above-mentioned mapping relationship may refer to a functional correspondence established between an image coordinate system (based on pixels) and a robotic arm coordinate system (based on spatial distances), which is used to accurately convert the acupoint points or path points recognized in the image into spatial coordinate points that the robotic arm can recognize and execute. Specifically, it can usually be obtained through multi-point calibration and mathematical modeling. For example, through a set of known corresponding point pairs of image coordinates and robotic arm coordinates, an interpolation, regression, or machine learning algorithm is used to train a function model capable of coordinate system conversion, and this mapping relationship is used as a coefficient to adjust the result after output mapping of the model.

[0057] In a possible embodiment, the above cupping robot arm movement trajectory generation system acquires the one-to-one correspondence between multiple image points and the spatial coordinates of the robot arm, uses a coordinate fitting algorithm to construct a mapping function model between the image coordinates and the robot arm coordinates, and after the user selects an acupoint, inputs its image position and depth information into the model to calculate the three-dimensional spatial position in the robot arm coordinate system, thereby realizing the conversion from the image space to the execution space.

[0058] Specifically, obtain multiple image points and their corresponding robot arm end position coordinates to form a set of calibration point pairs. For example, select 9 representative points (such as the center of the spine, left and right scapulas, waist, etc.) in the back image during shooting, record the coordinates (x, y) of these points in the image and the corresponding depth h at the same time, and obtain the coordinates (Xrobot, Yrobot, Zrobot) of the robot arm when actually contacting these points. Use a coordinate fitting algorithm (such as cubic polynomial regression, affine transformation, or neural network regression) to train or fit the data of these point pairs, establish a multivariable mapping model to describe the conversion rule between the image coordinates (combined with depth) and the robot arm coordinates, that is, generate a mapping relationship function. After the user selects an acupoint, input its image position and depth information into the model to calculate the three-dimensional spatial position in the robot arm coordinate system.

[0059] Through the above method steps, the robot arm can recognize image coordinates, accurately execute operations, adapt to actual environmental differences such as different user body shapes, shooting angles, and the positions of the camera and the robot arm, and improve the efficiency and stability of the cupping robot arm movement trajectory generation system in path generation.

[0060] Optionally, in the step of determining the target trajectory point in the robot arm coordinate axis based on the second calibration data and the second depth information, it further includes constructing spatial reference layer data of the robot arm coordinate axis according to at least one second calibration data and the second depth information; generating multiple trajectory points starting from the current reference space layer based on the preset trajectory type and depth data; generating the target trajectory point corresponding to the corresponding layer based on the multiple trajectory points and the layer number data.

[0061] In the embodiment of the present invention, the above spatial reference layer data may include, but is not limited to, depth data and layer number data, and the depth data corresponds to the layer number data. Specifically, it can be multiple spatial planes or levels divided along the Z axis of the robot arm with the target acupoint as the center. Each level serves as a reference plane for trajectory generation, has a specific spatial depth and number, and is used to realize the hierarchical construction and three-dimensional layout of the trajectory. For example, 3 layers are generated based on the depth data of 300 mm, and the Z values (depths) are 290, 300, and 310 mm respectively.

[0062] The above-mentioned preset trajectory types can be standard trajectory path forms for users to select, which determine the distribution of trajectory points in space. Specific types can include, but are not limited to, circular trajectories (generating trajectory points along the circumference of acupoints), spiral trajectories (rotating trajectories with gradually changing radii in the Z-axis direction), line segment trajectories (straight paths between the starting point and the ending point), custom trajectories (projecting the trajectories hand-drawn by users on the image into space), etc.

[0063] The above-mentioned trajectory points can refer to multiple three-dimensional space points generated along the preset trajectory types, representing the spatial pose points (position + attitude) of the end of the robotic arm during the execution of actions, and are the basic parameters for trajectory interpolation, attitude adjustment, and path execution.

[0064] The above-mentioned layer number data can refer to the parameters for numbering the spatial reference layers, used to identify the relative order of each layer during the trajectory generation process. The above-mentioned depth data can refer to the Z-axis coordinate values corresponding to each spatial reference layer or trajectory point, reflecting the actual depth position of the point in the vertical space.

[0065] In a possible embodiment, the above-mentioned cupping robotic arm movement trajectory generation system constructs multi-level spatial reference layer data centered on the second calibration data (Xrobot, Yrobot) and the second depth information (Zrobot) of the target acupoint. Among them, each layer represents a trajectory generation reference plane offset in the vertical space (Z-axis) direction. It should be noted that multiple depth levels (such as ±5mm, ±10mm) can be preset during the construction process to form a hierarchical structure, and a unique layer number data is assigned to each layer, and this structure is used as the spatial framework for trajectory generation. Then, according to the preset trajectory types selected by the user (such as spiral lines, circles, line segments, etc.), multiple two-dimensional or three-dimensional trajectory points are generated on a certain spatial reference layer (such as layer L0), and according to the cupping requirements or to achieve dynamic path changes, combined with the generated trajectory points and the layer number data of the reference layer, the trajectory is copied, transformed, or extended to other spatial levels (such as L1, L2) to form a complete set of target trajectory points with hierarchy, which is used to control the robotic arm to perform cupping operations along multiple paths in the three-dimensional space.

[0066] Optionally, in the step of generating the movement trajectory data of the robotic arm based on the preset physiotherapy requirements and the characteristic information of the target trajectory points, it further includes determining the physiotherapy parameters based on the preset physiotherapy requirements; determining the characteristic information of the target trajectory points in the coordinate axes of the robotic arm; and generating the movement trajectory data of the robotic arm based on the physiotherapy parameters and the characteristic information.

[0067] In an embodiment of the present invention, the above-mentioned physiotherapy parameters may refer to cupping operation related parameters selected or preset by the user, reflecting the physiotherapy purpose and personalized treatment needs. Specifically, they may include but are not limited to cupping duration, cupping technique, and cupping negative pressure intensity, etc., parameters used to constrain the dynamic attributes of the trajectory.

[0068] The above-mentioned feature information may refer to auxiliary information with geometric or spatial meaning extracted from the target trajectory point set, which is used to assist in determining the path generation method, movement behavior and posture adjustment. Specifically, it may include but is not limited to point spacing, distribution shape, surface normal angle, etc., which are used to intelligently determine which trajectory areas should slide slowly, which should jump quickly, and which areas should adjust their posture, so as to make the execution path fit the skin better and enhance the treatment experience.

[0069] In a possible embodiment, when the user selects the "cupping + circular trajectory + 60 seconds + -35KPa" hot cupping solution, the cupping robot arm movement trajectory generation system will read the preset circular trajectory points (a total of 16), analyze the small spacing between the trajectory points (3mm per step), determine that slow continuous path interpolation is required, and detect that the surface of the area is inclined by about 15°, and the end effector Rx angle needs to be tilted inward by 10°, generate complete path data including position + posture + speed + time control, and drive the robot arm to operate according to the physical therapy strategy.

[0070] Optionally, in the step of generating the movement trajectory data of the robot arm based on the physical therapy parameters and feature information, it also includes interpolating the target trajectory points according to the feature information to generate a continuous spatial path; determining the moving speed, acceleration and dwell time of each spatial path based on the physical therapy parameters; and determining the posture angle of the end of the robot arm at each target trajectory point according to the surface normal angle corresponding to each spatial path.

[0071] In the embodiment of the present invention, the above-mentioned spatial path may refer to the trajectory line that the end effector of the robot arm should continuously move in three-dimensional space, that is, the trajectory route that the robot arm drives the cup body to move in space. Specifically, each path point is a three-dimensional coordinate (X, Y, Z), and the overall description of the spatial direction of the cupping movement can also be used for path planning of modules such as trajectory following, speed control, and posture control.

[0072] The above-mentioned attitude angle may refer to the orientation angle of the end effector of the robot arm (i.e., the tank interface) relative to the three-dimensional coordinate axis at each spatial path point, which is usually expressed in Euler angles, which are: Rx: rotation angle around the X axis (pitch angle); Ry: rotation angle around the Y axis (yaw angle); Rz: Rotation angle around the Z axis (roll angle).

[0073] The above posture angles can be used to ensure that the end of the robot arm can still fit, vertically, and evenly contact the cupping area under different skin surface curvatures. For example, if the normal direction of a path point is tilted inward by 15°, then Rx needs to be set to -15°, and the remaining angles are further calculated based on the surface morphology.

[0074] In a possible embodiment, when the user selects the "cupping + spiral trajectory + medium speed + 60 seconds" solution, the cupping robot arm movement trajectory generation system generates 12 basic trajectory points on the circular trajectory, detects that the point spacing is large, uses B-spline interpolation to supplement 36 intermediate points, forms a smooth spatial path, and divides 60 seconds into the path segments according to the cupping mode, sets the speed to 5mm / s, and the acceleration to 0.5mm / s². When the cupping robot arm movement trajectory generation system detects that the surface inclination angles on the path are 0°~20°, the posture angle (Rx, Ry) of each point is calculated, and the end of the robot arm is controlled to adjust the posture in real time to ensure that the cup body is always in contact with the skin surface, thereby enhancing the smoothness of the path execution and the rationality of the posture, and improving the comfort and effect of physical therapy.

[0075] like Figure 3 As shown, the embodiment of the present invention further provides a cupping robot arm movement trajectory generating device 300, and the cupping robot arm movement trajectory generating device 300 includes: A first determination module 301 is used to determine first calibration data and first depth information of at least one target acupuncture point; A first acquisition module 302 is used to process the first calibration data and the first depth information by a coordinate fitting algorithm to obtain second calibration data and second depth information of the robotic arm; A second determination module 303, configured to determine a target trajectory point in the robot arm coordinate axis based on the second calibration data and the second depth information; The first generating module 304 is used to generate movement trajectory data of the robot arm based on the preset physical therapy requirements and the characteristic information of the target trajectory point.

[0076] Optionally, the first determining module 301 includes: A first determination submodule, used to determine first calibration data and first depth information of at least one target acupuncture point; A fitting submodule, used to process the first calibration data and the first depth information by a coordinate fitting algorithm to obtain second calibration data and second depth information of the robotic arm; A second determination submodule, configured to determine a target trajectory point in the robot arm coordinate axis based on the second calibration data and the second depth information; A generation sub-module, configured to generate the movement trajectory data of the robotic arm based on a preset physiotherapy requirement and the feature information of the target trajectory points.

[0077] Optionally, the first acquisition module 302 includes: A third determination sub-module, configured to process the first calibration data and the first depth information through a coordinate fitting algorithm to determine the mapping relationship between the coordinate axes corresponding to the back image data and the coordinate axes of the robotic arm; A fourth determination sub-module, configured to determine the second calibration data and the second depth information corresponding to the target acupoints mapped on the robotic arm in the coordinate axes of the robotic arm based on the mapping relationship.

[0078] Optionally, the second determination module 303 includes: A first construction sub-module, configured to construct the spatial reference layer data of the coordinate axes of the robotic arm according to at least one of the second calibration data and the second depth information, where the spatial reference layer data includes depth data and layer data, and the depth data corresponds to the layer data; A first generation sub-module, configured to generate a plurality of trajectory points starting from the current reference space layer based on a preset trajectory type and the depth data; A second generation sub-module, configured to generate target trajectory points at the corresponding layers based on the plurality of trajectory points and the layer data.

[0079] Optionally, the first generation module 304 includes: A fifth determination sub-module, configured to determine physiotherapy parameters based on the preset physiotherapy requirement, where the physiotherapy parameters include cupping duration, cupping technique, and cupping negative pressure intensity; A sixth determination sub-module, configured to determine the feature information of the target trajectory points in the coordinate axes of the robotic arm, where the feature information includes point spacing, distribution shape, and surface normal angle; A seventh determination sub-module, configured to generate the movement trajectory data of the robotic arm based on the physiotherapy parameters and the feature information.

[0080] Optionally, the seventh determination sub-module includes: A calculation unit, configured to perform interpolation calculation on the target trajectory points according to the feature information to generate a continuous spatial path; A determination unit, configured to determine the movement speed, acceleration, and residence time of each segment of the spatial path based on the physiotherapy parameters; An attitude unit, configured to determine the attitude angle of the end of the robotic arm at each target trajectory point according to the surface normal angle corresponding to each segment of the spatial path.

[0081] Such as Figure 4As shown in the figure, an embodiment of the present invention further provides an electronic device 400, including a processor, and the above-mentioned processor can execute any one of the above-mentioned cupping robot arm movement trajectory generation methods.

[0082] Specifically, it includes a processor 401, a memory 402, and a computer program stored on the memory 402 and capable of running on the processor 401 to execute the cupping robot arm movement trajectory generation method, where: The processor 401 runs the calculator program of the cupping robot arm movement trajectory generation method stored in the memory 402 and executes the following steps: Determine the first calibration data and the first depth information of at least one target acupoint; Process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robot arm; Based on the second calibration data and the second depth information, determine the target trajectory points in the robot arm coordinate axis; Generate the movement trajectory data of the robot arm based on the preset physiotherapy requirements and the characteristic information of the target trajectory points.

[0083] Optionally, when the processor 401 executes the step of determining the first calibration data and the first depth information of at least one target acupoint, it includes: Obtain the back image data; Perform acupoint matching and recognition on the back image data through an acupoint recognition algorithm, and determine at least one target acupoint in the back image data; Based on the depth algorithm, perform positioning measurement on the at least one target acupoint to obtain the first calibration data and the first depth information of the at least one target acupoint.

[0084] Optionally, when the processor 401 executes the step of processing the first calibration data and the first depth information through a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robot arm, it includes: Process the first calibration data and the first depth information through a coordinate fitting algorithm to determine the mapping relationship between the coordinate axis corresponding to the back image data and the robot arm coordinate axis; Based on the mapping relationship, determine the second calibration data and the second depth information of the target acupoint mapped on the robot arm corresponding to the robot arm coordinate axis.

[0085] Optionally, when the processor 401 executes the step of determining the target trajectory points in the robot arm coordinate axis based on the second calibration data and the second depth information, it includes: Construct spatial reference layer data for the robotic arm coordinate axes based on at least one of the second calibration data and the second depth information, where the spatial reference layer data includes depth data and layer data, and the depth data corresponds to the layer data; Generate a plurality of trajectory points starting from the current reference spatial layer based on a preset trajectory type and the depth data; Generate target trajectory points at the corresponding layers based on the plurality of trajectory points and the layer data.

[0086] Optionally, the processor 401 executes generating the movement trajectory data of the robotic arm based on the preset physiotherapy requirements and the feature information of the target trajectory points, including: Determine physiotherapy parameters based on the preset physiotherapy requirements, where the physiotherapy parameters include cupping duration, cupping technique, and cupping negative pressure intensity; Determine the feature information of the target trajectory points in the robotic arm coordinate axes, where the feature information includes point spacing, distribution shape, and surface normal angle; Generate the movement trajectory data of the robotic arm based on the physiotherapy parameters and the feature information.

[0087] Optionally, the processor 401 further executes generating the movement trajectory data of the robotic arm based on the physiotherapy parameters and the feature information, and the method further includes: Perform interpolation calculation on the target trajectory points according to the feature information to generate a continuous spatial path; Determine the movement speed, acceleration, and dwell time of each segment of the spatial path based on the physiotherapy parameters; Determine the attitude angle of the robotic arm end at each target trajectory point according to the surface normal angle corresponding to each segment of the spatial path.

[0088] The embodiment of the present invention further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it realizes each process of the cupping robotic arm movement trajectory generation method or the application-side cupping robotic arm movement trajectory generation method provided by the embodiment of the present invention, and can achieve the same technical effect. To avoid repetition, it will not be elaborated here.

[0089] Those of ordinary skill in the art can understand that all or part of the processes of implementing the methods in the above embodiments can be completed by instructing relevant hardware through a computer program, and the program can be stored in a computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. The storage medium can be a magnetic disk, an optical disk, a read-only memory (ROM), or a random access memory (RAM), etc.

[0090] The above-disclosed content is only the preferred embodiment of the present invention. Of course, it cannot be used to limit the scope of the rights of the present invention. Therefore, equivalent changes made according to the claims of the present invention still fall within the scope covered by the present invention.

Claims

1. A method for generating the moving trajectory of a cupping manipulator, characterized in that, include: Determining first calibration data and first depth information of at least one target acupuncture point; Processing the first calibration data and the first depth information by means of a coordinate fitting algorithm to obtain second calibration data and second depth information of the robotic arm; Based on the second calibration data and the second depth information, determining a target trajectory point in the robot arm coordinate axis; Based on the preset physical therapy needs and the characteristic information of the target trajectory points, the movement trajectory data of the robotic arm is generated.

2. The method for generating the moving trajectory of the cupping manipulator according to claim 1, characterized in that, The determining of the first calibration data and the first depth information of at least one target acupuncture point comprises: Acquire back image data; Performing acupoint matching and identification on the back image data by using an acupoint identification algorithm, and determining at least one target acupoint in the back image data; Based on the depth algorithm, positioning measurement is performed on the at least one target acupuncture point to obtain first calibration data and first depth information of the at least one target acupuncture point.

3. The method for generating the moving trajectory of the cupping manipulator according to claim 1, characterized in that, The first calibration data and the first depth information are processed by a coordinate fitting algorithm to obtain the second calibration data and the second depth information of the robotic arm, including: Processing the first calibration data and the first depth information through a coordinate fitting algorithm to determine a mapping relationship between a coordinate axis corresponding to the back image data and a coordinate axis of the robotic arm; Based on the mapping relationship, the second calibration data and the second depth information of the target acupuncture point mapped on the robotic arm corresponding to the robotic arm coordinate axis are determined.

4. The method for generating the moving trajectory of the cupping manipulator according to claim 1, characterized in that, Determining a target trajectory point in the robot arm coordinate axis based on the second calibration data and the second depth information includes: Constructing spatial reference layer data of the robot arm coordinate axis according to at least one of the second calibration data and the second depth information, wherein the spatial reference layer data includes depth data and layer number data, and the depth data corresponds to the layer number data; Based on the preset trajectory type and depth data, starting from the current reference space layer, generating a plurality of trajectory points; Based on the multiple track points and the layer number data, target track points at corresponding layers are generated.

5. The method for generating the moving trajectory of the cupping manipulator according to claim 1, characterized in that, The generating of the movement trajectory data of the robot arm based on the preset physical therapy requirements and the characteristic information of the target trajectory point includes: Based on the preset physical therapy needs, determining physical therapy parameters, the physical therapy parameters including cupping duration, cupping technique, and cupping negative pressure intensity; Determine characteristic information of the target trajectory point in the robot arm coordinate axis, the characteristic information including point spacing, distribution shape, and surface normal angle; Based on the therapy parameters and feature information, movement trajectory data of the robotic arm is generated.

6. The method for generating the moving trajectory of the cupping manipulator according to claim 5, characterized in that, The method further comprises: generating movement trajectory data of the robot arm based on the physical therapy parameters and the characteristic information; According to the feature information, interpolation calculation is performed on the target trajectory points to generate a continuous spatial path; Based on the therapy parameters, determining the moving speed, acceleration and dwell time of each spatial path; According to the surface normal angle corresponding to each segment of the space path, the posture angle of the end of the robot arm at each target trajectory point is determined.

7. A generating device for the moving trajectory of a cupping manipulator, characterized in that, include: A first determination module, used to determine first calibration data and first depth information of at least one target acupuncture point; A first acquisition module, configured to process the first calibration data and the first depth information through a coordinate fitting algorithm to obtain second calibration data and second depth information of the robotic arm; A second determination module, configured to determine target trajectory points in the robotic arm coordinate axes based on the second calibration data and the second depth information; A first generation module, configured to generate robotic arm movement trajectory data based on a preset physiotherapy requirement and feature information of the target trajectory points.

8. A cupping manipulator movement trajectory generation system, characterized in that, The cupping robotic arm movement trajectory generation system includes: a cupping robotic arm movement trajectory generation device; The cupping robotic arm movement trajectory generation device implements the cupping robotic arm movement trajectory generation method according to claim 1.

9. An electronic device, characterized in that, Comprising: A memory, a processor, and a computer program stored on the memory and executable on the processor, where when the processor executes the computer program, the steps in the cupping robotic arm movement trajectory generation method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by the processor, the steps in the cupping robotic arm movement trajectory generation method according to any one of claims 1 to 6 are implemented.

Images