Cupping mechanical arm control method and electronic equipment thereof

Abstract

The embodiment of the invention provides a cupping mechanical arm control method and device. The cupping mechanical arm control method comprises the steps that position information of a plurality of target objects is obtained; determining state information under each piece of position information, wherein the state information comprises temperature information and manipulation information; generating multi-section path trajectory data based on the multiple pieces of adjacent position information; generating target path trajectory data based on the state information and the multi-section path trajectory data; and controlling the cupping mechanical arm to perform attitude control and motion execution based on the target path trajectory data. By means of the method, the customized execution track can be generated according to individual differentiation cupping requirements, and the intelligent control and personalized adjustment degree of the cupping mechanical arm is improved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control, and in particular to a cupping robot arm control method, device, electronic equipment and storage medium thereof. Background Art

[0002] With the development of robots and intelligent control technology, robotic arms have been introduced into physical therapy scenarios to realize automated cupping. Traditional Chinese medicine physical therapy methods are gradually evolving towards intelligence and automation. Cupping, as a common non-drug therapy, is widely used in scenarios such as muscle soreness and meridian conditioning.

[0003] However, existing cupping robot arm control methods usually perform fixed actions based on preset paths, lack fine control between different cupping areas, and are unable to perform dynamic adjustments based on the individual's physiological state (such as skin temperature and sensitivity). Summary of the invention

[0004] The embodiment of the present invention provides a cupping robot arm control method to solve the problems that the existing cupping robot arm control method usually performs fixed actions based on a preset path, lacks fine control between different cupping areas, and cannot be dynamically adjusted according to the individual's physiological state (such as skin temperature and sensitivity).

[0005] In a first aspect, an embodiment of the present invention provides a cupping robot arm control method, the method comprising the following steps: Get the location information of multiple target objects; Determine state information under each position information, wherein the state information includes temperature information and technique information; Based on the position information of the plurality of adjacent locations, a plurality of path trajectory data are generated; Generate target path trajectory data based on the state information and the multiple path trajectory data; Based on the target path trajectory data, the cupping robot arm is controlled to perform posture control and motion execution.

[0006] Optionally, obtaining location information of multiple target objects includes: The image acquisition module acquires the plurality of target objects to obtain image data of a plurality of target areas; The plurality of image data are respectively identified by a depth recognition algorithm to obtain position information of the plurality of target objects, wherein the position information includes depth information and plane information.

[0007] Optionally, determining the status information under each location information includes: By presetting a human acupuncture point model, each of the position information is identified to determine the standard temperature information and standard manipulation information corresponding to the position information; According to the historical operation data of the position information, feedback calculation is performed on the standard temperature information and the standard technique information to determine the state information under each position information.

[0008] Optionally, the generating of multiple path trajectory data based on the position information of multiple adjacent locations includes: Determine distance information between adjacent position information; Based on the distance information, determining the adjacent position information capable of trajectory construction; A plurality of path trajectory data are generated based on the adjacent position information capable of trajectory construction.

[0009] Optionally, the generating target path trajectory data based on the state information and the multiple path trajectory data includes: Determine, from among the multiple segments of path trajectory data, at least one first path trajectory data with the smallest state information adjustment; Calculate the distances between multiple first path trajectory data by interpolation method to determine the shortest distance between two first path trajectory data; Determining second path trajectory data based on the shortest distance between the two first path trajectory data; The plurality of second path trajectory data are connected and constructed to generate target path trajectory data.

[0010] Optionally, controlling the cupping robot arm to perform posture control and motion execution based on the target path trajectory data includes: Determine the status information and position information of each track point in the target path track data; Based on the state information and position information of each trajectory point, the cupping robot arm is angle controlled and plane moved.

[0011] Optionally, based on the target path trajectory data, controlling the cupping robot arm to perform posture control and motion execution, the method includes: During the angle control and plane movement process, the rotational torque of the cupping robot arm is detected by a six-dimensional force sensor to determine the current rotational torque of the cupping robot arm; The cupping robot arm is adjusted in angle control and plane movement by the current rotation torque of the cupping robot arm.

[0012] In a second aspect, an embodiment of the present invention further provides a cupping robot arm control device, the cupping robot arm control device comprising: A first acquisition module is used to acquire location information of multiple target objects; A first determination module, used to determine the state information under each position information, wherein the state information includes temperature information and technique information; A first generating module, used for generating a plurality of path trajectory data based on a plurality of adjacent position information; A second generating module, configured to generate target path trajectory data based on the state information and the plurality of path trajectory data; The first control module is used to control the cupping robot arm to perform posture control and motion execution based on the target path trajectory data.

[0013] In a third aspect, an embodiment of 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, wherein when the processor executes the computer program, the steps in the cupping robot arm control method provided in an embodiment of the present invention are implemented.

[0014] In a fourth aspect, an embodiment of the present invention provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the steps in the cupping robot arm control method provided in the embodiment of the invention are implemented.

[0015] In an embodiment of the present invention, the position information of multiple target objects is obtained; the state information under each position information is determined, and the state information includes temperature information and technique information; based on the multiple adjacent position information, multiple path trajectory data are generated; based on the state information and the multiple path trajectory data, target path trajectory data is generated; based on the target path trajectory data, the cupping robot arm is controlled to perform posture control and motion execution. Through the above method, a customized execution trajectory can be generated according to the individual differentiated cupping needs, and the intelligent control and personalized adjustment degree of the cupping robot arm can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0017] Figure 1 is a flow chart of a cupping robot arm control method provided by an embodiment of the present invention; Figure 2 is a structural schematic diagram of another cupping robot arm control device provided in an embodiment of the present invention; Figure 3 It is a structural schematic diagram of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0018] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments 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 creative work are within the scope of protection of the present invention.

[0019] like Figure 1 As shown, Figure 1 1 is a flow chart of a cupping robot arm control method provided by an embodiment of the present invention, and the cupping robot arm control method comprises the steps of: 101. Obtain location information of multiple target objects.

[0020] In an embodiment of the present invention, the above-mentioned cupping robot arm control method can be applied to a cupping robot arm control platform. The above-mentioned cupping robot arm control platform has functions such as cupping robot arm data processing, cupping robot arm data transmission and reception, and cupping robot arm data memory storage, and can be constructed based on a server or a server cluster. The above-mentioned server or server cluster can be an electronic device with cupping robot arm data processing capabilities.

[0021] The above-mentioned target objects can be multiple treatment areas on the human body surface suitable for cupping operations, such as shoulders, back, waist, legs and other areas with concentrated acupoints or muscle tension. Generally speaking, the above-mentioned target objects can be identified and obtained through the corresponding camera module of the above-mentioned cupping robot arm control platform, and can also be obtained by pre-setting or manual selection by the user.

[0022] The above-mentioned position information may be the spatial position information corresponding to each target object, which is used to guide the end effector of the cupping robot arm to perform precise positioning and path planning. Specifically, it may include but is not limited to pixel coordinates in the image coordinate system (such as the position of the target area captured by the image acquisition device), or three-dimensional spatial coordinates (x, y, z) in the robot arm working coordinate system after coordinate conversion.

[0023] In a possible embodiment, the above-mentioned cupping robot arm control platform can obtain an image of the area to be operated through an image acquisition device (such as an RGB camera or an infrared thermal imager), identify multiple cupping target areas in the image through a target detection algorithm, and extract their corresponding image coordinates. It can also manually click or frame the cupping position on the displayed area image to automatically record its pixel coordinates. It can also map the image coordinates to the working coordinate system of the robot arm by combining the image calibration point information, thereby obtaining spatial position information suitable for robot arm control.

[0024] 102. Determine status information under each location information.

[0025] In an embodiment of the present invention, the above-mentioned state information may include but is not limited to any treatment parameter information associated with each target cupping position, such as temperature information and technique information, and may be used to guide the robotic arm to perform appropriate cupping operation techniques at that position.

[0026] The above temperature information may refer to the current temperature value of the skin surface at that location, which is used to determine whether it is necessary to increase the temperature for cupping or to avoid continuous pressure on high temperature areas. Specifically, the above temperature information may be obtained through thermal imaging equipment, infrared temperature sensors or multi-point patch thermometers.

[0027] The above-mentioned technique information may be the cupping operation method recommended for use at the location, such as "fixed-point cupping", "moving cupping", "gentle cupping", "quick cupping", etc., usually including parameters such as trajectory type, dwell time, and pressure application method.

[0028] It is understandable that the status information and temperature information of different target objects, combined with different technique information, can meet the treatment needs of the target objects, that is, the matching relationship between temperature information and technique information can be adjusted according to specific medical needs.

[0029] In a possible embodiment, the cupping robot arm control platform collects temperature information of the target object through a camera module, and according to the preset cupping technique template of the current target object or manually selected technique information, it can also combine historical cupping data or body part templates to automatically match the corresponding cupping technique strategy based on position information. For example, the shoulder area gives priority to using "walking cupping", and the waist area gives priority to using "fixed-point cupping", and combines somatosensory feedback or physiological parameters (such as skin resistance, muscle tension) to infer the cupping intensity and method that is more suitable for the position.

[0030] 103. Generate multiple path trajectory data based on multiple adjacent position information.

[0031] In an embodiment of the present invention, the adjacent position information may be a plurality of target points that are close in space and can continuously perform cupping operations. Whether the target positions are adjacent is usually determined by setting a preset distance threshold. For example, when the Euclidean distance between any two target points is less than a set cupping continuity threshold (such as 20 mm), the cupping robot arm control platform determines them as adjacent point pairs, and divides and generates corresponding path segments accordingly.

[0032] The above-mentioned path trajectory data can be the spatial movement trajectory information generated between multiple adjacent target points, usually composed of several trajectory points, each trajectory point contains at least one three-dimensional spatial coordinate (x, y, z), and optional posture angle information (such as Rx, Ry, Rz) or execution parameters (such as moving speed, downward force). The above-mentioned path trajectory data can be used to control the smooth movement of the end effector of the robotic arm between each point to achieve the coherent execution of the cupping action.

[0033] In a possible embodiment, the cupping robot arm control platform determines the Euclidean distance between multiple position information, determines the position information with the shortest distance or the most suitable cupping movement path, generates corresponding adjacent point pairs, constructs corresponding path segments, and connects the component path trajectory data of multiple path segments. It can automatically identify the cupping area and obtain key status information, thereby realizing personalized generation of the path.

[0034] 104. Generate target path trajectory data based on the state information and the multiple path trajectory data.

[0035] In an embodiment of the present invention, the target path trajectory data may refer to a complete execution trajectory generated after dynamic adjustment and fusion processing based on multiple initial path segments in combination with the cupping state information (such as temperature, cupping method, expected pressure, etc.) corresponding to each segment. The target path trajectory data may include a sequence of spatial trajectory points (x, y, z), and may also include execution parameters such as the attitude angle (Rx, Ry, Rz), speed, dwell time, and pressure threshold of each trajectory point, which are used to guide the robotic arm to implement the corresponding cupping strategy, such as how much Newton force to use for adsorption under the current position information on the current target object.

[0036] In a possible embodiment, the cupping robot arm control platform traverses each segment of path trajectory data, reads the status information corresponding to the segment, sets the execution speed, acceleration or dwell time of the path point in the segment according to the cupping method (such as "gentle cupping" or "cupping and dwelling"), and determines the skin sensitivity according to the temperature information. If the temperature is too high, the pressure of the segment is reduced or the contact time is reduced, and a posture transition segment is added between the path segments to achieve smooth switching of the posture angles. The adjusted segments of trajectory data are merged in sequence to form the final target path trajectory data.

[0037] By generating target path trajectory data through the above method, the robotic arm can adapt to different skin conditions and cupping requirements during operation, thereby improving the accuracy and comfort of the robotic arm in performing cupping actions.

[0038] 105. Based on the target path trajectory data, control the cupping robot arm to perform posture control and motion execution.

[0039] In an embodiment of the present invention, the above-mentioned posture control can be to control the angle or direction of the end effector of the robotic arm (such as the cupping head) in three-dimensional space to ensure that the orientation of the cupping tool at different trajectory points is in contact with, aligned with, or maintains a specified inclination angle with the target skin surface. The above-mentioned posture can usually be composed of rotation angles around the x, y, and z axes (i.e., Rx, Ry, Rz), which can be expressed by Euler angles or quaternions. It can be understood that the above-mentioned posture control can achieve differentiated action styles of various cupping methods, such as "tilted cupping" and "rotating cupping", etc., and can also affect the posture changes of the cup body by controlling the rotation of the forearm and upper arm of the cupping robotic arm.

[0040] The above-mentioned motion execution may refer to the process of controlling the end of the robotic arm to move sequentially in three-dimensional space according to the position coordinates (x, y, z) of the target path trajectory points, or it may refer to the process of controlling the movable parts such as the forearm and the upper arm of the cupping robotic arm to perform the same rotation, movement and other posture changes.

[0041] In a possible embodiment, the above-mentioned cupping robot arm control platform buffers the target path trajectory data in segments through the control module, and extracts the corresponding position information for each trajectory point for path movement control, and extracts the posture information for posture solution, and synchronously schedules the joint control instructions of displacement and angle through the controller to ensure that the end tool of the robot arm smoothly executes the path action with the target posture.

[0042] In another possible embodiment, the real-time feedback of the six-dimensional force sensor can be combined to fine-tune the position or posture deviation during the execution process to achieve smooth control. Specifically, during the cupping process, the built-in force control trajectory function of the robotic arm can be used to generate complete trajectory points, which are then sent to the robotic arm in segments. The robotic arm moves along the path according to the trajectory points to perform cupping. A six-dimensional force sensor is installed at the end of the robotic arm, which can sense the forces in the x, y, and z directions, and the three rotational torques of Rx\Ry\Rz. The robotic arm dynamically adjusts the posture and downward pressure of the robotic arm according to the dynamic data of the six-dimensional force sensor.

[0043] Through the above-mentioned posture control and motion execution process, cupping can be performed along the target path in conformity with the user's body surface, thereby improving the operation quality and user experience of cupping.

[0044] In an embodiment of the present invention, the position information of multiple target objects is obtained; the state information under each position information is determined, and the state information includes temperature information and technique information; based on multiple adjacent position information, multiple path trajectory data are generated; based on the state information and the multiple path trajectory data, target path trajectory data is generated; based on the target path trajectory data, the cupping robot arm is controlled to perform posture control and motion execution. Through the above method, a customized execution trajectory can be generated according to the individual differentiated cupping needs, and the intelligent control and personalized adjustment degree of the cupping robot arm can be improved.

[0045] Optionally, in the step of obtaining the position information of multiple target objects, the multiple target objects can be captured through an image acquisition module to obtain image data of multiple target areas; the multiple image data can be recognized separately through a depth recognition algorithm to obtain the position information of multiple target objects.

[0046] In an embodiment of the present invention, the above-mentioned image acquisition module may include but is not limited to an image sensor component installed on the robotic arm body or the operating platform, such as an RGB camera, an RGB-D depth camera, a structured light camera or a ToF (Time-of-Flight) sensor, etc. Its function is to collect image or video information of the target object, and can also output a single-frame image or an image sequence for subsequent analysis.

[0047] The above-mentioned image data may refer to the image information collected by the above-mentioned image acquisition module at a certain point in time, including but not limited to two-dimensional images (color images, grayscale images) and / or three-dimensional image data. The above-mentioned three-dimensional image data may include but not limited to the spatial coordinates or depth values ​​of each pixel point, forming an image description with a spatial structure.

[0048] In a possible embodiment, the cupping robot arm control platform can obtain image data of the target object at a predetermined time point (such as before user operation or before each execution) through the image acquisition module, which is used as input for subsequent image recognition and coordinate extraction.

[0049] The above-mentioned deep recognition algorithm can be any algorithm that can perform target recognition and spatial positioning on the above-mentioned image data, such as a convolutional neural network (CNN), a multi-scale segmentation network, a point cloud-based target recognition model, etc., which is used to detect multiple target object positions suitable for cupping operation in the image.

[0050] In a possible embodiment, the cupping robot arm control platform segments, detects or marks the location area of ​​the target object in the image data through a deep recognition algorithm, and extracts its coordinate information in the image or physical space. The recognition result can be in the form of multiple rectangular boxes, mask areas or three-dimensional point cloud cluster centers.

[0051] The above-mentioned position information may include but is not limited to depth information and plane information. The above-mentioned depth information may be the depth coordinate (distance in the Z-axis direction) corresponding to the target point in the image space, which can reflect the three-dimensional position of the target area relative to the camera and is used for subsequent spatial coordinate calculation and path planning. The above-mentioned plane information may be the coordinate position of the target point on the two-dimensional plane (x, y) of the image, which is usually expressed as pixel coordinates, position within the image frame or calibrated physical projection position.

[0052] Through the above method, the cupping robot arm control platform can realize automatic perception and position information extraction of the cupping target area, and provide high-precision initial input for the generation of personalized cupping paths.

[0053] Optionally, in the step of determining the status information under each position information, it also includes identifying each position information through a preset human acupuncture point model, and determining the standard temperature information and standard technique information under the corresponding position information; based on the historical operation data of the position information, feedback calculation is performed on the standard temperature information and the standard technique information to determine the status information under each position information.

[0054] In an embodiment of the present invention, the above-mentioned preset human acupoint model can be a set of digital human acupoint reference models constructed in advance based on human meridian theory and standard anatomical structure, which is used to assist in identifying cupping target areas and provide standard operating parameters.

[0055] The above-mentioned standard temperature information may refer to the skin surface temperature or the temperature parameter range inside the cup recommended for the acupuncture point or area during normal cupping operation, for example, "should be controlled between 38 and 42° C."

[0056] The above-mentioned standard technique information may refer to the cupping operation strategy commonly used for the acupoint, such as "leaving the cup at a fixed point for 5 minutes", "slowly moving the cup 3 times", "lifting operation", etc., which is used to guide the initial parameters of the personalized operation strategy.

[0057] The above historical operation data can be the specific parameters and feedback results of the cupping operation performed on the user or the position information, which are recorded long-term by the above cupping robot arm control platform, such as temperature setting value, actual execution time, user subjective comfort score, physiological response index, etc.

[0058] Specifically, the cupping robot arm control platform can perform feedback calculations through the historical operation data, that is, by comparing the difference between the historical actual data and the standard value, and using the average value, weighted adjustment, rule offset, or optimization method based on feedback learning, the standard temperature information and standard technique information are personalized and corrected, thereby determining the final state information under the current position information. This state information can be used for trajectory optimization and posture control in the path planning stage to ensure that the cupping operation complies with medical standards and fits the physiological differences of users.

[0059] In a possible embodiment, the cupping robot arm control platform acquires and optimizes the temperature information and technique information of the user's target object, i.e., the acupoints that need to be cupped, by integrating an image acquisition module, a preset human acupoint model, a depth recognition algorithm, a path trajectory generation and a feedback optimization module, thereby realizing intelligent management and personalized control of the entire process of the cupping operation.

[0060] Optionally, in the step of generating multi-segment path trajectory data based on multiple adjacent position information, it also includes determining distance information between adjacent position information; based on the distance information, determining adjacent position information that can be used to construct a trajectory; and generating multi-segment path trajectory data based on the adjacent position information that can be used to construct a trajectory.

[0061] In an embodiment of the present invention, the distance information may be the spatial geometric distance between two position information, which is usually calculated as a three-dimensional coordinate difference. Specifically, it can be calculated using the Euclidean distance formula to determine whether there is a possibility of constructing a continuous cupping path between two points. Generally speaking, it can also be a plurality of target points that are close in spatial position and can perform cupping operations continuously. It is usually determined whether the target positions are adjacent by setting a preset distance threshold. For example, when the Euclidean distance between any two target points is less than the set cupping continuity threshold (such as 20 mm), the cupping robot arm control platform determines it as an adjacent point pair, and divides and generates corresponding path segments accordingly.

[0062] When the distance information between two positions meets the construction requirements, several interpolation trajectory points can be generated between them to form a path segment for the robot to execute. Specifically, the above trajectory construction can use linear interpolation, cubic spline interpolation or Bezier curve algorithms to generate a trajectory point sequence, each point contains spatial position and optional posture, speed and other information More specifically, when multiple position information is determined to meet the continuous connection conditions, the cupping robot arm control platform will sequentially construct multiple continuous trajectory paths. On the contrary, if the distance between certain position information is too far or exceeds the set range, no trajectory will be generated between them, avoiding excessive spans or invalid paths during the execution of the robot arm.

[0063] Optionally, in the step of generating target path trajectory data based on state information and multiple path trajectory data, it also includes determining at least one first path trajectory data with the smallest state information adjustment in the multiple path trajectory data; calculating the distance between multiple first path trajectory data by interpolation method to determine the shortest distance between two first path trajectory data; determining second path trajectory data based on the shortest distance between the two first path trajectory data; and connecting and constructing multiple second path trajectory data to generate target path trajectory data.

[0064] In an embodiment of the present invention, the first path trajectory data with the minimum state information adjustment can be determined by minimizing the modification amount of the initial state parameters (such as standard temperature, default technique, etc.) during the fusion process of a certain path segment, that is, all path segments that meet the minimum state information adjustment condition are marked as the first path trajectory data, which has a high credibility and high adaptability path and is a core component of the target path construction.

[0065] In a possible embodiment, the transition trajectory between the first path trajectory data is estimated by using the spatial position between the trajectory endpoints and an interpolation method (such as linear interpolation, cubic spline interpolation, Bezier interpolation, etc.), and the length of the interpolation path is calculated. The path with the shortest distance after interpolation is selected as the preferred connection path and used as the second path trajectory data to connect the completion path of multiple main path segments. The multiple second path trajectory data are connected between the multiple first path trajectory data, and all the path segments are spliced ​​in the execution order to form a complete target path trajectory data for execution by the robotic arm control system.

[0066] Optionally, the step of controlling the cupping robot arm to perform posture control and motion execution based on the target path trajectory data also includes determining the state information and position information of each trajectory point in the target path trajectory data; and performing angle control and plane movement of the cupping robot arm based on the state information and position information of each trajectory point.

[0067] In an embodiment of the present invention, the state information and position information of each trajectory point are extracted from the above-mentioned target path trajectory data, such as the cupping operation parameters that should be met when the trajectory point is executed, including pressure intensity, expected temperature, cupping technique type (such as static cupping, walking cupping, lifting), etc., as well as the coordinate value (x, y, z) of the trajectory point in three-dimensional space, which is used to guide the end of the robotic arm to reach a precise position.

[0068] The above angle control may mean that the system controls the end tool of the robot arm to adjust the posture around each coordinate axis in space (i.e., adjust Rx, Ry, Rz) according to the cupping method or required posture in the status information. For example, for the "lifting" cupping trajectory point, the system will realize the rise and fall rotation of the cupping head by setting a periodic lifting angle.

[0069] The above-mentioned plane movement may refer to controlling the robot arm to move continuously along the target path on the horizontal plane according to the coordinate values ​​of the x-axis and the y-axis in the position information, so as to ensure that the tank slides or is fixed above the target area.

[0070] In a possible embodiment, the cupping robot arm control platform analyzes the trajectory point sequence into a continuous motion path of the end of the robot arm in real time according to the trajectory tracking algorithm, and executes the displacement and angle instructions of each trajectory point in segments, thereby achieving a stable, smooth and differentiated cupping action, which can improve the personalization and spatial accuracy of the cupping operation, and improve the response flexibility and therapeutic effect of the cupping robot arm.

[0071] Optionally, in the step of controlling the cupping robot arm to perform posture control and motion execution based on the target path trajectory data, the step also includes detecting the rotational torque of the cupping robot arm through a six-dimensional force sensor during the angle control and plane movement process to determine the current rotational torque of the cupping robot arm; and adjusting the angle control and plane movement of the cupping robot arm through the current rotational torque of the cupping robot arm.

[0072] In an embodiment of the present invention, the above-mentioned six-dimensional force sensor is a sensing device that can simultaneously sense linear forces in three directions (Fx, Fy, Fz) and rotational torques in three directions (Mx, My, Mz), and can be used to determine the contact state and mechanical relationship between the end and the external object.

[0073] The rotation torque can be the force state of the end of the cupping robot arm around any rotation axis (such as around the z-axis), reflecting the rotation torque deviation caused by skin resistance, posture mismatch or external interference during the cupping operation. By continuously monitoring the current rotation torque, it can be inferred whether the posture of the cupping head at the current trajectory point deviates from the expected one.

[0074] like Figure 2 As shown, the embodiment of the present invention further provides a cupping robot arm control device 200, and the cupping robot arm control device 200 includes: A first acquisition module 201 is used to acquire location information of multiple target objects; A first determination module 202, used to determine state information under each position information, wherein the state information includes temperature information and technique information; A first generating module 202, configured to generate a plurality of path trajectory data segments based on a plurality of adjacent position information; A second generating module 204, configured to generate target path trajectory data based on the state information and the plurality of path trajectory data; The first control module 205 is used to control the cupping robot arm to perform posture control and motion execution based on the target path trajectory data.

[0075] Optionally, the first acquisition module 201 includes: A collection submodule, used for collecting images of the plurality of target objects through an image collection module to obtain image data of a plurality of target areas; The recognition submodule is used to respectively recognize the plurality of image data by a depth recognition algorithm to obtain position information of the plurality of target objects, wherein the position information includes depth information and plane information.

[0076] Optionally, the first determining module 202 includes: The first determination submodule is used to identify each of the position information by presetting a human acupuncture point model, and determine the standard temperature information and standard manipulation information corresponding to the position information; The second determination submodule is used to perform feedback calculation on the standard temperature information and the standard technique information according to the historical operation data of the position information, so as to determine the state information under each position information.

[0077] Optionally, the first generating module 202 includes: A third determining submodule is used to determine distance information between adjacent position information; A fourth determination submodule, configured to determine, based on the distance information, the adjacent position information capable of performing trajectory construction; The generating submodule is used to generate multiple path trajectory data according to the adjacent position information capable of trajectory construction.

[0078] Optionally, the second generating module 204 includes: A fifth determining submodule, configured to determine, from among the multiple segments of path trajectory data, at least one first path trajectory data having the smallest state information adjustment; a sixth determination submodule, configured to calculate the distances between a plurality of first path trajectory data by interpolation method, and determine the shortest distance between two first path trajectory data; a seventh determination submodule, configured to determine the second path trajectory data based on the shortest distance between the two first path trajectory data; The eighth determination submodule is used to connect and construct the plurality of second path trajectory data to generate target path trajectory data.

[0079] Optionally, the first control module 205 includes: A ninth determination submodule, configured to determine the state information and position information of each track point in the target path track data; The control submodule is used to perform angle control and plane movement of the cupping robot arm based on the state information and position information of each trajectory point.

[0080] Optionally, the control submodule further includes: A determination unit, used to detect the rotational torque of the cupping robot arm through a six-dimensional force sensor during the angle control and plane movement process, and determine the current rotational torque of the cupping robot arm; A control unit is used to adjust the angle and plane movement of the cupping robot arm according to the current rotation torque of the cupping robot arm. like Figure 3 As shown, an embodiment of the present invention further provides an electronic device 300, including a processor, and the processor can execute any one of the above-mentioned cupping robot arm control methods.

[0081] Specifically, it includes a processor 301 and a memory 302, and a computer program for executing the cupping robot arm control method which is stored in the memory 302 and can be run on the processor 301, wherein: The processor 301 runs the computer program of the cupping robot arm control method stored in the memory 302 and performs the following steps: Get the location information of multiple target objects; Determine state information under each position information, wherein the state information includes temperature information and technique information; Based on the position information of the plurality of adjacent locations, a plurality of path trajectory data are generated; Generate target path trajectory data based on the state information and the multiple path trajectory data; Based on the target path trajectory data, the cupping robot arm is controlled to perform posture control and motion execution.

[0082] Optionally, the processor 301 executes the acquiring of location information of multiple target objects, including: The image acquisition module acquires the plurality of target objects to obtain image data of a plurality of target areas; The plurality of image data are respectively identified by a depth recognition algorithm to obtain position information of the plurality of target objects, wherein the position information includes depth information and plane information.

[0083] Optionally, the processor 301 executes the determining of the state information under each position information, including: By presetting a human acupuncture point model, each of the position information is identified to determine the standard temperature information and standard manipulation information corresponding to the position information; According to the historical operation data of the position information, feedback calculation is performed on the standard temperature information and the standard technique information to determine the state information under each position information.

[0084] Optionally, the processor 301 executes the step of generating a plurality of path trajectory data based on the position information of the plurality of adjacent paths, including: Determine distance information between adjacent position information; Based on the distance information, determining the adjacent position information capable of trajectory construction; A plurality of path trajectory data are generated based on the adjacent position information capable of trajectory construction.

[0085] Optionally, the processor 301 executes the step of generating target path trajectory data based on the state information and the multiple path trajectory data, including: Determine, from among the multiple segments of path trajectory data, at least one first path trajectory data with the smallest state information adjustment; Calculate the distances between multiple first path trajectory data by interpolation method to determine the shortest distance between two first path trajectory data; Determining second path trajectory data based on the shortest distance between the two first path trajectory data; The plurality of second path trajectory data are connected and constructed to generate target path trajectory data.

[0086] Optionally, the processor 301 further executes the control of the cupping robot arm to perform posture control and motion execution based on the target path trajectory data, including: Determine the status information and position information of each track point in the target path track data; Based on the state information and position information of each trajectory point, the cupping robot arm is angle controlled and plane moved.

[0087] Optionally, the processor 301 further executes the method of controlling the cupping robot arm to perform posture control and motion execution based on the target path trajectory data, and the method includes: During the angle control and plane movement process, the rotational torque of the cupping robot arm is detected by a six-dimensional force sensor to determine the current rotational torque of the cupping robot arm; The cupping robot arm is adjusted in angle control and plane movement by the current rotation torque of the cupping robot arm.

[0088] An 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, the various processes of the cupping robot arm control method or the application-end cupping robot arm control method provided in the embodiment of the present invention are implemented, and the same technical effect can be achieved. To avoid repetition, it will not be repeated here.

[0089] Those skilled in the art can understand that the implementation of all or part of the processes in the above-mentioned embodiments can be completed by instructing the relevant hardware through a computer program, and 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-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM).

[0090] The above disclosure is only the preferred embodiment of the present invention, which certainly cannot be used to limit the scope of the present invention. Therefore, equivalent changes made according to the claims of the present invention are still within the scope of the present invention.

Claims

1. A cupping robot arm control method, characterized in that: include: Get the location information of multiple target objects; Determine state information under each position information, wherein the state information includes temperature information and technique information; Based on the position information of the plurality of adjacent locations, a plurality of path trajectory data are generated; Generate target path trajectory data based on the state information and the multiple path trajectory data; Based on the target path trajectory data, the cupping robot arm is controlled to perform posture control and motion execution.

2. The cupping robot arm control method according to claim 1, characterized in that: The obtaining of location information of multiple target objects includes: The image acquisition module acquires the plurality of target objects to obtain image data of a plurality of target areas; The plurality of image data are respectively identified by a depth recognition algorithm to obtain position information of the plurality of target objects, wherein the position information includes depth information and plane information.

3. The cupping robot arm control method according to claim 1, characterized in that: The determining of the state information under each position information includes: By presetting a human acupuncture point model, each of the position information is identified to determine the standard temperature information and standard manipulation information corresponding to the position information; According to the historical operation data of the position information, feedback calculation is performed on the standard temperature information and the standard technique information to determine the state information under each position information.

4. The cupping robot arm control method according to claim 1, characterized in that: The generating of multiple path trajectory data based on the position information of the plurality of adjacent paths includes: Determine distance information between adjacent position information; Based on the distance information, determining the adjacent position information capable of trajectory construction; A plurality of path trajectory data are generated based on the adjacent position information capable of trajectory construction.

5. The cupping robot arm control method according to claims 2-4, characterized in that: The generating target path trajectory data based on the state information and the plurality of path trajectory data comprises: Determine, from among the multiple segments of path trajectory data, at least one first path trajectory data with the smallest state information adjustment; Calculate the distances between multiple first path trajectory data by interpolation method to determine the shortest distance between two first path trajectory data; Determining second path trajectory data based on the shortest distance between the two first path trajectory data; The plurality of second path trajectory data are connected and constructed to generate target path trajectory data.

6. The cupping robot arm control method according to claim 1, characterized in that: The method of controlling the cupping robot arm to perform posture control and motion execution based on the target path trajectory data includes: Determine the status information and position information of each track point in the target path track data; Based on the state information and position information of each trajectory point, the cupping robot arm is angle controlled and plane moved.

7. The cupping robot arm control method according to claim 6, characterized in that: Based on the target path trajectory data, controlling the cupping robot arm to perform posture control and motion execution, the method comprises: During the angle control and plane movement process, the rotational torque of the cupping robot arm is detected by a six-dimensional force sensor to determine the current rotational torque of the cupping robot arm; The cupping robot arm is adjusted in angle control and plane movement by the current rotation torque of the cupping robot arm.

8. A cupping robot arm control device, characterized in that: include: A first acquisition module is used to acquire location information of multiple target objects; A first determination module, used to determine the state information under each position information, wherein the state information includes temperature information and technique information; A first generating module, used for generating a plurality of path trajectory data based on a plurality of adjacent position information; A second generating module, configured to generate target path trajectory data based on the state information and the plurality of path trajectory data; The first control module is used to control the cupping robot arm to perform posture control and motion execution based on the target path trajectory data.

9. An electronic device, characterized in that: include: A memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps in the cupping robot arm control method as claimed in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in the cupping robot arm control method according to any one of claims 1 to 7 are implemented.

Images