Massage robot control method and system, medium, program product and terminal

Abstract

The invention provides a massage robot control method and system, a medium, a program product and a terminal. Through a massage robot control algorithm of global active planning and local passive planning, personalized, accurate, safe and effective massage treatment is realized. A massage path and a target area are defined by global active planning, and the overall massage direction and range are determined. Passive planning is adopted locally, and the robot adjusts in real time according to feedback and physical conditions of a patient. The self-adaptive technology is adopted, massage parameters and force are adjusted in real time, and the optimal massage effect is ensured. Compared with a traditional massage robot, the treatment precision and safety are improved, and the safety risk caused by the fact that the robot is not suitable for individual differences is reduced. Meanwhile, through application of the self-adaptive technology, the massage effect is balanced and optimized, and the technical defects that an existing massage robot achieves accurate control and adapts to the body types and muscle tissue characteristics of different patients are overcome.

Description

Technical Field

[0001] The present application relates to the field of massage equipment, and in particular to a massage robot control method, system, medium, program product and terminal. Background Art

[0002] As a traditional treatment method, Chinese massage therapy is widely used to relieve chronic pain, promote rehabilitation and improve physical health. With the advancement of technology, massage robots have emerged as an important tool to reduce the workload of massage physicians. Compared with traditional single-arm massage robots, dual-arm massage robots have higher massage efficiency and can use dual arms to coordinate more complex massage techniques, thereby better meeting the needs of patients. However, current massage robots still face many technical challenges in practical applications.

[0003] First of all, the working environment of the massage robot is complex and needs to be in close contact with the human body, which places extremely high demands on the safety and reliability of the system. In the actual massage process, there are significant differences in the patient's body height, body shape and muscle tissue stiffness, which makes it difficult for the massage robot to apply force and control position. The pressure changes of the massage head in different parts (such as the back, buttocks and legs) may lead to uneven massage effects and even cause discomfort or harm to the patient. Secondly, due to differences in patient body shape, a single massage strategy is difficult to adapt to the needs of all patients. The muscle tissue characteristics of different patients and their performance differences in different parts require the massage robot to make real-time adjustments during operation, which places higher requirements on the flexibility and accuracy of its control system.

[0004] In summary, although massage robots have shown broad application prospects in the field of traditional Chinese medicine massage, further research and optimization are still needed in terms of system safety, control accuracy and personalized treatment to ensure their effectiveness and reliability in practical applications. Summary of the invention

[0005] In view of the shortcomings of the prior art mentioned above, the purpose of the present application is to provide a massage robot control method, system, medium, program product and terminal, which are used to solve the problems that the existing massage robots have obvious technical defects in achieving precise control and adapting to the body shapes and muscle tissue characteristics of different patients, resulting in uneven massage effects and potential safety risks.

[0006] To achieve the above-mentioned purpose and other related purposes, the first aspect of the present application provides a method for controlling a massage robot, comprising: collecting image data of a subject, and constructing a three-dimensional model of the subject environment based on the image data to generate an environmental model; locating acupoints of the subject based on the image data to generate acupoint coordinate information included in the massage task to be performed; generating a three-dimensional coordinate of a starting point and a three-dimensional coordinate of a target point according to a preset massage strategy and acupoint coordinate information; using a preset path search algorithm, searching in the environmental model for a path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point to generate a global optimal path; performing the massage task according to the global optimal path, and performing local optimization operations and adaptive admittance compliance control operations during the massage process through the collected real-time feedback data until the massage task is completed.

[0007] In some embodiments of the first aspect of the present application, a preset path search algorithm is used to search for a path connecting the three-dimensional coordinates of a starting point and the three-dimensional coordinates of a target point in the environment model to generate a global optimal path, including: constructing a forward search tree and a reverse search tree based on the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point; and performing multiple rounds of node expansion iterative operations based on the forward search tree and the reverse search tree to generate a global optimal path.

[0008] In some embodiments of the first aspect of the present application, the process of the node expansion iterative operation includes: randomly selecting a direction for executing node expansion from the forward search tree and the reverse search tree; randomly selecting a node as a node to be expanded from the search tree corresponding to the selected direction for executing node expansion, and starting from the node to be expanded, performing a node expansion operation in a preset expansion direction to generate coordinates of new nodes after expansion; performing collision detection operations and encounter detection operations on the new node coordinates after expansion to generate a global optimal path consisting of three-dimensional coordinates of a starting point, one or more new node coordinates, and three-dimensional coordinates of a target point.

[0009] In some embodiments of the first aspect of the present application, performing collision detection operations and encounter detection operations on the expanded new node coordinates includes the following steps: the process of the collision detection operation includes: determining whether the expanded new node coordinates collide with obstacles in the environmental model, if a collision occurs, discarding the current expanded new node; otherwise, incorporating the current expanded new node into the updated path; the process of the encounter detection operation includes: determining whether the expanded new node coordinates encounter nodes in another search tree in a different direction of executing node expansion, if an encounter occurs, outputting the current path as the global optimal path; otherwise, executing the node expansion iteration operation again.

[0010] In some embodiments of the first aspect of the present application, the process of performing local optimization operations during the massage process by collecting real-time feedback data includes: collecting the current local environment model of the current local area in real time during the massage process; generating corresponding artificial potential fields and velocity fields based on the current local environment model, the global optimization path and the robot motion state; performing local optimization operations on the global optimization path in the current local environment model according to the artificial potential field and the velocity field to generate a local optimization path.

[0011] In some embodiments of the first aspect of the present application, the process of performing an adaptive admittance compliance control operation during a massage by collecting real-time feedback data during a massage includes: collecting the contact force of the current target part of the subject, and obtaining the expected force of the current target part of the subject and the contact force of the target part of the previous cycle; constructing a current part compliance control law based on the contact force and the expected force of the current target part; calculating a compensated contact force error based on the contact force of the current target part, the contact force of the target part of the previous cycle, and the expected force of the current target part; updating the current part compliance control law based on the compensated contact force error, and calculating the robot's updated acceleration, velocity and moving position information based on the updated compliance control law, and controlling the robot based on the robot's updated acceleration, velocity and moving position information.

[0012] To achieve the above-mentioned purpose and other related purposes, the second aspect of the present application provides a massage robot control system, including: a data input module: used to collect image data of a subject, and based on the image data, construct a three-dimensional model of the subject environment to generate an environmental model; an acupoint recognition module: used to locate the acupoints of the subject based on the image data to generate acupoint coordinate information included in the massage task to be performed; a strategy control module: used to generate the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point according to a preset massage strategy and acupoint coordinate information; using a preset path search algorithm, search for the path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environmental model to generate a global optimal path; a massage execution module: used to execute the massage task according to the global optimal path, and perform local optimization operations and adaptive admittance compliance control operations during the massage process through the collected real-time feedback data until the massage task is completed.

[0013] To achieve the above-mentioned purpose and other related purposes, the third aspect of the present application provides a computer-readable storage medium having a computer program stored thereon, and the computer program implements the massage robot control method when executed by a processor.

[0014] To achieve the above-mentioned purpose and other related purposes, the fourth aspect of the present application provides a computer program product, which includes a computer program code. When the computer program code runs on a computer, the computer implements the massage robot control method.

[0015] To achieve the above-mentioned purpose and other related purposes, the fifth aspect of the present application provides an electronic terminal, including a memory, a processor and a computer program stored in the memory; the processor executes the computer program to implement the massage robot control method.

[0016] As described above, the massage robot control method, system, medium, program product and terminal of the present application have the following beneficial effects: the robot uses actively planned massage paths and local optimization algorithms to perform personalized treatment according to the patient's body shape, muscle tissue and health status, significantly improving the pertinence and effectiveness of massage. Secondly, the adaptive compliant admittance control technology ensures safety, adjusts the massage intensity in real time to reduce the risk of potential injury, and enhances the patient's trust in robot massage. In addition, this solution combines traditional Chinese medicine theory with modern technology, effectively inherits traditional massage techniques, and promotes the modern application of traditional Chinese medicine culture. This fusion of culture and technology not only enriches the functions of massage robots, but also improves their market competitiveness. Through high-frequency automated services, robots reduce the workload of manual masseurs, improve overall treatment efficiency, and enable patients to quickly obtain the required treatment. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 A flow chart of an embodiment of a massage robot control method of the present application is shown.

[0018] Figure 2 A schematic diagram of a bidirectional fast search random tree algorithm for global active planning in an embodiment of a massage robot control method of the present application is shown.

[0019] Figure 3 A schematic diagram of a traditional artificial potential field in an embodiment of a massage robot control method of the present application is shown.

[0020] Figure 4 A model diagram of a traditional admittance control method in an embodiment of a massage robot control method of the present application is shown.

[0021] Figure 5 A model diagram of the adaptive admittance control method in one embodiment of the massage robot control method of the present application is shown.

[0022] Figure 6 A structural schematic diagram of an embodiment of a massage robot control system of the present application is shown.

[0023] Figure 7 A structural schematic diagram of another embodiment of the massage robot control system of the present application is shown.

[0024] Figure 8 A structural schematic diagram of an embodiment of a massage robot control terminal of the present application is shown. DETAILED DESCRIPTION

[0025] The following describes the embodiments of the present application through specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the contents disclosed in this specification. The present application can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and features in the embodiments can be combined with each other without conflict.

[0026] Before further explaining the present application in detail, the nouns and terms involved in the embodiments of the present application are explained. The nouns and terms involved in the embodiments of the present application are subject to the following interpretations:

[0027] <1> Path search algorithm: Path search algorithms are used to calculate the optimal path for the robot from the starting point to the end point in the environment. Common algorithms include A* algorithm, Dijkstra algorithm and Rapidly Expanding Random Tree (RRT). These algorithms take into account obstacles, robot motion capabilities and environmental dynamics to ensure safety and efficiency.

[0028] <2> Global environment model: The global environment model is the process of comprehensively modeling the entire environment that the robot is in. This model usually contains static features of the environment (such as obstacles, walls, furniture, etc.) and dynamic features (such as moving people or animals). The global environment model helps the robot to perform comprehensive path planning and task execution.

[0029] <3> Local-global model: The local-global model combines information about the local environment with data about the global environment to provide more flexible decision-making capabilities. By combining real-time sensor data and global maps, the local-global model allows the robot to quickly adjust its behavior to respond to unexpected situations in complex environments.

[0030] <4> Static artificial potential field: Static artificial potential field plans the path by simulating the potential energy field. In the massage robot, the target area (such as the part to be massaged) is regarded as the attraction source, and the obstacles are regarded as the repulsion source. The robot moves in the potential field and searches for the lowest energy path to reach the target.

[0031] <5> Velocity field: Velocity field is a field that describes the velocity vector at each position in space. In massage robots, velocity field can be used to control the movement and operation speed of the robot to achieve smooth massage action. Velocity field can be adjusted dynamically to respond to environmental changes and task requirements.

[0032] <6> Path optimization algorithm: Path optimization algorithms are designed to improve the results of path search and find a better route by considering multiple factors such as movement efficiency, time cost, and energy consumption. These algorithms can include genetic algorithms, ant colony algorithms, etc., which are suitable for complex and dynamic massage environments.

[0033] <7> Compliant control law: Compliant control law is a control method used to control the robot's contact with the human body, aiming to ensure that the force and motion during contact remain within a safe range to avoid causing discomfort or injury. This method allows the robot to show a certain degree of flexibility and adaptability when interacting with objects.

[0034] <8> Expected force: Expected force refers to the ideal state of simulated or calculated force, that is, the force that the massage robot expects to exert on the massage object during operation. This force is usually defined based on the preset massage strategy and human anatomical characteristics to ensure the expected soothing effect.

[0035] <9> Contact force: Contact force refers to the actual force generated between the massage robot and the massage object. The measurement of this force is crucial to ensure the safety and effectiveness of massage. The robot must monitor and adjust the contact force in real time to adapt to the needs and feedback of different individuals.

[0036] <10> Compensating for contact force error: Compensating for contact force error means adjusting the force applied by the robot through a feedback control mechanism to eliminate or reduce contact force errors caused by sensor errors or motion imbalances. This process ensures that the robot maintains a predetermined force level and operating accuracy during contact.

[0037] To facilitate understanding of the embodiments of the present application, first Figure 1 Detailed description. Figure 1 The flowchart of a massage robot control method in an embodiment of the present application is shown. The massage robot control method in this embodiment mainly includes the following steps:

[0038] Step S11: collecting image data of the subject, and constructing a three-dimensional model of the subject environment based on the image data to generate an environment model.

[0039] In one embodiment of the present application, the massage robot control method is applied to a two-arm robot, each arm is equipped with multiple joints and servo motors, and can perform complex movements, such as kneading, pushing and patting and other massage techniques. The joint design of the robot allows it to move freely in space to adapt to the body shape and posture of different subjects. At the same time, the two-arm structure enables the robot to perform synchronous or independent massage operations on both sides of the subject's body, thereby improving the massage effect. The robot is also equipped with advanced sensors that can collect and analyze the subject's physiological data in real time to dynamically adjust the massage intensity and technique to ensure a personalized and precise massage experience.

[0040] In one embodiment of the present application, when the robot first contacts the subject, it uses multiple sensors (such as RGB cameras and depth cameras) to collect comprehensive images and build a three-dimensional environment model and a body model of the subject. It also stores the detected physical characteristics of the subject, including height, weight, body shape, muscle distribution, etc., so as to be used as the basis for subsequent operations.

[0041] Furthermore, the image data includes one or more of expression images, expression images, depth images, thermal images, joint angle data, and body posture data. The expression image is used to identify the facial expression and skin condition of the subject to analyze the degree of relaxation. The depth image is used to capture the relative position between the subject and the massage robot to provide data support for path planning. Thermal imaging images are used to monitor temperature changes in different areas of the human body and identify temperature changes in specific acupuncture points, providing a physiological basis for traditional Chinese medicine theory. The joint angle data records the angle changes of the robot joints through built-in sensors to ensure the naturalness and comfort of the movement. The body posture data is used to analyze the subject's body posture according to the posture recognition algorithm to optimize the massage technique and strength.

[0042] In one embodiment of the present application, in addition to collecting image data of the subject for building a three-dimensional model, during the massage process, the massage robot will continue to collect real-time images and monitor the subject's body posture changes and facial expressions through the camera so as to adjust the massage force and angle in time. And through the image data captured by the camera, the robot can calculate the best massage path in real time to ensure that each acupoint can be properly stimulated while avoiding interference with other areas. In addition, the robot adjusts its own compliance based on real-time data to avoid discomfort or damage during the massage process. For example, if the subject is detected to be feeling uncomfortable, the robot can automatically reduce the force or change the massage method.

[0043] Step S12: Based on the image data, acupoints of the subject are located to generate acupoint coordinate information included in the massage task to be performed.

[0044] In one embodiment of the present application, acupoint positioning of subjects based on image data is combined with bone analysis, which includes the following steps: First, the subjects are imaged by a high-resolution camera or medical imaging equipment (such as CT, MRI) to ensure clear display of bone and muscle structure. Then, the collected images are preprocessed, denoised and contrast enhanced for subsequent analysis. Subsequently, image processing algorithms (such as CNN) are used to automatically identify and mark key skeletal anatomical points, such as spine and joints, as a benchmark for subsequent positioning. Through the bone analysis method, these marked points are combined with the acupoint distribution theory of traditional Chinese medicine to construct an acupoint mapping model to obtain the three-dimensional coordinates of each acupoint. Further, the calculated acupoint coordinates are converted into actual massage task coordinate information, and each acupoint and its coordinates are recorded and visualized for subsequent massage guidance.

[0045] In one embodiment of the present application, based on the image data, the following operation is also performed before the acupoints of the subject are located: the model training is performed on the collected multiple image data of the subject based on the deep learning model. Exemplarily, the deep learning model includes but is not limited to a convolutional neural network (CNN) to generate a trained CNN model. The process of locating the acupoints of the subject includes: improving the image quality through image preprocessing and enhancement technology. The spatial features in the image are extracted and parsed by the trained CNN model, and the key acupoints are accurately identified. Exemplarily, the key acupoints include Jianjing, Hegu, Zusanli, etc. Finally, each identified acupoint is converted into accurate three-dimensional coordinate information, and a detailed acupoint coordinate mapping is formed.

[0046] Step S13: Generate the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point according to the preset massage strategy and acupoint coordinate information; use the preset path search algorithm to search for the path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environmental model to generate a global optimal path.

[0047] In one embodiment of the present application, the generation process of the preset massage strategy includes: collecting the subject's main complaint, symptoms and physical condition information; inputting the subject's main complaint, symptoms and physical condition information into the TCM theory database to generate a corresponding plurality of acupoints to be treated, as well as the massage technique and massage intensity corresponding to each acupoint. For example, for shoulder pain, acupoints such as Jianjing and Hegu are often involved; while for back discomfort, acupoints such as Zusanli and Yangguan may be selected, so as to achieve effective matching of symptoms with corresponding acupoints through the TCM theory database. Techniques include but are not limited to massage, pressing, patting, etc., and the intensity includes but is not limited to light, medium and heavy to adapt to different diseases and individual differences. Finally, the massage duration of each acupoint is set.

[0048] In one embodiment of the present application, the method provides a dual-arm robot massage control method dedicated to traditional Chinese medicine massage. Therefore, the control method in this embodiment is deeply integrated with traditional Chinese medicine theory. Specifically, traditional Chinese medicine theory emphasizes the close relationship between acupoints and meridians, believing that meridians are important channels for the circulation of qi and blood, and acupoints are key points for regulating body functions. The interaction between acupoints and meridians can help improve the body's physiological state and deal with various health problems. Therefore, in this embodiment, in the recognition process, not only the positioning of acupoints is concerned, but also the direction of meridians and the functions of acupoints are considered.

[0049] Furthermore, the process of generating the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point includes: extracting the meridian direction information related to the acupoint coordinate information based on the preset massage strategy and the acupoint coordinate information; selecting two acupoints that are closest to the meridian direction information from the multiple acupoints contained in the acupoint coordinate information based on the meridian direction information, and confirming the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point among the two extracted acupoints according to the meridian direction information.

[0050] For example, if the subject's main complaint is shoulder pain, then based on the preset massage strategy and acupoint coordinate information, multiple acupoints related to the meridian direction are first extracted, and it is found that they include Jianjing acupoint and Tianzong acupoint. Based on the meridian direction information, two acupoints related to shoulder pain are analyzed and selected. Jianjing acupoint and Tianzong acupoint are the two acupoints closest to the patient's pain point. Then, based on the meridian direction information of these acupoints, the three-dimensional coordinates of Jianjing acupoint as the starting point are confirmed, and Tianzong acupoint is used as the three-dimensional coordinate of the target point.

[0051] In one embodiment of the present application, a preset path search algorithm is used to search for a path connecting the three-dimensional coordinates of a starting point and the three-dimensional coordinates of a target point in the environment model to generate a global optimal path, including: constructing a forward search tree and a reverse search tree based on the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point; and performing multiple rounds of node expansion iterative operations based on the forward search tree and the reverse search tree to generate a global optimal path.

[0052] In one embodiment of the present application, the environmental model refers to a virtual representation constructed in a specific space, including various elements of the human anatomy and the massage therapy environment, which provides necessary background information for path planning and the application of massage techniques. The environmental model includes muscle tissue, bone structure, and key points (such as acupoints and pain areas). Obstacle information in the environmental model represents inaccessible areas or potential interfering objects, such as furniture, walls, the therapist's own movement, and the patient's reaction. This information ensures the feasibility and safety of path planning and avoids conflicts with fixed or dynamic obstacles.

[0053] In one embodiment of the present application, based on the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point, the process of constructing a forward search tree and a reverse search tree includes: starting from the three-dimensional coordinates of the starting point, gradually expanding the nodes based on a preset path search algorithm. For each current node, identify and generate all movable adjacent nodes, add them to the search tree, and mark the visited nodes to avoid duplication, and continue this process until there are no new adjacent nodes to expand. In the reverse search, expand from the three-dimensional coordinates of the target point to the adjacent nodes, and also identify the movable adjacent nodes and add them to the reverse search tree. At the same time, mark the visited nodes to avoid duplication. Continue this process until there are no new adjacent nodes to expand, thereby forming a complete reverse search tree.

[0054] Furthermore, the preset path search algorithm is used to control the order and method of node expansion to affect the efficiency and effect of the search. The preset path search algorithm includes but is not limited to: breadth-first search (BFS), depth-first search (DFS) and A* algorithm. Breadth-first search (BFS) is suitable for finding the shortest path, but has high space complexity; depth-first search (DFS) takes up less memory and takes a long time to search; the A* algorithm combines heuristic search and cost evaluation to efficiently plan complex paths. For the massage field where this method is applied, especially the massage planning of acupuncture point meridian paths, the A* algorithm is most suitable because it can flexibly evaluate a variety of path options according to the actual meridian connection situation and path cost, so as to find a better meridian connection scheme, improve the treatment effect and optimize the path efficiency.

[0055] In one embodiment of the present application, the process of the node expansion iterative operation includes: randomly selecting a direction for executing node expansion from the forward search tree and the reverse search tree; randomly selecting a node as a node to be expanded from the search tree corresponding to the selected direction for executing node expansion, and starting from the node to be expanded, performing a node expansion operation in a preset expansion direction to generate coordinates of new nodes after expansion; performing collision detection operations and encounter detection operations on the new node coordinates after expansion to generate a global optimal path consisting of three-dimensional coordinates of a starting point, one or more new node coordinates, and three-dimensional coordinates of a target point.

[0056] In one embodiment of the present application, performing collision detection operations and encounter detection operations on the coordinates of the new node after expansion includes the following steps: the process of the collision detection operation includes: determining whether the coordinates of the new node after expansion collide with an obstacle in the environmental model, if a collision occurs, discarding the current new node after expansion; otherwise, incorporating the current new node after expansion into the updated path; the process of the encounter detection operation includes: determining whether the coordinates of the new node after expansion encounter a node in another search tree in a different direction from that in which the node expansion is performed, if an encounter occurs, outputting the current path as the global optimal path; otherwise, executing the node expansion iteration operation again.

[0057] Figure 2 The schematic diagram of the bidirectional fast search random tree algorithm for global active planning in one embodiment of the present application is shown. In this embodiment, starting point x init and the target point x end As input, it runs a parallel search of two trees in free space: the forward tree and the reverse tree. In each iteration, the algorithm selects a node from the two trees to expand and guides the search direction through randomly generated points. In each expansion process, the legitimacy of the new node is determined by calculating the distance between nodes and collision detection. Specifically, the distance calculation usually uses Euclidean distance, while the collision detection is based on the obstacle information in the environment. If the new node passes the collision detection, it is added to the corresponding tree and the connection relationship between the two trees is updated. The termination condition of the algorithm is when the search paths of the two trees meet, that is, a path connecting the starting point and the target point is found.

[0058] It is worth noting that the global bidirectional RRT algorithm proposed in this application can not only efficiently realize path planning in complex environments, but also ensure that the generated path is close to the optimal solution or the global optimal solution by optimizing the path generation method. The advantages of this method are its efficiency and adaptability, which can flexibly adapt to different environmental conditions and robot dynamic requirements, and provide reliable technical support for the global planning of dual-arm robots.

[0059] It should be explained that the method for judging encounters can be implemented through the following specific implementation steps: First, a distance threshold is set when the algorithm is initialized, for example, ∈. When the distance between two nodes is less than ∈, it is determined to be an encounter. Next, each time a node is expanded, the distance between the newly expanded node and all nodes in the other search tree is calculated, and a traversal is performed to check whether there are nodes that meet the encounter conditions. In order to improve the efficiency of judgment, a hash table can be used to store the expanded node information so that close new nodes can be quickly found during calculation. If a node that meets the encounter conditions is found, the algorithm will trigger the corresponding processing mechanism, including recording the path, tracing back to the encounter node, and evaluating the cost of the path to determine whether it is the global optimal path. This method uses precise distance calculation and efficient data structure to achieve fast and accurate encounter detection.

[0060] Step S14: Execute the massage task according to the global optimal path, and perform local optimization operations and adaptive admittance compliance control operations during the massage process through the collected real-time feedback data until the massage task is completed.

[0061] In one embodiment of the present application, the process of performing local optimization operations during the massage process by collecting real-time feedback data includes: collecting the current local environment model of the current local area in real time during the massage process; generating corresponding artificial potential fields and velocity fields based on the current local environment model, the global optimization path and the robot motion state; performing local optimization operations on the global optimization path in the current local environment model according to the artificial potential field and the velocity field to generate a local optimization path.

[0062] In this embodiment, the real-time feedback data includes one or more of the local environment information (such as the shape, hardness and temperature of the massage part), the user's physiological response during the massage process (such as muscle tension, pain and comfort), the robot's dynamic state (current position, speed and acceleration), various working parameters of the massage tool (such as pressure, vibration frequency and amplitude), and data collected by various sensors (tactile, temperature and pressure, etc.). By integrating these real-time feedback data, the massage process can be effectively optimized, thereby improving the user's overall experience and effect.

[0063] In one embodiment of the present application, an improved artificial potential field algorithm based on velocity field is used in the local optimization operation. The improved artificial potential field algorithm based on velocity field is a technology used for robot path planning and navigation, which generates a path by simulating the interaction force between objects. Compared with the traditional artificial potential field algorithm, the velocity field-based method introduces the concept of velocity field, dynamically generates a velocity field to describe the direction and speed of movement, and then optimizes the robot's movement strategy in the environment. This algorithm can make the robot path smoother, avoid sharp turns, improve the naturalness of the action, and can adjust in real time to cope with changes in obstacles in the environment, thereby improving dynamic obstacle avoidance capabilities.

[0064] In this embodiment, the traditional static artificial potential field is Figure 3 As shown in the figure. The potential energy function applies a repulsive force based on the relative position of each obstacle in the environment. Specifically, the potential energy function will act strongly on the robot that is close to the obstacle, and the magnitude of this force is usually inversely proportional to the distance between the robot and the obstacle. In other words, the closer the robot is to the obstacle, the stronger the repulsive force it will receive, which will cause the robot to tend to stay away from these obstacles and avoid potential collisions. At the same time, the potential energy function will also apply an attractive force to the target position to guide the robot to move toward the target. Ultimately, under the combined effect of repulsion and attraction, the robot will choose an effective path to safely cross the obstacles in the environment and reach the predetermined goal.

[0065] In one embodiment of the present application, based on the current local environment model, the global optimization path and the robot motion state, the process of generating the corresponding artificial potential field and velocity field includes: selecting a valid target point from the global path; to ensure that the robot can move toward the target point while not getting too close to obstacles, thereby increasing safety and efficiency, and the process is shown in Formula 1.

[0066] P t =SelectValidGoal(P global , E local , P r ) (Formula 1)

[0067] Where P t represents the target point coordinates, P global It represents the global optimization path consisting of the best path points from the starting point to the target point, which is used to provide the overall direction for the robot to move. local Represents the current local environment model, which records the specific information of obstacles in the environment so that the robot can perceive the surrounding spatial structure. Robot motion state S r Used to describe the current position P of the robot r (x r ,y r , z r ), speed Vr and posture, allowing the robot to assess its state in real time.

[0068] The process of constructing the attraction field based on the current position of the robot, the position of the robot's target point, and the attraction coefficient is shown in Formula 2. a The attraction vector represents the vector difference between the target point and the current point to generate the robot's movement direction and strength. a The attraction coefficient is an adjustable attraction strength to ensure that the robot approaches the target point smoothly. The velocity vector is normalized according to Formula 3 to generate the attraction velocity vector V a .

[0069] F a =k a ·(P t -P r ) (Formula 2)

[0070]

[0071] Then, a repulsive force field is constructed based on the current position of the robot, the position of the robot's target point, and the repulsive force coefficient, and the process is shown in Formula 4 and Formula 5. Among them, Represents the distance between the robot and each obstacle. The smaller the distance, the stronger the repulsion. M represents the number of obstacles. represents the position of the ith obstacle, k o Represents the repulsion coefficient, which is used to control the strength of the repulsion. The larger the value, the stronger the repulsion. o represents the repulsive velocity vector. H(d thr -d i ) represents a heuristic function that is used to determine the distance between the robot and the obstacle, ensuring that the repulsion force is only effective when the robot is close to the obstacle. If the distance between the robot and the obstacle is less than a certain threshold, the repulsion force will be generated.

[0072]

[0073] Finally, the calculation process of the final velocity field is shown in Formula 6.

[0074] V total =V a –V o (Formula 6)

[0075] In one embodiment of the present application, the process of performing a local optimization operation on the global optimization path in the current local environment model according to the artificial potential field and the velocity field to generate a local optimization path includes: superimposing the static artificial potential field and the velocity field, and dynamically adjusting the weights of the two fields by proportional increase, and the process is shown in Formula 7.

[0076]

[0077] Among them, V field Represents the comprehensive velocity vector that combines the guidance of the artificial potential field and the velocity field. Indicates the direction in which the artificial potential energy decreases, pushing the robot toward the target while avoiding obstacles. custom represents the additionally defined velocity field,

[0078] Furthermore, a feasible local path is generated based on the generated integrated velocity vector to ensure that the robot moves smoothly towards the target; then, the local segment that needs to be optimized is identified on the global path, and the obstacle situation and dynamic environment of this segment are evaluated using the path optimization algorithm to generate a new optimized path; then, by calculating the cost of the new path (such as distance or safety index), the local path is integrated with the global path, and a better path segment is selected; finally, combined with dynamic feedback, environmental changes and robot status are monitored in real time, and the global path is adjusted in time.

[0079] It is worth noting that the robot in the field of traditional Chinese medicine massage involved in this application needs to adapt to the changes in the dynamic environment in practical applications, because each person's body structure and pain point position are different, and the posture of the person will change continuously during the massage process. In order to provide personalized services and ensure safety, the robot needs to identify and adapt to these changes in real time. Therefore, the present embodiment generates a static artificial potential field and a velocity field corresponding to the current local environment model in the local optimization operation, and superimposes the static artificial potential field and the velocity field, so that the robot fully considers the influence of the current speed and acceleration on the path planning in the process of performing the massage task, and adjusts the shape and parameters of the potential field according to the real-time changes of the robot's motion state. This dynamic adjustment can make the robot more flexible and adapt to environmental changes when performing path planning.

[0080] In one embodiment of the present application, the process of performing an adaptive admittance compliance control operation during a massage by collecting real-time feedback data during a massage includes: collecting the contact force of the current target part of the subject, and obtaining the expected force of the current target part of the subject and the contact force of the target part of the previous cycle; constructing a current part compliance control law based on the contact force and the expected force of the current target part; calculating a compensated contact force error based on the contact force of the current target part, the contact force of the target part of the previous cycle, and the expected force of the current target part; updating the current part compliance control law based on the compensated contact force error, and calculating the robot's updated acceleration, velocity and moving position information based on the updated compliance control law, and controlling the robot based on the robot's updated acceleration, velocity and moving position information.

[0081] In this embodiment, the real-time feedback data includes: the contact force of the current target part of the subject, the expected force, the contact force of the previous cycle, and one or more of the compliance control laws constructed based on these data. In addition, there is compensation data for contact force errors and the robot's motion state information (including acceleration, velocity, and position information). By integrating these real-time feedback data, the robot can achieve adaptive admittance compliance control, thereby more effectively meeting the needs and expectations of the subject during the massage process.

[0082] Figure 4 FIG. 1 shows a schematic diagram of a traditional admittance control model in an embodiment of the present application. Figure 4 As shown, first, the reference input x is received by the admittance control module. r , generating the control signal x c This signal is converted into the joint angle θ through inverse kinematics. c , and then the robot performs the corresponding action. The forward kinematics module converts the joint angle θ into the actual position X. At the same time, the influence of the external environment is input, and the environment model K e Evaluate external driving force F d and resistance F e The net force ΔF is calculated. Finally, the actual output X and the desired position x are adjusted through the feedback mechanism. e The difference between and is used to achieve precise control. The compliant control law is shown in Formula 8.

[0083]

[0084] Among them, M, B, and K represent the inertia diagonal matrix, damping diagonal matrix, and stiffness diagonal matrix of the impedance model, respectively. X c They represent the control acceleration, velocity, and position vectors sent to the robot in the Cartesian coordinate system. X r Respectively represent the reference acceleration, velocity, and position vector of the robot in the Cartesian coordinate system. e Represents the contact force between the robot and the environment.

[0085] Furthermore, during the contact process between the robot and the environment, the motion can be divided into two regions: free space and contact space. The motion in both regions can be described by the model in Equation 8. In free space, the contact force F e =0, if the expected force f is set d =0, then X r =X c , which indicates that the robot will continue to move along the predetermined trajectory. In the contact space, the contact force F e≠0, in this case, the position adjustment amount needs to be generated according to the error between the contact force and the expected force. The mathematical expression of the position correction amount is shown in Formula 9.

[0086]

[0087] Among them, s represents the complex variable in Laplace transform, which is expressed as s=σ+jω. Among them, σ represents the real part, which represents the decay or growth rate of the system; j represents the imaginary unit; ω represents the imaginary part, which represents the frequency of the system (in radians per second). Through Laplace transform, time domain signals can be converted to frequency domain representation, making it easier to analyze and design linear time-invariant systems.

[0088] In particular, for massage tasks, the robot works on the patient's body. Due to the large difference in stiffness between different parts of the patient's body, and the fact that the same part also varies in curvature and height, the structure of the human body can be regarded as a complex spatial curved surface flexible system. This system is difficult to accurately describe through mathematical models, and it is also difficult to accurately measure, making it difficult to select a suitable reference trajectory, which makes it difficult to converge the force tracking error.

[0089] Considering the above situation, in one embodiment of the present application, the impedance parameter k is set to 0 to achieve an ideal contact force tracking condition in a dynamic environment. Therefore, the present method adopts a strategy of setting the impedance parameter k to 0 to achieve robot compliant massage. After setting k to 0, Formula 9 is updated to generate an updated compliant control law, as shown in Formula 10.

[0090]

[0091] In a specific known environment, using classic admittance control and selecting appropriate admittance parameters can keep the entire system stable and achieve the expected force tracking effect. However, in the field of traditional Chinese medicine massage, which is applied in this application, human tissue has characteristics such as nonlinearity and variable stiffness, which makes it difficult to select fixed admittance parameters to achieve good stabilization effects. In order to solve this problem, this application adopts a compensation scheme to achieve force tracking in an uncertain environment. The control block diagram is shown in the figure. Figure 5 As shown, the specific compliant control law is shown in formula 11. Among them, Indicates the error,

[0092]

[0093] Wherein φ(t) represents the adaptive compensation term, that is, the compensation contact force error, and the damping term is adjusted online according to the compensation contact force error in the previous cycle. The calculation process of φ(t) is shown in Formula 12.

[0094]

[0095] Where T is the sampling period. σ is the adjustment parameter used to adjust the robot's response to the input signal. ⊙(t) = 0. In a dynamic robot or feedback control robot, ⊙(t) = 0 means that the robot is currently in a balanced state, or it means the target state that the robot needs to achieve. When ⊙(t) = 0, the robot compares the past state (reflected by φ(tT)) with the input signal (reflected by f e (tT) and f d (tT) is adjusted) to determine the change in the current state.

[0096] Furthermore, common collaborative robots that can perform safe interactions with humans usually provide a position servo control interface that allows users to send instructions to control the position and motion of the robot. The control law in the control system is a mathematical expression used to adjust the robot's motion to achieve the target position. In order to enable these control instructions to be executed in a computer or digital control system, the continuous compliant control law needs to be converted into a discrete form, so the control instructions need to be decomposed into a series of specific steps or instructions. Formula 13 shows the specific mathematical expression of the discretization process, showing how to convert the position servo control instructions into control signals that can be executed by the robot. This conversion improves the control accuracy of the robot and simplifies the calculation process.

[0097]

[0098] In one embodiment of the present application, the process of the adaptive admittance compliance control operation also includes a verification operation. The verification operation specifically includes: first, applying a constant force at a specific position in contact with the user's body (such as shoulders, back or legs) to achieve precise pressure control to ensure that the user will not be harmed during the massage process; then, during the movement of the robot, maintain a constant force on the contact point to evaluate the impact of the dynamic environment (such as the user's body movements or external obstacles) on the massage effect; in addition, it is necessary to observe how the robot flexibly adjusts the massage intensity according to environmental changes (such as different needs of the user's body parts or posture changes) to adapt to various situations.

[0099] Furthermore, if the robot can always provide massage effects that meet the user's comfort requirements in different contact positions and dynamic environments, and no harm is caused to the user during the adjustment process. At the same time, the robot should be able to quickly respond to environmental changes and accurately adjust the massage intensity to meet the needs of different parts of the user, then the current adaptive admittance compliance control operation is verified; if the robot fails to meet the above standards, such as the user feels uncomfortable, the massage intensity is insufficient or excessive, or the robot cannot maintain appropriate force in a changing environment, it is deemed to have failed the verification. Through these experimental processes, the application effect of the adaptive admittance compliance control method in massage robots is verified, thereby promoting the development of related technologies and improving user experience.

[0100] It should be noted that in the embodiments of the present application, words such as "exemplary" or "for example" represent examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0101] In the embodiments of the present application, "at least one" refers to one or more, and "plurality" refers to two or more. "And / or" describes the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone, where A and B can be singular or plural. The character " / " generally indicates that the previous and next associated objects are in an "or" relationship. "At least one of the following" or similar expressions refers to any combination of these items, including any combination of single or plural items. For example, at least one of a, b or c can represent: a, b, c, ab, ac, bc or abc, where a, b, c can be single or multiple.

[0102] Figure 6 is a schematic block diagram of a massage robot control system 600 provided in an embodiment of the present application. Figure 6 As shown, the device includes a data input module 601, an acupoint identification module 602, a strategy control module 603 and a massage execution module 604.

[0103] Data input module 601: used to collect image data of the subject, and construct a three-dimensional model of the subject environment based on the image data to generate an environment model.

[0104] Acupoint identification module 602: used to locate the acupoints of the subject based on the image data to generate acupoint coordinate information included in the massage task to be performed.

[0105] Strategy control module 603: used to generate the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point according to the preset massage strategy and acupoint coordinate information; use the preset path search algorithm to search for the path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environmental model to generate a global optimal path.

[0106] Massage execution module 604: used to execute the massage task according to the global optimal path, and perform local optimization operations and adaptive admittance compliance control operations during the massage process through the collected real-time feedback data until the massage task is completed.

[0107] Figure 7 The structural diagram of the massage robot control system in one embodiment of the present application is shown. The massage robot control system is composed of multiple modules working together to ensure efficient and accurate completion of massage tasks. The physician input module is responsible for inputting massage instructions (such as acupoints, techniques, strength and time), and sending them and the three-dimensional coordinates of human acupoints to the system through the host computer. The human acupoint recognition module uses a camera to collect real-time images of the massage object, performs posture estimation, bone measurement method and coordinate conversion to accurately identify the acupoints. Then, the massage strategy control module receives the above information, outputs the specific coordinates, strength and motion trajectory of the robot massage, and generates a working sequence. The massage technique execution module implements specific massage operations according to the working sequence, including robot compliance control. Finally, the robotic arm performs actual massage according to these instructions to complete the whole process. Among them, the bone measurement method is a technology that determines and locates human acupoints by measuring the length and proportion of human bones.

[0108] It should be understood that the specific process of each module executing the above corresponding steps has been described in detail in the above method embodiment, and for the sake of brevity, it will not be repeated here.

[0109] It should also be understood that the division of modules in the embodiments of the present application is schematic and is only a logical function division. There may be other division methods in actual implementation. In addition, each functional module in each embodiment of the present application may be integrated into a processor, or may exist physically separately, or two or more modules may be integrated into one module. The above-mentioned integrated modules may be implemented in the form of hardware or in the form of software functional modules.

[0110] Figure 8 is a schematic block diagram of an electronic terminal provided in an embodiment of the present application. Figure 8As shown, the electronic terminal includes: at least one processor 801, a memory 802, at least one network interface 803 and a user interface 805. The various components in the device are coupled together through a bus system 804. It can be understood that the bus system 804 is used to realize the connection and communication between these components. In addition to the data bus, the bus system 804 also includes a power bus, a control bus and a status signal bus. However, for the sake of clarity, Figure 8 In the specification, various buses are labeled as bus systems.

[0111] The user interface 805 may include a display, a keyboard, a mouse, a trackball, a click gun, keys, buttons, a touch pad or a touch screen.

[0112] It is understood that the memory 802 can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM, Read Only Memory), a programmable read-only memory (PROM, Programmable Read-Only Memory), which is used as an external cache. By way of exemplary but not limiting explanation, many forms of RAM are available, such as static random access memory (SRAM, Static Random Access Memory), synchronous static random access memory (SSRAM, Synchronous Static Random Access Memory). The memory described in the embodiments of the present application is intended to include but is not limited to these and any other suitable categories of memory.

[0113] The memory 802 in the embodiment of the present application is used to store various categories of data to support the operation of the electronic terminal 800. Examples of these data include: any executable program for operating on the electronic terminal 800, such as an operating system 8021 and an application 8022; the operating system 8021 includes various system programs, such as a framework layer, a core library layer, a driver layer, etc., for implementing various basic services and processing hardware-based tasks. The application 8022 can include various applications, such as a media player (Media Player), a browser (Browser), etc., for implementing various application services. The massage robot control method provided in the embodiment of the present application can be included in the application 8022.

[0114] The method disclosed in the above embodiment of the present application can be applied to the processor 801, or implemented by the processor 801. The processor 801 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of the hardware in the processor 801 or an instruction in the form of software. The above processor 801 may be a general processor, a digital signal processor (DSP, Digital Signal Processor), or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. The processor 801 can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present application. The general processor 801 may be a microprocessor or any conventional processor, etc. In combination with the steps of the accessory optimization method provided in the embodiment of the present application, it can be directly embodied as a hardware decoding processor to execute, or it can be executed by a combination of hardware and software modules in the decoding processor. The software module can be located in a storage medium, which is located in a memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0115] In an exemplary embodiment, the electronic terminal 800 may be implemented by one or more application specific integrated circuits (ASIC), DSP, programmable logic device (PLD), complex programmable logic device (CPLD) to execute the aforementioned method.

[0116] According to the method provided in the embodiments of the present application, the present application also provides a computer program product, which includes: a computer program code, when the computer program code runs on a computer, the computer executes the massage robot control method of any embodiment shown in the above embodiments.

[0117] According to the method provided in the embodiments of the present application, the present application also provides a computer-readable storage medium, which stores a program code. When the program code runs on a computer, the computer executes the massage robot control method of any one of the embodiments shown above.

[0118] The terms "component", "module", "system", etc. used in this specification are used to represent computer-related entities, hardware, firmware, a combination of hardware and software, software, or software in execution. For example, a component can be, but is not limited to, a process running on a processor, a processor, an object, an executable file, an execution thread, a program and / or a computer. By way of illustration, both applications running on a computing device and a computing device can be components. One or more components may reside in a process and / or an execution thread, and a component may be located on a computer and / or distributed between two or more computers. In addition, these components may be executed from various computer-readable media having various data structures stored thereon. Components may, for example, communicate through local and / or remote processes according to signals having one or more data packets (e.g., data from two components interacting with another component between a local system, a distributed system and / or a network, such as the Internet interacting with other systems through signals).

[0119] Those of ordinary skill in the art will appreciate that the various illustrative logical blocks and steps described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0120] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0121] In the several embodiments provided in the present application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of units is only a logical function division. There may be other division methods in actual implementation. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0122] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0123] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0124] In the above embodiments, the functions of each functional unit can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions (programs). When loading and executing computer program instructions (programs) on a computer, the process or function according to the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions can be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (Digital Subscriber Line, DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server, data center, etc. that contains one or more available media integrated. Available media may be magnetic media (e.g., floppy disks, hard disks, tapes), optical media (e.g., high-density digital video discs (DVDs), or semiconductor media (e.g., solid state disks (SSDs)).

[0125] If the function is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc., various media that can store program codes.

[0126] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0127] In summary, the present application provides a massage robot control method, system, medium, program product and terminal, and realizes personalized, accurate, safe and effective massage therapy by combining a massage robot control algorithm with global active planning and local passive planning. First, the massage path and target area are defined by global active planning to determine the overall direction and range of the massage. Then, passive planning is adopted locally so that the robot can make real-time adjustments based on the patient's feedback and physical condition. In addition, adaptive technology is used during the massage process to adjust the massage parameters and strength in real time to ensure the best massage effect. Compared with traditional massage robots, the present application can improve the accuracy and safety of treatment and reduce the safety risks caused by inadaptability to individual differences. At the same time, through the application of adaptive technology, the balance and optimization of massage effects can also be achieved, solving the technical defects of existing massage robots in achieving precise control and adapting to different patient body shapes and muscle tissue characteristics. Therefore, the present application effectively overcomes the various shortcomings in the prior art and has a high industrial utilization value.

[0128] The above embodiments are merely illustrative of the principles and effects of the present application and are not intended to limit the present application. Anyone familiar with the technology may modify or change the above embodiments without violating the spirit and scope of the present application. Therefore, all equivalent modifications or changes made by a person of ordinary skill in the art without departing from the spirit and technical ideas disclosed in the present application shall still be covered by the claims of the present application.

Claims

1. A massage robot control method, characterized in that: include: Collecting image data of the subject, and constructing a three-dimensional model of the subject environment based on the image data to generate an environment model; Based on the image data, acupoints of the subject are located to generate acupoint coordinate information included in the massage task to be performed; Generate the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point according to the preset massage strategy and the acupoint coordinate information; use the preset path search algorithm to search for the path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environmental model to generate a global optimal path; The massage task is performed according to the global optimal path, and local optimization operations and adaptive admittance compliance control operations are performed during the massage process through the collected real-time feedback data until the massage task is completed.

2. The massage robot control method according to claim 1, characterized in that: The process of searching for a path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environment model to generate a global optimal path using a preset path search algorithm includes: Based on the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point, a forward search tree and a reverse search tree are constructed; Based on the forward search tree and the reverse search tree, multiple rounds of node expansion iteration operations are performed to generate a global optimal path.

3. The massage robot control method according to claim 2, characterized in that: The process of the node expansion iterative operation includes: Randomly selecting a direction for executing node expansion from the forward search tree and the reverse search tree; Randomly select a node as a node to be expanded from the search tree corresponding to the direction of the selected execution node expansion, and perform a node expansion operation in a preset expansion direction starting from the node to be expanded to generate coordinates of a new node after expansion; A collision detection operation and an encounter detection operation are performed on the expanded new node coordinates to generate a global optimal path consisting of the three-dimensional coordinates of the starting point, the coordinates of one or more new nodes, and the three-dimensional coordinates of the target point.

4. The massage robot control method according to claim 3, characterized in that: The collision detection operation and the encounter detection operation on the expanded new node coordinates include the following steps: The process of the collision detection operation includes: determining whether the coordinates of the expanded new node collide with the obstacle in the environment model, and if so, discarding the current expanded new node; otherwise, incorporating the current expanded new node into the updated path; The process of the encounter detection operation includes: determining whether the coordinates of the expanded new node meet with a node in another search tree with a different direction of executing node expansion; if an encounter occurs, outputting the current path as the global optimal path; otherwise, executing the node expansion iteration operation again.

5. The massage robot control method according to claim 1, characterized in that: The process of performing local optimization operations during the massage process by collecting real-time feedback data during the massage process includes: During the massage process, the current local environment model of the current local area is collected in real time; Based on the current local environment model, the global optimization path and the robot motion state, a corresponding artificial potential field and velocity field are generated; A local optimization operation is performed on the global optimization path in the current local environment model according to the artificial potential field and the velocity field to generate a local optimization path.

6. The massage robot control method according to claim 1, characterized in that: The process of performing adaptive admittance compliance control operation during massage by collecting real-time feedback data during massage includes: Collecting the contact force of the current target part of the subject, and obtaining the expected force of the current target part of the subject and the contact force of the target part of the previous cycle; Construct the compliance control law of the current target part based on the contact force and expected force of the current target part; Calculate the compensation contact force error according to the contact force of the current target part, the contact force of the target part in the previous cycle, and the expected force of the current target part; The current part compliance control law is updated according to the compensated contact force error, and the robot's updated acceleration, speed and moving position information are calculated according to the updated compliance control law, and the robot is controlled based on the robot's updated acceleration, speed and moving position information.

7. A massage robot control system, characterized in that: include: Data input module: used to collect image data of the subject, and build a three-dimensional model of the subject environment based on the image data to generate an environment model; Acupoint identification module: used to locate the acupoints of the subject based on the image data to generate acupoint coordinate information included in the massage task to be performed; Strategy control module: used to generate the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point according to the preset massage strategy and the acupoint coordinate information; use the preset path search algorithm to search for the path connecting the three-dimensional coordinates of the starting point and the three-dimensional coordinates of the target point in the environmental model to generate a global optimal path; Massage execution module: used to execute massage tasks according to the global optimal path, and perform local optimization operations and adaptive admittance compliance control operations during the massage process through the collected real-time feedback data until the massage task is completed.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the massage robot control method according to any one of claims 1 to 6 is implemented.

9. A computer program product, characterized in that The computer program product includes computer program codes, and when the computer program codes are executed on a computer, the computer is enabled to implement the massage robot control method as claimed in any one of claims 1 to 6.

10. An electronic terminal comprising a memory, a processor and a computer program stored in the memory, characterized in that: The processor executes the computer program to implement the massage robot control method according to any one of claims 1 to 6.

Images