A motion control method and system for a rehabilitation robot

Abstract

The present invention belongs to the field of rehabilitation instrument control technology, and relates to a motion control method and system for a rehabilitation therapy robot, the method comprising obtaining an original image of an area to be massaged; obtaining acupoint information of the area to be massaged according to the original image; determining trajectory parameters of the mechanical arm of the rehabilitation therapy robot according to the acupoint information; performing trajectory planning according to the trajectory parameters to obtain an operation trajectory; and driving the mechanical arm to operate according to the operation trajectory to achieve rehabilitation movement. According to the solution of the present invention, the problems of complex operation procedures and low treatment efficiency of the current rehabilitation therapy robot are solved.

Description

Technical Field

[0001] The present invention generally relates to the field of rehabilitation instrument control technology. More specifically, the present invention relates to a motion control method and system for a rehabilitation therapy robot. Background Art

[0002] With the development of society, work pressure is getting higher and higher, and the proportion of sub-healthy people is increasing. At present, the sub-healthy group has exceeded 70%. People's health needs are increasing day by day, and this part of the population has a need for medical care. At the same time, the trend of population aging is intensifying, the proportion of the elderly population is increasing, the problem of elderly care is becoming increasingly serious, the labor cost is high, and it is becoming more and more difficult to recruit workers. The demand for massage and moxibustion robots in the field of elderly care and rehabilitation treatment will gradually increase. At present, the public's awareness of health and physiotherapy has also increased, and the per capita investment in health care has also gradually increased.

[0003] With the increasing demand for health and the continuous advancement of robotics, collaborative robotics and artificial intelligence, the performance and functions of collaborative robots will gradually improve, and they will be used more and more in daily medical scenarios. At present, the collaborative robot products used for physical therapy are mainly based on automatic acupoint massage and meridian dredging. For patients with soft tissue cervical spondylosis, frozen shoulder, lumbar myofasciitis, and soft tissue adhesions and pain caused by muscle injuries, the intelligent robot system is used to operate the robot arm, thereby helping patients achieve rehabilitation and physical therapy effects in different dimensions and different parts.

[0004] However, the current domestic physiotherapy robots mainly mark the human body when performing physiotherapy operations on patients, and then perform massage and other operations accordingly. After completing the marking, the doctor needs to select the corresponding starting point based on experience to start one by one. On the one hand, this method requires manual re-marking every time, resulting in low efficiency of the physiotherapy process. On the other hand, it requires marking the patient, which is inconvenient and the patient's willingness is low. Moreover, the current physiotherapy equipment for different parts has different focuses, and it is impossible to achieve comprehensive physiotherapy operations.

[0005] Based on this, how to solve the current problems of complex operation procedures and low treatment efficiency of rehabilitation robots is one of the current research directions. Summary of the invention

[0006] To solve one or more of the above technical problems, the present invention proposes to determine the corresponding trajectory parameters by identifying acupoint information, and perform path planning in combination with the trajectory parameters, which effectively simplifies the operation process and achieves more accurate rehabilitation treatment. To this end, the present invention provides solutions in the following aspects.

[0007] In the first aspect, the present invention provides a motion control method for a rehabilitation therapy robot, comprising: acquiring an original image of an area to be massaged; obtaining acupoint information of the area to be massaged based on the original image; determining trajectory parameters of a mechanical arm of the rehabilitation therapy robot based on the acupoint information, wherein the trajectory parameters include distance characteristics, time characteristics, and motion process characteristics; performing trajectory planning based on the trajectory parameters to obtain an operation trajectory; and driving the mechanical arm to operate according to the operation trajectory to achieve rehabilitation movement.

[0008] In one embodiment, the trajectory planning includes movement trajectory planning, point working time planning and motion process planning.

[0009] In one embodiment, the movement trajectory planning includes: determining the point where the acupoint is located and the line segment between the points according to the acupoint to obtain point features and line segment features; determining the angle between the line segment feature and the baseline according to a preset baseline; selecting the acupoint point as the starting point, and selecting the next trajectory point according to a preset rule.

[0010] In one embodiment, the preset rules include: the distance between acupuncture points is the smallest, and / or the angle between the line segment feature and the reference line is the smallest.

[0011] In one embodiment, the preset rules further include: calculating a comprehensive score according to the distance between the acupuncture points and the angle between the line segment feature and the baseline; and selecting the acupuncture point with the highest comprehensive score as the next trajectory point.

[0012] In one embodiment, the calculation formula of the comprehensive score includes: x=αL+βθ, x is the importance of the next trajectory point, α is the importance of the distance, L is the distance between the two acupoints, β is the importance of the angle, and θ is the angle between the line segment feature and the baseline.

[0013] In one embodiment, the point working time planning includes: setting the working time according to the preset point working time and / or the importance of the acupoint.

[0014] In one embodiment, the motion process planning includes: obtaining the rehabilitation level of the area to be massaged, and setting the time and number of reciprocating motions of the robot arm according to the rehabilitation level.

[0015] In one embodiment, it also includes: after determining the moving trajectory, reproducing the running trajectory through a teaching process, and storing the running trajectory to drive the robot arm to operate.

[0016] In the second aspect, the present invention also provides a motion control system for a rehabilitation therapy robot, comprising: a processor; a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a motion control method for a rehabilitation therapy robot as described above is implemented.

[0017] The beneficial effects of the present invention are as follows: according to the scheme of the present invention, by automatically planning the operation trajectory of the robot arm, the operation efficiency can be effectively improved. At the same time, by combining the automatically acquired trajectory parameters for trajectory planning, the operation efficiency and ease of operation of the rehabilitation robot are effectively improved, and the accuracy of treatment can be effectively improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0019] Figure 1 is a flow chart schematically illustrating a motion control method for a rehabilitation robot according to an embodiment of the present invention;

[0020] Figure 2 is a schematic diagram schematically showing component modules of a rehabilitation therapy robot according to an embodiment of the present invention;

[0021] Figure 3 is a schematic diagram schematically illustrating the setting of acupoint coordinates according to an embodiment of the present invention;

[0022] Figure 4 is a schematic diagram schematically illustrating a first running trajectory according to an embodiment of the present invention;

[0023] Figure 5 is a schematic diagram schematically illustrating a second running trajectory according to an embodiment of the present invention;

[0024] Figure 6 is a schematic diagram schematically illustrating a third running trajectory according to an embodiment of the present invention;

[0025] Figure 7 Schematically shows a structural block diagram of a motion control system for a rehabilitation therapy robot according to this embodiment. DETAILED DESCRIPTION

[0026] 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 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 those skilled in the art without creative work are within the scope of protection of the present invention.

[0027] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0028] Figure 1 is a flow chart schematically illustrating a motion control method 100 for a rehabilitation therapy robot according to an embodiment of the present invention.

[0029] like Figure 1 As shown, at step S101, an original image of the area to be massaged is obtained. In some embodiments, a depth camera may be used to obtain an original image of the patient.

[0030] At step S102, the acupoint information of the area to be massaged is obtained based on the original image. After the depth camera obtains the acupoint data, the acupoints can be selected through the software interface, the path can be planned, and inappropriate path points can be dragged or deleted to make a reasonable plan. Furthermore, acupoint recognition can collect a large amount of human body data models through the depth camera, and then use the neural network algorithm to train the data model to achieve the ability to automatically obtain acupoints. The functions of the automatic acupoint acquisition function include: (1) Identifying acupoints on the neck, shoulders, waist, buttocks, arms, legs, and abdomen. (2) The ability to avoid the spine, back of the head, and special parts. (3) Add acupoint names and categories to the corresponding acupoints.

[0031] At step S103, the trajectory parameters of the mechanical arm of the rehabilitation robot are determined according to the acupoint information. In some embodiments, the trajectory parameters may include three parts: distance feature, time feature and process feature.

[0032] At step S104, trajectory planning is performed according to the trajectory parameters to obtain the running trajectory. In some embodiments, the trajectory parameters may include distance characteristics, time characteristics and process characteristics. Accordingly, trajectory planning includes moving trajectory planning, point working time planning and motion process planning.

[0033] In some embodiments, the movement trajectory planning includes determining the point where the acupoint is located and the line segment between the points according to the acupoint to obtain the point feature and the line segment feature. The angle between the line segment feature and the baseline is determined according to the preset baseline. The acupoint is selected as the starting point, and the next trajectory point is selected according to the preset rules. In an application scenario, the preset rules include the minimum distance between the acupoints, and / or the minimum angle between the line segment feature and the baseline.

[0034] In another application scenario, the comprehensive score can also be calculated based on the distance between acupuncture points and the angle between the line feature and the baseline. The acupuncture point with the highest comprehensive score is selected as the next trajectory point. The calculation formula for the comprehensive score includes: x = αL + βθ, where x is the importance of the next trajectory point, α is the importance of the distance, L is the distance between the two acupuncture points, β is the importance of the angle, and θ is the angle between the line feature and the baseline.

[0035] Point working time planning includes setting working time according to preset point working time and / or acupoint importance. Movement process planning includes obtaining the rehabilitation level of the area to be massaged, and setting the time and number of reciprocating movements of the robot arm according to the rehabilitation level.

[0036] In step S105, the robot arm is driven to operate according to the operation trajectory to achieve rehabilitation movement.

[0037] Furthermore, after the moving trajectory is determined according to the above method, the running trajectory can be reproduced through a teaching process, and the running trajectory can be stored to drive the robot arm to operate.

[0038] Next, the solution of the present invention will be further described in detail with reference to specific embodiments.

[0039] like Figure 2 As shown in the figure, the rehabilitation robot mainly includes a visual camera, a host computer module, a robotic arm, an MCU, a DC motor, a pressure sensor, a temperature sensor, a distance sensor and a voice module.

[0040] The visual camera can be used to obtain the human body contour coordinate model and data points or acupuncture points, including the direction vector of each coordinate acupuncture point. The host computer module is used to process the data flow of internal information between the camera, robotic arm, lower computer and other modules. The robotic arm module serves as the actuator of the massage process, replacing human labor. The communication process between the host computer and the robotic arm can use 5G and Bluetooth modules as data transmission channels. The MCU module is responsible for processing the information of each sensor and interacting with the host module. The connected devices include peripheral pressure sensors, temperature sensors, distance sensors, and voice recognition modules to obtain various types of information during operation. The human-machine delivery interface is mainly the device operation interface. At the same time, the device working status can be controlled by an Android tablet via Bluetooth, and the device can be debugged and controlled via a wireless network.

[0041] In actual operation, the original image of the patient is obtained through a visual camera, and the acupoint information is obtained through image analysis and processing. The acupoints can also be marked by clicking the acupoint information on the picture.

[0042] When planning the distance, the trajectory has two characteristic parameters, one is the point where the acupuncture point is located, and the other is the curve segment formed between the points, which are called point feature and line segment feature respectively. Add corresponding actions to the point feature and line segment feature for massage. Figure 3 As shown, A, B, C, D, E, and F are point features, where the point feature is a coordinate point with a direction vector. Line segments AB, BC, CD, etc. are line segment features, where the line segment features can be straight lines or curves. In the process of generating trajectories, the system must make corresponding judgments. By default, the back of the human body is used as the reference plane, the spine is used as the center reference line, and the acupoints are projected on the back reference plane. The smaller the angle between the formed line segment AB and the spine line, and the shorter the distance relative to other points, the system will give priority to connecting that acupoint. At the same time, the system selects the point closest to the shoulder reference line and the spine center line as the starting point, or the point closest to the coccyx and the spine center line as the starting point, or other special acupoints (position points) as the starting point for the reference feature formation. Among them, the shoulder reference line is a line segment formed by the feature points obtained by the camera.

[0043] After the starting point is selected, the system judges the adjacent acupuncture points and compares the distance and angle between the coordinate points. When the line segment AB is less than AC, AB is given priority. When the distance is equal, the larger or smaller angle α is given priority as the next trajectory point. On the other hand, these points can also be introduced into the following calculation mechanism, x = αL + βθ, x is the importance of the next trajectory point, α is the importance of the distance, L is the distance between the two acupuncture points, β is the importance of the angle, and θ is the angle between the line segment feature and the baseline, thus forming the following Figure 4 , Figure 5 or Figure 6 The trajectory in .

[0044] When planning the point working time, the working time of each massage head (or robotic arm) on the acupoints A to B can be freely set.

[0045] When planning the motion process, on each trajectory, the robotic arm can perform reciprocating motion on this trajectory to provide enhanced treatment according to the patient's requirements or the doctor's judgment.

[0046] Furthermore, the external force changes can be obtained in real time through the pressure sensor, and the external force changes can be continuously detected through the six-dimensional force control and pressure judgment process, so as to adjust the trajectory according to the external force changes. For example, the running trajectory, point working time and / or movement process can be adaptively adjusted according to the external force changes.

[0047] By planning the above process, the corresponding operation trajectory can be obtained, and the robotic arm can be driven to execute the operation trajectory, thereby realizing rehabilitation operation.

[0048] On the basis of completing the basic functions, the zero-force dragging function can also be used to drag the robotic arm for manual teaching, and the functional characteristics of the massage robot can be specifically combined to develop a highly reproducible trajectory action. The system automatically learns and records the path of the manipulation, and repeats the simulated massage action. The zero-force dragging technology can be based on the operation mechanism of the robotic arm, and the storage system that records the artificial dragging trajectory can reproduce the last motion trajectory for reuse. The implementation method is: drag the robotic arm to form the motion trajectory of the robotic arm, and install a six-dimensional force sensor at the end of the robotic arm. The force sensor collects the magnitude of the force at the end of the massage head and the angle vector of the force during the teaching process of the master teacher, and transmits the data to the host computer for storage, so that the patient can call it the next time.

[0049] During the massage process of the robotic arm, the end-use technique function can be used. It is required to have functions such as kneading, pulling, pushing, pressing, and vibration. The techniques are defined as follows:

[0050] Kneading: Using the end of the treatment head as the fulcrum, gently and slowly move the skin in the treatment area to create internal friction between the subcutaneous tissue layers.

[0051] Plucking: Press on the acupoint or a certain part, and use appropriate force to pluck back and forth in the direction perpendicular to the muscle fibers. It is like plucking the strings of a guitar. It is called plucking method, also known as plucking method, plucking method, finger plucking method, etc.

[0052] Push: Use the massage head instead of fingers or palms to apply force to a certain part of the patient, and push in a single direction in a straight line.

[0053] Press: Use the massage head instead of the fingertips or palms to apply pressure to a certain part or acupoint of the body, press down, and keep a certain pressure there for a while, then knead it slightly. This method is often used in conjunction with kneading.

[0054] Vibration: A technique that uses high-frequency vibration of the end massage head to cause passive vibration of the applied area.

[0055] In addition, a corresponding treatment plan can be formulated for the patient through the software operation interface. The doctor first confirms the massage head to be used and installs it. Then, the software controls the visual camera at the end of the robotic arm to generate acupoint trajectories through algorithm calculations. After the trajectory is generated, the point features or line segment features of each trajectory correspond to the five techniques of kneading, pulling, pushing, pressing, and vibrating. After selecting the technique, select the duration, and finally form a prescription for the patient's physical therapy.

[0056] If the patient feels that the force is too strong or not strong enough during use, they can control the force of the device through voice. The force range of voice control requires setting a threshold to avoid excessive force adjustment by voice.

[0057] The pressure at the end of the robotic arm can be sensed in time through the force sensor to ensure that the pressure applied by the end massage head on the patient is balanced. While ensuring the pressure balance, the pressure applied at the end is used as a controllable parameter and can be adjusted by voice. During the massage process, when the patient stands up and impacts the end of the robotic arm, the robotic arm moves in the opposite direction to avoid the patient.

[0058] Figure 7 Schematically shows a structural block diagram of a motion control system for a rehabilitation therapy robot according to this embodiment.

[0059] The present invention also provides a motion control system for a rehabilitation robot. Figure 7 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a motion control method for a rehabilitation robot according to the first aspect of the present invention is implemented.

[0060] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0061] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that may be used to store the required information and may be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0062] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0063] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A motion control method for a rehabilitation robot, characterized in that: include: Acquire an original image of the area to be massaged; Obtaining acupoint information of the area to be massaged according to the original image; Determine trajectory parameters of the mechanical arm of the rehabilitation robot according to the acupoint information, wherein the trajectory parameters include distance characteristics, time characteristics, and motion process characteristics; Performing trajectory planning according to the trajectory parameters to obtain an operating trajectory; Driving the robot arm to operate according to the operation trajectory to achieve rehabilitation movement; The trajectory planning includes moving trajectory planning, point working time planning and motion process planning; The mobile trajectory planning includes: According to the acupoints, the points where the acupoints are located and the line segments between the points are determined to obtain point features and line segment features; Determine the angle between the line segment feature and the baseline according to the preset baseline; Select an acupuncture point as the starting point, and select the next trajectory point according to the preset rules; The preset rules include: The distances between acupuncture points are minimal, and / or The angle between the line segment feature and the reference line is the smallest; The preset rules also include: Calculating a comprehensive score based on the distance between the acupuncture points and the angle between the line segment feature and the baseline; The acupuncture point with the highest comprehensive score is selected as the next trajectory point; The calculation formula for the comprehensive score includes: x=αL+βθ, where x is the importance of the next trajectory point, α is the importance of the distance, L is the distance between the two acupuncture points, β is the importance of the angle, and θ is the angle between the line segment feature and the baseline; The working time planning of the points includes: Set working time according to preset point working time and / or acupoint importance; The motion process planning includes: The rehabilitation level of the area to be massaged is obtained, and the time and frequency of the reciprocating motion of the robot arm are set according to the rehabilitation level.

2. The motion control method for a rehabilitation robot according to claim 1, characterized in that: Also includes: After the moving trajectory is determined, the running trajectory is reproduced through the teaching process, and the running trajectory is stored to drive the robot arm to operate.

3. A motion control system for a rehabilitation robot, characterized in that: include: processor; A memory storing computer program instructions, which, when executed by the processor, implements a motion control method for a rehabilitation robot according to claim 1 or 2.

Images