WO2025214523A1 - 面瘫康复训练机器人、系统及方法 - Google Patents

面瘫康复训练机器人、系统及方法

Info

Publication number
WO2025214523A1
WO2025214523A1 PCT/CN2025/100624 CN2025100624W WO2025214523A1 WO 2025214523 A1 WO2025214523 A1 WO 2025214523A1 CN 2025100624 W CN2025100624 W CN 2025100624W WO 2025214523 A1 WO2025214523 A1 WO 2025214523A1
Authority
WO
WIPO (PCT)
Prior art keywords
facial
traction
patient
rehabilitation training
head
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
PCT/CN2025/100624
Other languages
English (en)
French (fr)
Inventor
韩挺
杨雄杰
辛露怡
袁文昱
刘芸含
王铭萱
虞聪
邓则灵
朱兆鹏
李世亭
赵华
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
XinHua Hospital Affiliated To Shanghai JiaoTong University School of Medicine
Shanghai Jiao Tong University
Original Assignee
XinHua Hospital Affiliated To Shanghai JiaoTong University School of Medicine
Shanghai Jiao Tong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by XinHua Hospital Affiliated To Shanghai JiaoTong University School of Medicine, Shanghai Jiao Tong University filed Critical XinHua Hospital Affiliated To Shanghai JiaoTong University School of Medicine
Publication of WO2025214523A1 publication Critical patent/WO2025214523A1/zh
Pending legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H1/00—Apparatus for passive exercising; Vibrating apparatus; Chiropractic devices, e.g. body impacting devices, external devices for briefly extending or aligning unbroken bones
    • A61H1/02—Stretching or bending or torsioning apparatus for exercising
    • A—HUMAN NECESSITIES
    • A63—SPORTS; GAMES; AMUSEMENTS
    • A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
    • A63B23/00—Exercising apparatus specially adapted for particular parts of the body
    • A63B23/025—Exercising apparatus specially adapted for particular parts of the body for the head or the neck
    • A63B23/03—Exercising apparatus specially adapted for particular parts of the body for the head or the neck for face muscles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
    • A61H2201/12—Driving means
    • A61H2201/1207—Driving means with electric or magnetic drive
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
    • A61H2201/50—Control means thereof
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
    • A61H2201/50—Control means thereof
    • A61H2201/5007—Control means thereof computer controlled
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
    • A61H2205/00—Devices for specific parts of the body
    • A61H2205/02—Head
    • A61H2205/022—Face

Definitions

  • the present invention relates to the technical field of rehabilitation medical equipment, and in particular to a facial paralysis rehabilitation training robot, system and method.
  • Bell’s palsy is an acute unilateral paralysis of the facial nerve, resulting in a complete or partial loss of the ability to move the facial muscles on the affected side of the face. Patients mainly experience unilateral weakness of the facial muscles, resulting in asymmetry of the entire facial area. Due to the inability to control the facial muscles, patients with facial palsy often have less flexible facial movements and may have other symptoms, including drooling, speech disorders, and nasal congestion. Although facial palsy is not life-threatening, it is still relatively common and can have a really serious impact on a person's quality of life, with important consequences in terms of psychological impact and physiological burden. Bell's palsy accounts for 65% to 75% of peripheral facial nerve palsy cases, with an incidence of 20 to 30 cases per 100,000 people per year. Currently, rehabilitation training for patients with Bell's palsy usually requires the use of professional physical therapists for rehabilitation training.
  • the existing Chinese patent application document with publication number CN207286301U discloses a facial paralysis rehabilitation device for neurology, including a seat, with a turntable rotatably installed on the left and right sides of the seat respectively, and each turntable is eccentrically provided with a curved arm and a handle, the curved arm includes a mounting section connected to the turntable and a free section extending vertically, each free section is connected to a mask half body adapted to the shape of the human face, the two mask halves are connected by an elastic element, and each mask half body is provided with an arc-shaped slide, the arc-shaped slide extending from the lower end of the mask half body to the upper end of the mask half body, and a ball is slidably installed in the arc-shaped slide, and the ball near the face position protrudes from the surface of the mask half body.
  • the ball when the mask half moves left and right, the ball can slide up and down in the arc-shaped slide, so that the ball can stimulate the patient's face in the up and down directions.
  • the treatment effect is poor and there is room for improvement.
  • the purpose of the present invention is to provide a facial paralysis rehabilitation training robot, system and method.
  • a facial paralysis rehabilitation training robot includes a head-mounted robot body, a control system, a power system, a traction system and a power supply system; the control system, the power system and the traction system are all installed on the head-mounted robot body, the power supply system serves as a power source, and the traction system extends from the head-mounted robot body to the facial area; under the action of the control system, the power system drives the traction system to stretch or relax the patient's target facial muscles.
  • the traction system includes a traction rope, medical tape and a roller, one end of the traction rope is wound around the roller, and the other end of the traction rope extends to the facial area, and the medical tape sticks the end of the traction rope extending to the facial area to the target facial muscle of the patient.
  • the head-mounted robot body is provided with guide through-holes, and the free end of the traction rope passes through one or more guide through-holes and extends to the facial area of the head-mounted robot body.
  • the power system drives the roller to rotate, and the power system includes a steering gear, a servo motor or a stepper motor.
  • the traction system and the power system are arranged in correspondence, and multiple groups of the traction system and the power system are arranged on the head-mounted robot body, and the rollers of any traction system are located on the center line of the head-mounted robot body.
  • the medical tape includes an adhesive portion and a connecting portion, the adhesive portion is fitted to the patient's face, and the connecting portion is detachably connected to one end of the traction rope extending to the facial area of the head-mounted robot body.
  • the power system is provided with a rotary potentiometer to read the rotation angle information, forming a PID closed-loop control system;
  • the mathematical expression of the PID closed-loop control system can be expressed as:
  • u(t) is the control signal output by the controller at time t
  • Kp, Ki, and Kd are the proportional gain, integral gain, and differential gain, respectively
  • e(t) is the error between the input signal and the desired value.
  • the integral term of the error is the derivative of the error, that is, the rate of change of the error.
  • a facial paralysis rehabilitation training system also includes a visual device, which collects muscle movement information on the normal side of the patient's face.
  • the control system controls the traction system based on the muscle movement information on the normal side collected by the visual device to drive the muscles on the patient's facial paralysis side to make corresponding movements.
  • it also includes a cloud and a mobile terminal, the mobile terminal is communicatively connected to the cloud, and the mobile terminal and the cloud are respectively communicatively connected to the control system of the head-mounted robot body.
  • a facial paralysis rehabilitation training method includes the following steps: a visual device collects muscle movement information on the normal side of the patient's face, the visual device sends the collected muscle movement information on the normal side of the patient's face to a control system, and the control system controls the traction system based on the muscle movement information on the normal side collected by the visual device to drive the muscles on the patient's facial paralysis side to perform corresponding movements;
  • the mobile terminal sends control information to the control system, and the control system controls the traction system according to the control information to drive the muscles on the patient's facial paralysis side to make corresponding movements;
  • the mobile terminal sends instructions to the cloud
  • the cloud processes the received instructions to generate control information
  • the cloud sends the generated control information to the control system.
  • the control system controls the traction system according to the control information to drive the muscles on the patient's facial paralysis side to make corresponding movements.
  • the present invention has the following beneficial effects:
  • the present invention uses computer vision technology to identify the movements of the patient's normal side of the face, and then uses this identified movement information to control the facial muscle repair robot. It can accurately customize rehabilitation training according to the patient's own facial movements. This can not only improve rehabilitation efficiency, but also increase the safety and comfort of the rehabilitation process to a certain extent, and promote the recovery of the paralyzed side muscles in a more natural and effective way.
  • the present invention uses guide perforations and guide panels to control the direction of the traction rope, ultimately reaching the facial area, thereby achieving guidance and control of the pulling position and direction.
  • the present invention drives the traction system to move through the power system, applying appropriate force and resistance to the patient's facial muscles to promote muscle movement and activity.
  • the range of motion of the facial muscles can be increased, the neuromuscular connection can be improved, and the recovery of facial expressions can be promoted. It can be personalized according to the patient's specific situation, providing appropriate force and resistance to help the patient gradually restore the function of the facial muscles.
  • FIG1 is a diagram showing the internal structure of a head-mounted robot according to the present invention.
  • FIG2 is a front view of the facial area of the head-mounted robot body according to the present invention.
  • FIG3 is a side view of the facial area of the head-mounted robot body according to the present invention.
  • FIG4 is a schematic diagram of the installation structure of the rotary potentiometer and the steering gear according to the present invention.
  • FIG5 is an exploded view of a detachable connection structure of a traction rope and a medical tape according to the present invention
  • FIG6 is a schematic diagram of the connection structure of the traction rope and the medical tape according to the present invention.
  • FIG7 is a logic diagram of a control system according to the present invention.
  • FIG8 is a schematic diagram showing a PID control system according to the present invention.
  • FIG9 is a diagram of a rehabilitation training robot system according to the present invention.
  • FIG10 is a diagram showing a client framework of the present invention.
  • FIG11 is a rendering of the main interface of the APP according to the present invention.
  • FIG12 is a diagram showing the effect of an APP face detection report according to the present invention.
  • FIG13 is a diagram showing the APP control page effect of the present invention.
  • FIG14 is a diagram showing the effect of APP training data recording according to the present invention.
  • FIG15 is a diagram showing an Internet of Things architecture mainly embodied in the present invention.
  • FIG16 is a diagram showing the effect of setting the APP pulling distance parameters according to the present invention.
  • FIG17 is a flowchart showing user operations according to the present invention.
  • a facial paralysis rehabilitation training robot includes a head-mounted robot body 1, a control system, a power system, a traction system, and a power supply system.
  • the control system, power system, and traction system are all mounted on the head-mounted robot body 1, with the power supply system serving as the power source.
  • the traction system extends from the head-mounted robot body 1 to the facial area. Under the control of the control system, the power system drives the traction system to stretch or relax the patient's target facial muscles.
  • the power supply can be either internal or external, and is connected to the electrical components of the facial paralysis rehabilitation training robot via wires.
  • the power supply system can be an internal power source, such as a battery. Alternatively, it can be an external power source, such as a charging port.
  • the power supply system provides power to all electrical components of the facial paralysis rehabilitation training robot.
  • the power system drives the traction system, applying appropriate force and resistance to the patient's facial muscles to promote muscle movement and activation.
  • the facial paralysis rehabilitation training robot can increase the range of motion of facial muscles, improve neuromuscular connectivity, and promote the restoration of facial expressions. It can be personalized to the patient's specific condition, providing appropriate force and resistance to help the patient gradually regain facial muscle function.
  • the traction system includes a traction rope 2, medical tape 3, and a roller 4.
  • One end of the traction rope 2 is wrapped around the roller 4, and the other end of the traction rope 2 extends to the facial area.
  • the medical tape 3 adheres the end of the traction rope 2 extending to the facial area to the patient's target facial muscles.
  • the traction system is installed inside the head-mounted robot body 1.
  • the inner wall of the head-mounted robot body 1 is provided with guide holes 5.
  • the free end of the traction rope 2 passes through one or more guide holes 5 and extends to the facial area of the head-mounted robot body 1.
  • the power system drives the roller 4 to rotate, and the power system includes a servo 6, a servo motor or a stepper motor.
  • the present application preferably adopts a 360° servo 6, and the servo 6 is installed inside the head-mounted robot body 1.
  • the servo 6 pulls the facial muscles by pulling the rope.
  • the medical tape 3 includes an adhesive portion 31 and a connecting portion 32.
  • the adhesive portion 31 fits the patient's face, and the connecting portion 32 is detachably connected to the end of the traction rope 2 extending to the facial area of the head-mounted robot body 1.
  • the connecting portion 32 of the medical tape 3 includes a connecting hole 33.
  • a limiting connecting block 21 is provided at the end of the traction rope 2 extending to the facial space.
  • the limiting connecting block 21 is installed in the connecting hole 33, and the traction rope 2 passes through the connecting portion 32 of the medical tape 3.
  • Conventional medical tape 3 will lose its stickiness with repeated use, so the present application also proposes a detachable structure.
  • the lower half of the tape is sticky, the upper half is not sticky, and there are two connecting holes 33.
  • the end of the traction rope 2 passes through a limiting connecting block 21 composed of a certain structure.
  • the inner diameter of one end of the limiting connecting block 21 is smaller than the rope. After the rope passes through, it is knotted to achieve fixation, and the whole rope passes through the connecting hole 33 of the tape to achieve fixation.
  • the ends of the traction rope 2 are attached to the corresponding facial muscles using medical tape 3.
  • the servo 6 rotates a certain angle, it pulls the traction rope 2 a certain distance, thereby moving the facial muscles.
  • These servos 6 are used to pull the muscles commonly affected by facial paralysis.
  • This application preferably selects three muscles: the frontalis, zygomaticus major, and risorius, but the muscles are not limited to these three, and the number and type of muscles can be varied.
  • a guide panel 7 is provided on the head-mounted robot body 1, and the guide panel 7 is integrally formed with or fixedly connected to the head-mounted robot body 1.
  • the traction system extends from the head-mounted robot body 1 through the guide panel 7 to the facial area, and/or the traction system extends from the head-mounted robot body 1 to the facial area without passing through the guide panel 7.
  • the power system drives the traction system to pull or relax the target facial muscles of the patient.
  • a guide perforation 5 is provided on the guide panel 7, and the free end of the traction rope 2 passes through the guide perforation 5 on the guide panel 7 and extends to the facial area of the head-mounted robot body 1.
  • the guide perforation 5 and the guide panel 7 are used to control the direction of the traction rope 2, and finally reach the facial area, thereby achieving guidance and control of the traction position and direction.
  • the traction system and the power system are arranged in a corresponding manner. Multiple sets of the traction system and the power system are provided on the head-mounted robot body 1, and the rollers 4 of any traction system are located on the center line of the head-mounted robot body 1.
  • This application takes the arrangement of three traction systems as an example, wherein two traction systems enter the facial area through the guide panel 7, and one traction system enters the facial area directly.
  • the power system is equipped with a rotary potentiometer 8 to read rotation angle information.
  • the power system uses a steering gear 6.
  • Rotary potentiometer 8 has a groove inside and a protrusion on the top of the steering gear 6. The protrusion engages with the groove inside the rotary potentiometer 8, forming a PID closed-loop control system.
  • the steering gear 6 rotates, it drives the slider inside the rotary potentiometer 8 in a circular motion, causing the resistance to change.
  • the microcontroller reads the voltage change caused by this resistance change, thereby calculating the accurate rotation angle at that time.
  • L is the ideal pulling distance
  • D is the diameter of the shaft.
  • V is the voltage detected by the angle sensor
  • Vmax is the full-rated voltage D
  • n is the number of rotations
  • D is the diameter of the shaft.
  • the control system includes a microcontroller, a wireless transmission module, switches, and control buttons.
  • the wireless transmission module provides Bluetooth and Wi-Fi support.
  • a rotary potentiometer 8 detects the rotation angle of the servo 6.
  • the switch turns the power on and off, and the control buttons switch between programs.
  • the microcontroller executes the program, reading the data from the rotary potentiometer 8 sensor and issuing commands to the servo 6.
  • the control button leads are soldered to the central square PCB, which houses the onboard wireless transmission module and microcontroller chip. When an external power source is unavailable, the system can be powered by a lithium battery. When an external power source is available, it can be connected through the charging port.
  • the servo 6 is available in two types: 180° and 360°.
  • the 180° servo 6 can achieve precise angle control within 180°, but its limited rotation angle also limits its pull distance. Therefore, in the present invention, the servo 6 preferably uses a 360° servo 6, which can achieve multiple rotations and ensure a long pull distance.
  • the 360° servo 6 is achieved by controlling the speed and is not angle-sensitive. Therefore, the present invention incorporates a rotary potentiometer 8 to measure the actual rotation angle of the servo 6 in real time, forming a closed-loop control.
  • the mathematical expression of the PID closed-loop control system can be expressed as:
  • This formula shows that the PID control system calculates the control signal based on the current error and the rate of change of the error, where u(t) is the control signal output by the controller at time t; Kp, Ki, and Kd are the proportional gain, integral gain, and differential gain, respectively; and e(t) is the error between the input signal and the desired value.
  • the integral term of the error is adjusted according to the accumulated error to eliminate the static error of the system. It is the derivative of the error, that is, the rate of change of the error, and is used to control the dynamic response of the system.
  • the calculation process of the system is as follows: the system stores the pulling distance, and the control chip first solves the rotation angular velocity according to formula (1), which corresponds to the speed parameter of the 360° servo 6 drive.
  • formula (1) corresponds to the speed parameter of the 360° servo 6 drive.
  • the servo 6 is driven to rotate, and the voltage value of the potentiometer and the number of revolutions are read in real time.
  • the actual pulling distance is calculated using formula (2), compared with the set pulling distance, and the calculation of formula (3) is performed to finally realize PID closed-loop control, and finally realize the precise rotation of the 360° servo 6, which ultimately brings about a precise skin pulling distance.
  • servo 6 operates in different sequences and frequencies, achieving different facial movement training. For example, in a 10-minute training session, brow raising training begins with 5 minutes and 20 repetitions, followed by 5 minutes of smiling training. Accordingly, servo 6, which is responsible for stretching the forehead muscles, rotates 20 times over 5 minutes, and servo 6, which is responsible for stretching the zygomatic muscles, rotates 20 times over 5 minutes, driving the muscles to contract and stretch.
  • Hardware control method There are a power switch and a program switching button on the facial muscle function repair robot. The power supply is open to realize the power on and off of the entire robot system, and the program switching button can switch different training methods. This method is relatively simple and mechanical.
  • the facial paralysis rehabilitation training system also includes a visual device that collects muscle movement information on the normal side of the patient's face. Based on this information, a control system controls a stretching system to move the muscles on the paralyzed side of the patient's face. This allows patients to actively participate in rehabilitation training. Active patient participation in facial paralysis training is crucial. Self-directed facial muscle stretching exercises can strengthen neuromuscular connectivity and promote recovery of facial muscle function. Our facial muscle repair robot can assist with these training efforts, enhancing their effectiveness.
  • the present invention also proposes an innovative control strategy, the core of which is to use computer vision technology to identify the movements of the patient's normal side of the face, and then use this identified movement information to control the facial muscle repair robot. It can accurately customize rehabilitation training according to the patient's own facial movements. This can not only improve the efficiency of rehabilitation, but also increase the safety and comfort of the rehabilitation process to a certain extent, and can promote the recovery of the paralyzed side muscles more naturally and effectively.
  • the present invention adopts computer vision technology.
  • Computer vision technology can preferably adopt OpenFace.
  • OpenFace is an open source and high-performance facial behavior analysis tool, which is widely used in the fields of facial feature point detection, head posture estimation, facial action unit recognition, etc. It is based on machine learning methods, especially deep learning, to train facial recognition and analysis models.
  • the present invention uses openface detection to obtain the user's facial AU data. "AU” usually refers to "Action Units". The AU data obtained by analysis is then communicated with the facial muscle function repair robot through the computer's communication module, such as a Bluetooth module, a wireless module, etc., to guide the facial muscle repair robot to make corresponding instructions.
  • the facial action of smiling usually involves AU12 (levator anguli of the lips), which involves the elevation and abduction of the lip corners.
  • f(E) represents a function that extracts the activity level of AU12 from the facial expression E and outputs a value between 0 and 1, representing the activity level of the levator anguli muscles.
  • this value exceeds the preset threshold ⁇ , the system recognizes this behavior as a smile.
  • ⁇ is an empirically determined threshold used to distinguish smiling from non-smiling expressions.
  • ⁇ can be set to 0.4.
  • Real-time monitoring and traversal detection calculate the value of each AU.
  • AU12 > 0.4 the user is deemed smiling and the facial muscle repair robot is activated to stretch the muscles at the corners of the mouth on the paralyzed side, thereby achieving a smile on the paralyzed side.
  • This approach not only increases the accuracy of the treatment process but also improves the objectivity and efficiency of the intervention through quantitative analysis.
  • the mobile terminal is communicatively connected to the cloud, and the mobile terminal and the cloud are respectively communicatively connected to the control system of the head-mounted robot body 1.
  • the remote control terminal is a mobile phone or a computer, which can remotely control the facial muscle function repair robot through wireless communication technologies such as Bluetooth or WIFI.
  • the software part of the mobile terminal has a detection function, which can evaluate the level of facial paralysis, thereby providing personalized rehabilitation treatment. Users can check the connection status of the facial muscle repair robot and can choose different modes. Users can also view their own historical training data.
  • the system uses Internet of Things technology to achieve the combination of doctor-side and user-side.
  • Users can send instructions to the server through the mobile terminal at any location, or use Bluetooth direct connection or manual adjustment buttons to switch the use status and program of the facial muscle function repair robot.
  • the MQTT protocol can be used.
  • the user can also make an appointment with a therapist to re-evaluate his current status.
  • the therapist can remotely use the server as an intermediary to remotely adjust the parameters and training program of the facial traction distance for the user.
  • the adjustment method is shown in Figure 16, which visualizes the position of the patch on the face and can modify the distance that each facial muscle needs to be assisted in traction according to the actual situation of the patient. After clicking Save, the facial muscle traction will be performed according to the saved parameters during the next rehabilitation.
  • the invention also supports communication and docking between users and therapists. Users can make an appointment with therapists to re-evaluate them and modify and adjust the programs and parameters of their facial muscle function repair robots to achieve more personalized and better rehabilitation results.
  • the user operation process is shown in Figure 17.
  • the user puts on the facial muscle function repair robot, turns on the power switch, then opens the software of the host computer, selects a rehabilitation course, follows the voice and visual guidance of the rehabilitation course, faces the camera of the host computer, and makes facial movements.
  • the facial muscle function repair robot will also drive the traction of the paralyzed side according to the user's facial movements to realize the rehabilitation training process.
  • a facial paralysis rehabilitation training method includes the following steps: a visual device collects muscle movement information on the normal side of the patient's face, the visual device sends the collected muscle movement information on the normal side of the patient's face to a control system, and the control system controls the traction system based on the muscle movement information on the normal side collected by the visual device to drive the muscles on the patient's facial paralysis side to perform corresponding movements;
  • the mobile terminal sends control information to the control system, and the control system controls the traction system according to the control information to drive the muscles on the patient's facial paralysis side to make corresponding movements;
  • the mobile terminal sends instructions to the cloud
  • the cloud processes the received instructions to generate control information
  • the cloud sends the generated control information to the control system.
  • the control system controls the traction system according to the control information to drive the muscles on the patient's facial paralysis side to make corresponding movements.
  • system and its various devices, modules, and units provided by the present invention in addition to implementing the system and its various devices, modules, and units provided by the present invention in purely computer-readable program code, it is entirely possible to implement the same functions of the system and its various devices, modules, and units provided by the present invention in the form of logic gates, switches, application-specific integrated circuits, programmable logic controllers, and embedded microcontrollers by logically programming the method steps. Therefore, the system and its various devices, modules, and units provided by the present invention can be considered a hardware component, and the devices, modules, and units included therein for implementing various functions can also be considered as structures within the hardware component; the devices, modules, and units for implementing various functions can also be considered as both software modules implementing the method and structures within the hardware component.

Landscapes

  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Physical Education & Sports Medicine (AREA)
  • Pain & Pain Management (AREA)
  • Otolaryngology (AREA)
  • Epidemiology (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Rehabilitation Therapy (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Animal Behavior & Ethology (AREA)
  • Public Health (AREA)
  • Veterinary Medicine (AREA)
  • Rehabilitation Tools (AREA)

Abstract

本发明提供了一种面瘫康复训练机器人、系统及方法，包括头戴式机器人本体、控制系统、动力系统、牵拉系统以及电源系统；所述控制系统、动力系统以及牵拉系统三者均安装在头戴式机器人本体上，所述电源系统作为动力源，所述牵拉系统自头戴式机器人本体延伸至面部区域；在所述控制系统的作用下，所述动力系统带动牵拉系统对患者的目标面部肌肉进行牵拉或放松。利用计算机视觉技术来识别患者正常一侧面部的动作，然后通过这些识别出的动作信息来控制这个面肌修复机器人，能够精准地根据患者自身的面部动作来定制化康复训练，这样不仅可以提高康复效率，还能在一定程度上增加康复过程的安全性和舒适度，可以更自然、更有效地促进瘫痪侧肌肉的恢复。

Description

面瘫康复训练机器人、系统及方法 技术领域
本发明涉及康复医疗设备技术领域，具体地，涉及一种面瘫康复训练机器人、系统及方法。
背景技术
贝尔麻痹(Bell’s palsy)是面神经的急性单侧性麻痹，导致患者在受影响一侧面部完全或部分丧失自主运动面部肌肉的能力。患者主要表现为面部肌肉单侧无力，导致整个面部区域不对称，由于无法控制面部肌肉，面瘫患者脸部的动作往往不够灵活，且会存在其他症状，包括流口水、语言障碍和鼻塞等等。虽然面瘫没有生命危险，但它仍然相对常见，并会对一个人的生活质量产生真正严重的影响，在心理影响和生理负担方面产生重要的后果。贝尔麻痹占据了外周面神经麻痹病例的65％至75％，发病率为每年每10万人中的20至30例。目前，针对贝尔面瘫患者的康复训练通常需要依靠专业的物理治疗师进行康复训练。
现有公开号为CN207286301U的中国专利申请文献，其公开了一种神经内科用面瘫康复装置，包括座椅，所述座椅的左右两侧分别转动安装有一转盘，每所述转盘上均偏心设置有一曲臂和一把手，所述曲臂包括连接所述转盘的安装段和竖向延伸的自由段，每所述自由段上连接有与人体面部形状相适配的面罩半体，两所述面罩半体之间通过弹性元件相连接，每所述面罩半体上均开设有弧形滑道，所述弧形滑道由所述面罩半体的下端延伸至所述面罩半体的上端，所述弧形滑道内滑动安装有滚珠，靠近面部位置的所述滚珠凸出所述面罩半体表面。
现有技术中的面瘫康复装置，当面罩半体左右移动时，滚珠在弧形滑道内可以实现上下方向的滑动，使得滚珠可以实现上下方向对患者面部产生刺激，治疗效果差，存在待改进之处。
发明内容
针对现有技术中的缺陷，本发明的目的是提供一种面瘫康复训练机器人、系统及方法。
根据本发明提供的一种面瘫康复训练机器人,包括头戴式机器人本体、控制系统、动力系统、牵拉系统以及电源系统；所述控制系统、动力系统以及牵拉系统三者均安装在头戴式机器人本体上，所述电源系统作为动力源，所述牵拉系统自头戴式机器人本体延伸至面部区域；在所述控制系统的作用下，所述动力系统带动牵拉系统对患者的目标面部肌肉进行牵拉或放松。
优选地，所述牵拉系统包括牵引绳、医用胶带以及滚轮，所述牵引绳的一端绕设在滚轮上，所述牵引绳的另一端延伸至面部区域，所述医用胶带将牵引绳延伸至面部区域的一端粘贴在患者的目标面部肌肉上。
优选地，所述头戴式机器人本体上设置有引导穿孔，所述牵引绳的自由端穿过一个或多个引导穿孔延伸至头戴式机器人本体的面部区域。
优选地，所述动力系统带动滚轮转动，所述动力系统包括舵机、伺服电机或步进电机。
优选地，所述牵拉系统和动力系统二者呈对应设置，所述牵拉系统和动力系统二者在头戴式机器人本体上设置有多组，且任一所述牵拉系统的滚轮均位于头戴式机器人本体的中心线上。
优选地，所述医用胶带包括粘贴部和连接部，所述粘贴部与患者面部贴合，所述连接部与牵引绳延伸至头戴式机器人本体的面部区域的一端可拆卸连接。
优选地，所述动力系统上设置有旋转电位器读取旋转角度信息，形成PID闭环控制系统；PID闭环控制系统的数学表达式可以表示为：
其中，u(t)是控制器在时间t输出的控制信号；Kp，Ki，Kd分别是比例增益，积分增益和微分增益；e(t)是输入信号与期望值之间的误差；表示误差的积分项，是误差的导数，即误差的变化率。
根据本发明提供的一种面瘫康复训练系统,还包括视觉装置，所述视觉装置采集患者面部正常侧的肌肉运动信息，所述控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。
优选地，还包括云端和移动端，所述移动端与云端通信连接，且所述移动端和云端二者分别与头戴式机器人本体的控制系统通信连接。
根据本发明提供的一种面瘫康复训练方法,训练方法包括如下步骤：视觉装置采集患者面部正常侧的肌肉运动信息，视觉装置将采集的患者面部正常侧的肌肉运动信息发送至控制系统，控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
或，移动端向控制系统发送控制信息，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
或，移动端向云端发送指令，云端对接收到的指令进行处理生成控制信息，云端将生成的控制信息发送至控制系统，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。
与现有技术相比，本发明具有如下的有益效果：
1、本发明通过利用计算机视觉技术来识别患者正常一侧面部的动作，然后通过这些识别出的动作信息来控制这个面肌修复机器人，能够精准地根据患者自身的面部动作来定制化康复训练，这样不仅可以提高康复效率，还能在一定程度上增加康复过程的安全性和舒适度，可以更自然、更有效地促进瘫痪侧肌肉的恢复。
2、本发明通过引导穿孔和引导面板用来控制牵引绳的走向，最终达到面部区域，实现对牵拉位置和方向的引导控制
3、本发明通过动力系统带动牵拉系统运动，向患者的面部肌肉施加适当的力量和阻力，以促进肌肉的运动和活动，通过佩戴面瘫康复训练机器人并进行特定的面部运动和训练，可以增加面部肌肉的活动范围，改善神经肌肉连接，并促进面部表情的恢复，它可以根据患者的具体情况进行个性化调整，提供适当的力量和阻力，以帮助患者逐渐恢复面部肌肉的功能。
附图说明
通过阅读参照以下附图对非限制性实施例所作的详细描述，本发明的其它特征、目的和优点将会变得更明显：
图1为本发明主要体现头戴式机器人本体内部结构图；
图2为本发明主要体现头戴式机器人本体面部区域的正面示意图；
图3为本发明主要体现头戴式机器人本体面部区域的侧面示意图；
图4为本发明主要体现旋转电位器与舵机安装结构示意图；
图5为本发明主要体现牵引绳与医用胶带可拆卸连接结构的爆炸图；
图6为本发明主要体现牵引绳与医用胶带连接结构示意图；
图7为本发明主要体现控制系统的逻辑图；
图8为本发明主要体现PID控制系统的原理图；
图9为本发明主要体现康复训练机器人系统图；
图10为本发明主要体现客户端框架图；
图11为本发明主要体现APP主界面效果图；
图12为本发明主要体现APP面部检测报告效果图；
图13为本发明主要体现APP控制页面效果图；
图14为本发明主要体现APP训练数据记录效果图；
图15为本发明主要体现物联网架构图；
图16为本发明主要体现APP牵拉距离参数设置效果图；
图17为本发明主要体现用户操作流程图。
图中所示：
头戴式机器人本体1               连接孔33
牵引绳2                        滚轮4
限位连接块21                    引导穿孔5
医用胶带3                      舵机6
粘贴部31                       引导面板7
连接部32                       旋转电位器8
具体实施方式
下面结合具体实施例对本发明进行详细说明。以下实施例将有助于本领域的技术人员进一步理解本发明，但不以任何形式限制本发明。应当指出的是，对本领域的普通技术人员来说，在不脱离本发明构思的前提下，还可以做出若干变化和改进。这些都属于本发明的保护范围。
如图1、图2、图3以及图4所示，根据本发明提供的一种面瘫康复训练机器人，包括头戴式机器人本体1、控制系统、动力系统、牵拉系统以及电源系统。控制系统、动力系统以及牵拉系统三者均安装在头戴式机器人本体1上，电源系统作为动力源，牵拉系统自头戴式机器人本体1延伸至面部区域。在控制系统的作用下，动力系统带动牵拉系统对患者的目标面部肌肉进行牵拉或放松。
电源包括内置电源或外置电源，电源与面瘫康复训练机器人上的用电器件通过导线连接。电源系统可以为内置电源，例如电池。电源系统还可以为外置电源，例如充电插口。电源系统为面瘫康复训练机器人上的任一用电设备进行供电。
在控制系统的作用下，动力系统带动牵拉系统运动，向患者的面部肌肉施加适当的力量和阻力，以促进肌肉的运动和活动。通过佩戴面瘫康复训练机器人并进行特定的面部运动和训练，患者可以积极参与到面部肌肉的康复过程中。面瘫康复训练机器人的使用可以增加面部肌肉的活动范围，改善神经肌肉连接，并促进面部表情的恢复。它可以根据患者的具体情况进行个性化调整，提供适当的力量和阻力，以帮助患者逐渐恢复面部肌肉的功能。
具体地，牵拉系统包括牵引绳2、医用胶带3以及滚轮4，牵引绳2的一端绕设在滚轮4上，牵引绳2的另一端延伸至面部区域，医用胶带3将牵引绳2延伸至面部区域的一端粘贴在患者的目标面部肌肉上。进一步地，牵拉系统设置在头戴式机器人本体1的内部，头戴式机器人本体1的内壁上设置有引导穿孔5，牵引绳2的自由端穿过一个或多个引导穿孔5延伸至头戴式机器人本体1的面部区域。
动力系统带动滚轮4转动，动力系统包括舵机6、伺服电机或步进电机。本申请优选地采用360°舵机6，且将舵机6安装在头戴式机器人本体1的内部。舵机6通过牵拉绳子来牵拉面部肌肉。如图5和图6所示，医用胶带3包括粘贴部31和连接部32，粘贴部31与患者面部贴合，连接部32与牵引绳2延伸至头戴式机器人本体1的面部区域的一端可拆卸连接。所述医用胶带3的连接部32包括连接孔33，所述牵引绳2延伸至面部空间的一端设置有限位连接块21，所述限位连接块21安装在连接孔33中，所述牵引绳2穿出医用胶带3的连接部32。常规的医用胶带3会随着反复使用而失去粘性，因此本申请也提出了一种可拆卸结构。胶布下半部分有粘性，上半部分没有粘性，且有两个连接孔33，牵引绳2末端穿过某种结构体构成的限位连接块21，该限位连接块21的一端内径比绳子小一些，绳子穿过后并打结，实现固定，并整体穿过胶布的连接孔33，实现固定。
牵引绳2末端通过医用胶带3粘贴在面部相应肌肉上。当舵机6转动一定角度后，会牵拉牵引绳2移动一定距离，从而带动面部肌肉。这些舵机6用于牵拉面瘫患者常受影响的肌肉。本申请优选地，选择三块肌肉，分别是额肌、颧大肌和笑肌，但不局限于这三块肌肉，数量和种类都可以改变。
本申请提出一种可行的实施方式：头戴式机器人本体1上设置有引导面板7，引导面板7与头戴式机器人本体1一体成型或固定连接。牵拉系统自头戴式机器人本体1经过引导面板7延伸至面部区域，和/或，牵拉系统自头戴式机器人本体1不经过引导面板7延伸至面部区域。动力系统带动牵拉系统对患者的目标面部肌肉进行牵拉或放松。引导面板7上设置有引导穿孔5，牵引绳2的自由端穿过引导面板7上的引导穿孔5后延伸至头戴式机器人本体1的面部区域。引导穿孔5和引导面板7用来控制牵引绳2的走向，最终达到面部区域，实现对牵拉位置和方向的引导控制。
牵拉系统和动力系统二者呈对应设置，牵拉系统和动力系统二者在头戴式机器人本体1上设置有多组，且任一牵拉系统的滚轮4均位于头戴式机器人本体1的中心线上。本申请以设置三组牵拉系统为例，其中，两组牵拉系统经过引导面板7进入面部区域，一组牵拉系统直接进入面部区域。
如图7和图8所示，动力系统上设置有旋转电位器8读取旋转角度信息，动力系统采用舵机6，旋转电位器8内部设置有凹槽，舵机6的顶部设置有突起，舵机6顶部的凸起与旋转电位器8内部的凹槽卡接，形成PID闭环控制系统。当舵机6旋转后，带动旋转电位器8内部的滑块做圆周运动，电阻发生变化，微控制器读取到电阻变化带来的电压变化数值，从而能够求出此时准确的旋转角度。
其中，L为理想牵拉距离。为旋转角速度，D为轴的直径。
其中，La为实际牵拉距离。V为角度传感器检测到电压，Vmax为满额电压D，n为转动圈数，D为轴的直径。
控制系统包括微控制器、无线传输模块、开关以及控制按钮，无线传输模块提供蓝牙和WIFI的支持，旋转电位器8用来检测舵机6旋转角度，开关用来切断和接通电源，控制按钮用来进行程序的切换，微控制器执行程序，读取旋转电位器8传感器的数据，给舵机6组下达命令。控制按钮的引线焊接连接在中央方形的PCB上，PCB板上有板载无线传输模块和微控制器芯片。当没有外接电源的时候，可以用锂电池为该系统供电，有外接电源时候则通过充电口使用外接电源。
舵机6有180°和360°两种，其中180°舵机6可以实现在180°内的精准角度控制，但是其转动角度有限，也导致其可牵拉距离也有限。因此，在本发明中舵机6优先选择360°舵机6，可以实现多圈转动，保证牵拉距离长。然而360°舵机6是控制速度来实现的，其角度并不敏感，因此本发明加入了旋转电位器8，实时测量舵机6实际转动的角度，形成闭环控制。PID闭环控制系统的数学表达式可以表示为：
这个公式表示PID控制系统根据当前误差和误差的变化率进行控制信号的计算,其中，u(t)是控制器在时间t输出的控制信号；Kp，Ki，Kd分别是比例增益，积分增益和微分增益；e(t)是输入信号与期望值之间的误差；表示误差的积分项,根据误差累积进行调节，用于消除系统静态误差，是误差的导数，即误差的变化率,用于控制系统的动态响应。
系统的计算过程如下：系统存储牵拉距离，控制芯片根据公式(1)计算先求解出旋转角速度，对应到360°舵机6驱动的速度参数，根据程序设定，驱动舵机6旋转，并实时读取电位器的电压值和记录圈数，利用公式(2)来计算出实际牵拉距离，和设定的牵拉距离进行比较，进行公式(3)的计算，最终实现PID闭环控制，最终实现360°舵机6的精准旋转，最终带来精准的皮肤牵拉距离。
在控制系统不同程序的作用下，舵机6以不同的顺序和频次进行运作，实现不同的面部动作训练的切换。比如，有一套10分钟的训练，先抬眉训练5分钟20次，后微笑训练5分钟，那么对应的，负责牵拉额肌肉的舵机6在5分钟内反复转动20次，然后负责牵拉笑肌的舵机65分钟内反复转动20次，带动肌肉收缩和拉伸。
舵机6的程序切换控制有硬件控制和软件控制两种方式：硬件控制方式：面肌功能修复机器人上有电源开关和程序切换按钮，电源开源实现对整个机器人系统的开机和关机，程序切换按钮则可以切换不同的训练方式，这种方式相对简单机械。
根据本发明提供的一种面瘫康复训练系统,还包括视觉装置，视觉装置采集患者面部正常侧的肌肉运动信息，控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。从而使患者能够主动地进行康复训练，患者积极主动地参与面瘫训练非常重要，患者自主控制面部肌肉拉伸做训练，可以增强神经肌肉连接，促进面部肌肉功能的恢复。我们的面肌修复机器人能为他们的训练提供一定的辅助，使得训练效果更佳。
如图9所示，本发明还提出一种创新的控制策略，核心是利用计算机视觉技术来识别患者正常一侧面部的动作，然后通过这些识别出的动作信息来控制这个面肌修复机器人，能够精准地根据患者自身的面部动作来定制化康复训练，这样不仅可以提高康复效率，还能在一定程度上增加康复过程的安全性和舒适度，可以更自然、更有效地促进瘫痪侧肌肉的恢复。
即检测患者此时的面部动作并根据此来触发牵拉。关于如何检测到患者正常一侧的面部运动并根据此来触发瘫痪侧的牵拉，本发明采用计算机视觉的技术。计算机视觉技术优选地可以采用OpenFace。OpenFace是一个开源的且高性能的面部行为分析工具，广泛应用于面部特征点检测、头部姿态估计、面部动作单元识别等领域。它基于机器学习方法，特别是深度学习，来训练面部识别和分析模型。本发明利用openface检测得到用户的面部AU数据。"AU"通常指的是"ActionUnits"(动作单元)。然后将分析得到的AU数据通过计算机的通讯模块，比如蓝牙模块、无线模块等，和面肌功能修复机器人进行通信，指导面肌修复机器人作出相应的指令。
比如，微笑这个面部动作通常涉及到AU12(唇角提肌)，涉及到唇角的上提和外展，活动程度可以通过以下公式量化：
AU12＝f(E)
其中，f(E)代表一个从面部表情E中提取AU12活动水平的函数，输出一个介于0至1之间的数值，代表唇角提肌的活动程度。当此数值超过预设的阈值θ时，系统将此行为识别为微笑表情。数学上这可以表示为：
在此场景中，θ是一个经验确定的阈值，用于区分微笑与非微笑表情，如可设定θ＝0.4。通过实时监测遍历检测计算各个AU的值，当发现AU12>0.4时，判定用户正在微笑，并驱动面肌修复机器人对瘫痪侧的嘴角部分肌肉进行牵拉，从而实现瘫痪侧面部的微笑动作。这种方法不仅增加了处理过程的精确性，还通过量化分析提高了干预的客观性和效率。
如图10、图11、图12、图13、图14、图15、图16以及图17所示，还包括云端和移动端，移动端与云端通信连接，且移动端和云端二者分别与头戴式机器人本体1的控制系统通信连接。远程控制终端为手机或电脑，可以通过蓝牙或WIFI等无线通信技术实现远程对面肌功能修复机器人进行控制。移动端的软件部分具有检测功能，可以评估出面瘫等级，从而提供个性化的康复疗程。用户可以查看面肌修复机器人的连接情况，并可以选择不同的模式。用户也可以查看自己的历史训练数据。
同时该系统用物联网技术实现医生端和用户端的结合，用户可以在任何地点，通过移动端向服务器发送指令，也可以用蓝牙直接连接或者手动调节按钮的方式来切换面肌功能修复机器人的使用状态和程序。优选地，可使用mqtt协议。用户还可以预约治疗师对他的目前现状进行再次评估，治疗师根据实际情况，可以远程通过服务器作为中介，实现远程调整针对该用户的面部牵拉距离的参数和训练程序。调节方式如图16所示，可视化呈现贴片在面部的位置并可以根据患者实际情况修改需要每块面部肌肉需要辅助牵拉的距离，点击保存后，下次进行康复时就会按照保存的参数进行面部肌肉牵拉。
用户可以看到自己的训练记录，并可以设置训练方式，相比硬件控制提供了更多的操作细节，并且使用便捷，用户友好。具体原因如下：首先，相比硬件控制，软件控制能提供更多的细节和可视化的反馈，并且使得查看训练记录和设置训练方式等操作更加灵活和便捷。此外，结合物联网和互联网系统，该发明还支持用户和治疗师进行交流对接，用户可以预约治疗师对其进行重新评估，修改调整其面肌功能修复机器人的程序和参数，以达到更为个性化、更好的康复效果。
用户操作流程如图17所示，用户戴上面肌功能修复机器人，启动电源开关，然后打开上位机的软件，选择一个康复疗程，跟随康复疗程的语音和视觉引导，面朝上位机的摄像头，做着面部动作，此时面肌功能修复机器人也会根据用户的面部动作情况驱动瘫痪侧的牵拉，实现康复训练过程。
根据本发明提供的一种面瘫康复训练方法,训练方法包括如下步骤：视觉装置采集患者面部正常侧的肌肉运动信息，视觉装置将采集的患者面部正常侧的肌肉运动信息发送至控制系统，控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
或，移动端向控制系统发送控制信息，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
或，移动端向云端发送指令，云端对接收到的指令进行处理生成控制信息，云端将生成的控制信息发送至控制系统，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。
本领域技术人员知道，除了以纯计算机可读程序代码方式实现本发明提供的系统及其各个装置、模块、单元以外，完全可以通过将方法步骤进行逻辑编程来使得本发明提供的系统及其各个装置、模块、单元以逻辑门、开关、专用集成电路、可编程逻辑控制器以及嵌入式微控制器等的形式来实现相同功能。所以，本发明提供的系统及其各项装置、模块、单元可以被认为是一种硬件部件，而对其内包括的用于实现各种功能的装置、模块、单元也可以视为硬件部件内的结构；也可以将用于实现各种功能的装置、模块、单元视为既可以是实现方法的软件模块又可以是硬件部件内的结构。
在本申请的描述中，需要理解的是，术语“上”、“下”、“前”、“后”、“左”、“右”、“竖直”、“水平”、“顶”、“底”、“内”、“外”等指示的方位或位置关系为基于附图所示的方位或位置关系，仅是为了便于描述本申请和简化描述，而不是指示或暗示所指的装置或元件必须具有特定的方位、以特定的方位构造和操作，因此不能理解为对本申请的限制。
以上对本发明的具体实施例进行了描述。需要理解的是，本发明并不局限于上述特定实施方式，本领域技术人员可以在权利要求的范围内做出各种变化或修改，这并不影响本发明的实质内容。在不冲突的情况下，本申请的实施例和实施例中的特征可以任意相互组合。

Claims (10)

  1. 一种面瘫康复训练机器人，其特征在于，包括头戴式机器人本体(1)、控制系统、动力系统、牵拉系统以及电源系统；
    所述控制系统、动力系统以及牵拉系统三者均安装在头戴式机器人本体(1)上，所述电源系统作为动力源，所述牵拉系统自头戴式机器人本体(1)延伸至面部区域；
    在所述控制系统的作用下，所述动力系统带动牵拉系统对患者的目标面部肌肉进行牵拉或放松。
  2. 如权利要求1所述的面瘫康复训练机器人，其特征在于，所述牵拉系统包括牵引绳(2)、医用胶带(3)以及滚轮(4)，所述牵引绳(2)的一端绕设在滚轮(4)上，所述牵引绳(2)的另一端延伸至面部区域，所述医用胶带(3)将牵引绳(2)延伸至面部区域的一端粘贴在患者的目标面部肌肉上。
  3. 如权利要求2所述的面瘫康复训练机器人，其特征在于，所述头戴式机器人本体(1)上设置有引导穿孔(5)，所述牵引绳(2)的自由端穿过一个或多个引导穿孔(5)延伸至头戴式机器人本体(1)的面部区域。
  4. 如权利要求2所述的面瘫康复训练机器人，其特征在于，所述动力系统带动滚轮(4)转动，所述动力系统包括舵机(6)、伺服电机或步进电机。
  5. 如权利要求2所述的面瘫康复训练机器人，其特征在于，所述牵拉系统和动力系统二者呈对应设置，所述牵拉系统和动力系统二者在头戴式机器人本体(1)上设置有多组，且任一所述牵拉系统的滚轮(4)均位于头戴式机器人本体(1)的中心线上。
  6. 如权利要求2所述的面瘫康复训练机器人，其特征在于，所述医用胶带(3)包括粘贴部(31)和连接部(32)，所述粘贴部(31)与患者面部贴合，所述连接部(32)与牵引绳(2)延伸至头戴式机器人本体(1)的面部区域的一端可拆卸连接。
  7. 如权利要求1所述的面瘫康复训练机器人，其特征在于，所述动力系统上设置有旋转电位器(8)读取旋转角度信息，形成PID闭环控制系统；
    PID闭环控制系统的数学表达式可以表示为：
    其中，u(t)是控制器在时间t输出的控制信号；Kp，Ki，Kd分别是比例增益，积分增益和微分增益；e(t)是输入信号与期望值之间的误差；表示误差的积分项，是误差的导数，即误差的变化率。
  8. 一种面瘫康复训练系统，其特征在于，采用权利要求1-7任一项所述的面瘫康复训练机器人，还包括视觉装置，所述视觉装置采集患者面部正常侧的肌肉运动信息，所述控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。
  9. 如权利要求8所述的面瘫康复训练系统，其特征在于，还包括云端和移动端，所述移动端与云端通信连接，且所述移动端和云端二者分别与头戴式机器人本体(1)的控制系统通信连接。
  10. 一种面瘫康复训练方法，其特征在于，采用权利要求8所述的面瘫康复训练系统，训练方法包括如下步骤：视觉装置采集患者面部正常侧的肌肉运动信息，视觉装置将采集的患者面部正常侧的肌肉运动信息发送至控制系统，控制系统根据视觉装置采集的正常侧的肌肉运动信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
    或，移动端向控制系统发送控制信息，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动；
    或，移动端向云端发送指令，云端对接收到的指令进行处理生成控制信息，云端将生成的控制信息发送至控制系统，控制系统根据控制信息控制牵拉系统带动患者面瘫侧肌肉做出相应的运动。
PCT/CN2025/100624 2024-04-12 2025-06-12 面瘫康复训练机器人、系统及方法 Pending WO2025214523A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202410441701.2 2024-04-12
CN202410441701.2A CN118178162A (zh) 2024-04-12 2024-04-12 面瘫康复训练机器人、系统及方法

Publications (1)

Publication Number Publication Date
WO2025214523A1 true WO2025214523A1 (zh) 2025-10-16

Family

ID=91401584

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2025/100624 Pending WO2025214523A1 (zh) 2024-04-12 2025-06-12 面瘫康复训练机器人、系统及方法

Country Status (2)

Country Link
CN (1) CN118178162A (zh)
WO (1) WO2025214523A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN118178162A (zh) * 2024-04-12 2024-06-14 上海交通大学 面瘫康复训练机器人、系统及方法

Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009285115A (ja) * 2008-05-29 2009-12-10 Univ Of Tsukuba 装着型人支援装置
US20160296753A1 (en) * 2015-04-09 2016-10-13 The Regents Of The University Of California Nerve stimulation device for treating or reducing paralysis
CN209751585U (zh) * 2018-10-29 2019-12-10 广州军区广州总医院 一种面瘫训练器
CN112308037A (zh) * 2020-11-25 2021-02-02 郑州苏一电子科技有限公司 一种基于视觉感知和音频信息的面瘫检测方法
CN113069311A (zh) * 2021-05-08 2021-07-06 李鑫 一种神经内科面瘫理疗器
CN115154212A (zh) * 2022-07-01 2022-10-11 北京理工大学 一种用于远程康复的机器人训练系统
CN219355094U (zh) * 2022-12-02 2023-07-18 青岛大学 头戴式半脸面瘫辅助动作装置
CN118178162A (zh) * 2024-04-12 2024-06-14 上海交通大学 面瘫康复训练机器人、系统及方法
CN222841230U (zh) * 2024-04-12 2025-05-09 上海交通大学 面瘫康复训练机器人

Patent Citations (9)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009285115A (ja) * 2008-05-29 2009-12-10 Univ Of Tsukuba 装着型人支援装置
US20160296753A1 (en) * 2015-04-09 2016-10-13 The Regents Of The University Of California Nerve stimulation device for treating or reducing paralysis
CN209751585U (zh) * 2018-10-29 2019-12-10 广州军区广州总医院 一种面瘫训练器
CN112308037A (zh) * 2020-11-25 2021-02-02 郑州苏一电子科技有限公司 一种基于视觉感知和音频信息的面瘫检测方法
CN113069311A (zh) * 2021-05-08 2021-07-06 李鑫 一种神经内科面瘫理疗器
CN115154212A (zh) * 2022-07-01 2022-10-11 北京理工大学 一种用于远程康复的机器人训练系统
CN219355094U (zh) * 2022-12-02 2023-07-18 青岛大学 头戴式半脸面瘫辅助动作装置
CN118178162A (zh) * 2024-04-12 2024-06-14 上海交通大学 面瘫康复训练机器人、系统及方法
CN222841230U (zh) * 2024-04-12 2025-05-09 上海交通大学 面瘫康复训练机器人

Also Published As

Publication number Publication date
CN118178162A (zh) 2024-06-14

Similar Documents

Publication Publication Date Title
CN110742775B (zh) 基于力反馈技术的上肢主被动康复训练机器人系统
CN109091819B (zh) 上肢康复机器人控制系统
EP1734912B1 (en) Apparatus for rehabilitation and training
US20080234113A1 (en) Gait Rehabilitation Methods and Apparatuses
EP3654902B1 (en) Apparatuses for arm exercise
WO2025214523A1 (zh) 面瘫康复训练机器人、系统及方法
CN103142383A (zh) 康健运动训练器的主被动实现方法
CN110251898B (zh) 一种基于力反馈的手腕康复外骨骼的闭环控制系统
CN111803330A (zh) 一种上肢肘关节康复装置
CN107280910B (zh) 一种基于数据采集的自主智能按摩器及操作方法
CN118098604B (zh) 多源数据驱动的脑卒中上肢康复虚实交互方法及系统
CN114869306A (zh) 基于博弈论和sEMG的上肢康复机器人自适应控制方法及系统
US20140081432A1 (en) Method and Apparatus for Rehabilitation Using Adapted Video Games
CN106389068A (zh) 用于上肢单侧偏瘫患者自主康复训练的设备和控制方法
CN110308682B (zh) 一种背部按摩机器人控制系统及方法
CN102551999A (zh) 一种眼部肌肉锻炼装置和眼部肌肉锻炼方法
CN110812125A (zh) 一种基于六自由度机械臂的患侧手部康复训练方法及系统
CN111281752A (zh) 一种上肢康复训练系统及执行运动意图的方法
CN222841230U (zh) 面瘫康复训练机器人
CN113827920B (zh) 颞下颌关节训练装置及电子设备
CN213607940U (zh) 一种手功能障碍康复系统
CN120260821A (zh) 基于虚拟三维游戏的情景互动式肢体主被动康复训练系统
CN112545536A (zh) 基于脑可塑的动作辅助装置及其控制方法、电路
CN119386373A (zh) 一种基于机械臂按摩和电刺激的理疗方法、装置
CN119548373A (zh) 一种智能化模拟吞咽动作的康复设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 25785985

Country of ref document: EP

Kind code of ref document: A1