CN109910024B - Human body posture recognition system for back-holding type transfer nursing robot - Google Patents
Human body posture recognition system for back-holding type transfer nursing robot Download PDFInfo
- Publication number
- CN109910024B CN109910024B CN201910256688.2A CN201910256688A CN109910024B CN 109910024 B CN109910024 B CN 109910024B CN 201910256688 A CN201910256688 A CN 201910256688A CN 109910024 B CN109910024 B CN 109910024B
- Authority
- CN
- China
- Prior art keywords
- human body
- robot
- posture
- chest
- sinθ
- 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.)
- Expired - Fee Related
Links
- 230000000474 nursing effect Effects 0.000 title claims abstract description 78
- 230000008859 change Effects 0.000 claims abstract description 11
- 210000001364 upper extremity Anatomy 0.000 claims description 32
- 210000001015 abdomen Anatomy 0.000 claims description 16
- 238000000034 method Methods 0.000 claims description 15
- 210000003141 lower extremity Anatomy 0.000 claims description 9
- 210000000689 upper leg Anatomy 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 6
- 230000005484 gravity Effects 0.000 claims description 3
- 210000002414 leg Anatomy 0.000 claims description 3
- 230000003993 interaction Effects 0.000 abstract description 6
- 238000005192 partition Methods 0.000 abstract 1
- 230000036544 posture Effects 0.000 description 67
- 210000000038 chest Anatomy 0.000 description 32
- 210000000481 breast Anatomy 0.000 description 6
- 230000000875 corresponding effect Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000032683 aging Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009434 installation Methods 0.000 description 2
- 230000035882 stress Effects 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000001125 extrusion Methods 0.000 description 1
- XEBWQGVWTUSTLN-UHFFFAOYSA-M phenylmercury acetate Chemical group CC(=O)O[Hg]C1=CC=CC=C1 XEBWQGVWTUSTLN-UHFFFAOYSA-M 0.000 description 1
Images
Landscapes
- Manipulator (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention relates to a human body posture recognition system for a back-wrapping transfer nursing robot, which collects pressure distribution and change information of each partition generated during man-machine interaction in real time through an air bag type pressure sensor array arranged at a contact part of the nursing robot and a user, establishes a man-machine mechanics resolving model on a robot upper computer, combines the collected pressure information and the mechanics model to resolve real-time body posture of the user, and adjusts the robot posture by taking the body posture information as a control basis to achieve the aim of ensuring safety and comfort of the user. The invention can realize simple, unbound and accurate data acquisition under the condition of low cost, and takes the human posture information as control to drive the robot to carry out motion adjustment so as to ensure the comfortable safety of a user.
Description
Technical Field
The invention relates to the field of human body posture recognition, in particular to a human body posture recognition system for a back-holding type transfer nursing robot.
Background
China is about to enter an aging society, problems caused by aging of population are more and more serious, the problem of taking care of the old people is changed from a simple family problem to a social problem, an unbalanced population proportion brings huge impact to the old people care industry, the living and living of the old people taking care of half disability can generate huge demands for nursing work, meanwhile, greater workload can be brought to nursing staff, and the society has higher and higher call for robotization of the nursing work. The generation of the transfer nursing robot can greatly relieve the requirements of society on nursing staff, and the robot can assist the old people with inconvenient actions or other nursed persons to carry out daily movement at different positions in places such as families, hospitals, nursing institutions and the like.
The nursing robot directly contacts with the body of the cared person in the process of executing movement, so that the safety and the comfort of the cared person are guaranteed to be the vital requirements in the process of man-machine interaction. At present, the transfer and care robot belongs to an emerging direction, the related technology is not mature, and the research on the safety control strategy of the transfer and care robot is still few. The main problems of the safety control method of the transfer nursing robot are that: how to ensure the safety and comfort of the cared person during the movement performed by the robot.
In the human-computer interaction process, the comfort level of a user is closely related to the posture of the user, and in order to ensure the comfort level of the user, the nursing robot can perform corresponding action adjustment according to the posture of the user, so that the human body can reach a more comfortable posture. Because the human body structure is complicated, the human body cannot be simply and roughly regarded as a rigid body, otherwise, the judgment of the comfort degree is influenced. At present, methods based on computer vision and wearable motion sensors are mainly used for recognizing human body gestures. According to the method for acquiring the information through the computer vision, the Chinese patent 201810402486.X needs to acquire the information through a camera, is high in cost and is easily influenced by external interference such as light and the like to generate uncertainty on an identification result. The chinese patent cn201621078680.x is a wearable motion sensor, which is cumbersome and burdensome to wear and is not suitable for a long time.
Due to the complexity of the human body structure, the contact between the human body and the nursing robot is not completely fit, so the posture of the human body is not consistent with the posture of the nursing robot, and the posture of the human body is an important basis for judging whether a user is comfortable, so that the human body posture is necessarily recognized according to the distribution condition of the pressure actually applied to the human body. In the process of man-machine interaction, in order to ensure the comfort of a user, the nursing robot can perform corresponding action adjustment according to the posture of the user. Therefore, it is a problem to be considered by those skilled in the art to provide a simple, non-binding and accurate human body gesture recognition system to ensure the safety and comfort of human body during human-computer interaction.
Disclosure of Invention
Aiming at the defects in the prior art, the invention aims to solve the technical problem of providing a human body posture recognition system of a back-and-forth holding type transfer nursing robot. The system adopts the air bag type pressure sensor array to collect pressure data of the robot contacting with the human body, obtains human body posture through the human-machine mechanics calculation model, can realize simple, unbound and accurate data acquisition under the condition of low cost, and drives the robot to move and adjust the human body posture information as a control basis to ensure the comfortable safety of a user.
The invention aims to conveniently and quickly identify the body posture of a user so as to provide reference for the control of a robot. The invention collects the pressure distribution and change information of each subarea generated during man-machine interaction in real time through the air bag type pressure sensor array arranged on the contact part of the nursing robot and a user, simultaneously establishes a man-machine mechanical calculation model on the upper computer of the robot, combines the collected pressure information and the mechanical model to calculate the real-time body posture of the user, and adjusts the posture of the robot by taking the body posture information as a control basis to achieve the aim of ensuring the safety and comfort of the user.
The invention solves the technical problem by adopting the technical scheme that a human body posture recognition system of a face-to-back holding type transfer nursing robot is provided, the system comprises an air bag type pressure sensor array, sole pressure sensors and a nursing robot, wherein the sole pressure sensors are arranged on pedals of the nursing robot for placing two feet of a human body; the nursing robot adopts a back-clasping mode to move the position of a nursed person, and comprises a robot body, an upper computer and a robot motion controller, wherein the robot body comprises a moving part and a back-clasping part, the back-clasping part drives a mechanical arm and a chest backup plate by an electric cylinder to realize that the position of the mechanical arm of the robot and the angle change of the chest backup plate carry out back-clasping of the nursed person, the movement of the spatial position of the chest backup plate is realized by the rotation of the mechanical arm around a robot chassis and the rotation of the mechanical arm, and the rotation of the chest backup plate is realized by the electric cylinder between the mechanical arm and the chest backup plate;
the system comprises the following steps:
s1, information acquisition and processing:
the part of the nursing robot, which is in contact with the human body, is a chest backup plate, the upper limbs of the human body are divided into four parts, namely an upper chest, a lower chest, an upper abdomen and a lower abdomen, the mass centers of the upper chest, the lower chest, the upper abdomen and the lower abdomen are respectively recorded as A, B, C and D, the airbag type pressure sensor array is laid on the chest backup plate of the nursing robot and is provided with four sensing units which work independently, and each sensing unit correspondingly detects the pressure applied to one mass center position; the air bag type pressure sensor array is connected with an upper computer of the nursing robot, and data are transmitted to the upper computer through a data acquisition card;
s2, constructing a human-machine mechanical resolving model of nursing robot posture and human upper limb weight distribution:
the method comprises the following steps of obtaining pressures generated at different parts when a user body of the nursing robot is in contact with the nursing robot in any posture by constructing a human-machine mechanical calculation model of the posture and the weight distribution of the human body of the nursing robot in an upper computer, and specifically comprises the following steps:
establishing a rectangular coordinate system by taking the connecting part of a mechanical arm of the nursing robot and a chassis of the robot as a coordinate origin O, taking the direction above the ground as the positive direction of the Y direction and the direction of a human body in the horizontal direction as the positive direction of the X direction; the included angle between the chest backup plate of the nursing robot and the X direction is recorded as thetamThe included angles between the four parts of the upper limb of the human body and the horizontal plane are respectively thetah1、θh2、θh3And thetah4The pressure values of four sensing units corresponding to the air bag type pressure sensor array are respectively F1、F2、F3And F4(ii) a Satisfying the formulas (1) to (8) according to the posture stress relation of the upper limbs of the human body:
f1×cos(θh1-θm)+F1×sin(θh1-θm)+F1i+G1×sinθh1＝0 (1)
G1+F1i×sinθh1+F1×cosθm+f1×sinθm＝0 (2)
f2×cos(θh2-θm)+F2×sin(θh2-θm)+F2i+G2×sinθh2＝0 (3)
G2+F2i×sinθh2+F2×cosθm+f2×sinθm＝0 (4)
f3×cos(θh3-θm)+F3×sin(θh3-θm)+F3i+G3×sinθh3＝0 (5)
G3+F3i×sinθh3+F3×cosθm+f3×sinθm＝0 (6)
f4×cos(θh4-θm)+F4×sin(θh4-θm)+F4i+G4×sinθh4＝0 (7)
G4+F4i×sinθh4+F4×cosθm+f4×μ×sinθm＝0 (8)
wherein f is1、f2、f3And f4The friction force respectively borne by four parts of the upper limbs of the human body is F × mu, mu is the friction coefficient of the material of the chest backup plate, and F is1＝F1×μ、f2＝F2×μ、f3＝F3×μ、f4＝F4×μ；θmThe method comprises the steps of obtaining a target value by a robot controller; g1、G2、G3And G4Are the gravity borne by four parts of the upper limbs of the human body, F1i、F2i、F3iAnd F4iThe internal forces of the upper chest, the lower chest, the upper abdomen and the lower abdomen are recorded, and the total weight of the legs and the feet of the human body is 34.5 percent, so F1i、F2i、F3iAnd F4iThe value of (c) is obtained by equations (9) to (12):
wherein Fs is plantar pressure;
simultaneous solution of the above equations (1) - (12) based on the numerical change of the bladder type pressure sensor arrayThe upper computer obtains the included angles theta between the four parts of the upper limb of the human body and the horizontalh1、θh2、θh3And thetah4Thereby recognizing the posture of the upper limb of the human body;
and comparing the human body posture recognition result with a preset human body comfortable posture, and taking the difference value of the human body posture recognition result and the preset human body comfortable posture as a control target to be brought into the robot motion controller, so that the nursing robot moves and adjusts the human body posture to a reasonable position.
Compared with the prior art, the invention has the beneficial effects that:
according to the invention, the airbag type pressure sensor array is directly placed on the robot, the human posture is recognized without constraint through pressure and the established human-machine mechanics calculation model, and meanwhile, the recognized human posture is used as the control basis of the nursing robot, so that the self posture of the nursing robot is adjusted, and finally, a user is maintained in a comfortable posture, the human posture can be recognized accurately, the wearing of the user is not needed, the burden on the user is not generated, the installation is more concealed and convenient, the hardware cost can be greatly reduced, and the robot is more easily accepted by industrial personnel and the user.
The system adopts the air bag type pressure sensor, four sensing units are sequentially arranged side by side from top to bottom to form a 4 x 1 array form, each sensing unit works independently, the pressure distribution condition can be acquired through distributed arrangement, the cost is low, the structure is simple, and the wearing comfort is good.
Drawings
FIG. 1 is a bladder type pressure sensor array;
FIG. 2 is a schematic representation of a care robot equipped with an array of bladder type pressure sensors;
FIG. 3 is a schematic view of a part of a mechanical model established for an upper limb of a human body according to the present invention;
FIG. 4 is a model diagram of solving for internal forces of a human body according to the present invention;
FIG. 5 is a diagram of a system component model of the present invention;
in the figure, 1, a gas bag type pressure sensor array; 2. a chest rest plate; 3. a data acquisition card; 4. a plantar pressure sensor; 5. an upper computer; 6 robot motion controller; 7 robot chassis; 8 mechanical arm.
Detailed Description
Specific examples of the present invention are given below. The specific examples are intended to be illustrative of the invention only and are not intended to limit the scope of the claims of the present application.
The invention discloses a back-holding type transfer nursing robot-oriented human body posture recognition system (short for system), which provides a non-binding rapid human body posture recognition system, and comprises an air bag type pressure sensor array 1, a sole pressure sensor 4 and a transfer nursing robot, wherein the air bag type pressure sensor array converts air bag internal air pressure change information generated when an air bag bears external force extrusion into pressure information, the pressure information of the air bag at different positions is respectively and independently measured in an array air bag mode to obtain pressure distribution information, and data is transmitted to an upper computer 5 through a data acquisition card 3. The sole pressure sensors are arranged on pedals of the nursing robot for placing the feet of the human body, and are used for measuring the pressure of the human body distributed on the feet. The transfer nursing robot adopts a back-clasping mode to move a nursed person, and comprises a robot body, an upper computer 5 and a robot motion controller 6, wherein the robot body comprises a moving part and a back-clasping part, the back-clasping part is used for carrying the nursed person back onto the robot seat from a seat or bedside or other positions, the back-clasping part drives a mechanical arm 8 and a chest backup plate by an electric cylinder to realize that the position of the mechanical arm of the robot and the angle change of the chest backup plate carry the nursed person back, the movement of the spatial position of the chest backup plate is realized by the rotation of the mechanical arm around a robot chassis 7 and the rotation of the mechanical arm, and the rotation of the chest backup plate is realized by the electric cylinder between the mechanical arm and the chest backup plate.
The system comprises the following steps:
s1, information acquisition and processing:
the part of the transfer nursing robot, which is in contact with the human body, is a chest backup plate, pressure is mainly generated by upper limbs of the human body and the chest backup plate, the upper limbs of the human body are divided into an upper chest part, a lower chest part, an upper abdomen part and a lower abdomen part, the mass centers of the upper chest part, the lower chest part, the upper abdomen part and the lower abdomen part are respectively recorded as A, B, C and D, the airbag type pressure sensor array is laid on the chest backup plate of the transfer nursing robot, the airbag type pressure sensor array is provided with four sensing units which work independently, and each sensing unit correspondingly detects the pressure borne by one mass center position; the air bag type pressure sensor array is connected with an upper computer of the transfer nursing robot, and data are transmitted to the upper computer through a data acquisition card;
s2, constructing a human-machine mechanical resolving model of nursing robot posture and human upper limb weight distribution:
the pressure generated by different parts when the body of a user is in contact with the nursing robot in any posture of the transfer nursing robot is obtained by constructing a human-machine mechanical calculation model of the posture and the weight distribution of the human body of the nursing robot in the upper computer, and the method comprises the following specific steps:
establishing a rectangular coordinate system by taking the connecting part of a mechanical arm of the transfer nursing robot and a chassis of the robot as a coordinate origin O, taking the direction above the ground as the positive direction of the Y direction and the direction of the human body in the horizontal direction as the positive direction of the X direction; the included angle between the chest backup plate of the nursing robot and the X direction is recorded as thetamThe included angles between the four parts of the upper limb of the human body and the horizontal plane are respectively thetah1、θh2、θh3And thetah4The pressure values of four sensing units corresponding to the air bag type pressure sensor array are respectively F1、F2、F3And F4(ii) a Satisfying the formulas (1) to (8) according to the posture stress relation of the upper limbs of the human body:
f1×cos(θh1-θm)+F1×sin(θh1-θm)+F1i+G1×sinθh1＝0 (1)
G1+F1i×sinθh1+F1×cosθm+f1×sinθm＝0 (2)
f2×cos(θh2-θm)+F2×sin(θh2-θm)+F2i+G2×sinθh2＝0 (3)
G2+F2i×sinθh2+F2×cosθm+f2×sinθm＝0 (4)
f3×cos(θh3-θm)+F3×sin(θh3-θm)+F3i+G3×sinθh3＝0 (5)
G3+F3i×sinθh3+F3×cosθm+f3×sinθm＝0 (6)
f4×cos(θh4-θm)+F4×sin(θh4-θm)+F4i+G4×sinθh4＝0 (7)
G4+F4i×sinθh4+F4×cosθm+f4×μ×sinθm＝0 (8)
wherein F1, F2, F3 and F4 are friction forces respectively exerted on four parts of the upper limb of the human body, and F is F × mu, mu is the friction coefficient of the material of the breast backup plate, and F is the friction force of the four parts of the upper limb of the human body, and F is the friction coefficient of the material of the breast backup plate1＝F1×μ、f2＝F2×μ、f3＝F3×μ、f4＝F4×μ；θmThe method comprises the steps of obtaining a target value by a robot controller; g1、G2、G3And G4Respectively the gravity borne by four parts of the upper limbs of the human body, the total weight of the human body is G, and according to the human anatomy data, the weight of the human body is 47 percent of the total weight of the human body, so that the total weight of G1, G2, G3 and G4 are approximately divided into 0.1175G by quarters of the human body; due to the complexity of the structure of the human body, there is internal force in each part of the body, and it is recorded that the internal forces on the upper chest, the lower chest, the upper abdomen and the lower abdomen are F1i、F2i、F3iAnd F4iIf the total weight of the legs and feet of the human body is 34.5%, F1i、F2i、F3iAnd F4iThe value of (d) can be obtained by the following equation:
wherein Fs is plantar pressure; according to the numerical change of the air bag type pressure sensor array, the four parts of the upper limb of the human body and the horizontal included angles theta are obtained in an upper computer by simultaneously solving the equationh1、θh2、θh3And thetah4Thereby recognizing the posture of the upper limb of the human body;
s3, constructing a kinematics model of the posture of the nursing robot and the angles of all joints of the lower limbs of the human body:
let us remember that the thigh length of human body is H1The length of the shank is H2The angle between thigh and horizontal is thetaH1The angle between the lower leg and the horizontal is thetaH2The coordinate of the midpoint E of the line where the lower part of the chest rest plate coincides with the crotch of the human body is expressed as (X)E，YE) And the coordinate of the middle point of the heel of the human foot is marked as F (X)F，YF) (ii) a The angles of the joints of the lower limbs of the user of the nursing robot in any postures are obtained by constructing a kinematic model of the postures of the nursing robot and the angles of the joints of the lower limbs of the human body.
And S4, calculating the angles of all joints of the lower limbs of the human body according to the postures of the nursing robot.
Measuring the body data of the user, and bringing the body data into the human body with the thigh length of H1The length of the shank is H2Then, the posture of the lower limbs of the human body meets the following conditions:
wherein the midpoint E of the line joining the lower part of the breast-rest and the crotch part of the human bodyCoordinate (X)E，YE) The coordinate point F (X) of the middle point of the heel of the human foot can be obtained by performing kinematics positive solution through data in a motion controller of the nursing robotF，YF) For the preset value, the joint angle of the lower limb of the human body is obtained by solving the formula (13) and the formula (14), namely the included angle between the thigh and the horizontal is thetaH1The angle between the lower leg and the horizontal is thetaH2；
Through the steps, the main joint angles of the human body posture can be solved, and the human body posture recognition is finally realized. And comparing the human body posture recognition result with a preset human body comfortable posture, taking the difference value of the human body posture recognition result and the preset human body comfortable posture as a control target, and bringing the control target into a nursing robot controller to enable the nursing robot to move and adjust the human body posture to a reasonable position.
The robot motion controller is a PMAC motion controller, and the preset human body comfortable posture is obtained by a large number of experimental statistics in the early stage.
With reference to fig. 2, the airbag type pressure sensor array of the embodiment is placed on the breast backup plate of the nursing robot, because of the complexity of the human body structure, each part of the upper limb of the human body is not completely attached to the breast backup plate, but forms a certain angle with the horizontal, when the upper limb of the user contacts with the breast backup plate of the nursing robot, the upper limb of the user extrudes the airbag type pressure sensor array to change the pressure in the airbag, the sensor transmits the air pressure change information to the upper computer, the upper computer calculates the contact pressure and the distribution information of the human body and the robot, and then the pressure information is brought into a human-machine mechanical calculation model built in the upper computer, namely the equation built in the step S2, and the included angle between each part of the human body and the horizontal plane is solved, so that. And then, the posture of the robot can be adjusted according to the solved and recognized human body posture through a pre-established human body comfort level standard, and finally the purpose of meeting the safety and comfort of a user is achieved.
With reference to fig. 5, the system of the invention collects human body pressure signals by an air bag type pressure sensor array and a sole pressure sensor, wherein the air bag type pressure sensor array is arranged on a breast backup plate of a nursing robot to collect the contact pressure of the upper limbs of a user and the robot, the sole pressure sensor is arranged on a bottom pedal of the nursing robot to collect the pressure born by the feet of the human body, the two sensors send the collected pressure signals to an upper computer, the human body posture is identified by a pre-established human mechanics resolving model, and finally the posture and the track of the robot are corrected and adjusted by comparing the current human body posture with a standard comfortable posture.
The invention mainly aims at a back-holding type transfer nursing robot, the service target of the robot is a nursed person with inconvenient actions, and when the robot is contacted with the nursed person, the moving action process of the robot ensures that the safety and the comfort of the nursed person are very important. For the nursed person, the influence of the posture of the nursing robot on the comfort level is the largest, the nursing robot needs to be adjusted according to the posture of the human body, the nursing robot is adjusted to maintain the relatively comfortable posture of the nursed person as a target, and the nursing robot needs to be capable of efficiently and quickly recognizing the posture of the human body. The invention uses the air bag type pressure sensor array to collect the pressure and distribution information of the contact between the robot and the human body, identifies the human body posture according to the established human-machine mechanical calculation model, and can accurately identify the human body posture by combining the data of the robot kinematic model and the robot motion controller (which is a controller for controlling the motor and can control the motor to rotate and read the current position of the motor), thereby better meeting the requirement of the robot on adjustment according to the human body posture, and having the advantages of simple installation, lower cost, strong environment anti-interference capability and no constraint on the human body.
Nothing in this specification is said to apply to the prior art.
Claims (2)
1. A human body posture recognition system facing a back-holding type transfer nursing robot comprises an air bag type pressure sensor array, sole pressure sensors and the nursing robot, wherein the sole pressure sensors are arranged on pedals of the nursing robot for placing two feet of a human body; the nursing robot adopts a back-clasping mode to move the position of a nursed person, and comprises a robot body, an upper computer and a robot motion controller, wherein the robot body comprises a moving part and a back-clasping part, the back-clasping part drives a mechanical arm and a chest backup plate by an electric cylinder to realize that the position of the mechanical arm of the robot and the angle change of the chest backup plate carry out back-clasping of the nursed person, the movement of the spatial position of the chest backup plate is realized by the rotation of the mechanical arm around a robot chassis and the rotation of the mechanical arm, and the rotation of the chest backup plate is realized by the electric cylinder between the mechanical arm and the chest backup plate;
the system comprises the following steps:
s1, information acquisition and processing:
the part of the nursing robot, which is in contact with the human body, is a chest backup plate, the upper limbs of the human body are divided into four parts, namely an upper chest, a lower chest, an upper abdomen and a lower abdomen, the mass centers of the upper chest, the lower chest, the upper abdomen and the lower abdomen are respectively recorded as A, B, C and D, the airbag type pressure sensor array is laid on the chest backup plate of the nursing robot and is provided with four sensing units which work independently, and each sensing unit correspondingly detects the pressure applied to one mass center position; the air bag type pressure sensor array is connected with an upper computer of the nursing robot, and data are transmitted to the upper computer through a data acquisition card;
s2, constructing a human-machine mechanical resolving model of nursing robot posture and human upper limb weight distribution:
the method comprises the following steps of obtaining pressures generated at different parts when a user body of the nursing robot is in contact with the nursing robot in any posture by constructing a human-machine mechanical calculation model of the posture and the weight distribution of the human body of the nursing robot in an upper computer, and specifically comprises the following steps:
establishing a rectangular coordinate system by taking the connecting part of a mechanical arm of the nursing robot and a chassis of the robot as a coordinate origin O, taking the direction above the ground as the positive direction of the Y direction and the direction of a human body in the horizontal direction as the positive direction of the X direction; the included angle between the chest backup plate of the nursing robot and the X direction is recorded as thetamThe included angles between the four parts of the upper limb of the human body and the horizontal plane are respectively thetah1、θh2、θh3And thetah4The pressure values of four sensing units corresponding to the air bag type pressure sensor array are respectively F1、F2、F3And F4(ii) a Satisfying the formulas (1) to (8) according to the posture stress relation of the upper limbs of the human body:
f1×cos(θh1-θm)+F1×sin(θh1-θm)+F1i+G1×sinθh1＝0 (1)
G1+F1i×sinθh1+F1×cosθm+f1×sinθm＝0 (2)
f2×cos(θh2-θm)+F2×sin(θh2-θm)+F2i+G2×sinθh2＝0 (3)
G2+F2i×sinθh2+F2×cosθm+f2×sinθm＝0 (4)
f3×cos(θh3-θm)+F3×sin(θh3-θm)+F3i+G3×sinθh3＝0 (5)
G3+F3i×sinθh3+F3×cosθm+f3×sinθm＝0 (6)
f4×cos(θh4-θm)+F4×sin(θh4-θm)+F4i+G4×sinθh4＝0 (7)
G4+F4i×sinθh4+F4×cosθm+f4×μ×sinθm＝0 (8)
wherein f is1、f2、f3And f4The friction force respectively borne by four parts of the upper limbs of the human body is F × mu, mu is the friction coefficient of the material of the chest backup plate, and F is1＝F1×μ、f2＝F2×μ、f3＝F3×μ、f4＝F4×μ；θmThe method comprises the steps of obtaining a target value by a robot controller; g1、G2、G3And G4Are the gravity, G, on four parts of the upper limbs of the human body1、G2、G3And G4Is the quartering of the weight of the human trunk; f1i、F2i、F3iAnd F4iRespectively, to remember the internal forces on the upper and lower chest, upper and lower abdomenThe total weight of the legs and feet is 34.5%, F1i、F2i、F3iAnd F4iThe value of (c) is obtained by equations (9) to (12):
wherein Fs is plantar pressure;
according to the numerical change of the air bag type pressure sensor array, the four parts of the upper limb of the human body and the horizontal included angle theta are respectively obtained in an upper computer by simultaneously solving the equations (1) - (12)h1、θh2、θh3And thetah4Thereby recognizing the posture of the upper limb of the human body;
and comparing the human body posture recognition result with a preset human body comfortable posture, and taking the difference value of the human body posture recognition result and the preset human body comfortable posture as a control target to be brought into the robot motion controller, so that the nursing robot moves and adjusts the human body posture to a reasonable position.
2. The system for recognizing the posture of the human body as claimed in claim 1, wherein the lower limb posture recognition is performed after the upper limb posture recognition, and the specific process is as follows:
let us remember that the thigh length of human body is H1The length of the shank is H2The angle between thigh and horizontal is thetaH1The angle between the lower leg and the horizontal is thetaH2The coordinate of the midpoint E of the line where the lower part of the chest rest plate coincides with the crotch of the human body is expressed as (X)E，YE) Human footThe coordinate of the mid-point of the heel is denoted as F (X)F，YF)；
Measuring the body data of the user, and bringing the body data into the human body with the thigh length of H1The length of the shank is H2Then the posture of the lower limbs of the human body satisfies the formulas (13) and (14):
wherein the coordinate (X) of the center point E of the line joining the lower part of the chest support and the crotch part of the human bodyE，YE) The coordinate point F (X) of the middle point of the heel of the human foot can be obtained by performing kinematics positive solution through data in the robot motion controllerF，YF) For the preset value, the joint angle of the lower limb of the human body is obtained by solving the formula (13) and the formula (14), namely the included angle between the thigh and the horizontal is thetaH1The angle between the lower leg and the horizontal is thetaH2；
Through the steps, the main joint angles of the human body posture can be solved, and the human body posture recognition is finally realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910256688.2A CN109910024B (en) | 2019-04-01 | 2019-04-01 | Human body posture recognition system for back-holding type transfer nursing robot |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910256688.2A CN109910024B (en) | 2019-04-01 | 2019-04-01 | Human body posture recognition system for back-holding type transfer nursing robot |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109910024A CN109910024A (en) | 2019-06-21 |
| CN109910024B true CN109910024B (en) | 2020-10-09 |
Family
ID=66968002
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910256688.2A Expired - Fee Related CN109910024B (en) | 2019-04-01 | 2019-04-01 | Human body posture recognition system for back-holding type transfer nursing robot |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109910024B (en) |
Families Citing this family (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110097024B (en) * | 2019-05-13 | 2020-12-25 | 河北工业大学 | Human body posture visual recognition method of transfer, transportation and nursing robot |
| CN111564026A (en) * | 2020-03-23 | 2020-08-21 | 广东艾诗凯奇智能科技有限公司 | Posture correction method based on neck massager and neck massager |
| CN111714324A (en) * | 2020-05-07 | 2020-09-29 | 广西科技大学 | Man-machine interaction force acquisition system |
| CN111637959B (en) * | 2020-06-11 | 2021-12-03 | 中汽研汽车检验中心（天津）有限公司 | Method for testing position and quality of mass center of each part of human body |
| CN111993436B (en) * | 2020-08-21 | 2023-11-21 | 山东科亿宏智能科技有限公司 | Full-automatic transfer robot and working method |
| CN117690541B (en) * | 2024-02-01 | 2024-04-30 | 深圳大学总医院 | Nursing recording system |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5148557A (en) * | 1990-08-27 | 1992-09-22 | Vladimir Fridman | Invalid lift and transport apparatus |
| JP2005328950A (en) * | 2004-05-19 | 2005-12-02 | Toshiaki Hara | Apparatus and method for shifting |
| JP5773696B2 (en) * | 2011-03-25 | 2015-09-02 | 富士機械製造株式会社 | Stand-up motion assist robot |
| KR101394896B1 (en) * | 2012-10-22 | 2014-05-27 | 한국생산기술연구원 | robot of transportation for patients nursing |
| WO2017014134A1 (en) * | 2015-07-17 | 2017-01-26 | 大和ハウス工業株式会社 | Transfer assistance device |
| JP6547563B2 (en) * | 2015-09-30 | 2019-07-24 | 富士通株式会社 | Detection program, detection method and detection apparatus |
| JP6726880B2 (en) * | 2016-01-29 | 2020-07-22 | パナソニックＩｐマネジメント株式会社 | Robot, robot control method, and program |
| WO2018105034A1 (en) * | 2016-12-06 | 2018-06-14 | 株式会社アートプラン | Transfer device |
| CN107088128B (en) * | 2017-05-03 | 2019-03-19 | 河北工业大学 | It is a kind of to move the behavior safety control method for multiplying nursing robot |
| CN106983619B (en) * | 2017-05-15 | 2022-03-22 | 河北工业大学 | Transfer, transport and nursing robot |
| CN107825469B (en) * | 2017-12-04 | 2023-09-08 | 河北工业大学 | Double-arm moving and riding robot simulation experiment platform and test method thereof |
| CN108705512B (en) * | 2018-05-29 | 2020-08-04 | 浙江大学 | Can take advantage of and carry formula both arms omnidirectional movement nursing robot |
-
2019
- 2019-04-01 CN CN201910256688.2A patent/CN109910024B/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN109910024A (en) | 2019-06-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109910024B (en) | Human body posture recognition system for back-holding type transfer nursing robot | |
| CN110279557B (en) | Control system and control method for lower limb rehabilitation robot | |
| US10420695B2 (en) | Exoskeleton apparatus driven by pneumatic artificial muscle with functions of upper limb assist and rehabilitation training | |
| CN111631726B (en) | Upper limb function evaluation device and method and upper limb rehabilitation training system and method | |
| CN107088128B (en) | It is a kind of to move the behavior safety control method for multiplying nursing robot | |
| CN111604890B (en) | Motion control method suitable for exoskeleton robot | |
| CN203694079U (en) | Master-slave massage robot | |
| Mukai et al. | Tactile-based motion adjustment for the nursing-care assistant robot RIBA | |
| CN203417440U (en) | Composite sensing system for wearable pneumatic lower limb rehabilitation robot | |
| JP2020151469A (en) | Adjustment method of human body support device and system thereof | |
| JP3229392U (en) | Support device system and its support device | |
| CN106419929B (en) | Quantitative detection device for posture balance stability of Parkinson disease patient | |
| CN106112985B (en) | Exoskeleton hybrid control system and method for lower limb walking aid machine | |
| CN107825469B (en) | Double-arm moving and riding robot simulation experiment platform and test method thereof | |
| CN205126722U (en) | Low limbs function rehabilitation training robot | |
| CN110584911A (en) | Intelligent nursing bed based on prone position recognition | |
| CN111568393B (en) | Individuation traditional chinese medical science pulse-taking system based on artificial intelligence | |
| Jiang et al. | Research progress and prospect of nursing robot | |
| CN107536311B (en) | Intelligent multifunctional seat system | |
| TWI652039B (en) | Simple detection method and system for sarcopenia | |
| CN210962909U (en) | Multi-posture lower limb rehabilitation robot | |
| CN111685769A (en) | Exoskeleton function detection system | |
| Wu et al. | Robotic cane as a soft superlimb for elderly sit-to-stand assistance | |
| CN211300956U (en) | Horizontal lower limb rehabilitation robot | |
| CN210962908U (en) | Sitting type lower limb rehabilitation robot |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201009 |