CN106821680A - A kind of upper limb healing ectoskeleton control method based on lower limb gait - Google Patents
A kind of upper limb healing ectoskeleton control method based on lower limb gait Download PDFInfo
- Publication number
- CN106821680A CN106821680A CN201710107188.3A CN201710107188A CN106821680A CN 106821680 A CN106821680 A CN 106821680A CN 201710107188 A CN201710107188 A CN 201710107188A CN 106821680 A CN106821680 A CN 106821680A
- Authority
- CN
- China
- Prior art keywords
- gait
- upper limbs
- data
- lower limb
- vola
- 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
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
- A61H1/0274—Stretching or bending or torsioning apparatus for exercising for the upper limbs
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
- A61B5/1038—Measuring plantar pressure during gait
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/24—Detecting, measuring or recording bioelectric or biomagnetic signals of the body or parts thereof
- A61B5/316—Modalities, i.e. specific diagnostic methods
- A61B5/389—Electromyography [EMG]
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7225—Details of analog processing, e.g. isolation amplifier, gain or sensitivity adjustment, filtering, baseline or drift compensation
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
- A61B5/7235—Details of waveform analysis
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1602—Programme controls characterised by the control system, structure, architecture
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B25—HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
- B25J—MANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
- B25J9/00—Programme-controlled manipulators
- B25J9/16—Programme controls
- B25J9/1694—Programme controls characterised by use of sensors other than normal servo-feedback from position, speed or acceleration sensors, perception control, multi-sensor controlled systems, sensor fusion
-
- 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
- A61H2001/0211—Walking coordination of arms and legs
-
- 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
- A61H2201/14—Special force transmission means, i.e. between the driving means and the interface with the user
-
- 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
- A61H2201/16—Physical interface with patient
- A61H2201/1602—Physical interface with patient kind of interface, e.g. head rest, knee support or lumbar support
- A61H2201/1635—Hand or arm, e.g. handle
- A61H2201/1638—Holding means therefor
-
- 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
- A61H2201/16—Physical interface with patient
- A61H2201/1602—Physical interface with patient kind of interface, e.g. head rest, knee support or lumbar support
- A61H2201/164—Feet or leg, e.g. pedal
- A61H2201/1642—Holding means therefor
-
- 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
- A61H2201/16—Physical interface with patient
- A61H2201/1602—Physical interface with patient kind of interface, e.g. head rest, knee support or lumbar support
- A61H2201/165—Wearable interfaces
-
- 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
- A61H2205/00—Devices for specific parts of the body
- A61H2205/06—Arms
-
- 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
- A61H2230/00—Measuring physical parameters of the user
- A61H2230/08—Other bio-electrical signals
- A61H2230/085—Other bio-electrical signals used as a control parameter for the apparatus
-
- 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
- A61H2230/00—Measuring physical parameters of the user
- A61H2230/62—Posture
- A61H2230/625—Posture used as a control parameter for the apparatus
Abstract
A kind of upper limb healing ectoskeleton control method based on lower limb gait, comprises the following steps:1) data acquisition:The collection of the electromyographic signal, joint angles and vola contact force of different gait classifications when carrying out being tested normal walking by the pressure sensor in the myoelectric sensor positioned at lower limb, motion sensor and vola;2) data prediction:Electromyographic signal, joint angles and vola contact force to collecting are pre-processed;3) Gait Recognition;4) upper limbs swing position matching:According to upper limbs swing position corresponding with recognized gait categorical match;5) ectoskeleton control:Based on the upper limbs swing position for obtaining, corresponding control instruction is sent to upper limb healing ectoskeleton driver, carry out the control of upper limb healing ectoskeleton, drive upper limbs to carry out rehabilitation training.The present invention considers that upper limbs lower limb harmony, rehabilitation efficacy are preferable.
Description
Technical field
The present invention relates to rehabilitation ectoskeleton control technology field, in particular it relates to a kind of upper limbs health based on lower limb gait
Multiple ectoskeleton control method.
Background technology
With the aging of society, the hemiplegia number caused by cardiovascular and cerebrovascular and the nervous system disease etc. increases year by year
Plus, and patient tends to rejuvenation.Clinical research shows, six months after it there is apoplexy of the hemiplegic patient of 30%-60%, upper limbs
There is not recovery feature yet;The only patient of 5%-20% completes functional rehabilitation.Traditional manual human assistance rehabilitation training
There are numerous limitation, be first the then healthy upper limbs by patient or its family since under the guidance of medical practitioner teach-by-doing
Category, nurse are manually drawn repeatedly to patient's suffering limb.With the development of science and technology, medical robot technology is quickly sent out
Exhibition, such as upper limb healing exoskeleton system.Although domestic and international researcher carries out motion work(in upper limb healing exoskeleton system auxiliary
Can rebuild in the demonstration with rehabilitation efficacy and carry out extensive work, but not reach the requirement of clinical practice also in many aspects, need
Go deep into, systematic research and exploration.
Found by the retrieval to prior art, Chinese invention patent application number:201010174806.4, title:Dermoskeleton
Bone formula upper limb rehabilitation robot.The invention is related to a kind of ectoskeleton that upper limb healing is realized by the rotation of power-assist human body shoulder blade
Formula upper limb rehabilitation robot.But it is only capable of by mechanical assistance patient's rehabilitation training of upper limbs, does not account for upper limbs-lower limb and coordinate
Property, and seldom it is related to upper limbs to do the mode of circular-rotation in the action of our daily lifes.Chinese invention patent application number:
201410217852.6, title:A kind of many position upper and lower extremities linkage healing robots.It is upper and lower the invention provides a kind of many positions
Limb linkage healing robot, it is possible to achieve the gait rehabilitation of multiple positions, adjoint swing arm is moved.Although this takes into account upper and lower
The purpose of limb harmony, but patient is still integrally fixed on rehabilitation equipment, and upper and lower extremities can not reach in daily life when training
Natural walking states, and the enjoyment that lacks training, long-term abnormal uninteresting training may cause patient to be accustomed to the mistake of itself,
Cause later stage rehabilitation efficacy it is not good be even more difficult to correct.Therefore, upper limbs-lower limb harmony is lacked in rehabilitation training to examine
Consider, training action is unnatural, because uninteresting training causes the custom mistake of patient to be the main deficiency of existing upper limb healing ectoskeleton
Part.
When the mankind normally walk, arm is suitable swing with lower extremity movement.If lower limb are subject in gait motion
Interference, such as attachment additional mass block, the Muscle electrical activity that control upper limbs swings will strengthen, and this explanation upper and lower limb of human body is in step
Motion in state is contacted in the presence of certain, and the motion of human body upper and lower extremities is interacted by nerve and produces influence.Lost for upper limbs
The patient of motor function, the positive motion of lower limb is conducive to upper limbs to recover motor function as soon as possible.Although the swing of arm does not have
There is provided direct thrust function to walking, but arms swing improves gait stability during the kinematics angle, gait, carries
Energy-efficient.Therefore, when rehabilitation training of upper limbs is carried out, it is necessary to consider upper limbs-lower limb harmony, also, based on upper limbs-under
The rehabilitation training of limb harmony can further improve rehabilitation efficacy.Additionally, rehabilitation training of upper limbs is carried out in natural walking states,
Closer to the operating state of daily life, more meet the characteristics of motion of people, the custom mistake of patient will not be caused because of uninteresting training,
So as to promote rehabilitation efficacy.
The content of the invention
In order to overcome existing upper limb healing ectoskeleton control mode do not consider upper limbs-lower limb harmony, rehabilitation efficacy compared with
Poor deficiency, the present invention provides a kind of consideration upper limbs-lower limb harmony, the rehabilitation efficacy preferably upper limbs health based on lower limb gait
Multiple ectoskeleton control method.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of upper limb healing ectoskeleton control method based on lower limb gait, comprises the following steps:
1) data acquisition:Carried out by the pressure sensor in the myoelectric sensor positioned at lower limb, motion sensor and vola
The collection of the electromyographic signal, joint angles and vola contact force of different gait classifications during tested normal walking;
2) data prediction:Electromyographic signal, joint angles and vola contact force to collecting are pre-processed;
3) Gait Recognition, comprising following sub-step:
(3.1) data sectional:" overlapping window " method of the use every kind of gesture motion data tested to each carry out windowing point
Section;
(3.2) feature extraction:Electromyographic signal feature includes integration myoelectricity, root-mean-square value, three kinds of temporal signatures of mean square deviation
Value and frequency of average power, two kinds of frequency domain character values of centre frequency;Joint angles and vola contact force are characterized as its average value;
(3.3) gait is presorted:Gait Recognition is carried out as grader using BP neural network, disaggregated model is set up;Point
It is other row mode is entered to electromyographic signal, joint angles, vola contact force to presort, construct three three layers of BP neural network graders;
Electromyographic signal characteristic value, target joint angle character value and the target vola that the input of three graders is respectively target muscles connect
Touch characteristic value, is output as gait classification;All data of each tested every kind of gait classification are divided into training set, inspection set
And test set;Network model optimization and parameter adjustment are carried out using training set data and checking collection data, test set data are used
The discrimination of the model that test is trained, carries out Gait Recognition classification;
(3.4) data fusion:Data fusion of decision layer is carried out using D-S evidence theory;By the defeated of three BP neural networks
Go out to be converted to probability output, obtain respective Basic Probability As-signment, through D-S evidence fusions after, obtained finally according to decision rule
Gait Recognition result;
4) upper limbs swing position matching:According to upper limbs swing position corresponding with recognized gait categorical match;
5) ectoskeleton control:Based on the upper limbs swing position for obtaining, corresponding control is sent to upper limb healing ectoskeleton driver
System instruction, carries out the control of upper limb healing ectoskeleton, drives upper limbs to carry out rehabilitation training.
Further, the step 2) in, data prediction includes following sub-step:
(2.1) filter:Bandpass filtering and trap treatment, bandpass filtering 20-500Hz, power frequency are carried out to surface electromyogram signal
Trap 50Hz;1-30Hz bandpass filterings are carried out to joint angles and vola contact force;
(2.2) signal amplifies;
(2.3) flip-flop, the high-frequency noise and Hz noise of skin friction in removal noise, including signal, and lead to
Cross weighted average increase signal to noise ratio.
Further, in the step (3.1), sampling window length is 200ms, and moving step length is length of window
50%, i.e. 100ms.
In the step (3.3), all data of each tested every kind of gait classification are divided into 5 parts, 1 part used as test
Collection.
The step 1) in, described myoelectric sensor is located at gluteus maximus, hamstrings, quadriceps muscle of thigh and gastrocnemius, is used for
Four pieces of electromyographic signals of target muscles of collection;Described motion sensor is located at thigh front side and shank front side, big for gathering
The inclination angle on leg, shank and ground and kneed angle;Described pressure sensor is located at three of heel and toes region
Position, for detecting the contact condition and its interaction force in vola and ground.
The step 4) in, described gait classification is divided into 7 classes according to the support phase and swing phase of a gait cycle:
Heel contact, vola land, support that mid-term, heel are liftoff, toes are liftoff, swing early stage, swing mid-term;Described upper limbs swings
The different gait classifications of position correspondence, shoulder joint is different with Angle of Elbow Joint;In order to keep one's balance, the arm of homonymy swing with
The step direction for stepping is antithesis.
The step 5) in, described upper limb healing ectoskeleton is connected by two stepper motors, two rotary shafts, postbrachium metals
Bar, forearm metal link rod, two bandages, master control borad compositions;Rotary shaft is located at shoulder joint and elbow joint, stepper motor conduct respectively
Driver drives rotary shaft rotates;Bandage is used for connecting metal link rod and arm, fixed upper limbs ectoskeleton;Master control borad is used for adopting
The sensor signal for collecting carries out data prediction, Gait Recognition, and stepper motor driver is sent out after obtaining upper limbs swing position
Go out control instruction.
Technology design of the invention is:First by the pressure in the myoelectric sensor positioned at lower limb, motion sensor and vola
Force snesor carries out the collection of electromyographic signal, joint angles and vola contact force, secondly using BP neural network to the pre- place of data
Sensor information after reason carries out gait and presorts, and obtains final identification using Data fusion technique (D-S evidence theory)
As a result, corresponding control instruction is sent finally according to the upper limbs swing position that recognized gait matches, is carried out outside upper limb healing
The control of bone, drives upper limbs to carry out rehabilitation training.The method is based on upper limbs-lower limb harmony, enters in natural walking states
Row rehabilitation training of upper limbs, further promotes rehabilitation efficacy.
A kind of upper limb healing ectoskeleton control method based on lower limb gait of the invention, can be in natural walking states
Under, by recognizing that lower limb gait carries out the control of upper limb healing ectoskeleton exactly, further improve rehabilitation efficacy.
Beneficial effects of the present invention are mainly manifested in:
1) for the patient of upper limbs lost-motion function, the positive motion of lower limb is conducive to upper limbs to recover to move work(as soon as possible
Energy;When rehabilitation training of upper limbs is carried out, it is necessary to consider upper limbs-lower limb harmony, also, the health based on upper limbs-lower limb harmony
Refreshment white silk can further improve rehabilitation efficacy;
2) rehabilitation training of upper limbs is carried out in natural walking states, closer to the operating state of daily life, more meets people
The characteristics of motion, will not because it is uninteresting training cause the custom mistake of patient, so as to promote rehabilitation efficacy;
3) as a kind of upper limb healing ectoskeleton control technology of innovation, new voltage input is obtained from lower limb, it is universal feasible,
It is very useful, it is that vast upper limb healing patient brings facility, it is suitable to large-scale promotion application.
Brief description of the drawings
Fig. 1 is the method for the invention flow chart;
Fig. 2 is upper limb healing ectoskeleton structure and myoelectricity, motion sensor position view;
Fig. 3 is plantar pressure sensor position view;
Fig. 4 is gait classification and corresponding upper limbs swing position schematic diagram.
Specific embodiment
The invention will be further described below in conjunction with the accompanying drawings.
A kind of 1~Fig. 4 of reference picture, upper limb healing ectoskeleton control method based on lower limb gait is comprised the following steps:It is first
First, electromyographic signal, joint angles are carried out by the pressure sensor in the myoelectric sensor positioned at lower limb, motion sensor and vola
With the collection of vola contact force, gait secondly is carried out to the sensor information after data prediction using BP neural network and is divided in advance
Class, and final recognition result is obtained using Data fusion technique (D-S evidence theory), finally according to recognized gait phase
The upper limbs swing position matched somebody with somebody sends corresponding control instruction, carries out the control of upper limb healing ectoskeleton, drives upper limbs to carry out rehabilitation instruction
Practice.
Each step describes in detail as follows:
1) data acquisition:Carried out by the pressure sensor in the myoelectric sensor positioned at lower limb, motion sensor and vola
The collection of the electromyographic signal, joint angles and vola contact force of different gait classifications during tested normal walking.As shown in Fig. 2 institute
The myoelectric sensor stated use common Ag/AgCl electromyographic electrodes, positioned at gluteus maximus (6), hamstrings (7), quadriceps muscle of thigh (8) and
Gastrocnemius (9), for gathering four pieces of electromyographic signals of target muscles;Described motion sensor (10) is using China
The axis movement sensor of MPU6050 types six of InvenSense companies, positioned at thigh front side and shank front side, for gather thigh,
Inclination angle of the shank with ground and kneed angle;Described pressure sensor (11) is Tekscan companies of the U.S.
FlexiForce type pressure sensors, as shown in figure 3, positioned at three positions in heel and toes region, for detect vola with
The contact condition on ground and its interaction force.
2) data prediction:Electromyographic signal, joint angles and vola contact force to collecting are pre-processed, specific bag
Containing following sub-step:
(2.1) filter:Bandpass filtering and trap treatment, bandpass filtering 20-500Hz, power frequency are carried out to surface electromyogram signal
Trap 50Hz;1-30Hz bandpass filterings are carried out to joint angles and vola contact force;
(2.2) signal amplifies;
(2.3) flip-flop, the high-frequency noise and Hz noise of skin friction in removal noise, including signal, and lead to
Weighted average increase signal to noise ratio is crossed, influence of the noise to signal is reduced.
3) Gait Recognition, specifically comprising following sub-step:
(3.1) data sectional:" overlapping window " method of the use every kind of gesture motion data tested to each carry out windowing point
Section, sampling window length is 200ms, and moving step length is the 50% of length of window, i.e. 100ms;
(3.2) feature extraction:Electromyographic signal feature includes integration myoelectricity (iEMG), root-mean-square value (RMS), mean square deviation
(S2) three kinds of temporal signatures value and frequency of average power (MPF), two kinds of frequency domain character values of centre frequency (FC), computing formula difference
For:
Integration myoelectricity (iEMG):
Wherein, N1It is integration starting point, N2It is integration terminal, X (t) is myoelectricity curve, dtIt is the time interval of sampling;
Root-mean-square value (RMS):
Wherein, N is sampling number, XiIt is the emg amplitude of ith sample point;
Mean square deviation (S2):
Wherein, N is sampling number, XiIt is the emg amplitude of ith sample point, M is the average value of electromyographic signal;
Frequency of average power (MPF):
Wherein, f is power, and s (f) is power spectrum curve, and df is frequency resolution;
Centre frequency (FC):
Wherein, FsIt is the initial frequency of signal, FeIt is the termination frequency of signal;
The inclination angle theta 1 and θ 2 on thigh, shank and ground are respectively
Wherein, θ 1 ' and θ 2 ' is the z-axis of natural system of coordinates and the angle of motion sensor z-axis, ax、ayAnd azRespectively transport
The angular acceleration values of dynamic sensor x, y, z axle;Kneed angle, θ 3=θ 1+ θ 2;Three characteristic values of joint angles are flat for it
Average, i.e.,WithVola contact force characteristic value is its average value, i.e.,
(3.3) gait is presorted:Gait Recognition is carried out as grader using BP neural network, disaggregated model is set up;Point
It is other row mode is entered to electromyographic signal, joint angles, vola contact force to presort, three three layers of BP neural networks of construction (input layer,
Hidden layer and output layer) grader;The input of three graders is respectively electromyographic signal characteristic value, the target joint of target muscles
Angle character value and target vola contact force characteristic value, are output as gait classification;By the institute of each tested every kind of gait classification
There are data to be divided into 5 parts, wherein 3 parts used as training set (60% data), 1 part used as inspection set (20% data), 1 part of conduct
Test set (20% data);Network model optimization and parameter adjustment are carried out using training set data and checking collection data, is used
The discrimination of the model that test set data test is trained, carries out Gait Recognition classification;What neural network training process was used turns
Exchange the letters number is Sigmoid functions.Output valve can be drawn by below equation:
Wherein, y is output valve, xiIt is input value, wiIt is weight coefficient, e is error function, and f () is transfer function.
(3.4) data fusion:Data fusion of decision layer is carried out using D-S evidence theory.D-S evidential reasonings have good
Theoretical foundation and practical application effect, can improve the accuracy of pattern-recognition.D-S evidential reasonings are one kind similar to Bayes
The method of reasoning, it is obtained by prior probability assignment function, and posterior evidence is interval, quantified proposition credibility and
Likelihood ratio.Degree of support of the objective evidence to proposition is described using probability distribution function, belief function, likelihood function, it is used
Between reasoning and computing carry out target identification.D-S evidential reasonings can preferably be held compared to traditional probability theory and ask
The non-intellectual and uncertainty of topic.Because the judgement output of standard BP neural network belongs to hard decision output, pushed away with D-S evidences
, it is necessary to the output of BP neural network is converted into probability output in the information fusion that reason is combined, respective elementary probability is obtained
Assignment, through D-S evidence fusions after, last Gait Recognition result is obtained according to decision rule.
D-S evidential reasonings can combine the corroboration of several separate sources to improve discrimination.This implementation
There is the target to be identified of 7 class gaits in example, the set for being constituted is defined as identification framework, i.e. Θ={ C1, C2...C7}.According to
The definition of belief function, is calculated corresponding belief function Bel (Ci).Finally classification is awarded with maximum definitely reliability
Proposition:
Wherein, a is threshold value set in advance, and 0.5 is taken in the present embodiment.
4) upper limbs swing position matching:According to upper limbs swing position corresponding with recognized gait categorical match.Such as Fig. 4 institutes
Show, gait classification is divided into 7 classes according to the support phase and swing phase of a gait cycle:Heel contact, vola land, support
Phase, heel is liftoff, toes are liftoff, swing early stage, swing mid-term;The different gait classifications of upper limbs swing position correspondence, shoulder joint (α
1) it is different with elbow joint (α 2) angle, corresponding relation such as table 1 below:
Table 1
In order to keep one's balance, the arm of homonymy is swung with the step direction for stepping antithesis.
5) ectoskeleton control:Based on the upper limbs swing position for obtaining, corresponding control is sent to upper limb healing ectoskeleton driver
System instruction, carries out the control of upper limb healing ectoskeleton, drives upper limbs to carry out rehabilitation training.As shown in Fig. 2 described upper limb healing
Ectoskeleton is tied up by two stepper motors (1), two rotary shafts (2), postbrachium metal link rod (3), forearm metal link rod (4), two
Band (5), master control borad are constituted;Rotary shaft (2) respectively be located at shoulder joint and elbow joint, stepper motor (1) as driver, using two
The stepper motor of the line of phase four, drives rotary shaft rotation;Bandage (5) is fixed outside upper limbs for connecting metal link rod (3,4) and arm
Bone;Master control borad uses Arduino UNO control panels, using ATmega328 single-chip microcomputers, for the sensor signal to collecting
Data prediction, Gait Recognition are carried out, control instruction is sent to stepper motor (1) driver after obtaining upper limbs swing position.
The above is only the preferred embodiment of the present invention, it should be understood that the present invention is not limited to described herein
Form, is not to be taken as the exclusion to other embodiment, and can be used for various other combinations, modification and environment, and can be at this
In the text contemplated scope, it is modified by the technology or knowledge of above-mentioned teaching or association area.And those skilled in the art are entered
Capable change and change does not depart from the spirit and scope of the present invention, then all should be in the protection domain of appended claims of the present invention
It is interior.Such as the shoulder joint and Angle of Elbow Joint of each upper limbs swing position in embodiment, can be tested according to difference in other embodiment
Actual conditions regulation, fall within the scope of the present invention.
Claims (7)
1. a kind of upper limb healing ectoskeleton control method based on lower limb gait, it is characterised in that:Comprise the following steps:
1) data acquisition:It is tested by the pressure sensor in the myoelectric sensor positioned at lower limb, motion sensor and vola
The collection of the electromyographic signal, joint angles and vola contact force of different gait classifications during normal walking;
2) data prediction:Electromyographic signal, joint angles and vola contact force to collecting are pre-processed;
3) Gait Recognition, comprising following sub-step:
(3.1) data sectional:" overlapping window " method of the use every kind of gesture motion data tested to each carry out windowing segmentation;
(3.2) feature extraction:Electromyographic signal feature include integration myoelectricity, root-mean-square value, three kinds of temporal signatures values of mean square deviation and
Frequency of average power, two kinds of frequency domain character values of centre frequency;Joint angles and vola contact force are characterized as its average value;
(3.3) gait is presorted:Gait Recognition is carried out as grader using BP neural network, disaggregated model is set up;It is right respectively
Electromyographic signal, joint angles, vola contact force are entered row mode and are presorted, and construct three three layers of BP neural network graders;Three
The input of grader is respectively electromyographic signal characteristic value, target joint angle character value and the target vola contact force of target muscles
Characteristic value, is output as gait classification;All data of each tested every kind of gait classification are divided into training set, inspection set and survey
Examination collection;Network model optimization and parameter adjustment are carried out using training set data and checking collection data, test set data test is used
The discrimination of the model for training, carries out Gait Recognition classification;
(3.4) data fusion:Data fusion of decision layer is carried out using D-S evidence theory;Three outputs of BP neural network are turned
Be changed to probability output, obtain respective Basic Probability As-signment, through D-S evidence fusions after, last step is obtained according to decision rule
State recognition result;
4) upper limbs swing position matching:According to upper limbs swing position corresponding with recognized gait categorical match;
5) ectoskeleton control:Based on the upper limbs swing position for obtaining, send corresponding control to upper limb healing ectoskeleton driver and refer to
Order, carries out the control of upper limb healing ectoskeleton, drives upper limbs to carry out rehabilitation training.
2. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1, it is characterised in that:Institute
State step 2) in, data prediction includes following sub-step:
(2.1) filter:Bandpass filtering and trap treatment, bandpass filtering 20-500Hz, notch filter are carried out to surface electromyogram signal
50Hz;1-30Hz bandpass filterings are carried out to joint angles and vola contact force;
(2.2) signal amplifies;
(2.3) flip-flop, the high-frequency noise and Hz noise of skin friction in removal noise, including signal, and by adding
Weight average increases signal to noise ratio.
3. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1 or 2, its feature exists
In:In the step (3.1), sampling window length is 200ms, and moving step length is the 50% of length of window, i.e. 100ms.
4. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1 or 2, its feature exists
In:In the step (3.3), all data of each tested every kind of gait classification are divided into 5 parts, 1 part used as test set.
5. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1 or 2, its feature exists
In:The step 1) in, described myoelectric sensor is located at gluteus maximus, hamstrings, quadriceps muscle of thigh and gastrocnemius, for gathering four
The electromyographic signal of block target muscles;Described motion sensor is located at thigh front side and shank front side, for gathering thigh, shank
Inclination angle and kneed angle with ground;Described pressure sensor is located at three positions in heel and toes region, uses
To detect the contact condition and its interaction force in vola and ground.
6. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1 or 2, its feature exists
In:The step 4) in, described gait classification is divided into 7 classes according to the support phase and swing phase of a gait cycle:Heel
Land, vola lands, support that mid-term, heel are liftoff, toes are liftoff, swing early stage, swing mid-term;Described upper limbs swing position
The different gait classifications of correspondence, shoulder joint is different with Angle of Elbow Joint;In order to keep one's balance, the arm of homonymy swings and steps
Step direction antithesis.
7. a kind of upper limb healing ectoskeleton control method based on lower limb gait as claimed in claim 1 or 2, its feature exists
In:The step 5) in, described upper limb healing ectoskeleton is by two stepper motors, two rotary shafts, postbrachium metal link rod, preceding
Arm metal link rod, two bandages, master control borad compositions;Rotary shaft is located at shoulder joint and elbow joint respectively, and stepper motor is used as driving
Device drives rotary shaft rotation;Bandage is used for connecting metal link rod and arm, fixed upper limbs ectoskeleton;Master control borad is used for collecting
Sensor signal carry out data prediction, Gait Recognition, control is sent to stepper motor driver after obtaining upper limbs swing position
System instruction.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710107188.3A CN106821680A (en) | 2017-02-27 | 2017-02-27 | A kind of upper limb healing ectoskeleton control method based on lower limb gait |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710107188.3A CN106821680A (en) | 2017-02-27 | 2017-02-27 | A kind of upper limb healing ectoskeleton control method based on lower limb gait |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106821680A true CN106821680A (en) | 2017-06-13 |
Family
ID=59133604
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710107188.3A Pending CN106821680A (en) | 2017-02-27 | 2017-02-27 | A kind of upper limb healing ectoskeleton control method based on lower limb gait |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106821680A (en) |
Cited By (34)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107466263A (en) * | 2017-07-10 | 2017-12-12 | 深圳市艾唯尔科技有限公司 | A kind of joint of robot anticollision protection system and its method for sensing integration technology |
CN107536311A (en) * | 2017-10-17 | 2018-01-05 | 国家康复辅具研究中心 | Intelligent multifunctional seat system |
CN107802384A (en) * | 2017-11-22 | 2018-03-16 | 上海大学 | A kind of active hip disarticulation prosthesis control system and control method |
CN107854774A (en) * | 2017-10-25 | 2018-03-30 | 国家康复辅具研究中心 | A kind of wireless electro photoluminescence walk help system of plantar pressure feedback driving |
CN107874763A (en) * | 2017-12-11 | 2018-04-06 | 无锡智开医疗机器人有限公司 | A kind of lower limb data collecting system |
CN108890621A (en) * | 2018-07-10 | 2018-11-27 | 安春亭 | A kind of wearable smart machine control method that auxiliary is carried |
CN109350071A (en) * | 2018-11-08 | 2019-02-19 | 华东师范大学 | A kind of flexible gait monitoring method calculated based on artificial intelligence |
CN109620645A (en) * | 2019-01-31 | 2019-04-16 | 西安中科龙华军警装备有限公司 | A kind of hand recovery exercising robot |
CN110141239A (en) * | 2019-05-30 | 2019-08-20 | 东北大学 | A kind of motion intention identification and installation method for lower limb exoskeleton |
CN110279557A (en) * | 2019-07-02 | 2019-09-27 | 安徽工业大学 | A kind of lower limb rehabilitation robot control system and control method |
WO2019213399A1 (en) * | 2018-05-04 | 2019-11-07 | Baylor College Of Medicine | Detecting frailty and foot at risk using lower extremity motor performance screening |
CN110553643A (en) * | 2019-09-17 | 2019-12-10 | 电子科技大学 | pedestrian self-adaptive zero-speed updating point selection method based on neural network |
CN110801226A (en) * | 2019-11-01 | 2020-02-18 | 西安交通大学 | Human knee joint moment testing system method based on surface electromyographic signals and application |
CN111168667A (en) * | 2019-12-13 | 2020-05-19 | 天津大学 | Robot control method based on Bayesian classifier |
CN111506189A (en) * | 2020-03-31 | 2020-08-07 | 哈尔滨工业大学 | Motion mode prediction and switching control method for complex motion of human body |
CN111531537A (en) * | 2020-05-07 | 2020-08-14 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
CN111588376A (en) * | 2020-05-07 | 2020-08-28 | 北京联合大学 | Lower limb gait information extraction equipment based on electromyographic signals and angle signals |
CN111616848A (en) * | 2020-06-02 | 2020-09-04 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
CN111657870A (en) * | 2020-07-02 | 2020-09-15 | 杭州电子科技大学 | Apnea judgment system based on D-S evidence theory |
CN111938656A (en) * | 2020-07-28 | 2020-11-17 | 南京审计大学 | Real-time walking mode identification method and system based on knee joint exoskeleton |
WO2020245398A1 (en) * | 2019-06-05 | 2020-12-10 | Otto Bock Healthcare Products Gmbh | Method for operating an orthopedic device and corresponding device |
CN112223263A (en) * | 2020-10-09 | 2021-01-15 | 贵州航天控制技术有限公司 | Man-machine cooperation real-time control method of flexible exoskeleton system |
CN112315747A (en) * | 2019-11-20 | 2021-02-05 | 河南水滴智能技术有限公司 | Novel exoskeleton control scheme |
CN112494282A (en) * | 2020-12-01 | 2021-03-16 | 天津理工大学 | Exoskeleton main power parameter optimization method based on deep reinforcement learning |
CN112754468A (en) * | 2021-01-07 | 2021-05-07 | 华南理工大学 | Human body lower limb movement detection and identification method based on multi-source signals |
CN112842327A (en) * | 2021-01-05 | 2021-05-28 | 北京诺亦腾科技有限公司 | Body posture generation method and device, electronic equipment and medium |
CN113274039A (en) * | 2021-05-19 | 2021-08-20 | 福州市第二医院(福建省福州中西医结合医院、福州市职业病医院) | Prediction classification method and device based on surface electromyogram signals and motion signals |
CN114089757A (en) * | 2021-11-17 | 2022-02-25 | 北京石油化工学院 | Control method and device for upper and lower limb coordinated active rehabilitation robot |
CN114404214A (en) * | 2020-10-28 | 2022-04-29 | 北京机械设备研究所 | Exoskeleton gait identification method and device |
CN114652578A (en) * | 2022-03-18 | 2022-06-24 | 法罗适(上海)医疗技术有限公司 | Lower limb rehabilitation training evaluation device and rehabilitation training evaluation method |
CN115252368A (en) * | 2022-07-29 | 2022-11-01 | 安徽哈工标致医疗健康产业有限公司 | Method and system for controlling lower limb exoskeleton robot through brain-computer interface |
CN115644858A (en) * | 2022-12-27 | 2023-01-31 | 广东工业大学 | Wearable intelligent gait analyzer based on multi-sensor data fusion technology |
CN116999034A (en) * | 2023-09-28 | 2023-11-07 | 中国康复科学所(中国残联残疾预防与控制研究中心) | Evaluation system and evaluation method |
CN112915382B (en) * | 2017-10-25 | 2024-04-30 | 国家康复辅具研究中心 | Walking aid system |
-
2017
- 2017-02-27 CN CN201710107188.3A patent/CN106821680A/en active Pending
Cited By (50)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107466263A (en) * | 2017-07-10 | 2017-12-12 | 深圳市艾唯尔科技有限公司 | A kind of joint of robot anticollision protection system and its method for sensing integration technology |
CN107536311A (en) * | 2017-10-17 | 2018-01-05 | 国家康复辅具研究中心 | Intelligent multifunctional seat system |
CN107536311B (en) * | 2017-10-17 | 2020-05-26 | 国家康复辅具研究中心 | Intelligent multifunctional seat system |
CN112915382B (en) * | 2017-10-25 | 2024-04-30 | 国家康复辅具研究中心 | Walking aid system |
CN107854774A (en) * | 2017-10-25 | 2018-03-30 | 国家康复辅具研究中心 | A kind of wireless electro photoluminescence walk help system of plantar pressure feedback driving |
CN107854774B (en) * | 2017-10-25 | 2021-03-09 | 国家康复辅具研究中心 | Wireless stimulation walking aid system driven by plantar pressure feedback |
CN112915382A (en) * | 2017-10-25 | 2021-06-08 | 国家康复辅具研究中心 | Walking aid system |
CN107802384A (en) * | 2017-11-22 | 2018-03-16 | 上海大学 | A kind of active hip disarticulation prosthesis control system and control method |
CN107874763A (en) * | 2017-12-11 | 2018-04-06 | 无锡智开医疗机器人有限公司 | A kind of lower limb data collecting system |
US20210236021A1 (en) * | 2018-05-04 | 2021-08-05 | Baylor College Of Medicine | Detecting frailty and foot at risk using lower extremity motor performance screening |
WO2019213399A1 (en) * | 2018-05-04 | 2019-11-07 | Baylor College Of Medicine | Detecting frailty and foot at risk using lower extremity motor performance screening |
CN108890621A (en) * | 2018-07-10 | 2018-11-27 | 安春亭 | A kind of wearable smart machine control method that auxiliary is carried |
CN109350071A (en) * | 2018-11-08 | 2019-02-19 | 华东师范大学 | A kind of flexible gait monitoring method calculated based on artificial intelligence |
CN109620645A (en) * | 2019-01-31 | 2019-04-16 | 西安中科龙华军警装备有限公司 | A kind of hand recovery exercising robot |
CN110141239B (en) * | 2019-05-30 | 2020-08-04 | 东北大学 | Movement intention recognition and device method for lower limb exoskeleton |
CN110141239A (en) * | 2019-05-30 | 2019-08-20 | 东北大学 | A kind of motion intention identification and installation method for lower limb exoskeleton |
WO2020245398A1 (en) * | 2019-06-05 | 2020-12-10 | Otto Bock Healthcare Products Gmbh | Method for operating an orthopedic device and corresponding device |
CN110279557A (en) * | 2019-07-02 | 2019-09-27 | 安徽工业大学 | A kind of lower limb rehabilitation robot control system and control method |
CN110279557B (en) * | 2019-07-02 | 2021-08-27 | 安徽工业大学 | Control system and control method for lower limb rehabilitation robot |
CN110553643A (en) * | 2019-09-17 | 2019-12-10 | 电子科技大学 | pedestrian self-adaptive zero-speed updating point selection method based on neural network |
CN110553643B (en) * | 2019-09-17 | 2021-12-21 | 电子科技大学 | Pedestrian self-adaptive zero-speed updating point selection method based on neural network |
CN110801226A (en) * | 2019-11-01 | 2020-02-18 | 西安交通大学 | Human knee joint moment testing system method based on surface electromyographic signals and application |
CN112315747A (en) * | 2019-11-20 | 2021-02-05 | 河南水滴智能技术有限公司 | Novel exoskeleton control scheme |
CN112315747B (en) * | 2019-11-20 | 2023-08-22 | 河南水滴智能技术有限公司 | Design method of exoskeleton equipment |
CN111168667A (en) * | 2019-12-13 | 2020-05-19 | 天津大学 | Robot control method based on Bayesian classifier |
CN111168667B (en) * | 2019-12-13 | 2022-08-05 | 天津大学 | Robot control method based on Bayesian classifier |
CN111506189A (en) * | 2020-03-31 | 2020-08-07 | 哈尔滨工业大学 | Motion mode prediction and switching control method for complex motion of human body |
CN111588376A (en) * | 2020-05-07 | 2020-08-28 | 北京联合大学 | Lower limb gait information extraction equipment based on electromyographic signals and angle signals |
CN111531537B (en) * | 2020-05-07 | 2022-11-01 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
CN111531537A (en) * | 2020-05-07 | 2020-08-14 | 金陵科技学院 | Mechanical arm control method based on multiple sensors |
CN111616848B (en) * | 2020-06-02 | 2021-06-08 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
CN111616848A (en) * | 2020-06-02 | 2020-09-04 | 中国科学技术大学先进技术研究院 | Five-degree-of-freedom upper arm prosthesis control system based on FSM |
CN111657870A (en) * | 2020-07-02 | 2020-09-15 | 杭州电子科技大学 | Apnea judgment system based on D-S evidence theory |
CN111938656A (en) * | 2020-07-28 | 2020-11-17 | 南京审计大学 | Real-time walking mode identification method and system based on knee joint exoskeleton |
CN112223263A (en) * | 2020-10-09 | 2021-01-15 | 贵州航天控制技术有限公司 | Man-machine cooperation real-time control method of flexible exoskeleton system |
CN112223263B (en) * | 2020-10-09 | 2022-07-15 | 贵州航天控制技术有限公司 | Man-machine cooperation real-time control method of flexible exoskeleton system |
CN114404214A (en) * | 2020-10-28 | 2022-04-29 | 北京机械设备研究所 | Exoskeleton gait identification method and device |
CN114404214B (en) * | 2020-10-28 | 2024-02-13 | 北京机械设备研究所 | Exoskeleton gait recognition device |
CN112494282A (en) * | 2020-12-01 | 2021-03-16 | 天津理工大学 | Exoskeleton main power parameter optimization method based on deep reinforcement learning |
CN112842327A (en) * | 2021-01-05 | 2021-05-28 | 北京诺亦腾科技有限公司 | Body posture generation method and device, electronic equipment and medium |
CN112754468A (en) * | 2021-01-07 | 2021-05-07 | 华南理工大学 | Human body lower limb movement detection and identification method based on multi-source signals |
CN112754468B (en) * | 2021-01-07 | 2022-08-05 | 华南理工大学 | Human body lower limb movement detection and identification method based on multi-source signals |
CN113274039A (en) * | 2021-05-19 | 2021-08-20 | 福州市第二医院(福建省福州中西医结合医院、福州市职业病医院) | Prediction classification method and device based on surface electromyogram signals and motion signals |
CN114089757A (en) * | 2021-11-17 | 2022-02-25 | 北京石油化工学院 | Control method and device for upper and lower limb coordinated active rehabilitation robot |
CN114089757B (en) * | 2021-11-17 | 2024-02-02 | 北京石油化工学院 | Control method and device for upper and lower limb coordination active rehabilitation robot |
CN114652578A (en) * | 2022-03-18 | 2022-06-24 | 法罗适(上海)医疗技术有限公司 | Lower limb rehabilitation training evaluation device and rehabilitation training evaluation method |
CN115252368A (en) * | 2022-07-29 | 2022-11-01 | 安徽哈工标致医疗健康产业有限公司 | Method and system for controlling lower limb exoskeleton robot through brain-computer interface |
CN115644858A (en) * | 2022-12-27 | 2023-01-31 | 广东工业大学 | Wearable intelligent gait analyzer based on multi-sensor data fusion technology |
CN116999034A (en) * | 2023-09-28 | 2023-11-07 | 中国康复科学所(中国残联残疾预防与控制研究中心) | Evaluation system and evaluation method |
CN116999034B (en) * | 2023-09-28 | 2023-12-22 | 中国康复科学所(中国残联残疾预防与控制研究中心) | Evaluation system and evaluation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106821680A (en) | A kind of upper limb healing ectoskeleton control method based on lower limb gait | |
CN103431976B (en) | Based on lower limb rehabilitation robot system and the control method thereof of electromyographic signal feedback | |
CN109394476B (en) | Method and system for automatic intention recognition of brain muscle information and intelligent control of upper limbs | |
WO2021243918A1 (en) | Upper-limb function evaluation apparatus and method, and upper-limb rehabilitation training system and method | |
CN104207793B (en) | A kind of grip function assessment and training system | |
CN101791255B (en) | Walk-aiding exoskeleton robot system and control method | |
CN103212188B (en) | A kind of method and system of auxiliary gait training | |
CN106236503B (en) | The wearable exoskeleton system of the electrically driven (operated) upper limb of flesh and control method | |
CN104382595A (en) | Upper limb rehabilitation system and method based on myoelectric signal and virtual reality interaction technology | |
CN202288542U (en) | Artificial limb control device | |
CN109288651A (en) | Personalized upper-limbs rehabilitation training robot system and its recovery training method | |
CN110742775A (en) | Upper limb active and passive rehabilitation training robot system based on force feedback technology | |
CN111696645A (en) | Hand exoskeleton rehabilitation training device and method based on surface electromyographic signals | |
CN106334265A (en) | Exoskeleton assisted walking system driven by functional muscle electric stimulation and assisted walking method | |
CN109481226A (en) | A kind of both hands tracking mode multiple degrees of freedom software finger gymnastic robot and application method | |
CN105012057A (en) | Intelligent artificial limb based on double-arm electromyogram and attitude information acquisition and motion classifying method | |
Wang et al. | Bionic control of exoskeleton robot based on motion intention for rehabilitation training | |
Lamounier et al. | On the use of virtual and augmented reality for upper limb prostheses training and simulation | |
Xiao et al. | Real time motion intention recognition method with limited number of surface electromyography sensors for A 7-DOF hand/wrist rehabilitation exoskeleton | |
CN107126303A (en) | A kind of upper and lower extremities exercising support method based on mobile phone A PP | |
CN109223441A (en) | A kind of human upper limb rehabilitation training and movement auxiliary system based on Kinect sensor | |
Luo et al. | Research of intent recognition in rehabilitation robots: a systematic review | |
Geng et al. | Lower limb joint nursing and rehabilitation system based on intelligent medical treatment | |
CN111035535A (en) | Cerebral apoplexy rehabilitation training system and method | |
Hioki et al. | Finger rehabilitation support system using a multifingered haptic interface controlled by a surface electromyogram |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170613 |
|
RJ01 | Rejection of invention patent application after publication |