CN103494660B - Based on the myoelectric prosthetic hand control method of accidental resonance - Google Patents

Based on the myoelectric prosthetic hand control method of accidental resonance Download PDF

Info

Publication number
CN103494660B
CN103494660B CN201310487341.1A CN201310487341A CN103494660B CN 103494660 B CN103494660 B CN 103494660B CN 201310487341 A CN201310487341 A CN 201310487341A CN 103494660 B CN103494660 B CN 103494660B
Authority
CN
China
Prior art keywords
signal
output
electromyographic signal
another person
grip
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.)
Active
Application number
CN201310487341.1A
Other languages
Chinese (zh)
Other versions
CN103494660A (en
Inventor
宋爱国
吴常铖
李会军
徐宝国
曾洪
崔建伟
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN201310487341.1A priority Critical patent/CN103494660B/en
Publication of CN103494660A publication Critical patent/CN103494660A/en
Application granted granted Critical
Publication of CN103494660B publication Critical patent/CN103494660B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Prostheses (AREA)

Abstract

The invention provides a kind of myoelectric prosthetic hand control method based on accidental resonance, comprise the electromyographic signal action recognition process based on accidental resonance and grip control treatment, the control signal that generation is done evil through another person for driving direct current generator, thus realizes the action control to EMG-controlling prosthetic hand.Pretreated electromyographic signal EMG1, the closed electromyographic signal EMG2 of opening such as the process that the electromyographic signal action recognition process based on accidental resonance gathers on human arm a pair Antagonistic muscle is amplified, take absolute value are as input signal, after accidental resonance action recognition, inhibit the impact of signal noise, the electromyographic signal realizing producing when shrinking diastole according to wearer's arm muscles exports the expectation grip of doing evil through another person.Grip control treatment can realize the tracking expecting grip of doing evil through another person, thus realization basis is done evil through another person, the intensity of wearer's arm electromyographic signal controls the grip size of doing evil through another person.This method can realize the active suppression of noise in electromyographic signal, improves the Stability and veracity of EMG-controlling prosthetic hand action control.

Description

Based on the myoelectric prosthetic hand control method of accidental resonance
Technical field
The present invention relates to special instrument control field, especially a kind of myoelectric prosthetic hand control method based on accidental resonance, is suitable for the control of EMG-controlling prosthetic hand.
Background technology
EMG-controlling prosthetic hand uses electromyographic signal as the control signal of doing evil through another person, and by extracting the feature of myoelectricity letter, identifies that the action of electromyographic signal representative controls the folding of doing evil through another person.This control model due to meet the operating habit of human body, action from however paid close attention to widely.But electromyographic signal is small-signal, collects in electromyographic signal with larger noise from the residual arm of people with disability, be unfavorable for the stability contorting of doing evil through another person.Accidental resonance is that a kind of noise plays the non-linear phenomena of assistance and potentiation to small-signal, adopt accidental resonance technology can be highlighted by the useful component in electromyographic signal very well, suppress noise in signal, improve the Stability and veracity that EMG-controlling prosthetic hand controls.
Summary of the invention
The object of the invention is to provide a kind of myoelectric prosthetic hand control method based on accidental resonance, can realize the active suppression of noise in electromyographic signal, improves the Stability and veracity of EMG-controlling prosthetic hand action control.
For reaching above-mentioned purpose, the technical solution adopted in the present invention is as follows:
Based on a myoelectric prosthetic hand control method for accidental resonance, comprise the following steps:
Step 1: get the first myoelectric sensor and the second myoelectric sensor, described first myoelectric sensor and the second myoelectric sensor be respectively used in the electromyographic signal of a pair Antagonistic muscle gathered on arm open this on electromyographic signal EMG1 and arm to the closed electromyographic signal EMG2 in the electromyographic signal of Antagonistic muscle; Then to opening, electromyographic signal EMG1 and closed electromyographic signal EMG2 amplifies, take absolute value process, obtains pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2;
Step 2: electromyographic signal action recognition, exports the expectation grip F done evil through another person d, detailed step is as follows:
Step 2.1: step 1 obtained pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2, input voltage comparator compares respectively, wherein:
The pretreated electromyographic signal EMG1 that opens is inputted the 1st respectively and compares to N number of voltage comparator; Pretreated closed electromyographic signal EMG2 is sent into respectively N+1 to compare to 2N voltage comparator, N>=2; Described 1st is used for realizing to 2N voltage comparator: when input signal is more than or equal to the threshold level of voltage comparator, comparator exports high level 1; When input signal is less than the threshold level of voltage comparator, the threshold level of comparator output low level 0, n-th comparator is V rEFn, be expressed as follows:
V R E F n = n × V m 1 N , ( 1 ≤ n ≤ N ) ( n - N ) × V m 2 N , ( N + 1 ≤ n ≤ 2 N )
Wherein, V m1for the pretreated maximum opening electromyographic signal EMG1, V m2for the maximum of pretreated closed electromyographic signal EMG2;
Step 2.2: by the 1st to N number of voltage comparator output by sequence number from small to large order carry out arranging and be sent to microprocessor, individual for the N+1 output to 2N voltage comparator from small to large by sequence number sequentially carried out arranging and be sent to microprocessor, microprocessor controls the first D/A converter and the second D/A converter output voltage signal V respectively according to the output signal of voltage comparator o1and V o2, wherein:
For the 1st output signal to N number of voltage comparator, if the output of the 1st voltage comparator is 0, then the voltage that Microprocessor S3C44B0X first D/A converter exports is:
V 01＝0，
If the output signal of n-th (n<N) comparator is 1 and the output signal of (n+1)th comparator is 0, then Microprocessor S3C44B0X first D/A converter output voltage is:
V o 1 = n &times; V m 1 N ,
If the output signal of N number of voltage comparator is 1, then Microprocessor S3C44B0X first D/A converter output voltage is:
V o1＝V m1；
For N+1 to the output signal of 2N voltage comparator, if the output of N+1 voltage comparator is 0, then the voltage that Microprocessor S3C44B0X second D/A converter exports is:
V 02＝0，
If the output signal that the output signal of n-th (N<n<2N-1) comparator is 1, (n+1)th comparator is 0, then Microprocessor S3C44B0X second D/A converter output voltage is:
V o 2 = ( n - N ) &times; V m 2 N ,
If the output signal of 2N voltage comparator is 1, then Microprocessor S3C44B0X second D/A converter output voltage is:
V 02＝V m2；
Step 2.3: first integrator is to the output valve V of the first D/A converter o1carry out integral operation, export E 1; Second integral device is to the output valve V of the second D/A converter o2carry out integral operation, export E 2;
Step 2.4: according to the output E of first integrator 1with the output E of second integral device 2carry out action differentiation, differentiation result is F dif: F d> 0, corresponding to the expectation action of doing evil through another person for opening; If F d< 0 is closed corresponding to the expectation action of doing evil through another person, F d=0 corresponding to the expectation action of doing evil through another person for stop, wherein:
F d＝E 1-E 2，
Step 3: obtained the control signal y done evil through another person by a grip processing controller, performing step is as follows:
Step 3.1: gather the current grip signal F done evil through another person n, calculate grip tracking error Δ F:
ΔF＝F d-F n，
Step 3.2: grip tracking error Δ F is inputted grip processing controller, grip processing controller exports the control signal y for driving action of doing evil through another person;
Step 4: be used for driving the direct current generator on doing evil through another person after control signal y is carried out power amplification, thus the grip that control is done evil through another person.
In further embodiment, described grip processing controller is a PID controller.
In further embodiment, described first myoelectric sensor and the second myoelectric sensor are fitted on a pair Antagonistic muscle of wearer's arm respectively.
From the above technical solution of the present invention shows that, beneficial effect of the present invention is:
1, the electromyographic signal action identification method based on accidental resonance is adopted effectively on the impact of action recognition accuracy, the accuracy that vacant seat of doing evil through another person controls can be improved by restraint speckle.
2, extract electromyographic signal feature with existing by Fourier transformation, wavelet transformation etc., identify the method for electromyographic signal action compared with, there is the features such as amount of calculation is little, algorithm complex is low, the flexible control of doing evil through another person just can be realized without the need to high-end processor, reduce cost, be suitable for commercialization do evil through another person in application.
3, arrange integrator, weakening electromyographic signal shakes the impact that hand control of granting the leave is brought, and improves false hand-guided stability.
Accompanying drawing explanation
Fig. 1 is the principle schematic of the myoelectric prosthetic hand control method based on accidental resonance.
Fig. 2 is the realization flow figure based on the electromyographic signal action identification method of accidental resonance in Fig. 1 embodiment.
Detailed description of the invention
In order to more understand technology contents of the present invention, institute's accompanying drawings is coordinated to be described as follows especially exemplified by specific embodiment.
As depicted in figs. 1 and 2, according to preferred embodiment of the present invention, based on the myoelectric prosthetic hand control method of accidental resonance, comprise the electromyographic signal action recognition process based on accidental resonance and grip control treatment, the control signal that generation is done evil through another person for driving direct current generator, thus realizes the action control to EMG-controlling prosthetic hand.
Shown in figure 1 and Fig. 2, the myoelectric prosthetic hand control method based on accidental resonance comprises the following steps:
Step 1: get the first myoelectric sensor and the second myoelectric sensor, described first myoelectric sensor and the second myoelectric sensor be respectively used in the electromyographic signal of a pair Antagonistic muscle gathered on arm open this on electromyographic signal EMG1 and arm to the closed electromyographic signal EMG2 in the electromyographic signal of Antagonistic muscle; Then to opening, electromyographic signal EMG1 and closed electromyographic signal EMG2 amplifies, take absolute value process, obtains pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2;
Step 2: electromyographic signal action recognition, exports the expectation grip F done evil through another person d, shown in figure 2, implementation step is as follows:
Step 2.1: step 1 obtained pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2, input voltage comparator compares respectively, wherein:
The pretreated electromyographic signal EMG1 that opens is inputted the 1st respectively and compares to N number of voltage comparator; Pretreated closed electromyographic signal EMG2 is sent into respectively N+1 to compare to 2N voltage comparator, N>=2; Described 1st is used for realizing to 2N voltage comparator: when input signal is more than or equal to the threshold level of voltage comparator, comparator exports high level 1; When input signal is less than the threshold level of voltage comparator, the threshold level of comparator output low level 0, n-th comparator is V rEFn, be expressed as follows:
V R E F n = n &times; V m 1 N , ( 1 &le; n &le; N ) ( n - N ) &times; V m 2 N , ( N + 1 &le; n &le; 2 N )
Wherein, V m1for the pretreated maximum opening electromyographic signal EMG1, V m2for the maximum of pretreated closed electromyographic signal EMG2;
Step 2.2: by the 1st to N number of voltage comparator output by sequence number from small to large order carry out arranging and be sent to microprocessor, individual for the N+1 output to 2N voltage comparator from small to large by sequence number sequentially carried out arranging and be sent to microprocessor, microprocessor controls the first D/A converter and the second D/A converter output voltage signal V respectively according to the output signal of voltage comparator o1and V o2, wherein:
For the 1st output signal to N number of voltage comparator, if the output of the 1st voltage comparator is 0, then the voltage that Microprocessor S3C44B0X first D/A converter exports is:
V 01＝0，
If the output signal of n-th (n<N) comparator is 1 and the output signal of (n+1)th comparator is 0, then Microprocessor S3C44B0X first D/A converter output voltage is:
V o 1 = n &times; V m 1 N ,
If the output signal of N number of voltage comparator is 1, then Microprocessor S3C44B0X first D/A converter output voltage is: V o1=V m1;
For N+1 to the output signal of 2N voltage comparator, if the output of N+1 voltage comparator is 0, then the voltage that Microprocessor S3C44B0X second D/A converter exports is:
V 02＝0，
If the output signal that the output signal of n-th (N<n<2N-1) comparator is 1, (n+1)th comparator is 0, then Microprocessor S3C44B0X second D/A converter output voltage is:
V o 2 = ( n - N ) &times; V m 2 N ,
If the output signal of 2N voltage comparator is 1, then Microprocessor S3C44B0X second D/A converter output voltage is:
V 02＝V m2；
Step 2.3: first integrator is to the output valve V of the first D/A converter o1carry out integral operation, export E 1; Second integral device is to the output valve V of the second D/A converter o2carry out integral operation, export E 2;
Step 2.4: according to the output E of first integrator 1with the output E of second integral device 2carry out action differentiation, differentiation result is F dif: F d> 0, corresponding to the expectation action of doing evil through another person for opening; If F d< 0 is closed corresponding to the expectation action of doing evil through another person, F d=0 corresponding to the expectation action of doing evil through another person for stop, wherein:
F d＝E 1-E 2，
Step 3: obtained the control signal y done evil through another person by a grip processing controller, detailed step is as follows:
Step 3.1: gather the current grip signal F done evil through another person n, calculate grip tracking error Δ F:
ΔF＝F d-F n，
Step 3.2: grip tracking error Δ F is inputted grip processing controller, grip processing controller exports the control signal y for driving action of doing evil through another person;
Step 4: be used for driving the direct current generator on doing evil through another person after the control signal y that grip processing controller exports is carried out power amplification, thus the grip that control is done evil through another person.
Preferably, described grip processing controller is PID controller.Certainly not as restriction, the controller of other types can also be adopted.
In the present embodiment, described first myoelectric sensor and the second myoelectric sensor are fitted on a pair Antagonistic muscle of wearer's arm respectively.Therefore, only needing two myoelectric sensors to be fitted on a pair Antagonistic muscle of wearer's arm, open power supply of doing evil through another person, wearer lifting and control that lower wrist can realize doing evil through another person.
In sum, beneficial effect of the present invention is:
1, the electromyographic signal action identification method based on accidental resonance is adopted effectively on the impact of action recognition accuracy, the accuracy that vacant seat of doing evil through another person controls can be improved by restraint speckle.
2, extract electromyographic signal feature with existing by Fourier transformation, wavelet transformation etc., identify the method for electromyographic signal action compared with, there is the features such as amount of calculation is little, algorithm complex is low, the flexible control of doing evil through another person just can be realized without the need to high-end processor, reduce cost, be suitable for commercialization do evil through another person in application.
3, arrange integrator, weakening electromyographic signal shakes the impact that hand control of granting the leave is brought, and improves false hand-guided stability.
Although the present invention with preferred embodiment disclose as above, so itself and be not used to limit the present invention.Persond having ordinary knowledge in the technical field of the present invention, without departing from the spirit and scope of the present invention, when being used for a variety of modifications and variations.Therefore, protection scope of the present invention is when being as the criterion depending on those as defined in claim.

Claims (3)

1. based on a myoelectric prosthetic hand control method for accidental resonance, it is characterized in that, comprise the following steps:
Step 1: get the first myoelectric sensor and the second myoelectric sensor, described first myoelectric sensor and the second myoelectric sensor be respectively used in the electromyographic signal of a pair Antagonistic muscle gathered on arm open this on electromyographic signal EMG1 and arm to the closed electromyographic signal EMG2 in the electromyographic signal of Antagonistic muscle; Then to opening, electromyographic signal EMG1 and closed electromyographic signal EMG2 amplifies, take absolute value process, obtains pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2;
Step 2: electromyographic signal action recognition, exports the expectation grip F done evil through another person d, detailed step is as follows:
Step 2.1: step 1 obtained pretreatedly opening electromyographic signal EMG1 and pretreated closed electromyographic signal EMG2, input voltage comparator compares respectively, wherein:
The pretreated electromyographic signal EMG1 that opens is inputted the 1st respectively and compares to N number of voltage comparator; Pretreated closed electromyographic signal EMG2 is sent into respectively N+1 to compare to 2N voltage comparator, N>=2; Described 1st is used for realizing to 2N voltage comparator: when input signal is more than or equal to the threshold level of voltage comparator, comparator exports high level 1; When input signal is less than the threshold level of voltage comparator, the threshold level of comparator output low level 0, n-th comparator is V rEFn, be expressed as follows:
V R E F n = n &times; V m 1 N , ( 1 &le; n &le; N ) ( n - N ) &times; V m 2 N , ( N + 1 &le; n &le; 2 N )
Wherein, V m1for the pretreated maximum opening electromyographic signal EMG1, V m2for the maximum of pretreated closed electromyographic signal EMG2;
Step 2.2: by the 1st to N number of voltage comparator output by sequence number from small to large order carry out arranging and be sent to microprocessor, individual for the N+1 output to 2N voltage comparator from small to large by sequence number sequentially carried out arranging and be sent to microprocessor, microprocessor controls the first D/A converter and the second D/A converter output voltage signal V respectively according to the output signal of voltage comparator o1and V o2, wherein:
For the 1st output signal to N number of voltage comparator, if the output of the 1st voltage comparator is 0, then the voltage that Microprocessor S3C44B0X first D/A converter exports is:
V 01＝0，
If the output signal of n-th (n<N) comparator is 1 and the output signal of (n+1)th comparator is 0, then Microprocessor S3C44B0X first D/A converter output voltage is:
V o 1 = n &times; V m 1 N ,
If the output signal of N number of voltage comparator is 1, then Microprocessor S3C44B0X first D/A converter output voltage is: V o1=V m1;
For N+1 to the output signal of 2N voltage comparator, if the output of N+1 voltage comparator is 0, then the voltage that Microprocessor S3C44B0X second D/A converter exports is:
V 02＝0，
If the output signal that the output signal of n-th (N<n<2N-1) comparator is 1, (n+1)th comparator is 0, then Microprocessor S3C44B0X second D/A converter output voltage is:
V o 2 = ( n - N ) &times; V m 2 N ,
If the output signal of 2N voltage comparator is 1, then Microprocessor S3C44B0X second D/A converter output voltage is:
V 02＝V m2；
Step 2.3: first integrator is to the output valve V of the first D/A converter o1carry out integral operation, export E 1; Second integral device is to the output valve V of the second D/A converter o2carry out integral operation, export E 2;
Step 2.4: according to the output E of first integrator 1with the output E of second integral device 2carry out action differentiation, differentiation result is F dif: F d> 0, corresponding to the expectation action of doing evil through another person for opening; If F d< 0 is closed corresponding to the expectation action of doing evil through another person, F d=0 corresponding to the expectation action of doing evil through another person for stop, wherein:
F d＝E 1-E 2，
Step 3: obtained the control signal y done evil through another person by a grip processing controller, performing step is as follows:
Step 3.1: gather the current grip signal F done evil through another person n, calculate grip tracking error Δ F:
ΔF＝F d-F n，
Step 3.2: grip tracking error Δ F is inputted grip processing controller, grip processing controller exports the control signal y for driving action of doing evil through another person;
Step 4: be used for driving the direct current generator on doing evil through another person after control signal y is carried out power amplification, thus the grip that control is done evil through another person.
2. the myoelectric prosthetic hand control method based on accidental resonance according to claim 1, is characterized in that, described grip processing controller is a PID controller.
3. the myoelectric prosthetic hand control method based on accidental resonance according to claim 1, is characterized in that, described first myoelectric sensor and the second myoelectric sensor are fitted on a pair Antagonistic muscle of wearer's arm respectively.
CN201310487341.1A 2013-10-17 2013-10-17 Based on the myoelectric prosthetic hand control method of accidental resonance Active CN103494660B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201310487341.1A CN103494660B (en) 2013-10-17 2013-10-17 Based on the myoelectric prosthetic hand control method of accidental resonance

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201310487341.1A CN103494660B (en) 2013-10-17 2013-10-17 Based on the myoelectric prosthetic hand control method of accidental resonance

Publications (2)

Publication Number Publication Date
CN103494660A CN103494660A (en) 2014-01-08
CN103494660B true CN103494660B (en) 2015-11-18

Family

ID=49859992

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201310487341.1A Active CN103494660B (en) 2013-10-17 2013-10-17 Based on the myoelectric prosthetic hand control method of accidental resonance

Country Status (1)

Country Link
CN (1) CN103494660B (en)

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102319130A (en) * 2011-07-21 2012-01-18 山东科技大学 Control system and method for triggering multi-degree-of-freedom movement of upper artificial limbs by using toe
CN202665758U (en) * 2012-05-07 2013-01-16 丹阳精博假肢矫形器技术有限公司 Single electrode control system for two degrees-freedom electromyography artificial limb of upper arm
CN102961203A (en) * 2012-12-10 2013-03-13 杭州电子科技大学 Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy
CN103006358A (en) * 2012-12-27 2013-04-03 东南大学 Control method of myoelectric artificial hand

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102319130A (en) * 2011-07-21 2012-01-18 山东科技大学 Control system and method for triggering multi-degree-of-freedom movement of upper artificial limbs by using toe
CN202665758U (en) * 2012-05-07 2013-01-16 丹阳精博假肢矫形器技术有限公司 Single electrode control system for two degrees-freedom electromyography artificial limb of upper arm
CN102961203A (en) * 2012-12-10 2013-03-13 杭州电子科技大学 Method for identifying surface electromyography (sEMG) on basis of empirical mode decomposition (EMD) sample entropy
CN103006358A (en) * 2012-12-27 2013-04-03 东南大学 Control method of myoelectric artificial hand

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
肌电信号特征提取方法综述;加玉涛等;《电子器件》;20070228;第30卷(第1期);第327页第1栏第1－2段，第2栏第4段 *

Also Published As

Publication number Publication date
CN103494660A (en) 2014-01-08

Similar Documents

Publication Publication Date Title
Manimegalai Hand gesture recognition based on EMG signals using ANN
CN105012057A (en) Intelligent artificial limb based on double-arm electromyogram and attitude information acquisition and motion classifying method
CN103006358B (en) Control method of myoelectric artificial hand
CN102228399A (en) Myoelectricity artificial hand grip strength controlling method based on fuzzy controller
Chen et al. Towards robot-assisted post-stroke hand rehabilitation: Fugl-Meyer gesture recognition using sEMG
CN103494660B (en) Based on the myoelectric prosthetic hand control method of accidental resonance
Francis et al. EEG-Controlled Robot Navigation using Hjorth Parameters and Welch-PSD.
CN106955111A (en) Brain paralysis youngster&#39;s gait recognition method based on surface electromyogram signal
Boschmann et al. FPGA-based acceleration of high density myoelectric signal processing
CN105813011B (en) Robot device based on cell-phone customer terminal perceives signal detecting method when participating in the cintest
CN108415250A (en) A kind of man-machine coordination control system and its control method for preventing the elderly from falling down
CN204909750U (en) Intelligence artificial limb based on both arms flesh electricity, Attitude information gather
Song et al. Recognition of motion of human upper limb using semg in real time: Towards bilateral rehabilitation
Maufroy et al. CNN-Based detection and classification of grasps relevant for worker support scenarios using sEMG signals of forearm muscles
Chen et al. SoC-based architecture for robotic prosthetics control using surface electromyography
Li et al. A gait recognition system for rehabilitation based on wearable micro inertial measurement unit
Kashiwagi et al. Discrimination of waist motions based on surface EMG for waist power assist suit using support vector machine
Wang et al. Posture recognition of elbow flexion and extension using semg signal based on multi-scale entropy
Zhao et al. Motion intention estimation of lower limbs based on sEMG supplement with acceleration signal
CN206549048U (en) Neck muscle group functional training servicing unit and system
Suresh et al. Motor-activated multi-functional wrist orthotic to assist individuals with cervical spinal cord injuries with activities of daily living
Wolczowski et al. Control of hand prosthesis using fusion of biosignals and information from prosthesis sensors
Huang et al. Design of a grasp force adaptive control system with tactile and slip perception
Bhatnagar et al. Smart Solar Power‐Assisted Wheelchairs For the Handicapped
Guangying Study of myoelectric prostheses hand based on independent component analysis and fuzzy controller

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant