CN101987048A - Artificial limb control method and system thereof - Google Patents
Artificial limb control method and system thereof Download PDFInfo
- Publication number
- CN101987048A CN101987048A CN 200910109087 CN200910109087A CN101987048A CN 101987048 A CN101987048 A CN 101987048A CN 200910109087 CN200910109087 CN 200910109087 CN 200910109087 A CN200910109087 A CN 200910109087A CN 101987048 A CN101987048 A CN 101987048A
- Authority
- CN
- China
- Prior art keywords
- artificial limb
- characteristic information
- signal
- control method
- bioelectrical signals
- 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.)
- Granted
Links
Images
Abstract
The invention provides an artificial limb control method which comprises the following steps: acquiring a bioelectric signal; extracting feature information of the bioelectric signal; identifying action types according to the feature information; and controlling an artificial limb to complete corresponding actions according to the action types. In the artificial limb control method, by extracting the feature information of the bioelectric signal and identifying the action types according to the feature information, the actions that a physical disabled person intends to execute can be forecasted so as to control the artificial limb to execute the corresponding actions according to the forecasted action types. By adopting the artificial limb control method, an artificial limb user can naturally and directly select and perform various different physical actions that the user intends to complete just like before amputation. The control technology based on action type identification can realize intuitive control of the myoelectric artificial limb so as to realize natural and intuitive control of the multifunctional artificial limb, thus enhancing use convenience of the artificial limb. In addition, the invention further provides an artificial limb control system.
Description
[technical field]
The present invention relates to prosthesis technique, especially relate to a kind of artificial limb control method and system.
[background technology]
According to State Statistics Bureau 2006 China disabled population sampling survey data are calculated that in all kinds of people with disabilitys in the whole nation, physical disabilities population is maximum, is 2,412 ten thousand people, accounts for 29.07% of total disabled population.Owing to reasons such as contingency, birth defect, disease, natural disasters, physical disabilities population is also in continuous increase.Only in Wenchuan, the Sichuan violent earthquake in May, 2008, just there is people more than 20,000 to lose limbs.These amputation personage needs to dress the AFL with auxiliary its daily life and work.
According to the control mode of artificial limb, present domestic and international commercialization AFL can be divided into: mechanical cable-operated prosthesis, myoelectric limb and myoelectricity rope control mixing artificial limb.
Traditional mechanical cable-operated prosthesis is self the power source that utilizes the prosthetic user, elbow joint and the terminal device of controlling artificial limb by the mechanical action pulling rope or the chain of residual limbs.Because the inherent limitation of control method, mechanical cable-operated prosthesis exists function singleness, controls problems such as slow, clumsy in one's movement, difficult in maintenance.
Closely for decades, the electromyographic signal from residual limbs surface recording is widely used in artificial upper extremity's the control.During the residual muscle contraction of amputee, complicated biochemical reaction can take place, produce the faint signal of telecommunication.Can obtain the signal of telecommunication that muscle produces with the electromyographic electrode that places residual limbs surface, this signal of telecommunication is called as: electromyographic signal.Electromyographic signal is amplified and is handled through amplifier, as the control signal of artificial limb.The artificial limb controller drives the joint of artificial limb opening and closing by drive system such as micromotors.
Present myoelectric limb utilizes degree of freedom of motion of a pair of residual muscle (agonist and Antagonistic muscle) control.After the limbs amputation, the myoelectric information source is limited, and the degree of amputation is high more, and residual limb muscle is few more, and needs the limb action of recovery many more.Therefore, this myoelectricity control mode can not directly realize the multiple degrees of freedom control of artificial limb, and the use of artificial limb is difficulty very.In order to control a plurality of degree of freedom with a pair of muscle, myoelectric limb has increased action " pattern " handoff functionality.The switching of " pattern " utilizes a pair of muscle " contraction " or extra switch is realized." pattern " of supposing current artificial limb is hand motion, and the prosthetic user next step want to do the action of ancon, they need make a pair of muscle " contractions " generation myoelectricity simultaneously.When the electromyographic signal amplitude of two electrodes during all greater than given " threshold value ", the limb action of artificial limb " pattern " switches to ancon from hand.Then, can control two different ancon actions of artificial limb in order to two electromyographic electrodes respectively, for example forearm lifting and putting down.This myoelectric limb control method does not meet the mode that people's " nature " use limbs, causes using inconvenience.For example,, need, but before amputation, biceps with triceps muscle is and the relevant muscle of ancon action with residual biceps and triceps muscle control wrist movement or hand motion for the above amputee of ancon.This causes artificial limb clumsy in one's movement in using, prosthetic user's mental burden is big wait not enough.According to statistics, even in having the people with disability of myoelectric limb, approximately often use their artificial limb less than 50% people.
[summary of the invention]
In view of this, be necessary to provide a kind of artificial limb control method that improves ease of use.
In addition, also be necessary to provide a kind of artificial limb control system that improves ease of use.
A kind of artificial limb control method comprises the steps: to gather bioelectrical signals; Extract the characteristic information of bioelectrical signals; According to characteristic information identification maneuver type; Finish corresponding action according to type of action control artificial limb.
Preferably, described bioelectrical signals is an electromyographic signal, and described electromyographic signal comprises plural passage.
Preferably, the step of described collection bioelectrical signals comprises: the signal of telecommunication of electromyographic electrode record is amplified with Filtering Processing after mould/number conversion is a digital signal, and the sample frequency that described Filtering Processing bandwidth is 5-450 hertz or described mould/number conversion is the 500-1000 hertz.
Preferably, the step of the characteristic information of described extraction bioelectrical signals comprises from described electromyographic signal and to extract temporal signatures parameter and the frequency domain character parameter characteristic information as described electromyographic signal.
Preferably, described temporal signatures parameter is one or more in average absolute value, G-bar absolute value, sampling point difference in magnitude, the zero-crossing rate.
Preferably, described extraction frequency domain character parameter is for to carry out Fourier transform to described electromyographic signal, extracts in the following frequency domain character parameter one or both: the mean power of power spectrum, median frequency.
Preferably, the step of the characteristic information of described extraction bioelectrical signals comprises the data analysis window that described electromyographic signal is divided into scheduled time length, from described data analysis window, extract described temporal signatures parameter and frequency domain character parameter, and combine the characteristic vector of the characteristic information that forms described electromyographic signal, described two combination of eigenvectors with the electromyographic signal of upper channel are the myoelectricity eigenmatrix.
Preferably, described step according to characteristic information identification maneuver type comprises: adopt the linear discriminant analysis method to analyze described characteristic information also according to the training result identification maneuver type of storing in advance.
A kind of artificial limb control system comprises: signal acquisition module is used to gather bioelectrical signals; Characteristic extracting module links to each other with described signal acquisition module and to extract the characteristic information of described bioelectrical signals; Pattern recognition module is according to the described characteristic information identification maneuver type of described characteristic extracting module acquisition; Driver module is finished corresponding action according to described pattern recognition module recognized action type control artificial limb.
Preferably, the described bioelectrical signals of described signal acquisition module collection is an electromyographic signal, and the characteristic information of the described bioelectrical signals that described characteristic extracting module is extracted is temporal signatures parameter and frequency domain character parameter.
Preferably, described pattern recognition module adopts the linear discriminant analysis method to analyze described characteristic information also according to the training result identification maneuver type of storing in advance.
Above-mentioned artificial limb control method and system predict that by the characteristic information of extraction bioelectrical signals and according to this characteristic information identification maneuver type physical disabilities person wants the action of carrying out, and according to the type of action of prediction, the control artificial limb is carried out corresponding action.Utilize above-mentioned artificial limb control method, yet the prosthetic user can be from directly selecting and doing the various different limb actions that they feel like doing, before their amputation.This control technology based on type of action identification can realize that the intuition of myoelectric limb controls, thereby realizes natural, the intuition control of multi-functional artificial limb, improves the convenience that artificial limb uses.
[description of drawings]
Fig. 1 is the flow chart of artificial limb control method;
Fig. 2 is the sketch map of electromyographic signal;
Fig. 3 is the module map of artificial limb control system.
[specific embodiment]
Following embodiment disclose a kind of can be by the surface electromyography signal decoding being realized the technology of multi-functional artificial limb control.Along with advanced person's the signal processing technology and the appearance of high-performance microprocessor, making becomes possibility by the method that the surface electromyography signal decoding is realized multi-functional artificial limb control.The theory of this method (neuroelectricity physiology) basis is that nervus motorius information can be by decoding obtains to electromyographic signal.When the amputee does different action by the imagination with the limbs that lost, can and produce the signal of telecommunication with the electromyographic electrode induction after making remaining muscle contraction from the nervus motorius signal of brain, after the signal of telecommunication handled, with the mode identification method decoding, obtain the limb action type that the amputee feels like doing; Control artificial limb according to the recognized action type and finish corresponding action.Utilize this control method, yet the prosthetic user can be from directly selecting and finishing the various different limb actions that they feel like doing.Therefore, this control scheme based on the myoelectricity mode decoding can overcome the deficiency of traditional myoelectric limb control, realizes having the bionical control of intuition, multi-freedom artificial limb, improves the convenience that uses.
As shown in Figure 1, it is the flow chart of artificial limb control method.
At first, step S110 gathers bioelectrical signals.Present embodiment is that example describes bioelectrical signals with the surface electromyogram signal.When the amputee does different action by the imagination with the limbs that lost, make remaining muscle contraction from the nervus motorius signal of brain, use attached to the electromyographic electrode induction of muscle surface and produce the signal of telecommunication.With the electromyographic signal of electromyographic electrode record, after amplification and filtering (bandwidth is preferably the 5-450 hertz) processing, be quantified as digital signal with analog-digital converter, as electromyographic signal, sample frequency is preferably the 500-1000 hertz with this digital signal.For different limbs amputation degree and the limb action number that need to recover, the number of electromyographic electrode and position are with different.The electromyographic electrode number can be more than one or two, and to obtain two electromyographic signals with upper channel, general electromyographic electrode number is 3-12.For the BE amputation person below the elbow joint, electromyographic electrode places residual forearm and upper arm; And for the BE amputation person more than the elbow joint, electromyographic electrode places residual upper arm.Except the application surface electromyographic signal, still have the other biological signal of telecommunication (as the EEG signals and the peripheral nerve signal of telecommunication of human-machine interface technology, and intrusive mood deep layer electromyographic signal etc.) comprises certain movable information equally, also can be used as bioelectrical signals, this bioelectrical signals is carried out the identification control of artificial limb type of action as information source.
Step S120, the characteristic information of extraction bioelectrical signals.From electromyographic signal, extract temporal signatures parameter and frequency domain character parameter characteristic information as electromyographic signal.The temporal signatures parameter can be in average absolute value, G-bar absolute value, sampling point difference in magnitude, the zero-crossing rate one or more.Extract the frequency domain character parameter for electromyographic signal is carried out Fourier transform, extract in the following frequency domain character parameter one or both: the mean power of power spectrum, median frequency.The detailed process of feature extraction is: the data analysis window (being illustrated in figure 2 as the electromyographic signal of a passage) that the electromyographic signal of each passage collection is divided into scheduled time length (for example 50-250ms), data analysis window can have certain overlapping (recruitment between the adjacent window apertures is t), from each data analysis window, extract the temporal signatures parameter and the frequency domain character parameter of electromyographic signal, and combine the characteristic vector of the characteristic information that forms electromyographic signal, described two combination of eigenvectors with the electromyographic signal of upper channel are the myoelectricity eigenmatrix.Except the characteristic information as bioelectrical signals, can also adopt higher-order spectrum and chaos and characteristic parameter extraction method such as fractal characteristic information as bioelectrical signals with temporal signatures parameter and frequency domain character parameter.
Step S130 is according to characteristic information identification maneuver type.(LinearDiscriminant Analysis LDA) analyzes described characteristic information and the basis training result identification maneuver type of storage in advance, promptly identifies the pattern that user need use to adopt the linear discriminant analysis method.Before utilizing the limb action that a LDA pattern classifier real-time estimate experimenter wants to carry out, just before user formally uses this artificial limb, need characteristic information training classifier, make it " remember " type of action that is comprised with electromyographic signal.Realize the training of classification of motion device by the training program module.The output of grader can be selected the type of action of artificial limb in real time, acts on the artificial limb motor and carries out this action.The linear discriminant analysis method makes full use of the classification attaching information, and operation is simple, and required amount of calculation is little, and computation time is short, easily embeds hardware system and realizes extensive use.And, studies have shown that the accuracy of linear discriminant analysis method and other main several recognition methodss (artificial neural network, gauss hybrid models) no significant difference or identity are better.Except above-mentioned linear discriminant analysis method, can also adopt artificial nerve network classifier (Artificial Neural Network, ANN) and hidden Markov model (Hidden Markov Models, HMM) identification maneuver type.
Step S140 finishes corresponding action according to type of action control artificial limb.The classification of motion result that grader is made is as the control input signal of artificial limb, the action that decision artificial limb that can be real-time will be carried out.In addition, the difference of prosthetic user's muscle contraction strength will change the amplitude of electromyographic signal, utilizes the emg amplitude size to regulate and control the speed of artificial limb action, and amplitude greatly then speed is fast, otherwise then speed is slow.
Above-mentioned artificial limb control method predicts that by the characteristic information of extraction bioelectrical signals and according to this characteristic information identification maneuver type physical disabilities person wants the action of carrying out, and according to the type of action of prediction, the control artificial limb is carried out corresponding action.Utilize above-mentioned artificial limb control method, yet the prosthetic user can be from directly selecting and doing the various different limb actions that they feel like doing, before their amputation.This control technology based on type of action identification can realize that the intuition of myoelectric limb controls, thereby realizes natural, the intuition control of multi-functional artificial limb, improves the convenience that artificial limb uses.
Adopt a plurality of electromyographic electrode record electromyographic signals, and the different limb action types that feel like doing of the identification limbs disabled, control artificial limb according to the recognized action type then and do corresponding action, this control technology based on type of action identification can realize the control of multi-freedom artificial limb, carries out the control of wrist movement or the control of ancon action such as the result according to type of action identification.
Because the control of present myoelectric limb is not the technology of controlling of a kind of nature (intuition), add the different joint action of contraction control that utilizes same muscle, thereby the training process that makes study control artificial limb becomes very very long and uninteresting; Artificial limb slow in one's movements, clumsy; Prosthetic user's mental burden is big etc.And utilize myoelectricity control technology of the present invention, yet the prosthetic user can be from directly selecting and doing the various different limb actions that they feel like doing, before their amputation.Therefore, can reduce the learning training time that artificial limb is controlled greatly, reduce prosthetic user's mental burden.
Experimental simulation through experiment and the control of virtual reality myoelectric limb proves that above-mentioned artificial limb control system is feasible, effective.For example, be in the experimentation of study subject with the ancon amputee, utilize the 4-6 surface electrode to gather electromyographic signal, for 6 the most frequently used wrists and hand motion, the nicety of grading height of type of action identification is more than 95%.This explanation can realize the high accuracy control of multi-freedom artificial limb based on the control technology of type of action identification.
In addition, also provide a kind of artificial limb control system.As shown in Figure 3, this artificial limb control system 300 comprises successively the signal acquisition module 310, characteristic extracting module 320, pattern recognition module 330, driver module 340 and the memory module 350 that is connected with pattern recognition module 330 that connect, is connected the amplitude computing module 360 between signal acquisition module 310 and the driver module 340.
Signal acquisition module 310 is used to gather bioelectrical signals.In the present embodiment, signal acquisition module 310 comprises surface myoelectric electrode, amplifier, wave filter and the analog-digital converter that connects successively.Attached to the muscle surface induction and the generation signal of telecommunication, this signal of telecommunication is converted to digital signal by analog-digital converter to the surface myoelectric electrode behind amplifier amplification and filter filtering by noninvasive mode.
Characteristic extracting module 320 links to each other with signal acquisition module 310 and extracts the characteristic information of bioelectrical signals.In the present embodiment, the characteristic information of the bioelectrical signals that characteristic extracting module 320 is extracted is temporal signatures parameter and frequency domain character parameter, that is to say, can be independent temporal signatures parameter or frequency domain character parameter, also can be the temporal signatures parameter and the combining of frequency domain character parameter.
The characteristic information identification maneuver type that pattern recognition module 330 obtains according to characteristic extracting module 320.In the present embodiment, pattern recognition module 330 adopts the linear discriminant analysis method to analyze described characteristic information also according to the training result identification maneuver type of storing in advance.Pattern recognition module 330 links to each other with memory module 350, and memory module 350 is used to be stored in user formally to be used before this artificial limb, with in the characteristic information training process of electromyographic signal, and the pairing type of action of the characteristic information of various electromyographic signals.When user formally used this artificial limb, pattern recognition module 330 was determined the type of action that the characteristic information of current electromyographic signal is corresponding and is exported this type of action according to the characteristic information of electromyographic signal in the training process of storage in advance and the corresponding relation of type of action.
Driver module 340 is finished corresponding action according to pattern recognition module 330 recognized action types control artificial limb.For example, if the type of action of determining is the swing forearm, then driver module 340 drives the activity of elbow joint.
Amplitude computing module 360 is used to calculate the bioelectrical signals range value, and range value is sent to driver module 340, and driver module 340 is according to the translational speed of this range value control artificial limb.
Above-mentioned artificial limb control system predicts that by the characteristic information of extraction bioelectrical signals and according to this characteristic information identification maneuver type physical disabilities person wants the action of carrying out, and according to the type of action of prediction, the control artificial limb is carried out corresponding action.Utilize above-mentioned artificial limb control system, yet the prosthetic user can be from directly selecting and doing the various different limb actions that they feel like doing, before their amputation.This control technology based on type of action identification can realize that the intuition of myoelectric limb controls, thereby realizes natural, the intuition control of multi-functional artificial limb, improves the convenience that artificial limb uses.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to claim of the present invention.Should be pointed out that for the person of ordinary skill of the art without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (11)
1. an artificial limb control method is characterized in that, comprises the steps:
Gather bioelectrical signals;
Extract the characteristic information of bioelectrical signals;
According to characteristic information identification maneuver type;
Finish corresponding action according to type of action control artificial limb.
2. artificial limb control method according to claim 1 is characterized in that, described bioelectrical signals is an electromyographic signal, and described electromyographic signal comprises plural passage.
3. artificial limb control method according to claim 2, it is characterized in that, the step of described collection bioelectrical signals comprises: the signal of telecommunication of electromyographic electrode record is amplified with Filtering Processing after mould/number conversion is a digital signal, and the sample frequency that described Filtering Processing bandwidth is 5-450 hertz or described mould/number conversion is the 500-1000 hertz.
4. artificial limb control method according to claim 2, it is characterized in that the step of the characteristic information of described extraction bioelectrical signals comprises from described electromyographic signal and to extract temporal signatures parameter and the frequency domain character parameter characteristic information as described electromyographic signal.
5. artificial limb control method according to claim 4 is characterized in that, described temporal signatures parameter is one or more in average absolute value, G-bar absolute value, sampling point difference in magnitude, the zero-crossing rate.
6. artificial limb control method according to claim 4, it is characterized in that, described extraction frequency domain character parameter is for to carry out Fourier transform to described electromyographic signal, extracts in the following frequency domain character parameter one or both: the mean power of power spectrum, median frequency.
7. artificial limb control method according to claim 4, it is characterized in that, the step of the characteristic information of described extraction bioelectrical signals comprises the data analysis window that described electromyographic signal is divided into scheduled time length, from described data analysis window, extract described temporal signatures parameter and frequency domain character parameter, and combine the characteristic vector of the characteristic information that forms described electromyographic signal, described two combination of eigenvectors with the electromyographic signal of upper channel are the myoelectricity eigenmatrix.
8. artificial limb control method according to claim 1 is characterized in that, described step according to characteristic information identification maneuver type comprises: adopt the linear discriminant analysis method to analyze described characteristic information also according to the training result identification maneuver type of storing in advance.
9. an artificial limb control system is characterized in that, comprising:
Signal acquisition module is used to gather bioelectrical signals;
Characteristic extracting module links to each other with described signal acquisition module and to extract the characteristic information of described bioelectrical signals;
Pattern recognition module is according to the described characteristic information identification maneuver type of described characteristic extracting module acquisition;
Driver module is finished corresponding action according to described pattern recognition module recognized action type control artificial limb.
10. artificial limb control system according to claim 9, it is characterized in that, the described bioelectrical signals of described signal acquisition module collection is an electromyographic signal, and the characteristic information of the described bioelectrical signals that described characteristic extracting module is extracted is temporal signatures parameter and frequency domain character parameter.
11. artificial limb control system according to claim 9 is characterized in that, described pattern recognition module adopts the linear discriminant analysis method to analyze described characteristic information also according to the training result identification maneuver type of storing in advance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910109087 CN101987048B (en) | 2009-08-03 | 2009-08-03 | Artificial limb control method and system thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200910109087 CN101987048B (en) | 2009-08-03 | 2009-08-03 | Artificial limb control method and system thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101987048A true CN101987048A (en) | 2011-03-23 |
| CN101987048B CN101987048B (en) | 2013-07-03 |
Family
ID=43743973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200910109087 Active CN101987048B (en) | 2009-08-03 | 2009-08-03 | Artificial limb control method and system thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101987048B (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| CN102499797A (en) * | 2011-10-25 | 2012-06-20 | 中国科学院深圳先进技术研究院 | Artificial limb control method and system |
| CN102641196A (en) * | 2011-12-30 | 2012-08-22 | 中国科学院深圳先进技术研究院 | Rehealthy training robot control system and control method thereof |
| CN102836021A (en) * | 2012-09-29 | 2012-12-26 | 哈尔滨工业大学 | Coding type multi-degree-of-freedom myoelectric prosthetic hand control system |
| CN103212188A (en) * | 2013-05-13 | 2013-07-24 | 中山大学 | Method and system for assisting gait training |
| CN103358311A (en) * | 2012-04-01 | 2013-10-23 | 中国科学院深圳先进技术研究院 | Robot control method and system based on bioelectricity signal decoding |
| CN103519924A (en) * | 2013-10-22 | 2014-01-22 | 深圳先进技术研究院 | Intelligent artificial hand system |
| CN103941859A (en) * | 2014-03-21 | 2014-07-23 | 上海威璞电子科技有限公司 | Algorithm for differentiating different gestures through signal power |
| CN104997581A (en) * | 2015-07-17 | 2015-10-28 | 西安交通大学 | Artificial hand control method and apparatus for driving EEG signals on the basis of facial expressions |
| CN104997582A (en) * | 2015-07-30 | 2015-10-28 | 沈阳工业大学 | Device and method for controlling intelligent artificial limb based on eye and lower jaw electromyographic signals |
| CN105139038A (en) * | 2015-09-14 | 2015-12-09 | 李玮琛 | Electromyographic signal mode identification method |
| CN107870583A (en) * | 2017-11-10 | 2018-04-03 | 国家康复辅具研究中心 | artificial limb control method, device and storage medium |
| CN108008821A (en) * | 2017-12-14 | 2018-05-08 | 中国科学院深圳先进技术研究院 | Performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device |
| CN109223264A (en) * | 2018-11-13 | 2019-01-18 | 深圳先进技术研究院 | A kind of knee joint artificial limb and control method |
| CN109453509A (en) * | 2018-11-07 | 2019-03-12 | 龚映清 | It is a kind of based on myoelectricity and motion-captured virtual upper limb control system and its method |
| CN109998742A (en) * | 2019-05-07 | 2019-07-12 | 北京通和营润智能科技发展有限公司 | A kind of bionical artificial limb control system of multi-freedom degree muscle-electric |
| CN110337269A (en) * | 2016-07-25 | 2019-10-15 | 开创拉布斯公司 | The method and apparatus that user is intended to are inferred based on neuromuscular signals |
| CN110811940A (en) * | 2019-10-31 | 2020-02-21 | 中国科学院长春光学精密机械与物理研究所 | Intelligent artificial limb device and control method |
| CN110974497A (en) * | 2019-12-30 | 2020-04-10 | 南方科技大学 | Electric artificial limb control system and control method |
| CN111317600A (en) * | 2018-12-13 | 2020-06-23 | 深圳先进技术研究院 | Artificial limb control method, device, system, equipment and storage medium |
| CN111743668A (en) * | 2020-06-30 | 2020-10-09 | 北京海益同展信息科技有限公司 | Prosthesis control method, device, electronic apparatus, and storage medium |
| CN113157095A (en) * | 2021-04-23 | 2021-07-23 | 上海交通大学 | Embedded real-time self-adaptive control method and system based on surface electromyogram signal |
| CN113288532A (en) * | 2021-05-31 | 2021-08-24 | 北京京东乾石科技有限公司 | Myoelectric control method and device |
| CN114533089A (en) * | 2022-02-22 | 2022-05-27 | 北京工业大学 | Lower limb action recognition and classification method based on surface electromyographic signals |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101317794B (en) * | 2008-03-11 | 2010-04-14 | 清华大学 | Myoelectric control ability detecting and training method for hand-prosthesis with multiple fingers and multiple degrees of freedom |
| CN101371804A (en) * | 2008-07-16 | 2009-02-25 | 哈尔滨工业大学 | On-line recognizing method of hand gesture mode established based on sEMG |
-
2009
- 2009-08-03 CN CN 200910109087 patent/CN101987048B/en active Active
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101874758B (en) * | 2010-05-07 | 2012-02-22 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| CN101874758A (en) * | 2010-05-07 | 2010-11-03 | 中国科学院深圳先进技术研究院 | Supplementary motion system and control method thereof |
| CN102499797A (en) * | 2011-10-25 | 2012-06-20 | 中国科学院深圳先进技术研究院 | Artificial limb control method and system |
| CN102641196A (en) * | 2011-12-30 | 2012-08-22 | 中国科学院深圳先进技术研究院 | Rehealthy training robot control system and control method thereof |
| CN103358311A (en) * | 2012-04-01 | 2013-10-23 | 中国科学院深圳先进技术研究院 | Robot control method and system based on bioelectricity signal decoding |
| CN102836021A (en) * | 2012-09-29 | 2012-12-26 | 哈尔滨工业大学 | Coding type multi-degree-of-freedom myoelectric prosthetic hand control system |
| CN103212188B (en) * | 2013-05-13 | 2015-08-05 | 中山大学 | A kind of method and system of auxiliary gait training |
| CN103212188A (en) * | 2013-05-13 | 2013-07-24 | 中山大学 | Method and system for assisting gait training |
| CN103519924B (en) * | 2013-10-22 | 2015-12-02 | 深圳先进技术研究院 | Intelligent artificial hand system |
| CN103519924A (en) * | 2013-10-22 | 2014-01-22 | 深圳先进技术研究院 | Intelligent artificial hand system |
| CN103941859A (en) * | 2014-03-21 | 2014-07-23 | 上海威璞电子科技有限公司 | Algorithm for differentiating different gestures through signal power |
| CN104997581A (en) * | 2015-07-17 | 2015-10-28 | 西安交通大学 | Artificial hand control method and apparatus for driving EEG signals on the basis of facial expressions |
| CN104997582A (en) * | 2015-07-30 | 2015-10-28 | 沈阳工业大学 | Device and method for controlling intelligent artificial limb based on eye and lower jaw electromyographic signals |
| CN104997582B (en) * | 2015-07-30 | 2017-03-22 | 沈阳工业大学 | Device and method for controlling intelligent artificial limb based on eye and lower jaw electromyographic signals |
| CN105139038A (en) * | 2015-09-14 | 2015-12-09 | 李玮琛 | Electromyographic signal mode identification method |
| CN110337269A (en) * | 2016-07-25 | 2019-10-15 | 开创拉布斯公司 | The method and apparatus that user is intended to are inferred based on neuromuscular signals |
| CN110337269B (en) * | 2016-07-25 | 2021-09-21 | 脸谱科技有限责任公司 | Method and apparatus for inferring user intent based on neuromuscular signals |
| CN107870583A (en) * | 2017-11-10 | 2018-04-03 | 国家康复辅具研究中心 | artificial limb control method, device and storage medium |
| CN108008821A (en) * | 2017-12-14 | 2018-05-08 | 中国科学院深圳先进技术研究院 | Performance estimating method, device, terminal and the storage medium of artificial limb classification of motion device |
| CN108008821B (en) * | 2017-12-14 | 2021-04-02 | 中国科学院深圳先进技术研究院 | Performance evaluation method, device, terminal and storage medium of artificial limb action classifier |
| CN109453509A (en) * | 2018-11-07 | 2019-03-12 | 龚映清 | It is a kind of based on myoelectricity and motion-captured virtual upper limb control system and its method |
| CN109223264A (en) * | 2018-11-13 | 2019-01-18 | 深圳先进技术研究院 | A kind of knee joint artificial limb and control method |
| CN109223264B (en) * | 2018-11-13 | 2023-11-21 | 深圳先进技术研究院 | Knee joint prosthesis and control method |
| CN111317600A (en) * | 2018-12-13 | 2020-06-23 | 深圳先进技术研究院 | Artificial limb control method, device, system, equipment and storage medium |
| CN111317600B (en) * | 2018-12-13 | 2022-03-15 | 深圳先进技术研究院 | Artificial limb control method, device, system, equipment and storage medium |
| CN109998742A (en) * | 2019-05-07 | 2019-07-12 | 北京通和营润智能科技发展有限公司 | A kind of bionical artificial limb control system of multi-freedom degree muscle-electric |
| CN109998742B (en) * | 2019-05-07 | 2023-07-11 | 北京通和营润智能科技发展有限公司 | Multi-degree-of-freedom myoelectric bionic artificial limb control system |
| CN110811940A (en) * | 2019-10-31 | 2020-02-21 | 中国科学院长春光学精密机械与物理研究所 | Intelligent artificial limb device and control method |
| CN110974497A (en) * | 2019-12-30 | 2020-04-10 | 南方科技大学 | Electric artificial limb control system and control method |
| CN111743668A (en) * | 2020-06-30 | 2020-10-09 | 北京海益同展信息科技有限公司 | Prosthesis control method, device, electronic apparatus, and storage medium |
| CN111743668B (en) * | 2020-06-30 | 2023-12-05 | 京东科技信息技术有限公司 | Prosthesis control method, device, electronic equipment and storage medium |
| CN113157095A (en) * | 2021-04-23 | 2021-07-23 | 上海交通大学 | Embedded real-time self-adaptive control method and system based on surface electromyogram signal |
| CN113288532A (en) * | 2021-05-31 | 2021-08-24 | 北京京东乾石科技有限公司 | Myoelectric control method and device |
| CN114533089A (en) * | 2022-02-22 | 2022-05-27 | 北京工业大学 | Lower limb action recognition and classification method based on surface electromyographic signals |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101987048B (en) | 2013-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101987048B (en) | Artificial limb control method and system thereof | |
| CN108681396B (en) | Human-computer interaction system and method based on brain-myoelectricity bimodal neural signals | |
| Englehart et al. | A robust, real-time control scheme for multifunction myoelectric control | |
| CN102499797B (en) | Artificial limb control method and system | |
| CN106726030B (en) | Brain machine interface system and its application based on Clinical EEG Signals control robot movement | |
| CN202288542U (en) | Artificial limb control device | |
| CN103793058B (en) | A kind of active brain-computer interactive system Mental imagery classification of task method and device | |
| CN101711709B (en) | Method for controlling electrically powered artificial hands by utilizing electro-coulogram and electroencephalogram information | |
| Nazarpour et al. | Application of higher order statistics to surface electromyogram signal classification | |
| CN106236336A (en) | A kind of myoelectric limb gesture and dynamics control method | |
| CN105549743A (en) | Robot system based on brain-computer interface and implementation method | |
| CN100515366C (en) | Real time control device and control method by two-degrees-of freedom myoelectricity artificial hand | |
| CN202223388U (en) | Wearable brain-controlled intelligent prosthesis | |
| Chen et al. | Exploring the relation between EMG sampling frequency and hand motion recognition accuracy | |
| CN110059575A (en) | A kind of augmentative communication system based on the identification of surface myoelectric lip reading | |
| Zhang et al. | PCA and LDA for EMG-based control of bionic mechanical hand | |
| CN111544855B (en) | Pure idea control intelligent rehabilitation method based on distillation learning and deep learning and application | |
| WO2020118797A1 (en) | Prosthesis control method, apparatus, system and device, and storage medium | |
| CN109009586A (en) | A kind of myoelectricity continuous decoding method of the man-machine natural driving angle of artificial hand wrist joint | |
| CN102309365A (en) | Wearable brain-control intelligent prosthesis | |
| Gauthaam et al. | EMG controlled bionic arm | |
| CN105012057A (en) | Intelligent artificial limb based on double-arm electromyogram and attitude information acquisition and motion classifying method | |
| CN105411580A (en) | Brain control wheelchair system based on touch and auditory evoked potential | |
| CN102306303A (en) | Electroencephalography signal characteristic extraction method based on small training samples | |
| CN113111831A (en) | Gesture recognition technology based on multi-mode information fusion |
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 |