CN113081671B - Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization - Google Patents
Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization Download PDFInfo
- Publication number
- CN113081671B CN113081671B CN202110346485.XA CN202110346485A CN113081671B CN 113081671 B CN113081671 B CN 113081671B CN 202110346485 A CN202110346485 A CN 202110346485A CN 113081671 B CN113081671 B CN 113081671B
- Authority
- CN
- China
- Prior art keywords
- robot
- tested
- training
- auxiliary
- rehabilitation
- 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
Links
- 238000012549 training Methods 0.000 title claims abstract description 50
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000005457 optimization Methods 0.000 title claims abstract description 23
- 238000011156 evaluation Methods 0.000 claims abstract description 26
- 230000006870 function Effects 0.000 claims abstract description 18
- 230000033001 locomotion Effects 0.000 claims abstract description 11
- 230000008569 process Effects 0.000 claims description 29
- 230000007246 mechanism Effects 0.000 claims description 10
- 230000037147 athletic performance Effects 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 7
- 210000003205 muscle Anatomy 0.000 claims description 6
- 238000012360 testing method Methods 0.000 claims description 5
- 230000001537 neural effect Effects 0.000 claims description 4
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 230000000386 athletic effect Effects 0.000 claims description 3
- 230000003183 myoelectrical effect Effects 0.000 claims description 2
- 230000037078 sports performance Effects 0.000 claims description 2
- 238000004590 computer program Methods 0.000 claims 2
- 210000005036 nerve Anatomy 0.000 abstract description 7
- 230000008859 change Effects 0.000 abstract description 5
- 230000006798 recombination Effects 0.000 abstract description 3
- 238000005215 recombination Methods 0.000 abstract description 3
- 230000004936 stimulating effect Effects 0.000 abstract description 2
- 238000011217 control strategy Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 3
- 210000001364 upper extremity Anatomy 0.000 description 3
- 208000006011 Stroke Diseases 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000001483 mobilizing effect Effects 0.000 description 2
- 238000002560 therapeutic procedure Methods 0.000 description 2
- 241000282414 Homo sapiens Species 0.000 description 1
- 206010061296 Motor dysfunction Diseases 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000008451 emotion Effects 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 230000005021 gait Effects 0.000 description 1
- 230000004630 mental health Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 238000011158 quantitative evaluation Methods 0.000 description 1
Images
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
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- A61H2201/00—Characteristics of apparatus not provided for in the preceding codes
- A61H2201/50—Control means thereof
- A61H2201/5007—Control means thereof computer controlled
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61H—PHYSICAL THERAPY APPARATUS, e.g. DEVICES FOR LOCATING OR STIMULATING REFLEX POINTS IN THE BODY; ARTIFICIAL RESPIRATION; MASSAGE; BATHING DEVICES FOR SPECIAL THERAPEUTIC OR HYGIENIC PURPOSES OR SPECIFIC PARTS OF THE BODY
- 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
Landscapes
- Health & Medical Sciences (AREA)
- Epidemiology (AREA)
- Pain & Pain Management (AREA)
- Physical Education & Sports Medicine (AREA)
- Rehabilitation Therapy (AREA)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Manipulator (AREA)
- Rehabilitation Tools (AREA)
Abstract
The invention discloses a method for improving the participation degree of auxiliary rehabilitation training on demand based on Bayes optimization, which aims to improve the active participation degree in the training of a tested object by evaluating the motion performance index and the motion participation degree index of the tested object in a random preset track following task for multiple times to establish an evaluation function, trains the relation between the learning evaluation function and the hyperparameter of an auxiliary strategy on demand by adopting a Bayes optimization method, and searches the most appropriate auxiliary strategy on demand in the next round of auxiliary strategy on demand. The method quantitatively evaluates the exercise performance index and the exercise participation index of the tested robot at the same time, can monitor the physiological and psychological state of the tested robot in real time, and provides an individualized and intelligent optimal auxiliary strategy on demand according to the change condition of the exercise performance and the exercise participation of the tested robot, thereby ensuring the active input state of the tested robot, effectively stimulating nerves to effectively cause nerve function recombination, improving the training efficiency of the robot technology assisted rehabilitation, and being a key element for the rehabilitation robot to more quickly enter clinical application.
Description
Technical Field
The invention belongs to the technical field of rehabilitation robots, rehabilitation training and machine learning, and particularly relates to a method for improving on-demand auxiliary rehabilitation training participation based on Bayesian optimization.
Background
Stroke has become one of the major diseases threatening physical and mental health and life safety of human beings, and more than half of stroke patients have upper limb motor dysfunction which seriously affects their activities of daily life. The traditional upper limb rehabilitation therapy mode mainly depends on a rehabilitation therapist for manual auxiliary training, and the mode needs to consume a large amount of physical strength of the rehabilitation therapist and is difficult to accurately evaluate the rehabilitation state of a patient. With the development of the robot technology, the appearance of the rehabilitation robot provides a new way for rehabilitation therapy. The rehabilitation robot can assist a patient to carry out rehabilitation training without the on-site guidance of a rehabilitation therapist, and a large amount of labor cost is saved. In addition, the rehabilitation robot can accurately evaluate the rehabilitation state of the patient through various sensors, is beneficial to a rehabilitation therapist to make a subsequent treatment scheme for the patient, and has wide market application prospect.
The control strategy of the rehabilitation robot is one of the key factors influencing the rehabilitation treatment effect. In recent years, on-demand assist control strategies have become a research focus in this field. As the name suggests, the main idea of the on-demand auxiliary control strategy is that the rehabilitation robot provides the auxiliary torque required by the rehabilitation robot to complete the rehabilitation training task according to the rehabilitation requirement to be tested. The control strategy minimizes the auxiliary moment provided by the rehabilitation robot on the premise of ensuring that the rehabilitation training task is completed by the test, thereby maximizing the main moment provided by the test. Researches show that the repeated nature of rehabilitation training easily makes the tested person lose interest and feel bored, and an inappropriate auxiliary training strategy is very likely to make the tested person lose confidence, generate boring emotion for rehabilitation training and have extremely adverse effects on rehabilitation effect. Therefore, one of the research focuses on maintaining and improving the active participation of the subject in rehabilitation training. Studies have shown that maintaining active participation in subjects can improve the efficiency of rehabilitation. However, most of the existing rehabilitation robots only consider the movement performance of the subject to change an on-demand auxiliary strategy, lack a quantitative evaluation mechanism for the active participation degree of the subject, and cannot monitor the physiological and psychological state change of the subject in real time so as to know the change of the participation degree of the subject. There is also no effective mechanism for mobilizing the positivity of the subject, and the active participation and the input status of the subject cannot be guaranteed. In other words, the existing rehabilitation robot can not effectively guide the active participation of the tested person in the auxiliary training on the basis of force and motion, and can not feed back the tested state in real time and carry out targeted auxiliary strategy adjustment on demand. Therefore, the motor performance index and the motor participation index of the tested body are quantitatively evaluated at the same time, a machine learning method is combined to develop a strategy which can monitor the physiological and psychological states of the tested body in real time, and a personalized and optimal auxiliary strategy on demand is provided according to the change conditions of the motor performance and the motor participation of the tested body, so that the active input state of the tested body is ensured, nerves are effectively stimulated to effectively cause nerve function recombination, the training efficiency of the robot technology auxiliary rehabilitation is expected to be improved, and the method is also a key element for the rehabilitation robot to enter clinical application more quickly.
Disclosure of Invention
In order to solve the problems, the invention discloses a method for improving the participation degree of the on-demand auxiliary rehabilitation training based on Bayesian optimization, which monitors the physiological and psychological states of a tested person in real time and provides an individualized and intelligent optimal on-demand auxiliary strategy, thereby ensuring the active input state of the tested person, effectively stimulating nerves to effectively cause nerve function recombination, improving the training efficiency of the robot technology auxiliary rehabilitation, and being a key element for the rehabilitation robot to enter clinical application more quickly.
In order to achieve the purpose, the technical scheme of the invention is as follows:
a method for improving on-demand auxiliary rehabilitation training participation based on Bayesian optimization comprises the following steps:
step 1, designing a track following task: the target track is designed into a quasi-sinusoidal curve formed by two semicircles, but only five reference points are uniformly displayed on the track in the whole track to serve as guide points, and the tail end of the robot is controlled to follow the track according to the reference points in the process of the operation to be tested;
step 2, evaluation index: selecting a trial tracking error F E As the sports performance evaluation index of the subject; selection of the root mean square value (RMS) of the surface electromyographic signal, i.e. the degree of muscle activation F MA And evaluating the exercise participation degree of the subject in training.
Step 3, evaluation mechanism: aiming at improving the training efficiency of the rehabilitation robot for assisting the neural rehabilitation, taking improving the active participation degree in the tested training as an entry point, and establishing an evaluation function by integrating the athletic performance index and the athletic participation degree index
Wherein,
a minimum lower limit for muscle activation, typically set to 0.5; beta is a weight parameter and is generally set to be 4000-8000.
Step 4, BayesThe optimization process comprises the following steps: firstly, obtaining the athletic performance index F of n tested wheels through a random process E Degree of engagement with movement F MA And an evaluation function J, learning the evaluation function J and the hyperparameter f of the on-demand auxiliary strategy by using Bayesian optimization training max Namely the functional relation of the maximum boundary auxiliary force, and finding out the hyperparameter which enables the evaluation function J to be maximum in the next round of on-demand auxiliary strategy
Further, the random process in step 4 is that the tested subject performs n rounds of track tracking tasks, and in each round of training, the hyper-parameter f max Random values in the selected range, namely the adaptive adjustment mechanism is different in each round of the random process, so that the most real tested performance can be obtained according to the tested capacity under different auxiliary conditions;
further, in the bayesian optimization process in step 4, after a new round of evaluation results is obtained, new data is merged into the data set
Then carrying out Bayesian optimization according to the new data set to obtain the superparameter f of the next round max After repeating the process several times, the training is finished.
Step 5, auxiliary strategy according to needs: in the training process, the robot self-adaptation is carried out according to the position error delta d and the over-parameter f of the tested object in the operation process max And adjusting the force applied by the robot to the tested object in real time according to the auxiliary force field rule.
Further, the auxiliary force field formula in step 5 is as follows:
f＝f max *[1-exp(-(△d/λ) 2 )]
wherein f is the auxiliary force applied to the tested object by the robot, f max Is the maximum boundary auxiliary force, and lambda is the excitation of the auxiliary force fieldThe live area value, here, is 0.2.
The invention has the beneficial effects that:
1. the method monitors the physiological and psychological states of the testee in real time, evaluates the motor performance and the motor participation degree of the testee at the same time, adopts a Bayesian optimization learning mechanism to assist decision making, makes an effective mechanism for mobilizing the positivity of the testee, ensures the active participation and input states of the testee, and provides a solution for intelligent and efficient nerve rehabilitation.
2. Aiming at the problem that the influence of the on-demand auxiliary strategy on the active participation degree of the tested person has individual difference, the method can independently make a personalized on-demand auxiliary training strategy, so that the rehabilitation training efficiency of each tested person is improved.
3. The method adopts Bayes optimization to make a lower-round optimal on-demand auxiliary strategy, can improve the motion capability of the tested object in a short period due to less iteration times, stimulate the neural perception of the tested object on force and motion control, and avoid useless training process as far as possible.
Drawings
FIG. 1 is a schematic diagram of an algorithm framework;
fig. 2 is a schematic diagram of a trajectory following task and assisting force adjustment.
Detailed Description
The present invention will be further illustrated with reference to the accompanying drawings and specific embodiments, which are to be understood as merely illustrative of the invention and not as limiting the scope of the invention.
As shown in fig. 1, the method for improving on-demand assisted rehabilitation training participation based on bayesian optimization provided by the embodiment of the present invention includes the following steps:
1. designing a track following task:
the target track is designed into a quasi-sinusoidal plane curve composed of two semicircles, as shown in fig. 1, only five reference points G1-G5 are uniformly displayed on the track in the whole track and are used as guide points, and the tail end of the robot is controlled to follow the track according to the reference points in the process of operation to be tested. Especially in the familiar stage, the therapist/technician explains the trajectory tracking task of the subject, including the shape of the desired trajectory, the position of the guide point, the start and stop conditions, etc., and the subject usually performs about 3-5 cycle periods in the familiar stage;
2. evaluation indexes are as follows:
(1) index of athletic performance
In order to measure the exercise performance in the process of the trial training, the time for completing the training task, the tracking error of the exercise trajectory, the flexibility of the exercise trajectory and other evaluation indexes are generally selected. Here, the motion tracking error F is selected E The athletic performance of the test subjects was evaluated, and the expression is as follows:
wherein xs is a plane horizontal coordinate starting point, and xe is a plane horizontal coordinate ending point; y is i Is the ordinate, y, of the actual position e A corresponding desired ordinate for each position.
(2) Index of sport participation
The engagement on the sport is defined as a state of being tried to actively and strive for the sport. In rehabilitation training, the movement state is generally monitored and characterized by an electromyographic signal (EMG). Trainees use Root Mean Square (RMS) value of EMG signal in gait rehabilitation training combined with virtual reality technology to evaluate the exercise participation degree of the trainees in training. Since the energy of the signal can be characterized, the rms value is considered to be the most meaningful method for analyzing the amplitude of the electromyographic signal. Therefore, the biceps brachii, the long head of the triceps brachii, the short head of the triceps brachii and the brachioradialis of which the upper limbs are mainly responsible for the exercise function are selected as the muscle group to be analyzed, and the exercise participation is defined as follows:
wherein,
is the myoelectric signal amplitude vector of the ith channel, and M is the length of the signal。
3. Evaluation mechanism: aiming at improving the training efficiency of the rehabilitation robot for assisting the neural rehabilitation, taking improving the active participation degree in the tested training as an entry point, and establishing an evaluation function by integrating the athletic performance index and the athletic participation degree index
Wherein,
the minimum lower limit value of the muscle activation degree is set to be 0.5; beta is a weight parameter and is generally set to be 4000-8000.
1. Bayesian optimization process:
firstly, obtaining the athletic performance index F of n tested wheels through a random process E Degree of engagement with sports F MA And an evaluation function J, learning the evaluation function J and the hyperparameter f of the on-demand auxiliary strategy by using Bayesian optimization training max Namely the functional relation of the maximum boundary auxiliary force, and finding out the hyperparameter which enables the evaluation function J to be maximum in the next round of on-demand auxiliary strategy
Further, the random process is that the tested object carries out n rounds of track tracking tasks, and in each round of training, the hyper-parameter f max Random values in the selected range, namely the adaptive adjustment mechanism is different in each round of the random process, so that the most real tested performance can be obtained according to the tested capacity under different auxiliary conditions;
further, in the Bayesian optimization process, after a new round of evaluation result is obtained, new data is merged into a data set
Then carrying out Bayesian optimization according to the new data set to obtain the superparameter f of the next round max After repeating the process several times, the training is finished.
2. Auxiliary strategy according to the requirement:
in the training process, the robot self-adaptation is carried out according to the position error delta d and the over-parameter f of the tested object in the operation process max And adjusting the force applied by the robot to the tested object in real time according to the auxiliary force field rule.
Further, the auxiliary force field formula is as follows:
f＝f max *[1-exp(-(△d/λ) 2 )]
wherein f is the auxiliary force applied to the tested object by the robot, f max For the maximum boundary assist force, λ is the value of the activation region of the assist force field, here 0.2.
Further, because the operation plane of the robot is a two-dimensional plane, and θ is an included angle between a connecting line between the tail end of the robot operated by the test and the current semicircular track center of circle and a horizontal plane, a method for calculating the output force of the tail end of the robot according to the track of the tail end is as follows:
f x ＝f*cosθ*sig(f)
f y ＝f*sinθ*sig(f)
wherein sig (f) is a symbol value of the adjusting force of the robot.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (4)
1. A rehabilitation training robot comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, wherein the computer program, when loaded into the processor, is configured to implement a method for improving on-demand assisted rehabilitation training engagement based on bayesian optimization, the method comprising the steps of:
step 1, designing a track following task: the target track is designed to be a quasi-sinusoidal curve consisting of two semicircles, but in the whole track, only five reference points are uniformly displayed on the track and serve as guide points, and the tail end of the robot is controlled to follow the track according to the reference points in the process of the operation to be tested;
step 2, evaluation index: selecting a trial tracking error F E As the sports performance evaluation index of the subject; selecting the root mean square value of the surface electromyographic signal, i.e. the muscle activation degree F MA Evaluating the exercise participation of the subject in training;
step 3, evaluation mechanism: aiming at improving the training efficiency of the rehabilitation robot for assisting the neural rehabilitation, taking improving the active participation degree in the training to be tested as an entry point, and establishing an evaluation function J by integrating the athletic performance index and the athletic participation degree index;
wherein,
the minimum lower limit value of the muscle activation degree is set to be 0.5; beta is a weight parameter and is set to be 4000-8000;
step 4, Bayesian optimization process: firstly, obtaining the athletic performance index F of n tested wheels through a random process E Degree of engagement with movement F MA And an evaluation function J, learning the evaluation function J and the hyperparameter f of the on-demand auxiliary strategy by using Bayesian optimization training max Namely the functional relation of the maximum boundary auxiliary force, and finding out the hyperparameter which enables the evaluation function J to be maximum in the next round of on-demand auxiliary strategy
The random process is that the tested object carries out n rounds of track tracking tasks, and each round of trainingMiddle and super parameter f max The random values in the selected range are different in each round of the random process, namely the adaptive adjustment mechanism is different, so that the most real tested performance can be obtained according to the tested capacity under different auxiliary conditions;
the Bayesian optimization process incorporates new data into the data set after obtaining a new round of evaluation results
Then carrying out Bayesian optimization according to the new data set to obtain the superparameter f of the next round max After repeating the process for a plurality of times, the training is finished;
step 5, auxiliary strategy according to needs: in the training process, the robot self-adaptation is carried out according to the position error delta d and the over-parameter f of the tested object in the operation process max And adjusting the force applied by the robot to the tested object in real time according to the auxiliary force field rule.
2. The robot of claim 1, wherein the athletic performance assessment indicator F of step 2 E The formula is as follows:
wherein xs is a plane horizontal coordinate starting point, and xe is a plane horizontal coordinate ending point; y is i Is the ordinate, y, of the actual position e A desired ordinate corresponding to each position.
3. The robot of claim 1, wherein the motion participation F of step 2 MA The formula is as follows:
wherein,
the myoelectric signal amplitude vector of the ith channel is shown, and M is the length of the signal.
4. The robot of claim 1, wherein the assisting force field law of step 5 is as follows:
f＝f max *[1-exp(-(△d/λ) 2 )]
wherein f is the auxiliary force applied to the tested object by the robot, f max The maximum boundary auxiliary force is obtained, lambda is the width of an activation region of an auxiliary force field, and the value of lambda is 0.2; further, because the operation plane of the robot is a two-dimensional plane, and θ is an included angle between a connecting line between the tail end of the robot operated by the test and the current semicircular track center of circle and a horizontal plane, a method for calculating the output force of the tail end of the robot according to the track of the tail end is as follows:
f x ＝f*cosθ*sig(f)
f y ＝f*sinθ*sig(f)
wherein sig (f) is a symbol value of the adjusting force of the robot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110346485.XA CN113081671B (en) | 2021-03-31 | 2021-03-31 | Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110346485.XA CN113081671B (en) | 2021-03-31 | 2021-03-31 | Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113081671A CN113081671A (en) | 2021-07-09 |
| CN113081671B true CN113081671B (en) | 2022-09-30 |
Family
ID=76671542
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110346485.XA Active CN113081671B (en) | 2021-03-31 | 2021-03-31 | Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113081671B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114869306A (en) * | 2022-06-14 | 2022-08-09 | 东南大学 | Game theory and sEMG-based upper limb rehabilitation robot self-adaptive control method and system |
| CN115040840A (en) * | 2022-06-20 | 2022-09-13 | 山西医科大学第二医院 | Upper limb rehabilitation training method and device |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8280503B2 (en) * | 2008-10-27 | 2012-10-02 | Michael Linderman | EMG measured during controlled hand movement for biometric analysis, medical diagnosis and related analysis |
| JP2012524636A (en) * | 2009-04-24 | 2012-10-18 | アドバンスド ブレイン モニタリング，インコーポレイテッド | Adaptive behavior trainer |
| CN105054927B (en) * | 2015-07-16 | 2017-08-15 | 西安交通大学 | The biological quantitative estimation method for degree of being actively engaged in a kind of lower limb rehabilitation system |
| CN109789543B (en) * | 2016-07-22 | 2022-09-27 | 哈佛大学校长及研究员协会 | Control optimization for wearable systems |
| CN110300542A (en) * | 2016-07-25 | 2019-10-01 | 开创拉布斯公司 | Method and apparatus for predicting musculoskeletal location information using wearable automated sensors |
| US10639510B2 (en) * | 2017-03-20 | 2020-05-05 | The Trustees Of Columbia University In The City Of New York | Human musculoskeletal support and training system methods and devices |
| CN110303471B (en) * | 2018-03-27 | 2021-02-09 | 清华大学 | Power-assisted exoskeleton control system and control method |
| CN108681396B (en) * | 2018-04-28 | 2021-07-06 | 北京机械设备研究所 | Human-computer interaction system and method based on brain-myoelectricity bimodal neural signals |
| CN109381184A (en) * | 2018-10-15 | 2019-02-26 | 刘丹 | A kind of wearable smart machine control method that auxiliary is carried |
| CN110400619B (en) * | 2019-08-30 | 2023-07-21 | 上海大学 | Hand function rehabilitation training method based on surface electromyographic signals |
| CN111631923A (en) * | 2020-06-02 | 2020-09-08 | 中国科学技术大学先进技术研究院 | Neural network control system of exoskeleton robot based on intention recognition |
| CN111816309B (en) * | 2020-07-13 | 2022-02-01 | 国家康复辅具研究中心 | Rehabilitation training prescription self-adaptive recommendation method and system based on deep reinforcement learning |
-
2021
- 2021-03-31 CN CN202110346485.XA patent/CN113081671B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113081671A (en) | 2021-07-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101961527B (en) | Rehabilitation training system and method combined with functional electric stimulation and robot | |
| Türker et al. | Surface electromyography in sports and exercise | |
| CN113081671B (en) | Method for improving on-demand auxiliary rehabilitation training participation degree based on Bayesian optimization | |
| US9563740B2 (en) | Neural interface activity simulator | |
| Loconsole et al. | An EMG-based approach for on-line predicted torque control in robotic-assisted rehabilitation | |
| CN102488963B (en) | Functional electrical stimulation knee joint angle control method | |
| CN113713252B (en) | Bionic type body sense reconstruction method for prosthetic wrist and elbow joint | |
| CN109106339A (en) | A kind of On-line Estimation method of elbow joint torque under functional electrostimulation | |
| Cardoso et al. | Soft robotics and functional electrical stimulation advances for restoring hand function in people with SCI: a narrative review, clinical guidelines and future directions | |
| CN115206484A (en) | Cerebral apoplexy rehabilitation training system | |
| CN108543216A (en) | A kind of hand function reconstructing device and its implementation based on master ＆ slave control | |
| Hu et al. | Stiffness optimal modulation of a variable stiffness energy storage hip exoskeleton and experiments on its assistance effect | |
| Wang et al. | Research progress of rehabilitation exoskeletal robot and evaluation methodologies based on bioelectrical signals | |
| CN116831897A (en) | Self-adaptive intelligent massage relaxing device | |
| CN112932898B (en) | On-demand auxiliary rehabilitation robot based on Bayesian optimization | |
| CN209253488U (en) | A kind of bionical class brain intelligent hand electric mechanical ectoskeleton and its control system entirely | |
| CN111437509B (en) | Functional electric stimulation device for hand reflex zone and control method | |
| US20220143407A1 (en) | System for providing neuromodulation, especially neurostimulation | |
| CN117563135B (en) | Multi-mode information visual functional electric stimulation closed-loop regulation and control system and method | |
| Zhang et al. | Estimation of Joint Angle Using sEMG Based on WOA-SVR Algorithm | |
| Yu et al. | Design of Control System for Lower Limb Rehabilitation Robot on the Healthy Side sEMG Signal | |
| Wang et al. | Automated discrimination of gait patterns based on sEMG recognition using neural networks | |
| Mahmud | Development of a Real–Time, Artificial Neural Network Based sEMG Classification Algorithm For Motion Identification | |
| Ay | The effect of EMG-based attentional focus on human machine interface applications | |
| Shi et al. | SEMG and KNN Based Human Motion Intention Recognition for Active and Safe Neurorehabilitation. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |